From a79c3175a7bda80ceb541ed60c8580de08a7445b Mon Sep 17 00:00:00 2001 From: it1804 Date: Fri, 14 Aug 2020 02:00:12 +0500 Subject: [PATCH 01/73] Allow authenticate Redis with requirepass option --- src/Dictionaries/RedisDictionarySource.cpp | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/src/Dictionaries/RedisDictionarySource.cpp b/src/Dictionaries/RedisDictionarySource.cpp index 8794f0620e2..030ee2b1a06 100644 --- a/src/Dictionaries/RedisDictionarySource.cpp +++ b/src/Dictionaries/RedisDictionarySource.cpp @@ -51,12 +51,14 @@ namespace DB const String & host_, UInt16 port_, UInt8 db_index_, + const String & password_, RedisStorageType storage_type_, const Block & sample_block_) : dict_struct{dict_struct_} , host{host_} , port{port_} , db_index{db_index_} + , password{password_} , storage_type{storage_type_} , sample_block{sample_block_} , client{std::make_shared(host, port)} @@ -77,16 +79,22 @@ namespace DB ErrorCodes::INVALID_CONFIG_PARAMETER}; // suppose key[0] is primary key, key[1] is secondary key } + if (!password.empty()) + { + RedisCommand command("AUTH"); + command << password; + String reply = client->execute(command); + if (reply != "OK") + throw Exception{"Authentication failed with reason " + + reply, ErrorCodes::INTERNAL_REDIS_ERROR}; + } if (db_index != 0) { RedisCommand command("SELECT"); - // Use poco's Int64, because it is defined as long long, and on - // MacOS, for the purposes of template instantiation, this type is - // distinct from int64_t, which is our Int64. - command << static_cast(db_index); + command << std::to_string(db_index); String reply = client->execute(command); - if (reply != "+OK\r\n") + if (reply != "OK") throw Exception{"Selecting database with index " + DB::toString(db_index) + " failed with reason " + reply, ErrorCodes::INTERNAL_REDIS_ERROR}; } @@ -103,6 +111,7 @@ namespace DB config_.getString(config_prefix_ + ".host"), config_.getUInt(config_prefix_ + ".port"), config_.getUInt(config_prefix_ + ".db_index", 0), + config_.getString(config_prefix_ + ".password",""), parseStorageType(config_.getString(config_prefix_ + ".storage_type", "")), sample_block_) { @@ -114,6 +123,7 @@ namespace DB other.host, other.port, other.db_index, + other.password, other.storage_type, other.sample_block} { From a1c0c52c5bdda2358139d712352c706f4dd20086 Mon Sep 17 00:00:00 2001 From: it1804 Date: Fri, 14 Aug 2020 02:01:25 +0500 Subject: [PATCH 02/73] Allow authenticate Redis with requirepass option --- src/Dictionaries/RedisDictionarySource.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/Dictionaries/RedisDictionarySource.h b/src/Dictionaries/RedisDictionarySource.h index b30c428cb2d..75dcc2fb081 100644 --- a/src/Dictionaries/RedisDictionarySource.h +++ b/src/Dictionaries/RedisDictionarySource.h @@ -41,6 +41,7 @@ namespace ErrorCodes const std::string & host, UInt16 port, UInt8 db_index, + const std::string & password, RedisStorageType storage_type, const Block & sample_block); @@ -91,6 +92,7 @@ namespace ErrorCodes const std::string host; const UInt16 port; const UInt8 db_index; + const std::string password; const RedisStorageType storage_type; Block sample_block; From 1006c4f11bce91b4fdf82f575f8f427828347805 Mon Sep 17 00:00:00 2001 From: "Ivan A. Torgashov" Date: Sat, 15 Aug 2020 14:18:17 +0500 Subject: [PATCH 03/73] Update tests for Redis dictionary requirepass authorization support --- .../integration/runner/compose/docker_compose_redis.yml | 1 + .../external_sources.py | 9 ++++++--- .../test_dictionaries_all_layouts_and_sources/test.py | 4 ++-- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/docker/test/integration/runner/compose/docker_compose_redis.yml b/docker/test/integration/runner/compose/docker_compose_redis.yml index 2dc79ed5910..2c9ace96d0c 100644 --- a/docker/test/integration/runner/compose/docker_compose_redis.yml +++ b/docker/test/integration/runner/compose/docker_compose_redis.yml @@ -5,3 +5,4 @@ services: restart: always ports: - 6380:6379 + command: redis-server --requirepass "clickhouse" diff --git a/tests/integration/test_dictionaries_all_layouts_and_sources/external_sources.py b/tests/integration/test_dictionaries_all_layouts_and_sources/external_sources.py index f6985e7de54..fac7dcdea1e 100644 --- a/tests/integration/test_dictionaries_all_layouts_and_sources/external_sources.py +++ b/tests/integration/test_dictionaries_all_layouts_and_sources/external_sources.py @@ -483,23 +483,27 @@ class SourceRedis(ExternalSource): name, internal_hostname, internal_port, docker_hostname, docker_port, user, password ) self.storage_type = storage_type + self.db_index = 1 def get_source_str(self, table_name): return ''' {host} {port} - 0 + {password} + {db_index} {storage_type} '''.format( host=self.docker_hostname, port=self.docker_port, + password=self.password, storage_type=self.storage_type, # simple or hash_map + db_index=self.db_index, ) def prepare(self, structure, table_name, cluster): - self.client = redis.StrictRedis(host=self.internal_hostname, port=self.internal_port) + self.client = redis.StrictRedis(host=self.internal_hostname, port=self.internal_port, db=self.db_index, password=self.password or None) self.prepared = True self.ordered_names = structure.get_ordered_names() @@ -525,7 +529,6 @@ class SourceRedis(ExternalSource): return True return False - class SourceAerospike(ExternalSource): def __init__(self, name, internal_hostname, internal_port, docker_hostname, docker_port, user, password): diff --git a/tests/integration/test_dictionaries_all_layouts_and_sources/test.py b/tests/integration/test_dictionaries_all_layouts_and_sources/test.py index f4b0ba9c1e4..994d8e5e65d 100644 --- a/tests/integration/test_dictionaries_all_layouts_and_sources/test.py +++ b/tests/integration/test_dictionaries_all_layouts_and_sources/test.py @@ -134,8 +134,8 @@ DICTIONARIES = [] # Key-value dictionaries with only one possible field for key SOURCES_KV = [ - SourceRedis("RedisSimple", "localhost", "6380", "redis1", "6379", "", "", storage_type="simple"), - SourceRedis("RedisHash", "localhost", "6380", "redis1", "6379", "", "", storage_type="hash_map"), + SourceRedis("RedisSimple", "localhost", "6380", "redis1", "6379", "", "clickhouse", storage_type="simple"), + SourceRedis("RedisHash", "localhost", "6380", "redis1", "6379", "", "clickhouse", storage_type="hash_map"), ] DICTIONARIES_KV = [] From 43839a97b6a214cdbeeb5d6fdbf8c9cccfbd5e95 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Sat, 15 Aug 2020 21:29:24 +0800 Subject: [PATCH 04/73] ISSUES-4006 add factor with DateTime type --- src/DataTypes/DataTypeDateTime.cpp | 27 ----- src/DataTypes/DataTypeDateTime64.cpp | 61 ---------- src/DataTypes/registerDataTypeDateTime.cpp | 110 ++++++++++++++++++ src/DataTypes/ya.make | 1 + src/Functions/FunctionsConversion.cpp | 1 + src/Functions/FunctionsConversion.h | 33 ++++++ .../01442_date_time_with_params.reference | 4 + .../01442_date_time_with_params.sql | 15 +++ 8 files changed, 164 insertions(+), 88 deletions(-) create mode 100644 src/DataTypes/registerDataTypeDateTime.cpp create mode 100644 tests/queries/0_stateless/01442_date_time_with_params.reference create mode 100644 tests/queries/0_stateless/01442_date_time_with_params.sql diff --git a/src/DataTypes/DataTypeDateTime.cpp b/src/DataTypes/DataTypeDateTime.cpp index c860766406e..9ea698d4fbb 100644 --- a/src/DataTypes/DataTypeDateTime.cpp +++ b/src/DataTypes/DataTypeDateTime.cpp @@ -185,31 +185,4 @@ bool DataTypeDateTime::equals(const IDataType & rhs) const return typeid(rhs) == typeid(*this); } -namespace ErrorCodes -{ - extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH; - extern const int ILLEGAL_TYPE_OF_ARGUMENT; -} - -static DataTypePtr create(const ASTPtr & arguments) -{ - if (!arguments) - return std::make_shared(); - - if (arguments->children.size() != 1) - throw Exception("DateTime data type can optionally have only one argument - time zone name", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); - - const auto * arg = arguments->children[0]->as(); - if (!arg || arg->value.getType() != Field::Types::String) - throw Exception("Parameter for DateTime data type must be string literal", ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); - - return std::make_shared(arg->value.get()); -} - -void registerDataTypeDateTime(DataTypeFactory & factory) -{ - factory.registerDataType("DateTime", create, DataTypeFactory::CaseInsensitive); - factory.registerAlias("TIMESTAMP", "DateTime", DataTypeFactory::CaseInsensitive); -} - } diff --git a/src/DataTypes/DataTypeDateTime64.cpp b/src/DataTypes/DataTypeDateTime64.cpp index 97dd28439d7..ee4139c2b7a 100644 --- a/src/DataTypes/DataTypeDateTime64.cpp +++ b/src/DataTypes/DataTypeDateTime64.cpp @@ -201,65 +201,4 @@ bool DataTypeDateTime64::equals(const IDataType & rhs) const return false; } -namespace ErrorCodes -{ - extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH; - extern const int ILLEGAL_TYPE_OF_ARGUMENT; -} - -enum class ArgumentKind -{ - Optional, - Mandatory -}; - -template -std::conditional_t, T> -getArgument(const ASTPtr & arguments, size_t argument_index, const char * argument_name, const std::string context_data_type_name) -{ - using NearestResultType = NearestFieldType; - const auto field_type = Field::TypeToEnum::value; - const ASTLiteral * argument = nullptr; - - auto exception_message = [=](const String & message) - { - return std::string("Parameter #") + std::to_string(argument_index) + " '" - + argument_name + "' for " + context_data_type_name - + message - + ", expected: " + Field::Types::toString(field_type) + " literal."; - }; - - if (!arguments || arguments->children.size() <= argument_index - || !(argument = arguments->children[argument_index]->as())) - { - if constexpr (Kind == ArgumentKind::Optional) - return {}; - else - throw Exception(exception_message(" is missing"), - ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); - } - - if (argument->value.getType() != field_type) - throw Exception(exception_message(String(" has wrong type: ") + argument->value.getTypeName()), - ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); - - return argument->value.get(); -} - -static DataTypePtr create64(const ASTPtr & arguments) -{ - if (!arguments || arguments->size() == 0) - return std::make_shared(DataTypeDateTime64::default_scale); - - const auto scale = getArgument(arguments, 0, "scale", "DateType64"); - const auto timezone = getArgument(arguments, !!scale, "timezone", "DateType64"); - - return std::make_shared(scale.value_or(DataTypeDateTime64::default_scale), timezone.value_or(String{})); -} - -void registerDataTypeDateTime64(DataTypeFactory & factory) -{ - factory.registerDataType("DateTime64", create64, DataTypeFactory::CaseInsensitive); -} - } diff --git a/src/DataTypes/registerDataTypeDateTime.cpp b/src/DataTypes/registerDataTypeDateTime.cpp new file mode 100644 index 00000000000..47487641e09 --- /dev/null +++ b/src/DataTypes/registerDataTypeDateTime.cpp @@ -0,0 +1,110 @@ + +#include +#include +#include +#include +#include +#include +#include + +namespace DB +{ + +namespace ErrorCodes +{ + extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH; + extern const int ILLEGAL_TYPE_OF_ARGUMENT; +} + +enum class ArgumentKind +{ + Optional, + Mandatory +}; + +template +std::conditional_t, T> +getArgument(const ASTPtr & arguments, size_t argument_index, const char * argument_name, const std::string context_data_type_name) +{ + using NearestResultType = NearestFieldType; + const auto field_type = Field::TypeToEnum::value; + const ASTLiteral * argument = nullptr; + + auto exception_message = [=](const String & message) + { + return std::string("Parameter #") + std::to_string(argument_index) + " '" + + argument_name + "' for " + context_data_type_name + + message + + ", expected: " + Field::Types::toString(field_type) + " literal."; + }; + + if (!arguments || arguments->children.size() <= argument_index + || !(argument = arguments->children[argument_index]->as()) + || argument->value.getType() != field_type) + { + if constexpr (Kind == ArgumentKind::Optional) + return {}; + else + throw Exception(exception_message(" is missing"), + ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); + } + + return argument->value.get(); +} + +static DataTypePtr create(const ASTPtr & arguments) +{ + if (!arguments || arguments->size() == 0) + return std::make_shared(); + + const auto scale = getArgument(arguments, 0, "scale", "DateTime"); + const auto timezone = getArgument(arguments, !!scale, "timezone", "DateTime"); + + if (scale) + return std::make_shared(scale.value_or(DataTypeDateTime64::default_scale), timezone.value_or(String{})); + + return std::make_shared(timezone.value_or(String{})); +} + +static DataTypePtr create32(const ASTPtr & arguments) +{ + if (!arguments || arguments->size() == 0) + return std::make_shared(); + + if (arguments->children.size() != 1) + throw Exception("DateTime32 data type can optionally have only one argument - time zone name", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); + + const auto timezone = getArgument(arguments, 0, "timezone", "DateTime32"); + + return std::make_shared(timezone); +} + +static DataTypePtr create64(const ASTPtr & arguments) +{ + if (!arguments || arguments->size() == 0) + return std::make_shared(DataTypeDateTime64::default_scale); + + if (arguments->children.size() > 2) + throw Exception("DateTime64 data type can optionally have two argument - scale and time zone name", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); + + const auto scale = getArgument(arguments, 0, "scale", "DateTime64"); + const auto timezone = getArgument(arguments, !!scale, "timezone", "DateTime64"); + + return std::make_shared(scale.value_or(DataTypeDateTime64::default_scale), timezone.value_or(String{})); +} + +void registerDataTypeDateTime(DataTypeFactory & factory) +{ + factory.registerDataType("DateTime", create, DataTypeFactory::CaseInsensitive); + factory.registerDataType("DateTime32", create32, DataTypeFactory::CaseInsensitive); + factory.registerDataType("DateTime64", create64, DataTypeFactory::CaseInsensitive); + + factory.registerAlias("TIMESTAMP", "DateTime", DataTypeFactory::CaseInsensitive); +} + +void registerDataTypeDateTime64(DataTypeFactory & /*factory*/) +{ +// factory.registerDataType("DateTime64", create64, DataTypeFactory::CaseInsensitive); +} + +} diff --git a/src/DataTypes/ya.make b/src/DataTypes/ya.make index 82e9baf76f2..4237ca920ae 100644 --- a/src/DataTypes/ya.make +++ b/src/DataTypes/ya.make @@ -38,6 +38,7 @@ SRCS( getMostSubtype.cpp IDataType.cpp NestedUtils.cpp + registerDataTypeDateTime.cpp ) diff --git a/src/Functions/FunctionsConversion.cpp b/src/Functions/FunctionsConversion.cpp index da42c8a2623..804c16d946d 100644 --- a/src/Functions/FunctionsConversion.cpp +++ b/src/Functions/FunctionsConversion.cpp @@ -32,6 +32,7 @@ void registerFunctionsConversion(FunctionFactory & factory) factory.registerFunction(); factory.registerFunction(); + factory.registerFunction(); factory.registerFunction(); factory.registerFunction(); factory.registerFunction(); diff --git a/src/Functions/FunctionsConversion.h b/src/Functions/FunctionsConversion.h index 4aacafafd96..a8e8ad81ff8 100644 --- a/src/Functions/FunctionsConversion.h +++ b/src/Functions/FunctionsConversion.h @@ -968,6 +968,7 @@ struct ConvertImpl /// Declared early because used below. struct NameToDate { static constexpr auto name = "toDate"; }; struct NameToDateTime { static constexpr auto name = "toDateTime"; }; +struct NameToDateTime32 { static constexpr auto name = "toDateTime32"; }; struct NameToDateTime64 { static constexpr auto name = "toDateTime64"; }; struct NameToString { static constexpr auto name = "toString"; }; struct NameToDecimal32 { static constexpr auto name = "toDecimal32"; }; @@ -1027,6 +1028,14 @@ public: { mandatory_args.push_back({"scale", &isNativeInteger, &isColumnConst, "const Integer"}); } + + if constexpr (std::is_same_v && std::is_same_v) + { + /// toDateTime(value, scale:Integer) + if ((arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3) + mandatory_args.push_back({"scale", &isNativeInteger, &isColumnConst, "const Integer"}); + } + // toString(DateTime or DateTime64, [timezone: String]) if ((std::is_same_v && arguments.size() > 0 && (isDateTime64(arguments[0].type) || isDateTime(arguments[0].type))) // toUnixTimestamp(value[, timezone : String]) @@ -1076,6 +1085,17 @@ public: scale = static_cast(arguments[1].column->get64(0)); } + if constexpr (std::is_same_v && std::is_same_v) + { + /// For toDateTime('xxxx-xx-xx xx:xx:xx.00', 2[, 'timezone']) we need to it convert to DateTime64 + if ((arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3) + { + timezone_arg_position += 1; + scale = static_cast(arguments[1].column->get64(0)); + return std::make_shared(scale, extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); + } + } + if constexpr (std::is_same_v) return std::make_shared(extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); else if constexpr (to_datetime64) @@ -1179,6 +1199,18 @@ private: return true; }; + if constexpr (std::is_same_v && std::is_same_v) + { + /// For toDateTime('xxxx-xx-xx xx:xx:xx.00', 2[, 'timezone']) we need to it convert to DateTime64 + if ((arguments.size() == 2 && isUnsignedInteger(block.getByPosition(arguments[1]).type)) || arguments.size() == 3) + { + if (!callOnIndexAndDataType(from_type->getTypeId(), call)) + throw Exception("Illegal type " + block.getByPosition(arguments[0]).type->getName() + " of argument of function " + getName(), + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + return; + } + } + bool done = callOnIndexAndDataType(from_type->getTypeId(), call); if (!done) { @@ -1607,6 +1639,7 @@ using FunctionToFloat32 = FunctionConvert>; using FunctionToDate = FunctionConvert; using FunctionToDateTime = FunctionConvert; +using FunctionToDateTime32 = FunctionConvert; using FunctionToDateTime64 = FunctionConvert; using FunctionToUUID = FunctionConvert>; using FunctionToString = FunctionConvert; diff --git a/tests/queries/0_stateless/01442_date_time_with_params.reference b/tests/queries/0_stateless/01442_date_time_with_params.reference new file mode 100644 index 00000000000..a6cb7f7b948 --- /dev/null +++ b/tests/queries/0_stateless/01442_date_time_with_params.reference @@ -0,0 +1,4 @@ +2020-01-01 00:00:00 DateTime 2020-01-01 00:01:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') 2020-01-01 00:05:00 DateTime 2020-01-01 00:06:00 DateTime(\'Europe/Moscow\') +2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') +2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') +2020-01-01 00:00:00 DateTime diff --git a/tests/queries/0_stateless/01442_date_time_with_params.sql b/tests/queries/0_stateless/01442_date_time_with_params.sql new file mode 100644 index 00000000000..1e75089bc05 --- /dev/null +++ b/tests/queries/0_stateless/01442_date_time_with_params.sql @@ -0,0 +1,15 @@ +DROP TABLE IF EXISTS test; + +CREATE TABLE test (a DateTime, b DateTime(), c DateTime(2), d DateTime('Europe/Moscow'), e DateTime(3, 'Europe/Moscow'), f DateTime32, g DateTime32('Europe/Moscow')) ENGINE = MergeTree ORDER BY a; + +INSERT INTO test VALUES('2020-01-01 00:00:00', '2020-01-01 00:01:00', '2020-01-01 00:02:00.11', '2020-01-01 00:03:00', '2020-01-01 00:04:00.22', '2020-01-01 00:05:00', '2020-01-01 00:06:00') + +SELECT a, toTypeName(a), b, toTypeName(b), c, toTypeName(c), d, toTypeName(d), e, toTypeName(e), f, toTypeName(f), g, toTypeName(g) FROM test; + +SELECT toDateTime('2020-01-01 00:00:00') AS a, toTypeName(a), toDateTime('2020-01-01 00:02:00.11', 2) AS b, toTypeName(b), toDateTime('2020-01-01 00:03:00', 'Europe/Moscow') AS c, toTypeName(c), toDateTime('2020-01-01 00:04:00.22', 3, 'Europe/Moscow') AS d, toTypeName(d); + +SELECT CAST('2020-01-01 00:00:00', 'DateTime') AS a, toTypeName(a), CAST('2020-01-01 00:02:00.11', 'DateTime(2)') AS b, toTypeName(b), CAST('2020-01-01 00:03:00', 'DateTime(\'Europe/Moscow\')') AS c, toTypeName(c), CAST('2020-01-01 00:04:00.22', 'DateTime(3, \'Europe/Moscow\')') AS d, toTypeName(d); + +SELECT toDateTime32('2020-01-01 00:00:00') AS a, toTypeName(a); + +DROP TABLE IF EXISTS test; From 4ad267571e5454349e3fca00c9ec34d0c578e794 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Sat, 15 Aug 2020 21:43:44 +0800 Subject: [PATCH 05/73] ISSUES-4006 remove unused code --- src/DataTypes/DataTypeFactory.cpp | 1 - src/DataTypes/DataTypeFactory.h | 1 - src/DataTypes/registerDataTypeDateTime.cpp | 5 ----- 3 files changed, 7 deletions(-) diff --git a/src/DataTypes/DataTypeFactory.cpp b/src/DataTypes/DataTypeFactory.cpp index 664927389b5..9386f4b39f1 100644 --- a/src/DataTypes/DataTypeFactory.cpp +++ b/src/DataTypes/DataTypeFactory.cpp @@ -165,7 +165,6 @@ DataTypeFactory::DataTypeFactory() registerDataTypeDecimal(*this); registerDataTypeDate(*this); registerDataTypeDateTime(*this); - registerDataTypeDateTime64(*this); registerDataTypeString(*this); registerDataTypeFixedString(*this); registerDataTypeEnum(*this); diff --git a/src/DataTypes/DataTypeFactory.h b/src/DataTypes/DataTypeFactory.h index 67b72945acc..ea77c50170c 100644 --- a/src/DataTypes/DataTypeFactory.h +++ b/src/DataTypes/DataTypeFactory.h @@ -82,7 +82,6 @@ void registerDataTypeInterval(DataTypeFactory & factory); void registerDataTypeLowCardinality(DataTypeFactory & factory); void registerDataTypeDomainIPv4AndIPv6(DataTypeFactory & factory); void registerDataTypeDomainSimpleAggregateFunction(DataTypeFactory & factory); -void registerDataTypeDateTime64(DataTypeFactory & factory); void registerDataTypeDomainGeo(DataTypeFactory & factory); } diff --git a/src/DataTypes/registerDataTypeDateTime.cpp b/src/DataTypes/registerDataTypeDateTime.cpp index 47487641e09..c6a79e48335 100644 --- a/src/DataTypes/registerDataTypeDateTime.cpp +++ b/src/DataTypes/registerDataTypeDateTime.cpp @@ -102,9 +102,4 @@ void registerDataTypeDateTime(DataTypeFactory & factory) factory.registerAlias("TIMESTAMP", "DateTime", DataTypeFactory::CaseInsensitive); } -void registerDataTypeDateTime64(DataTypeFactory & /*factory*/) -{ -// factory.registerDataType("DateTime64", create64, DataTypeFactory::CaseInsensitive); -} - } From fb1417db7188a5b83c8a02344993597e054c7db1 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Sun, 16 Aug 2020 01:08:03 +0800 Subject: [PATCH 06/73] ISSUES-4006 try fix test failure --- src/DataTypes/registerDataTypeDateTime.cpp | 41 ++++++++++++------- src/Functions/FunctionsConversion.h | 25 +++++++---- .../0_stateless/00921_datetime64_basic.sql | 4 +- .../01442_date_time_with_params.reference | 6 +-- .../01442_date_time_with_params.sql | 10 ++--- 5 files changed, 53 insertions(+), 33 deletions(-) diff --git a/src/DataTypes/registerDataTypeDateTime.cpp b/src/DataTypes/registerDataTypeDateTime.cpp index c6a79e48335..0596b229494 100644 --- a/src/DataTypes/registerDataTypeDateTime.cpp +++ b/src/DataTypes/registerDataTypeDateTime.cpp @@ -22,6 +22,16 @@ enum class ArgumentKind Mandatory }; +String getExceptionMessage( + const String & message, size_t argument_index, const char * argument_name, + const std::string & context_data_type_name, Field::Types::Which field_type) +{ + return std::string("Parameter #") + std::to_string(argument_index) + " '" + + argument_name + "' for " + context_data_type_name + + message + + ", expected: " + Field::Types::toString(field_type) + " literal."; +} + template std::conditional_t, T> getArgument(const ASTPtr & arguments, size_t argument_index, const char * argument_name, const std::string context_data_type_name) @@ -30,14 +40,6 @@ getArgument(const ASTPtr & arguments, size_t argument_index, const char * argume const auto field_type = Field::TypeToEnum::value; const ASTLiteral * argument = nullptr; - auto exception_message = [=](const String & message) - { - return std::string("Parameter #") + std::to_string(argument_index) + " '" - + argument_name + "' for " + context_data_type_name - + message - + ", expected: " + Field::Types::toString(field_type) + " literal."; - }; - if (!arguments || arguments->children.size() <= argument_index || !(argument = arguments->children[argument_index]->as()) || argument->value.getType() != field_type) @@ -45,8 +47,8 @@ getArgument(const ASTPtr & arguments, size_t argument_index, const char * argume if constexpr (Kind == ArgumentKind::Optional) return {}; else - throw Exception(exception_message(" is missing"), - ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); + throw Exception(getExceptionMessage(" is missing", argument_index, argument_name, context_data_type_name, field_type), + ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); } return argument->value.get(); @@ -54,21 +56,26 @@ getArgument(const ASTPtr & arguments, size_t argument_index, const char * argume static DataTypePtr create(const ASTPtr & arguments) { - if (!arguments || arguments->size() == 0) + if (!arguments || arguments->children.size() == 0) return std::make_shared(); const auto scale = getArgument(arguments, 0, "scale", "DateTime"); const auto timezone = getArgument(arguments, !!scale, "timezone", "DateTime"); - if (scale) - return std::make_shared(scale.value_or(DataTypeDateTime64::default_scale), timezone.value_or(String{})); + if (!scale && !timezone) + throw Exception(getExceptionMessage(" has wrong type: ", 0, "scale", "DateTime", Field::Types::Which::UInt64), + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + + /// If scale is defined, the data type is DateTime when scale = 0 otherwise the data type is DateTime64 + if (scale && scale.value() != 0) + return std::make_shared(scale.value(), timezone.value_or(String{})); return std::make_shared(timezone.value_or(String{})); } static DataTypePtr create32(const ASTPtr & arguments) { - if (!arguments || arguments->size() == 0) + if (!arguments || arguments->children.size() == 0) return std::make_shared(); if (arguments->children.size() != 1) @@ -81,7 +88,7 @@ static DataTypePtr create32(const ASTPtr & arguments) static DataTypePtr create64(const ASTPtr & arguments) { - if (!arguments || arguments->size() == 0) + if (!arguments || arguments->children.size() == 0) return std::make_shared(DataTypeDateTime64::default_scale); if (arguments->children.size() > 2) @@ -90,6 +97,10 @@ static DataTypePtr create64(const ASTPtr & arguments) const auto scale = getArgument(arguments, 0, "scale", "DateTime64"); const auto timezone = getArgument(arguments, !!scale, "timezone", "DateTime64"); + if (!scale && !timezone) + throw Exception(getExceptionMessage(" has wrong type: ", 0, "scale", "DateTime", Field::Types::Which::UInt64), + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + return std::make_shared(scale.value_or(DataTypeDateTime64::default_scale), timezone.value_or(String{})); } diff --git a/src/Functions/FunctionsConversion.h b/src/Functions/FunctionsConversion.h index a8e8ad81ff8..9e5a781240d 100644 --- a/src/Functions/FunctionsConversion.h +++ b/src/Functions/FunctionsConversion.h @@ -1029,7 +1029,7 @@ public: mandatory_args.push_back({"scale", &isNativeInteger, &isColumnConst, "const Integer"}); } - if constexpr (std::is_same_v && std::is_same_v) + if constexpr (std::is_same_v) { /// toDateTime(value, scale:Integer) if ((arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3) @@ -1085,14 +1085,16 @@ public: scale = static_cast(arguments[1].column->get64(0)); } - if constexpr (std::is_same_v && std::is_same_v) + if constexpr (std::is_same_v) { /// For toDateTime('xxxx-xx-xx xx:xx:xx.00', 2[, 'timezone']) we need to it convert to DateTime64 if ((arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3) { timezone_arg_position += 1; scale = static_cast(arguments[1].column->get64(0)); - return std::make_shared(scale, extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); + if (scale != 0) /// toDateTime('xxxx-xx-xx xx:xx:xx', 0) return DateTime + return std::make_shared( + scale, extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); } } @@ -1199,15 +1201,22 @@ private: return true; }; - if constexpr (std::is_same_v && std::is_same_v) + if constexpr (std::is_same_v) { /// For toDateTime('xxxx-xx-xx xx:xx:xx.00', 2[, 'timezone']) we need to it convert to DateTime64 if ((arguments.size() == 2 && isUnsignedInteger(block.getByPosition(arguments[1]).type)) || arguments.size() == 3) { - if (!callOnIndexAndDataType(from_type->getTypeId(), call)) - throw Exception("Illegal type " + block.getByPosition(arguments[0]).type->getName() + " of argument of function " + getName(), - ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); - return; + const ColumnWithTypeAndName & scale_column = block.getByPosition(arguments[1]); + UInt32 scale = extractToDecimalScale(scale_column); + + if (scale != 0) /// When scale = 0, the data type is DateTime otherwise the data type is DateTime64 + { + if (!callOnIndexAndDataType(from_type->getTypeId(), call)) + throw Exception("Illegal type " + block.getByPosition(arguments[0]).type->getName() + " of argument of function " + getName(), + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + + return; + } } } diff --git a/tests/queries/0_stateless/00921_datetime64_basic.sql b/tests/queries/0_stateless/00921_datetime64_basic.sql index 2d7cb975cfc..bc881e3175d 100644 --- a/tests/queries/0_stateless/00921_datetime64_basic.sql +++ b/tests/queries/0_stateless/00921_datetime64_basic.sql @@ -1,11 +1,11 @@ DROP TABLE IF EXISTS A; -SELECT CAST(1 as DateTime64('abc')); -- { serverError 43 } # Invalid scale parameter type +SELECT CAST(1 as DateTime64('abc')); -- { serverError 1000 } # invalid timezone SELECT CAST(1 as DateTime64(100)); -- { serverError 69 } # too big scale SELECT CAST(1 as DateTime64(-1)); -- { serverError 43 } # signed scale parameter type SELECT CAST(1 as DateTime64(3, 'qqq')); -- { serverError 1000 } # invalid timezone -SELECT toDateTime64('2019-09-16 19:20:11.234', 'abc'); -- { serverError 43 } # invalid scale +SELECT toDateTime64('2019-09-16 19:20:11.234', 'abc'); -- { serverError 43 } # invalid timezone SELECT toDateTime64('2019-09-16 19:20:11.234', 100); -- { serverError 69 } # too big scale SELECT toDateTime64(CAST([['CLb5Ph ']], 'String'), uniqHLL12('2Gs1V', 752)); -- { serverError 44 } # non-const string and non-const scale SELECT toDateTime64('2019-09-16 19:20:11.234', 3, 'qqq'); -- { serverError 1000 } # invalid timezone diff --git a/tests/queries/0_stateless/01442_date_time_with_params.reference b/tests/queries/0_stateless/01442_date_time_with_params.reference index a6cb7f7b948..03b591a34bb 100644 --- a/tests/queries/0_stateless/01442_date_time_with_params.reference +++ b/tests/queries/0_stateless/01442_date_time_with_params.reference @@ -1,4 +1,4 @@ -2020-01-01 00:00:00 DateTime 2020-01-01 00:01:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') 2020-01-01 00:05:00 DateTime 2020-01-01 00:06:00 DateTime(\'Europe/Moscow\') -2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') -2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') +2020-01-01 00:00:00 DateTime 2020-01-01 00:01:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') 2020-01-01 00:05:00 DateTime 2020-01-01 00:06:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:06:00 DateTime +2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') 2020-01-01 00:05:00 DateTime +2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') 2020-01-01 00:05:00 DateTime 2020-01-01 00:00:00 DateTime diff --git a/tests/queries/0_stateless/01442_date_time_with_params.sql b/tests/queries/0_stateless/01442_date_time_with_params.sql index 1e75089bc05..d2664a4e316 100644 --- a/tests/queries/0_stateless/01442_date_time_with_params.sql +++ b/tests/queries/0_stateless/01442_date_time_with_params.sql @@ -1,14 +1,14 @@ DROP TABLE IF EXISTS test; -CREATE TABLE test (a DateTime, b DateTime(), c DateTime(2), d DateTime('Europe/Moscow'), e DateTime(3, 'Europe/Moscow'), f DateTime32, g DateTime32('Europe/Moscow')) ENGINE = MergeTree ORDER BY a; +CREATE TABLE test (a DateTime, b DateTime(), c DateTime(2), d DateTime('Europe/Moscow'), e DateTime(3, 'Europe/Moscow'), f DateTime32, g DateTime32('Europe/Moscow'), h DateTime(0)) ENGINE = MergeTree ORDER BY a; -INSERT INTO test VALUES('2020-01-01 00:00:00', '2020-01-01 00:01:00', '2020-01-01 00:02:00.11', '2020-01-01 00:03:00', '2020-01-01 00:04:00.22', '2020-01-01 00:05:00', '2020-01-01 00:06:00') +INSERT INTO test VALUES('2020-01-01 00:00:00', '2020-01-01 00:01:00', '2020-01-01 00:02:00.11', '2020-01-01 00:03:00', '2020-01-01 00:04:00.22', '2020-01-01 00:05:00', '2020-01-01 00:06:00', '2020-01-01 00:06:00'); -SELECT a, toTypeName(a), b, toTypeName(b), c, toTypeName(c), d, toTypeName(d), e, toTypeName(e), f, toTypeName(f), g, toTypeName(g) FROM test; +SELECT a, toTypeName(a), b, toTypeName(b), c, toTypeName(c), d, toTypeName(d), e, toTypeName(e), f, toTypeName(f), g, toTypeName(g), h, toTypeName(h) FROM test; -SELECT toDateTime('2020-01-01 00:00:00') AS a, toTypeName(a), toDateTime('2020-01-01 00:02:00.11', 2) AS b, toTypeName(b), toDateTime('2020-01-01 00:03:00', 'Europe/Moscow') AS c, toTypeName(c), toDateTime('2020-01-01 00:04:00.22', 3, 'Europe/Moscow') AS d, toTypeName(d); +SELECT toDateTime('2020-01-01 00:00:00') AS a, toTypeName(a), toDateTime('2020-01-01 00:02:00.11', 2) AS b, toTypeName(b), toDateTime('2020-01-01 00:03:00', 'Europe/Moscow') AS c, toTypeName(c), toDateTime('2020-01-01 00:04:00.22', 3, 'Europe/Moscow') AS d, toTypeName(d), toDateTime('2020-01-01 00:05:00', 0) AS e, toTypeName(e); -SELECT CAST('2020-01-01 00:00:00', 'DateTime') AS a, toTypeName(a), CAST('2020-01-01 00:02:00.11', 'DateTime(2)') AS b, toTypeName(b), CAST('2020-01-01 00:03:00', 'DateTime(\'Europe/Moscow\')') AS c, toTypeName(c), CAST('2020-01-01 00:04:00.22', 'DateTime(3, \'Europe/Moscow\')') AS d, toTypeName(d); +SELECT CAST('2020-01-01 00:00:00', 'DateTime') AS a, toTypeName(a), CAST('2020-01-01 00:02:00.11', 'DateTime(2)') AS b, toTypeName(b), CAST('2020-01-01 00:03:00', 'DateTime(\'Europe/Moscow\')') AS c, toTypeName(c), CAST('2020-01-01 00:04:00.22', 'DateTime(3, \'Europe/Moscow\')') AS d, toTypeName(d), CAST('2020-01-01 00:05:00', 'DateTime(0)') AS e, toTypeName(e); SELECT toDateTime32('2020-01-01 00:00:00') AS a, toTypeName(a); From ade8c19b571f1f0ab1eb47727bd48341c1219f6d Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Sun, 16 Aug 2020 13:21:38 +0800 Subject: [PATCH 07/73] ISSUES-4006 try fix build & test failure --- src/DataTypes/registerDataTypeDateTime.cpp | 16 ++++++---------- .../0_stateless/00921_datetime64_basic.sql | 6 +++--- 2 files changed, 9 insertions(+), 13 deletions(-) diff --git a/src/DataTypes/registerDataTypeDateTime.cpp b/src/DataTypes/registerDataTypeDateTime.cpp index 0596b229494..9b6af5f6e0b 100644 --- a/src/DataTypes/registerDataTypeDateTime.cpp +++ b/src/DataTypes/registerDataTypeDateTime.cpp @@ -34,7 +34,7 @@ String getExceptionMessage( template std::conditional_t, T> -getArgument(const ASTPtr & arguments, size_t argument_index, const char * argument_name, const std::string context_data_type_name) +getArgument(const ASTPtr & arguments, size_t argument_index, const char * argument_name [[maybe_unused]], const std::string context_data_type_name) { using NearestResultType = NearestFieldType; const auto field_type = Field::TypeToEnum::value; @@ -56,7 +56,7 @@ getArgument(const ASTPtr & arguments, size_t argument_index, const char * argume static DataTypePtr create(const ASTPtr & arguments) { - if (!arguments || arguments->children.size() == 0) + if (!arguments || arguments->children.empty()) return std::make_shared(); const auto scale = getArgument(arguments, 0, "scale", "DateTime"); @@ -75,7 +75,7 @@ static DataTypePtr create(const ASTPtr & arguments) static DataTypePtr create32(const ASTPtr & arguments) { - if (!arguments || arguments->children.size() == 0) + if (!arguments || arguments->children.empty()) return std::make_shared(); if (arguments->children.size() != 1) @@ -88,20 +88,16 @@ static DataTypePtr create32(const ASTPtr & arguments) static DataTypePtr create64(const ASTPtr & arguments) { - if (!arguments || arguments->children.size() == 0) + if (!arguments || arguments->children.empty()) return std::make_shared(DataTypeDateTime64::default_scale); if (arguments->children.size() > 2) throw Exception("DateTime64 data type can optionally have two argument - scale and time zone name", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); - const auto scale = getArgument(arguments, 0, "scale", "DateTime64"); + const auto scale = getArgument(arguments, 0, "scale", "DateTime64"); const auto timezone = getArgument(arguments, !!scale, "timezone", "DateTime64"); - if (!scale && !timezone) - throw Exception(getExceptionMessage(" has wrong type: ", 0, "scale", "DateTime", Field::Types::Which::UInt64), - ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); - - return std::make_shared(scale.value_or(DataTypeDateTime64::default_scale), timezone.value_or(String{})); + return std::make_shared(scale, timezone.value_or(String{})); } void registerDataTypeDateTime(DataTypeFactory & factory) diff --git a/tests/queries/0_stateless/00921_datetime64_basic.sql b/tests/queries/0_stateless/00921_datetime64_basic.sql index bc881e3175d..1fc534d8afd 100644 --- a/tests/queries/0_stateless/00921_datetime64_basic.sql +++ b/tests/queries/0_stateless/00921_datetime64_basic.sql @@ -1,11 +1,11 @@ DROP TABLE IF EXISTS A; -SELECT CAST(1 as DateTime64('abc')); -- { serverError 1000 } # invalid timezone +SELECT CAST(1 as DateTime64('abc')); -- { serverError 42 } # Miss scale parameter type SELECT CAST(1 as DateTime64(100)); -- { serverError 69 } # too big scale -SELECT CAST(1 as DateTime64(-1)); -- { serverError 43 } # signed scale parameter type +SELECT CAST(1 as DateTime64(-1)); -- { serverError 42 } # Miss scale parameter type SELECT CAST(1 as DateTime64(3, 'qqq')); -- { serverError 1000 } # invalid timezone -SELECT toDateTime64('2019-09-16 19:20:11.234', 'abc'); -- { serverError 43 } # invalid timezone +SELECT toDateTime64('2019-09-16 19:20:11.234', 'abc'); -- { serverError 43 } # Miss scale parameter type SELECT toDateTime64('2019-09-16 19:20:11.234', 100); -- { serverError 69 } # too big scale SELECT toDateTime64(CAST([['CLb5Ph ']], 'String'), uniqHLL12('2Gs1V', 752)); -- { serverError 44 } # non-const string and non-const scale SELECT toDateTime64('2019-09-16 19:20:11.234', 3, 'qqq'); -- { serverError 1000 } # invalid timezone From bdb20738e57f24c84384f78336772cb9efe69ad9 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Wed, 19 Aug 2020 13:19:36 +0800 Subject: [PATCH 08/73] ISSUES-4006 compatible DateTime64 --- src/DataTypes/registerDataTypeDateTime.cpp | 10 ++++++++-- tests/queries/0_stateless/00921_datetime64_basic.sql | 6 +++--- 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/src/DataTypes/registerDataTypeDateTime.cpp b/src/DataTypes/registerDataTypeDateTime.cpp index 9b6af5f6e0b..eceb531b892 100644 --- a/src/DataTypes/registerDataTypeDateTime.cpp +++ b/src/DataTypes/registerDataTypeDateTime.cpp @@ -47,8 +47,14 @@ getArgument(const ASTPtr & arguments, size_t argument_index, const char * argume if constexpr (Kind == ArgumentKind::Optional) return {}; else - throw Exception(getExceptionMessage(" is missing", argument_index, argument_name, context_data_type_name, field_type), - ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); + { + if (argument->value.getType() != field_type) + throw Exception(getExceptionMessage(String(" has wrong type: ") + argument->value.getTypeName(), + argument_index, argument_name, context_data_type_name, field_type), ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + else + throw Exception(getExceptionMessage(" is missing", argument_index, argument_name, context_data_type_name, field_type), + ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); + } } return argument->value.get(); diff --git a/tests/queries/0_stateless/00921_datetime64_basic.sql b/tests/queries/0_stateless/00921_datetime64_basic.sql index 1fc534d8afd..2d7cb975cfc 100644 --- a/tests/queries/0_stateless/00921_datetime64_basic.sql +++ b/tests/queries/0_stateless/00921_datetime64_basic.sql @@ -1,11 +1,11 @@ DROP TABLE IF EXISTS A; -SELECT CAST(1 as DateTime64('abc')); -- { serverError 42 } # Miss scale parameter type +SELECT CAST(1 as DateTime64('abc')); -- { serverError 43 } # Invalid scale parameter type SELECT CAST(1 as DateTime64(100)); -- { serverError 69 } # too big scale -SELECT CAST(1 as DateTime64(-1)); -- { serverError 42 } # Miss scale parameter type +SELECT CAST(1 as DateTime64(-1)); -- { serverError 43 } # signed scale parameter type SELECT CAST(1 as DateTime64(3, 'qqq')); -- { serverError 1000 } # invalid timezone -SELECT toDateTime64('2019-09-16 19:20:11.234', 'abc'); -- { serverError 43 } # Miss scale parameter type +SELECT toDateTime64('2019-09-16 19:20:11.234', 'abc'); -- { serverError 43 } # invalid scale SELECT toDateTime64('2019-09-16 19:20:11.234', 100); -- { serverError 69 } # too big scale SELECT toDateTime64(CAST([['CLb5Ph ']], 'String'), uniqHLL12('2Gs1V', 752)); -- { serverError 44 } # non-const string and non-const scale SELECT toDateTime64('2019-09-16 19:20:11.234', 3, 'qqq'); -- { serverError 1000 } # invalid timezone From e44975df3b44b5dbaac36256ff5d34225a7aa682 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Wed, 19 Aug 2020 23:18:25 +0800 Subject: [PATCH 09/73] ISSUES-4006 try fix test failure --- src/DataTypes/registerDataTypeDateTime.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/DataTypes/registerDataTypeDateTime.cpp b/src/DataTypes/registerDataTypeDateTime.cpp index eceb531b892..70b89bf7545 100644 --- a/src/DataTypes/registerDataTypeDateTime.cpp +++ b/src/DataTypes/registerDataTypeDateTime.cpp @@ -101,7 +101,7 @@ static DataTypePtr create64(const ASTPtr & arguments) throw Exception("DateTime64 data type can optionally have two argument - scale and time zone name", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH); const auto scale = getArgument(arguments, 0, "scale", "DateTime64"); - const auto timezone = getArgument(arguments, !!scale, "timezone", "DateTime64"); + const auto timezone = getArgument(arguments, 1, "timezone", "DateTime64"); return std::make_shared(scale, timezone.value_or(String{})); } From edeb983eb0d93ec66351238f349ef09a472ae083 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Thu, 20 Aug 2020 19:18:29 +0800 Subject: [PATCH 10/73] ISSUES-4006 some refactor --- src/Functions/FunctionsConversion.h | 64 ++++++++++++++--------------- 1 file changed, 32 insertions(+), 32 deletions(-) diff --git a/src/Functions/FunctionsConversion.h b/src/Functions/FunctionsConversion.h index 9e5a781240d..5fbcce4bc59 100644 --- a/src/Functions/FunctionsConversion.h +++ b/src/Functions/FunctionsConversion.h @@ -994,6 +994,18 @@ DEFINE_NAME_TO_INTERVAL(Year) #undef DEFINE_NAME_TO_INTERVAL +template +static inline bool isDateTime64(const ColumnsWithTypeAndName &arguments) +{ + if constexpr (std::is_same_v) + return true; + else if constexpr (std::is_same_v) + { + return (arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3; + } + + return false; +} template class FunctionConvert : public IFunction @@ -1024,16 +1036,14 @@ public: FunctionArgumentDescriptors mandatory_args = {{"Value", nullptr, nullptr, nullptr}}; FunctionArgumentDescriptors optional_args; - if constexpr (to_decimal || to_datetime64) + if constexpr (to_decimal) { mandatory_args.push_back({"scale", &isNativeInteger, &isColumnConst, "const Integer"}); } - if constexpr (std::is_same_v) + if (!to_decimal && isDateTime64(arguments)) { - /// toDateTime(value, scale:Integer) - if ((arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3) - mandatory_args.push_back({"scale", &isNativeInteger, &isColumnConst, "const Integer"}); + mandatory_args.push_back({"scale", &isNativeInteger, &isColumnConst, "const Integer"}); } // toString(DateTime or DateTime64, [timezone: String]) @@ -1079,29 +1089,22 @@ public: UInt32 scale [[maybe_unused]] = DataTypeDateTime64::default_scale; // DateTime64 requires more arguments: scale and timezone. Since timezone is optional, scale should be first. - if constexpr (to_datetime64) + if (isDateTime64(arguments)) { timezone_arg_position += 1; scale = static_cast(arguments[1].column->get64(0)); - } - if constexpr (std::is_same_v) - { - /// For toDateTime('xxxx-xx-xx xx:xx:xx.00', 2[, 'timezone']) we need to it convert to DateTime64 - if ((arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3) - { - timezone_arg_position += 1; - scale = static_cast(arguments[1].column->get64(0)); - if (scale != 0) /// toDateTime('xxxx-xx-xx xx:xx:xx', 0) return DateTime - return std::make_shared( - scale, extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); - } + if (to_datetime64 || scale != 0) /// toDateTime('xxxx-xx-xx xx:xx:xx', 0) return DateTime + return std::make_shared(scale, + extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); + + return std::make_shared(extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); } if constexpr (std::is_same_v) return std::make_shared(extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); - else if constexpr (to_datetime64) - return std::make_shared(scale, extractTimeZoneNameFromFunctionArguments(arguments, timezone_arg_position, 0)); + else if constexpr (std::is_same_v) + throw Exception("LOGICAL ERROR: It is a bug.", ErrorCodes::LOGICAL_ERROR); else return std::make_shared(); } @@ -1201,22 +1204,19 @@ private: return true; }; - if constexpr (std::is_same_v) + if (isDateTime64(block.getColumnsWithTypeAndName())) { /// For toDateTime('xxxx-xx-xx xx:xx:xx.00', 2[, 'timezone']) we need to it convert to DateTime64 - if ((arguments.size() == 2 && isUnsignedInteger(block.getByPosition(arguments[1]).type)) || arguments.size() == 3) + const ColumnWithTypeAndName & scale_column = block.getByPosition(arguments[1]); + UInt32 scale = extractToDecimalScale(scale_column); + + if (scale != 0) /// When scale = 0, the data type is DateTime otherwise the data type is DateTime64 { - const ColumnWithTypeAndName & scale_column = block.getByPosition(arguments[1]); - UInt32 scale = extractToDecimalScale(scale_column); + if (!callOnIndexAndDataType(from_type->getTypeId(), call)) + throw Exception("Illegal type " + block.getByPosition(arguments[0]).type->getName() + " of argument of function " + getName(), + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); - if (scale != 0) /// When scale = 0, the data type is DateTime otherwise the data type is DateTime64 - { - if (!callOnIndexAndDataType(from_type->getTypeId(), call)) - throw Exception("Illegal type " + block.getByPosition(arguments[0]).type->getName() + " of argument of function " + getName(), - ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); - - return; - } + return; } } From 45cc0778a0a65204e3c49653c7db067fa9fc1744 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Thu, 20 Aug 2020 22:41:03 +0800 Subject: [PATCH 11/73] ISSUES-4006 support scale with parserDateTime --- src/Functions/FunctionsConversion.h | 92 ++++++++++++++++++----------- 1 file changed, 59 insertions(+), 33 deletions(-) diff --git a/src/Functions/FunctionsConversion.h b/src/Functions/FunctionsConversion.h index 5fbcce4bc59..e4b990b53f4 100644 --- a/src/Functions/FunctionsConversion.h +++ b/src/Functions/FunctionsConversion.h @@ -994,14 +994,22 @@ DEFINE_NAME_TO_INTERVAL(Year) #undef DEFINE_NAME_TO_INTERVAL +struct NameParseDateTimeBestEffort; +struct NameParseDateTimeBestEffortOrZero; +struct NameParseDateTimeBestEffortOrNull; + template -static inline bool isDateTime64(const ColumnsWithTypeAndName &arguments) +static inline bool isDateTime64(const ColumnsWithTypeAndName & arguments, const ColumnNumbers & arguments_index = {}) { if constexpr (std::is_same_v) return true; - else if constexpr (std::is_same_v) + else if constexpr (std::is_same_v || std::is_same_v + || std::is_same_v || std::is_same_v) { - return (arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3; + if (arguments_index.empty()) + return (arguments.size() == 2 && isUnsignedInteger(arguments[1].type)) || arguments.size() == 3; + else + return (arguments_index.size() == 2 && isUnsignedInteger(arguments[arguments_index[1]].type)) || arguments_index.size() == 3; } return false; @@ -1204,7 +1212,7 @@ private: return true; }; - if (isDateTime64(block.getColumnsWithTypeAndName())) + if (isDateTime64(block.getColumnsWithTypeAndName(), arguments)) { /// For toDateTime('xxxx-xx-xx xx:xx:xx.00', 2[, 'timezone']) we need to it convert to DateTime64 const ColumnWithTypeAndName & scale_column = block.getByPosition(arguments[1]); @@ -1273,7 +1281,8 @@ public: DataTypePtr getReturnTypeImpl(const ColumnsWithTypeAndName & arguments) const override { DataTypePtr res; - if constexpr (to_datetime64) + + if (isDateTime64(arguments)) { validateFunctionArgumentTypes(*this, arguments, FunctionArgumentDescriptors{{"string", isStringOrFixedString, nullptr, "String or FixedString"}}, @@ -1283,11 +1292,12 @@ public: {"timezone", isStringOrFixedString, isColumnConst, "const String or FixedString"}, }); - UInt64 scale = DataTypeDateTime64::default_scale; + UInt64 scale = to_datetime64 ? DataTypeDateTime64::default_scale : 0; if (arguments.size() > 1) scale = extractToDecimalScale(arguments[1]); const auto timezone = extractTimeZoneNameFromFunctionArguments(arguments, 2, 0); - res = std::make_shared(scale, timezone); + + res = scale == 0 ? res = std::make_shared(timezone) : std::make_shared(scale, timezone); } else { @@ -1334,6 +1344,8 @@ public: if constexpr (std::is_same_v) res = std::make_shared(extractTimeZoneNameFromFunctionArguments(arguments, 1, 0)); + else if constexpr (std::is_same_v) + throw Exception("LOGICAL ERROR: It is a bug.", ErrorCodes::LOGICAL_ERROR); else if constexpr (to_decimal) { UInt64 scale = extractToDecimalScale(arguments[1]); @@ -1358,42 +1370,53 @@ public: return res; } - void executeImpl(Block & block, const ColumnNumbers & arguments, size_t result, size_t input_rows_count) const override + template + bool executeInternal(Block & block, const ColumnNumbers & arguments, size_t result, size_t input_rows_count, UInt32 scale = 0) const { const IDataType * from_type = block.getByPosition(arguments[0]).type.get(); - bool ok = true; - if constexpr (to_decimal || to_datetime64) + if (checkAndGetDataType(from_type)) { - const UInt32 scale = assert_cast(*removeNullable(block.getByPosition(result).type)).getScale(); - - if (checkAndGetDataType(from_type)) - { - ConvertThroughParsing::execute( - block, arguments, result, input_rows_count, scale); - } - else if (checkAndGetDataType(from_type)) - { - ConvertThroughParsing::execute( - block, arguments, result, input_rows_count, scale); - } - else - ok = false; + ConvertThroughParsing::execute( + block, arguments, result, input_rows_count, scale); + return true; } + else if (checkAndGetDataType(from_type)) + { + ConvertThroughParsing::execute( + block, arguments, result, input_rows_count, scale); + return true; + } + + return false; + } + + void executeImpl(Block & block, const ColumnNumbers & arguments, size_t result, size_t input_rows_count) const override + { + bool ok = true; + + if constexpr (to_decimal) + ok = executeInternal(block, arguments, result, input_rows_count, + assert_cast(*removeNullable(block.getByPosition(result).type)).getScale()); else { - if (checkAndGetDataType(from_type)) + if (isDateTime64(block.getColumnsWithTypeAndName(), arguments)) { - ConvertThroughParsing::execute( - block, arguments, result, input_rows_count); - } - else if (checkAndGetDataType(from_type)) - { - ConvertThroughParsing::execute( - block, arguments, result, input_rows_count); + UInt64 scale = to_datetime64 ? DataTypeDateTime64::default_scale : 0; + if (arguments.size() > 1) + scale = extractToDecimalScale(block.getColumnsWithTypeAndName()[arguments[1]]); + + if (scale == 0) + ok = executeInternal(block, arguments, result, input_rows_count); + else + { + ok = executeInternal(block, arguments, result, input_rows_count, static_cast(scale)); + } } else - ok = false; + { + ok = executeInternal(block, arguments, result, input_rows_count); + } } if (!ok) @@ -1757,6 +1780,9 @@ struct NameParseDateTimeBestEffort { static constexpr auto name = "parseDateTime struct NameParseDateTimeBestEffortUS { static constexpr auto name = "parseDateTimeBestEffortUS"; }; struct NameParseDateTimeBestEffortOrZero { static constexpr auto name = "parseDateTimeBestEffortOrZero"; }; struct NameParseDateTimeBestEffortOrNull { static constexpr auto name = "parseDateTimeBestEffortOrNull"; }; +struct NameParseDateTime32BestEffort { static constexpr auto name = "parseDateTime32BestEffort"; }; +struct NameParseDateTime32BestEffortOrZero { static constexpr auto name = "parseDateTime32BestEffortOrZero"; }; +struct NameParseDateTime32BestEffortOrNull { static constexpr auto name = "parseDateTime32BestEffortOrNull"; }; struct NameParseDateTime64BestEffort { static constexpr auto name = "parseDateTime64BestEffort"; }; struct NameParseDateTime64BestEffortOrZero { static constexpr auto name = "parseDateTime64BestEffortOrZero"; }; struct NameParseDateTime64BestEffortOrNull { static constexpr auto name = "parseDateTime64BestEffortOrNull"; }; From ec1572d7be7edc35d044dac603af2544b381b17e Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Fri, 21 Aug 2020 13:06:06 +0800 Subject: [PATCH 12/73] ISSUES-4006 support parserDateTime32 functions --- src/Functions/FunctionsConversion.cpp | 3 ++ src/Functions/FunctionsConversion.h | 7 +++ .../01442_date_time_with_params.reference | 40 +++++++++++++++ .../01442_date_time_with_params.sql | 50 +++++++++++++++++++ 4 files changed, 100 insertions(+) diff --git a/src/Functions/FunctionsConversion.cpp b/src/Functions/FunctionsConversion.cpp index 804c16d946d..428c6ba8138 100644 --- a/src/Functions/FunctionsConversion.cpp +++ b/src/Functions/FunctionsConversion.cpp @@ -82,6 +82,9 @@ void registerFunctionsConversion(FunctionFactory & factory) factory.registerFunction(); factory.registerFunction(); factory.registerFunction(); + factory.registerFunction(); + factory.registerFunction(); + factory.registerFunction(); factory.registerFunction(); factory.registerFunction(); factory.registerFunction(); diff --git a/src/Functions/FunctionsConversion.h b/src/Functions/FunctionsConversion.h index e4b990b53f4..bcafcc3b59f 100644 --- a/src/Functions/FunctionsConversion.h +++ b/src/Functions/FunctionsConversion.h @@ -1797,6 +1797,13 @@ using FunctionParseDateTimeBestEffortOrZero = FunctionConvertFromString< using FunctionParseDateTimeBestEffortOrNull = FunctionConvertFromString< DataTypeDateTime, NameParseDateTimeBestEffortOrNull, ConvertFromStringExceptionMode::Null, ConvertFromStringParsingMode::BestEffort>; +using FunctionParseDateTime32BestEffort = FunctionConvertFromString< + DataTypeDateTime, NameParseDateTime32BestEffort, ConvertFromStringExceptionMode::Throw, ConvertFromStringParsingMode::BestEffort>; +using FunctionParseDateTime32BestEffortOrZero = FunctionConvertFromString< + DataTypeDateTime, NameParseDateTime32BestEffortOrZero, ConvertFromStringExceptionMode::Zero, ConvertFromStringParsingMode::BestEffort>; +using FunctionParseDateTime32BestEffortOrNull = FunctionConvertFromString< + DataTypeDateTime, NameParseDateTime32BestEffortOrNull, ConvertFromStringExceptionMode::Null, ConvertFromStringParsingMode::BestEffort>; + using FunctionParseDateTime64BestEffort = FunctionConvertFromString< DataTypeDateTime64, NameParseDateTime64BestEffort, ConvertFromStringExceptionMode::Throw, ConvertFromStringParsingMode::BestEffort>; using FunctionParseDateTime64BestEffortOrZero = FunctionConvertFromString< diff --git a/tests/queries/0_stateless/01442_date_time_with_params.reference b/tests/queries/0_stateless/01442_date_time_with_params.reference index 03b591a34bb..f38732b3f2f 100644 --- a/tests/queries/0_stateless/01442_date_time_with_params.reference +++ b/tests/queries/0_stateless/01442_date_time_with_params.reference @@ -2,3 +2,43 @@ 2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') 2020-01-01 00:05:00 DateTime 2020-01-01 00:00:00 DateTime 2020-01-01 00:02:00.11 DateTime64(2) 2020-01-01 00:03:00 DateTime(\'Europe/Moscow\') 2020-01-01 00:04:00.220 DateTime64(3, \'Europe/Moscow\') 2020-01-01 00:05:00 DateTime 2020-01-01 00:00:00 DateTime +2020-05-14 03:37:03.000 DateTime64(3, \'UTC\') +2020-05-14 03:37:03.000 DateTime64(3, \'UTC\') +2020-05-14 03:37:03.253 DateTime64(3, \'UTC\') +2020-05-14 03:37:03.253 DateTime64(3, \'UTC\') +2020-05-14 06:37:03.253 DateTime64(3, \'Europe/Minsk\') +2020-05-14 03:37:03.253 DateTime64(3, \'UTC\') +\N Nullable(DateTime64(3)) +2020-05-14 03:37:03.000 Nullable(DateTime64(3, \'UTC\')) +2020-05-14 03:37:03.000 Nullable(DateTime64(3, \'UTC\')) +2020-05-14 03:37:03.253 Nullable(DateTime64(3, \'UTC\')) +2020-05-14 03:37:03.253 Nullable(DateTime64(3, \'UTC\')) +2020-05-14 06:37:03.253 Nullable(DateTime64(3, \'Europe/Minsk\')) +2020-05-14 03:37:03.253 Nullable(DateTime64(3, \'UTC\')) +1970-01-01 08:00:00.000 DateTime64(3) +2020-05-14 03:37:03.000 DateTime64(3, \'UTC\') +2020-05-14 03:37:03.000 DateTime64(3, \'UTC\') +2020-05-14 03:37:03.253 DateTime64(3, \'UTC\') +2020-05-14 03:37:03.253 DateTime64(3, \'UTC\') +2020-05-14 06:37:03.253 DateTime64(3, \'Europe/Minsk\') +2020-05-14 03:37:03.253 DateTime64(3, \'UTC\') +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 06:37:03 DateTime(\'Europe/Minsk\') +2020-05-14 03:37:03 DateTime(\'UTC\') +\N Nullable(DateTime) +2020-05-14 03:37:03 Nullable(DateTime(\'UTC\')) +2020-05-14 03:37:03 Nullable(DateTime(\'UTC\')) +2020-05-14 03:37:03 Nullable(DateTime(\'UTC\')) +2020-05-14 03:37:03 Nullable(DateTime(\'UTC\')) +2020-05-14 06:37:03 Nullable(DateTime(\'Europe/Minsk\')) +2020-05-14 03:37:03 Nullable(DateTime(\'UTC\')) +1970-01-01 08:00:00 DateTime +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 03:37:03 DateTime(\'UTC\') +2020-05-14 06:37:03 DateTime(\'Europe/Minsk\') +2020-05-14 03:37:03 DateTime(\'UTC\') diff --git a/tests/queries/0_stateless/01442_date_time_with_params.sql b/tests/queries/0_stateless/01442_date_time_with_params.sql index d2664a4e316..5ae7fe22699 100644 --- a/tests/queries/0_stateless/01442_date_time_with_params.sql +++ b/tests/queries/0_stateless/01442_date_time_with_params.sql @@ -12,4 +12,54 @@ SELECT CAST('2020-01-01 00:00:00', 'DateTime') AS a, toTypeName(a), CAST('2020-0 SELECT toDateTime32('2020-01-01 00:00:00') AS a, toTypeName(a); +SELECT parseDateTimeBestEffort('', 3) AS a, toTypeName(a); -- {serverError 6} +SELECT parseDateTimeBestEffort('2020-05-14T03:37:03', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffort('2020-05-14 03:37:03', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffort('2020-05-14T03:37:03.253184', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffort('2020-05-14T03:37:03.253184Z', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffort('2020-05-14T03:37:03.253184Z', 3, 'Europe/Minsk') AS a, toTypeName(a); +SELECT parseDateTimeBestEffort(materialize('2020-05-14T03:37:03.253184Z'), 3, 'UTC') AS a, toTypeName(a); + +SELECT parseDateTimeBestEffortOrNull('', 3) AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrNull('2020-05-14T03:37:03', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrNull('2020-05-14 03:37:03', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrNull('2020-05-14T03:37:03.253184', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrNull('2020-05-14T03:37:03.253184Z', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrNull('2020-05-14T03:37:03.253184Z', 3, 'Europe/Minsk') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrNull(materialize('2020-05-14T03:37:03.253184Z'), 3, 'UTC') AS a, toTypeName(a); + +SELECT parseDateTimeBestEffortOrZero('', 3) AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrZero('2020-05-14T03:37:03', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrZero('2020-05-14 03:37:03', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrZero('2020-05-14T03:37:03.253184', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrZero('2020-05-14T03:37:03.253184Z', 3, 'UTC') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrZero('2020-05-14T03:37:03.253184Z', 3, 'Europe/Minsk') AS a, toTypeName(a); +SELECT parseDateTimeBestEffortOrZero(materialize('2020-05-14T03:37:03.253184Z'), 3, 'UTC') AS a, toTypeName(a); + + +SELECT parseDateTime32BestEffort('') AS a, toTypeName(a); -- {serverError 6} +SELECT parseDateTime32BestEffort('2020-05-14T03:37:03', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffort('2020-05-14 03:37:03', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffort('2020-05-14T03:37:03.253184', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffort('2020-05-14T03:37:03.253184Z', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffort('2020-05-14T03:37:03.253184Z', 'Europe/Minsk') AS a, toTypeName(a); +SELECT parseDateTime32BestEffort(materialize('2020-05-14T03:37:03.253184Z'), 'UTC') AS a, toTypeName(a); + +SELECT parseDateTime32BestEffortOrNull('') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrNull('2020-05-14T03:37:03', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrNull('2020-05-14 03:37:03', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrNull('2020-05-14T03:37:03.253184', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrNull('2020-05-14T03:37:03.253184Z', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrNull('2020-05-14T03:37:03.253184Z', 'Europe/Minsk') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrNull(materialize('2020-05-14T03:37:03.253184Z'), 'UTC') AS a, toTypeName(a); + +SELECT parseDateTime32BestEffortOrZero('') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrZero('2020-05-14T03:37:03', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrZero('2020-05-14 03:37:03', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrZero('2020-05-14T03:37:03.253184', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrZero('2020-05-14T03:37:03.253184Z', 'UTC') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrZero('2020-05-14T03:37:03.253184Z', 'Europe/Minsk') AS a, toTypeName(a); +SELECT parseDateTime32BestEffortOrZero(materialize('2020-05-14T03:37:03.253184Z'), 'UTC') AS a, toTypeName(a); + + DROP TABLE IF EXISTS test; From 3318b6ea00c478a0986d1fe526c172860dac1997 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Fri, 21 Aug 2020 13:08:45 +0800 Subject: [PATCH 13/73] ISSUES-4006 try fix build failure --- src/DataTypes/registerDataTypeDateTime.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/DataTypes/registerDataTypeDateTime.cpp b/src/DataTypes/registerDataTypeDateTime.cpp index 70b89bf7545..815948c6531 100644 --- a/src/DataTypes/registerDataTypeDateTime.cpp +++ b/src/DataTypes/registerDataTypeDateTime.cpp @@ -48,7 +48,7 @@ getArgument(const ASTPtr & arguments, size_t argument_index, const char * argume return {}; else { - if (argument->value.getType() != field_type) + if (argument && argument->value.getType() != field_type) throw Exception(getExceptionMessage(String(" has wrong type: ") + argument->value.getTypeName(), argument_index, argument_name, context_data_type_name, field_type), ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); else From b679b2e30cdf01170352de3007880a01834341b7 Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Fri, 21 Aug 2020 13:16:50 +0800 Subject: [PATCH 14/73] ISSUES-4006 fix toDateTime64 with scale 0 --- src/Functions/FunctionsConversion.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/Functions/FunctionsConversion.h b/src/Functions/FunctionsConversion.h index bcafcc3b59f..5539d73d2eb 100644 --- a/src/Functions/FunctionsConversion.h +++ b/src/Functions/FunctionsConversion.h @@ -1218,7 +1218,7 @@ private: const ColumnWithTypeAndName & scale_column = block.getByPosition(arguments[1]); UInt32 scale = extractToDecimalScale(scale_column); - if (scale != 0) /// When scale = 0, the data type is DateTime otherwise the data type is DateTime64 + if (to_datetime64 || scale != 0) /// When scale = 0, the data type is DateTime otherwise the data type is DateTime64 { if (!callOnIndexAndDataType(from_type->getTypeId(), call)) throw Exception("Illegal type " + block.getByPosition(arguments[0]).type->getName() + " of argument of function " + getName(), From ff84040cd5394516a64688fc2701472325c00be6 Mon Sep 17 00:00:00 2001 From: Winter Zhang Date: Fri, 21 Aug 2020 14:42:31 +0800 Subject: [PATCH 15/73] ISSUES-4006 try fix test failure --- .../queries/0_stateless/01442_date_time_with_params.reference | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/queries/0_stateless/01442_date_time_with_params.reference b/tests/queries/0_stateless/01442_date_time_with_params.reference index f38732b3f2f..f55d095d164 100644 --- a/tests/queries/0_stateless/01442_date_time_with_params.reference +++ b/tests/queries/0_stateless/01442_date_time_with_params.reference @@ -15,7 +15,7 @@ 2020-05-14 03:37:03.253 Nullable(DateTime64(3, \'UTC\')) 2020-05-14 06:37:03.253 Nullable(DateTime64(3, \'Europe/Minsk\')) 2020-05-14 03:37:03.253 Nullable(DateTime64(3, \'UTC\')) -1970-01-01 08:00:00.000 DateTime64(3) +1970-01-01 03:00:00.000 DateTime64(3) 2020-05-14 03:37:03.000 DateTime64(3, \'UTC\') 2020-05-14 03:37:03.000 DateTime64(3, \'UTC\') 2020-05-14 03:37:03.253 DateTime64(3, \'UTC\') @@ -35,7 +35,7 @@ 2020-05-14 03:37:03 Nullable(DateTime(\'UTC\')) 2020-05-14 06:37:03 Nullable(DateTime(\'Europe/Minsk\')) 2020-05-14 03:37:03 Nullable(DateTime(\'UTC\')) -1970-01-01 08:00:00 DateTime +1970-01-01 03:00:00 DateTime 2020-05-14 03:37:03 DateTime(\'UTC\') 2020-05-14 03:37:03 DateTime(\'UTC\') 2020-05-14 03:37:03 DateTime(\'UTC\') From 2a96151516008a7b338346d87a6c88151cc95dae Mon Sep 17 00:00:00 2001 From: Vitaly Baranov Date: Sat, 22 Aug 2020 01:14:34 +0300 Subject: [PATCH 16/73] Fix GRANT ALL statement when executed on a non-global level. --- src/Access/AccessFlags.h | 29 +++++++++ src/Access/AccessRights.cpp | 75 ++++++---------------- src/Access/AccessRightsElement.h | 46 +++++++++++++ src/Interpreters/InterpreterGrantQuery.cpp | 2 +- src/Parsers/ASTGrantQuery.cpp | 8 +++ src/Parsers/ASTGrantQuery.h | 1 + src/Parsers/ParserGrantQuery.cpp | 27 ++++++++ 7 files changed, 131 insertions(+), 57 deletions(-) diff --git a/src/Access/AccessFlags.h b/src/Access/AccessFlags.h index 9b801fd88a3..11d39585238 100644 --- a/src/Access/AccessFlags.h +++ b/src/Access/AccessFlags.h @@ -96,6 +96,22 @@ public: /// Returns all the flags related to a dictionary. static AccessFlags allDictionaryFlags(); + /// Returns all the flags which could be granted on the global level. + /// The same as allFlags(). + static AccessFlags allFlagsGrantableOnGlobalLevel(); + + /// Returns all the flags which could be granted on the global level. + /// Returns allDatabaseFlags() | allTableFlags() | allDictionaryFlags() | allColumnFlags(). + static AccessFlags allFlagsGrantableOnDatabaseLevel(); + + /// Returns all the flags which could be granted on the table level. + /// Returns allTableFlags() | allDictionaryFlags() | allColumnFlags(). + static AccessFlags allFlagsGrantableOnTableLevel(); + + /// Returns all the flags which could be granted on the global level. + /// The same as allColumnFlags(). + static AccessFlags allFlagsGrantableOnColumnLevel(); + private: static constexpr size_t NUM_FLAGS = 128; using Flags = std::bitset; @@ -193,6 +209,10 @@ public: const Flags & getTableFlags() const { return all_flags_for_target[TABLE]; } const Flags & getColumnFlags() const { return all_flags_for_target[COLUMN]; } const Flags & getDictionaryFlags() const { return all_flags_for_target[DICTIONARY]; } + const Flags & getAllFlagsGrantableOnGlobalLevel() const { return getAllFlags(); } + const Flags & getAllFlagsGrantableOnDatabaseLevel() const { return all_flags_grantable_on_database_level; } + const Flags & getAllFlagsGrantableOnTableLevel() const { return all_flags_grantable_on_table_level; } + const Flags & getAllFlagsGrantableOnColumnLevel() const { return getColumnFlags(); } private: enum NodeType @@ -381,6 +401,9 @@ private: } for (const auto & child : start_node->children) collectAllFlags(child.get()); + + all_flags_grantable_on_table_level = all_flags_for_target[TABLE] | all_flags_for_target[DICTIONARY] | all_flags_for_target[COLUMN]; + all_flags_grantable_on_database_level = all_flags_for_target[DATABASE] | all_flags_grantable_on_table_level; } Impl() @@ -431,6 +454,8 @@ private: std::vector access_type_to_flags_mapping; Flags all_flags; Flags all_flags_for_target[static_cast(DICTIONARY) + 1]; + Flags all_flags_grantable_on_database_level; + Flags all_flags_grantable_on_table_level; }; @@ -447,6 +472,10 @@ inline AccessFlags AccessFlags::allDatabaseFlags() { return Impl<>::instance().g inline AccessFlags AccessFlags::allTableFlags() { return Impl<>::instance().getTableFlags(); } inline AccessFlags AccessFlags::allColumnFlags() { return Impl<>::instance().getColumnFlags(); } inline AccessFlags AccessFlags::allDictionaryFlags() { return Impl<>::instance().getDictionaryFlags(); } +inline AccessFlags AccessFlags::allFlagsGrantableOnGlobalLevel() { return Impl<>::instance().getAllFlagsGrantableOnGlobalLevel(); } +inline AccessFlags AccessFlags::allFlagsGrantableOnDatabaseLevel() { return Impl<>::instance().getAllFlagsGrantableOnDatabaseLevel(); } +inline AccessFlags AccessFlags::allFlagsGrantableOnTableLevel() { return Impl<>::instance().getAllFlagsGrantableOnTableLevel(); } +inline AccessFlags AccessFlags::allFlagsGrantableOnColumnLevel() { return Impl<>::instance().getAllFlagsGrantableOnColumnLevel(); } inline AccessFlags operator |(AccessType left, AccessType right) { return AccessFlags(left) | right; } inline AccessFlags operator &(AccessType left, AccessType right) { return AccessFlags(left) & right; } diff --git a/src/Access/AccessRights.cpp b/src/Access/AccessRights.cpp index 65c78f39e86..8ce71dd8da8 100644 --- a/src/Access/AccessRights.cpp +++ b/src/Access/AccessRights.cpp @@ -1,5 +1,4 @@ #include -#include #include #include #include @@ -8,12 +7,6 @@ namespace DB { -namespace ErrorCodes -{ - extern const int INVALID_GRANT; -} - - namespace { using Kind = AccessRightsElementWithOptions::Kind; @@ -214,30 +207,14 @@ namespace COLUMN_LEVEL, }; - AccessFlags getAcceptableFlags(Level level) + AccessFlags getAllGrantableFlags(Level level) { switch (level) { - case GLOBAL_LEVEL: - { - static const AccessFlags res = AccessFlags::allFlags(); - return res; - } - case DATABASE_LEVEL: - { - static const AccessFlags res = AccessFlags::allDatabaseFlags() | AccessFlags::allTableFlags() | AccessFlags::allDictionaryFlags() | AccessFlags::allColumnFlags(); - return res; - } - case TABLE_LEVEL: - { - static const AccessFlags res = AccessFlags::allTableFlags() | AccessFlags::allDictionaryFlags() | AccessFlags::allColumnFlags(); - return res; - } - case COLUMN_LEVEL: - { - static const AccessFlags res = AccessFlags::allColumnFlags(); - return res; - } + case GLOBAL_LEVEL: return AccessFlags::allFlagsGrantableOnGlobalLevel(); + case DATABASE_LEVEL: return AccessFlags::allFlagsGrantableOnDatabaseLevel(); + case TABLE_LEVEL: return AccessFlags::allFlagsGrantableOnTableLevel(); + case COLUMN_LEVEL: return AccessFlags::allFlagsGrantableOnColumnLevel(); } __builtin_unreachable(); } @@ -276,21 +253,7 @@ public: void grant(const AccessFlags & flags_) { - if (!flags_) - return; - - AccessFlags flags_to_add = flags_ & getAcceptableFlags(); - - if (!flags_to_add) - { - if (level == DATABASE_LEVEL) - throw Exception(flags_.toString() + " cannot be granted on the database level", ErrorCodes::INVALID_GRANT); - else if (level == TABLE_LEVEL) - throw Exception(flags_.toString() + " cannot be granted on the table level", ErrorCodes::INVALID_GRANT); - else if (level == COLUMN_LEVEL) - throw Exception(flags_.toString() + " cannot be granted on the column level", ErrorCodes::INVALID_GRANT); - } - + AccessFlags flags_to_add = flags_ & getAllGrantableFlags(); addGrantsRec(flags_to_add); optimizeTree(); } @@ -456,8 +419,8 @@ public: } private: - AccessFlags getAcceptableFlags() const { return ::DB::getAcceptableFlags(level); } - AccessFlags getChildAcceptableFlags() const { return ::DB::getAcceptableFlags(static_cast(level + 1)); } + AccessFlags getAllGrantableFlags() const { return ::DB::getAllGrantableFlags(level); } + AccessFlags getChildAllGrantableFlags() const { return ::DB::getAllGrantableFlags(static_cast(level + 1)); } Node * tryGetChild(const std::string_view & name) const { @@ -480,7 +443,7 @@ private: Node & new_child = (*children)[*new_child_name]; new_child.node_name = std::move(new_child_name); new_child.level = static_cast(level + 1); - new_child.flags = flags & new_child.getAcceptableFlags(); + new_child.flags = flags & new_child.getAllGrantableFlags(); return new_child; } @@ -496,12 +459,12 @@ private: bool canEraseChild(const Node & child) const { - return ((flags & child.getAcceptableFlags()) == child.flags) && !child.children; + return ((flags & child.getAllGrantableFlags()) == child.flags) && !child.children; } void addGrantsRec(const AccessFlags & flags_) { - if (auto flags_to_add = flags_ & getAcceptableFlags()) + if (auto flags_to_add = flags_ & getAllGrantableFlags()) { flags |= flags_to_add; if (children) @@ -547,7 +510,7 @@ private: const AccessFlags & parent_flags) { auto flags = node.flags; - auto parent_fl = parent_flags & node.getAcceptableFlags(); + auto parent_fl = parent_flags & node.getAllGrantableFlags(); auto revokes = parent_fl - flags; auto grants = flags - parent_fl; @@ -576,9 +539,9 @@ private: const Node * node_go, const AccessFlags & parent_flags_go) { - auto acceptable_flags = ::DB::getAcceptableFlags(static_cast(full_name.size())); - auto parent_fl = parent_flags & acceptable_flags; - auto parent_fl_go = parent_flags_go & acceptable_flags; + auto grantable_flags = ::DB::getAllGrantableFlags(static_cast(full_name.size())); + auto parent_fl = parent_flags & grantable_flags; + auto parent_fl_go = parent_flags_go & grantable_flags; auto flags = node ? node->flags : parent_fl; auto flags_go = node_go ? node_go->flags : parent_fl_go; auto revokes = parent_fl - flags; @@ -672,8 +635,8 @@ private: } max_flags_with_children |= max_among_children; - AccessFlags add_acceptable_flags = getAcceptableFlags() - getChildAcceptableFlags(); - min_flags_with_children &= min_among_children | add_acceptable_flags; + AccessFlags add_flags = getAllGrantableFlags() - getChildAllGrantableFlags(); + min_flags_with_children &= min_among_children | add_flags; } void makeUnionRec(const Node & rhs) @@ -689,7 +652,7 @@ private: for (auto & [lhs_childname, lhs_child] : *children) { if (!rhs.tryGetChild(lhs_childname)) - lhs_child.flags |= rhs.flags & lhs_child.getAcceptableFlags(); + lhs_child.flags |= rhs.flags & lhs_child.getAllGrantableFlags(); } } } @@ -738,7 +701,7 @@ private: if (new_flags != flags) { - new_flags &= getAcceptableFlags(); + new_flags &= getAllGrantableFlags(); flags_added |= static_cast(new_flags - flags); flags_removed |= static_cast(flags - new_flags); flags = new_flags; diff --git a/src/Access/AccessRightsElement.h b/src/Access/AccessRightsElement.h index f9f7c433308..36cb64e6eba 100644 --- a/src/Access/AccessRightsElement.h +++ b/src/Access/AccessRightsElement.h @@ -71,6 +71,8 @@ struct AccessRightsElement { } + bool empty() const { return !access_flags || (!any_column && columns.empty()); } + auto toTuple() const { return std::tie(access_flags, any_database, database, any_table, table, any_column, columns); } friend bool operator==(const AccessRightsElement & left, const AccessRightsElement & right) { return left.toTuple() == right.toTuple(); } friend bool operator!=(const AccessRightsElement & left, const AccessRightsElement & right) { return !(left == right); } @@ -86,6 +88,9 @@ struct AccessRightsElement /// If the database is empty, replaces it with `new_database`. Otherwise does nothing. void replaceEmptyDatabase(const String & new_database); + /// Resets flags which cannot be granted. + void removeNonGrantableFlags(); + /// Returns a human-readable representation like "SELECT, UPDATE(x, y) ON db.table". String toString() const; }; @@ -111,6 +116,9 @@ struct AccessRightsElementWithOptions : public AccessRightsElement friend bool operator==(const AccessRightsElementWithOptions & left, const AccessRightsElementWithOptions & right) { return left.toTuple() == right.toTuple(); } friend bool operator!=(const AccessRightsElementWithOptions & left, const AccessRightsElementWithOptions & right) { return !(left == right); } + /// Resets flags which cannot be granted. + void removeNonGrantableFlags(); + /// Returns a human-readable representation like "GRANT SELECT, UPDATE(x, y) ON db.table". String toString() const; }; @@ -120,9 +128,14 @@ struct AccessRightsElementWithOptions : public AccessRightsElement class AccessRightsElements : public std::vector { public: + bool empty() const { return std::all_of(begin(), end(), [](const AccessRightsElement & e) { return e.empty(); }); } + /// Replaces the empty database with `new_database`. void replaceEmptyDatabase(const String & new_database); + /// Resets flags which cannot be granted. + void removeNonGrantableFlags(); + /// Returns a human-readable representation like "GRANT SELECT, UPDATE(x, y) ON db.table". String toString() const; }; @@ -134,6 +147,9 @@ public: /// Replaces the empty database with `new_database`. void replaceEmptyDatabase(const String & new_database); + /// Resets flags which cannot be granted. + void removeNonGrantableFlags(); + /// Returns a human-readable representation like "GRANT SELECT, UPDATE(x, y) ON db.table". String toString() const; }; @@ -157,4 +173,34 @@ inline void AccessRightsElementsWithOptions::replaceEmptyDatabase(const String & element.replaceEmptyDatabase(new_database); } +inline void AccessRightsElement::removeNonGrantableFlags() +{ + if (!any_column) + access_flags &= AccessFlags::allFlagsGrantableOnColumnLevel(); + else if (!any_table) + access_flags &= AccessFlags::allFlagsGrantableOnTableLevel(); + else if (!any_database) + access_flags &= AccessFlags::allFlagsGrantableOnDatabaseLevel(); + else + access_flags &= AccessFlags::allFlagsGrantableOnGlobalLevel(); +} + +inline void AccessRightsElementWithOptions::removeNonGrantableFlags() +{ + if (kind == Kind::GRANT) + AccessRightsElement::removeNonGrantableFlags(); +} + +inline void AccessRightsElements::removeNonGrantableFlags() +{ + for (auto & element : *this) + element.removeNonGrantableFlags(); +} + +inline void AccessRightsElementsWithOptions::removeNonGrantableFlags() +{ + for (auto & element : *this) + element.removeNonGrantableFlags(); +} + } diff --git a/src/Interpreters/InterpreterGrantQuery.cpp b/src/Interpreters/InterpreterGrantQuery.cpp index 2f468507eb6..57cb701036e 100644 --- a/src/Interpreters/InterpreterGrantQuery.cpp +++ b/src/Interpreters/InterpreterGrantQuery.cpp @@ -29,7 +29,6 @@ namespace current_access.grant(access_to_grant); } - AccessRightsElements getFilteredAccessRightsElementsToRevoke( const AccessRights & current_access, const AccessRightsElements & access_to_revoke, bool grant_option) { @@ -214,6 +213,7 @@ BlockIO InterpreterGrantQuery::execute() auto access = context.getAccess(); auto & access_control = context.getAccessControlManager(); query.replaceEmptyDatabaseWithCurrent(context.getCurrentDatabase()); + query.removeNonGrantableFlags(); RolesOrUsersSet roles_from_query; if (query.roles) diff --git a/src/Parsers/ASTGrantQuery.cpp b/src/Parsers/ASTGrantQuery.cpp index ae9649cdddc..63489e0417f 100644 --- a/src/Parsers/ASTGrantQuery.cpp +++ b/src/Parsers/ASTGrantQuery.cpp @@ -144,4 +144,12 @@ void ASTGrantQuery::replaceCurrentUserTagWithName(const String & current_user_na if (to_roles) to_roles->replaceCurrentUserTagWithName(current_user_name); } + + +void ASTGrantQuery::removeNonGrantableFlags() +{ + if (kind == Kind::GRANT) + access_rights_elements.removeNonGrantableFlags(); +} + } diff --git a/src/Parsers/ASTGrantQuery.h b/src/Parsers/ASTGrantQuery.h index c36e42689a5..5f172fe3298 100644 --- a/src/Parsers/ASTGrantQuery.h +++ b/src/Parsers/ASTGrantQuery.h @@ -33,6 +33,7 @@ public: void formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const override; void replaceEmptyDatabaseWithCurrent(const String & current_database); void replaceCurrentUserTagWithName(const String & current_user_name) const; + void removeNonGrantableFlags(); ASTPtr getRewrittenASTWithoutOnCluster(const std::string &) const override { return removeOnCluster(clone()); } }; } diff --git a/src/Parsers/ParserGrantQuery.cpp b/src/Parsers/ParserGrantQuery.cpp index 6e42b165b21..7dd721c9af2 100644 --- a/src/Parsers/ParserGrantQuery.cpp +++ b/src/Parsers/ParserGrantQuery.cpp @@ -14,6 +14,7 @@ namespace DB { namespace ErrorCodes { + extern const int INVALID_GRANT; extern const int SYNTAX_ERROR; } @@ -156,6 +157,29 @@ namespace } + void removeNonGrantableFlags(AccessRightsElements & elements) + { + for (auto & element : elements) + { + if (element.empty()) + continue; + auto old_flags = element.access_flags; + element.removeNonGrantableFlags(); + if (!element.empty()) + continue; + + if (!element.any_column) + throw Exception(old_flags.toString() + " cannot be granted on the column level", ErrorCodes::INVALID_GRANT); + else if (!element.any_table) + throw Exception(old_flags.toString() + " cannot be granted on the table level", ErrorCodes::INVALID_GRANT); + else if (!element.any_database) + throw Exception(old_flags.toString() + " cannot be granted on the database level", ErrorCodes::INVALID_GRANT); + else + throw Exception(old_flags.toString() + " cannot be granted", ErrorCodes::INVALID_GRANT); + } + } + + bool parseRoles(IParser::Pos & pos, Expected & expected, Kind kind, bool id_mode, std::shared_ptr & roles) { return IParserBase::wrapParseImpl(pos, [&] @@ -274,6 +298,9 @@ bool ParserGrantQuery::parseImpl(Pos & pos, ASTPtr & node, Expected & expected) if (admin_option && !elements.empty()) throw Exception("ADMIN OPTION should be specified for roles", ErrorCodes::SYNTAX_ERROR); + if (kind == Kind::GRANT) + removeNonGrantableFlags(elements); + auto query = std::make_shared(); node = query; From 4c8a8d5e67ec613f9d164366279e9e7b81577111 Mon Sep 17 00:00:00 2001 From: Vitaly Baranov Date: Sat, 22 Aug 2020 01:37:01 +0300 Subject: [PATCH 17/73] Add test. --- tests/integration/test_grant_and_revoke/test.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tests/integration/test_grant_and_revoke/test.py b/tests/integration/test_grant_and_revoke/test.py index 92ffb78a1cb..1557e81bce8 100644 --- a/tests/integration/test_grant_and_revoke/test.py +++ b/tests/integration/test_grant_and_revoke/test.py @@ -107,6 +107,15 @@ def test_revoke_requires_grant_option(): assert instance.query("SHOW GRANTS FOR B") == "" +def test_grant_all_on_table(): + instance.query("CREATE USER A, B") + instance.query("GRANT ALL ON test.table TO A WITH GRANT OPTION") + instance.query("GRANT ALL ON test.table TO B", user='A') + assert instance.query("SHOW GRANTS FOR B") == "GRANT SHOW TABLES, SHOW COLUMNS, SHOW DICTIONARIES, SELECT, INSERT, ALTER, CREATE TABLE, CREATE VIEW, CREATE DICTIONARY, DROP TABLE, DROP VIEW, DROP DICTIONARY, TRUNCATE, OPTIMIZE, SYSTEM MERGES, SYSTEM TTL MERGES, SYSTEM FETCHES, SYSTEM MOVES, SYSTEM SENDS, SYSTEM REPLICATION QUEUES, SYSTEM DROP REPLICA, SYSTEM SYNC REPLICA, SYSTEM RESTART REPLICA, SYSTEM FLUSH DISTRIBUTED, dictGet ON test.table TO B\n" + instance.query("REVOKE ALL ON test.table FROM B", user='A') + assert instance.query("SHOW GRANTS FOR B") == "" + + def test_implicit_show_grants(): instance.query("CREATE USER A") assert instance.query("select count() FROM system.databases WHERE name='test'", user="A") == "0\n" From 308e094d04401144603fb12a64b4604bb0bde02d Mon Sep 17 00:00:00 2001 From: Azat Khuzhin Date: Tue, 25 Aug 2020 21:06:21 +0300 Subject: [PATCH 18/73] Fix arrayJoin() capturing in lambda Fixes the following LOGICAL_ERROR: $ clickhouse-client -q 'select arrayFilter((a) -> ((a, arrayJoin([[]])) IN (Null, [Null])), [])' 2020.08.16 00:32:01.967102 [ 1744189 ] {b40a5ebd-d710-4f03-bb18-57db67de1181} : Logical error: 'Lambda captured argument arrayJoin(array(array())) not found in required columns.'. clickhouse-server: ../src/Common/Exception.cpp:45: DB::Exception::Exception(const string&, int): Assertion `false' failed. Since there are multiple input columns for arrayJoin(): (gdb) p captured_names_ $6 = std::vector of length 3, capacity 4 = {"arrayJoin(array(array()))", "arrayJoin(array(array()))", "__set"} While FunctionCaptureOverloadResolver cannot handle non-unique columns. --- src/Interpreters/ActionsVisitor.cpp | 15 ++++++++++++++- src/Interpreters/ActionsVisitor.h | 7 +++++++ .../0_stateless/01407_lambda_arrayJoin.reference | 1 + .../0_stateless/01407_lambda_arrayJoin.sql | 6 ++++++ 4 files changed, 28 insertions(+), 1 deletion(-) create mode 100644 tests/queries/0_stateless/01407_lambda_arrayJoin.reference create mode 100644 tests/queries/0_stateless/01407_lambda_arrayJoin.sql diff --git a/src/Interpreters/ActionsVisitor.cpp b/src/Interpreters/ActionsVisitor.cpp index f2a1d570773..0df83f11c1f 100644 --- a/src/Interpreters/ActionsVisitor.cpp +++ b/src/Interpreters/ActionsVisitor.cpp @@ -447,6 +447,19 @@ void ScopeStack::addAction(const ExpressionAction & action) } } +void ScopeStack::addActionNoInput(const ExpressionAction & action) +{ + size_t level = 0; + Names required = action.getNeededColumns(); + for (const auto & elem : required) + level = std::max(level, getColumnLevel(elem)); + + Names added; + stack[level].actions->add(action, added); + + stack[level].new_columns.insert(added.begin(), added.end()); +} + ExpressionActionsPtr ScopeStack::popLevel() { ExpressionActionsPtr res = stack.back().actions; @@ -549,7 +562,7 @@ void ActionsMatcher::visit(const ASTFunction & node, const ASTPtr & ast, Data & /// It could have been possible to implement arrayJoin which keeps source column, /// but in this case it will always be replicated (as many arrays), which is expensive. String tmp_name = data.getUniqueName("_array_join_" + arg->getColumnName()); - data.addAction(ExpressionAction::copyColumn(arg->getColumnName(), tmp_name)); + data.addActionNoInput(ExpressionAction::copyColumn(arg->getColumnName(), tmp_name)); data.addAction(ExpressionAction::arrayJoin(tmp_name, result_name)); } diff --git a/src/Interpreters/ActionsVisitor.h b/src/Interpreters/ActionsVisitor.h index dbcc54c01d6..d8d85f1c0bf 100644 --- a/src/Interpreters/ActionsVisitor.h +++ b/src/Interpreters/ActionsVisitor.h @@ -12,6 +12,7 @@ namespace DB class Context; class ASTFunction; +struct ExpressionAction; class ExpressionActions; using ExpressionActionsPtr = std::shared_ptr; @@ -49,6 +50,8 @@ struct ScopeStack size_t getColumnLevel(const std::string & name); void addAction(const ExpressionAction & action); + /// For arrayJoin() to avoid double columns in the input. + void addActionNoInput(const ExpressionAction & action); ExpressionActionsPtr popLevel(); @@ -115,6 +118,10 @@ public: { actions_stack.addAction(action); } + void addActionNoInput(const ExpressionAction & action) + { + actions_stack.addActionNoInput(action); + } const Block & getSampleBlock() const { diff --git a/tests/queries/0_stateless/01407_lambda_arrayJoin.reference b/tests/queries/0_stateless/01407_lambda_arrayJoin.reference new file mode 100644 index 00000000000..fe51488c706 --- /dev/null +++ b/tests/queries/0_stateless/01407_lambda_arrayJoin.reference @@ -0,0 +1 @@ +[] diff --git a/tests/queries/0_stateless/01407_lambda_arrayJoin.sql b/tests/queries/0_stateless/01407_lambda_arrayJoin.sql new file mode 100644 index 00000000000..4f34bb59527 --- /dev/null +++ b/tests/queries/0_stateless/01407_lambda_arrayJoin.sql @@ -0,0 +1,6 @@ +SELECT arrayFilter((a) -> ((a, arrayJoin([])) IN (Null, [Null])), []); +SELECT arrayFilter((a) -> ((a, arrayJoin([[]])) IN (Null, [Null])), []); + +-- simplified from the https://clickhouse-test-reports.s3.yandex.net/10373/6c4748a63e7acde2cc3283d96ffec590aae1e724/fuzzer/fuzzer.log#fail1 +SELECT * FROM system.one ARRAY JOIN arrayFilter((a) -> ((a, arrayJoin([])) IN (NULL)), []) AS arr_x; -- { serverError 43; } +SELECT * FROM numbers(1) LEFT ARRAY JOIN arrayFilter((x_0, x_1) -> (arrayJoin([]) IN (NULL)), [], []) AS arr_x; From c09891b4f8b6c78eebbd1ed9acd08e9a921b5197 Mon Sep 17 00:00:00 2001 From: romanzhukov Date: Wed, 26 Aug 2020 02:12:51 +0300 Subject: [PATCH 19/73] DOCSUP-203: Update by PR#11558. --- docs/ru/operations/utilities/clickhouse-copier.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/ru/operations/utilities/clickhouse-copier.md b/docs/ru/operations/utilities/clickhouse-copier.md index b05db93b28b..b43f5ccaf7a 100644 --- a/docs/ru/operations/utilities/clickhouse-copier.md +++ b/docs/ru/operations/utilities/clickhouse-copier.md @@ -24,7 +24,7 @@ Утилиту следует запускать вручную следующим образом: ``` bash -$ clickhouse-copier copier --daemon --config zookeeper.xml --task-path /task/path --base-dir /path/to/dir +$ clickhouse-copier --daemon --config zookeeper.xml --task-path /task/path --base-dir /path/to/dir ``` Параметры запуска: From 3f53553522a34e1dd2312d8c7e85d9ae687f9df5 Mon Sep 17 00:00:00 2001 From: romanzhukov Date: Wed, 26 Aug 2020 02:37:32 +0300 Subject: [PATCH 20/73] DOCSUP-2031: Update by PR#11242. Added temporary_files_codec and join_on_disk_max_files_to_merge settings. --- docs/ru/operations/settings/settings.md | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/docs/ru/operations/settings/settings.md b/docs/ru/operations/settings/settings.md index e8d3f1057df..ab64fb757f1 100644 --- a/docs/ru/operations/settings/settings.md +++ b/docs/ru/operations/settings/settings.md @@ -401,12 +401,33 @@ INSERT INTO test VALUES (lower('Hello')), (lower('world')), (lower('INSERT')), ( Устанавливает тип поведения [JOIN](../../sql-reference/statements/select/join.md). При объединении таблиц могут появиться пустые ячейки. ClickHouse заполняет их по-разному в зависимости от настроек. -Возможные значения +Возможные значения: - 0 — пустые ячейки заполняются значением по умолчанию соответствующего типа поля. - 1 — `JOIN` ведёт себя как в стандартном SQL. Тип соответствующего поля преобразуется в [Nullable](../../sql-reference/data-types/nullable.md#data_type-nullable), а пустые ячейки заполняются значениями [NULL](../../sql-reference/syntax.md). -Значение по умолчанию: 0. +## join_on_disk_max_files_to_merge {#join_on_disk_max_files_to_merge} + +Устанавливет количество файлов, разрешенных для параллельной сортировки, при выполнении операций MergeJoin на диске. + +Чем больше значение параметра, тем больше оперативной памяти используется и тем меньше используется диск (I/O). + +Возможные значения: + +- Положительное целое число, больше 2. + +Значение по умолчанию: 64. + +## temporary_files_codec {#temporary_files_codec} + +Устанавливает метод сжатия для временных файлов на диске, используемых при сортировки и объединения. + +Возможные значения: + +- LZ4 — применять сжатие, используя алгоритм [LZ4](https://ru.wikipedia.org/wiki/LZ4) +- NONE — не применять сжатие. + +Значение по умолчанию: LZ4. ## max\_block\_size {#setting-max_block_size} From c48d3b9d63f38e6a9f281b39060ab5e7bfbd5dfb Mon Sep 17 00:00:00 2001 From: 243f6a88 85a308d3 <33170174+243f6a8885a308d313198a2e037@users.noreply.github.com> Date: Wed, 26 Aug 2020 10:28:03 +0900 Subject: [PATCH 21/73] fixed Japanese translation for data-types/date.md --- docs/ja/sql-reference/data-types/date.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/docs/ja/sql-reference/data-types/date.md b/docs/ja/sql-reference/data-types/date.md index ff6e028e885..528872d61c2 100644 --- a/docs/ja/sql-reference/data-types/date.md +++ b/docs/ja/sql-reference/data-types/date.md @@ -7,8 +7,7 @@ toc_title: "\u65E5\u4ED8" # 日付 {#date} -デートだ 1970-01-01(符号なし)以降の日数として二バイト単位で格納されます。 Unixエポックの開始直後から、コンパイル段階で定数によって定義される上限しきい値までの値を格納できます（現在は2106年までですが、完全にサポート -最小値は1970-01-01として出力されます。 +日付型です。 1970-01-01 からの日数が2バイトの符号なし整数として格納されます。 UNIX時間の開始直後から、変換段階で定数として定義される上限しきい値までの値を格納できます（現在は2106年までですが、一年分を完全にサポートしているのは2105年までです）。 日付値は、タイムゾーンなしで格納されます。 From cdcdb5a2c1f94cd629b2f1103340a6e08750c2fc Mon Sep 17 00:00:00 2001 From: Ivan Blinkov Date: Wed, 26 Aug 2020 10:47:00 +0300 Subject: [PATCH 22/73] Update date.md --- docs/ja/sql-reference/data-types/date.md | 2 -- 1 file changed, 2 deletions(-) diff --git a/docs/ja/sql-reference/data-types/date.md b/docs/ja/sql-reference/data-types/date.md index 528872d61c2..bcdc8f7224d 100644 --- a/docs/ja/sql-reference/data-types/date.md +++ b/docs/ja/sql-reference/data-types/date.md @@ -1,6 +1,4 @@ --- -machine_translated: true -machine_translated_rev: 72537a2d527c63c07aa5d2361a8829f3895cf2bd toc_priority: 47 toc_title: "\u65E5\u4ED8" --- From 0f3351d983775eeee067d5d9d2e538238ed343bf Mon Sep 17 00:00:00 2001 From: Vitaly Baranov Date: Wed, 26 Aug 2020 13:22:08 +0300 Subject: [PATCH 23/73] Fix testflows checks. --- .../rbac/tests/syntax/grant_privilege.py | 47 ++++++++++--------- 1 file changed, 24 insertions(+), 23 deletions(-) diff --git a/tests/testflows/rbac/tests/syntax/grant_privilege.py b/tests/testflows/rbac/tests/syntax/grant_privilege.py index cabb3a3780b..82c459f546d 100755 --- a/tests/testflows/rbac/tests/syntax/grant_privilege.py +++ b/tests/testflows/rbac/tests/syntax/grant_privilege.py @@ -20,30 +20,30 @@ def setup(node): node.query("DROP ROLE IF EXISTS role1") @TestOutline(Scenario) -@Examples("privilege on allow_introspection", [ - ("dictGet", ("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_DictGet("1.0"))), - ("INTROSPECTION", ("*.*",), True, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Introspection("1.0"))), - ("SELECT", ("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Select("1.0"))), - ("INSERT",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Insert("1.0"))), - ("ALTER",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Alter("1.0"))), - ("CREATE",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Create("1.0"))), - ("DROP",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Drop("1.0"))), - ("TRUNCATE",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Truncate("1.0"))), - ("OPTIMIZE",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Optimize("1.0"))), - ("SHOW",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Show("1.0"))), - ("KILL QUERY",("*.*",), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_KillQuery("1.0"))), - ("ACCESS MANAGEMENT",("*.*",), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_AccessManagement("1.0"))), - ("SYSTEM",("db0.table0","db0.*","*.*","tb0","*"), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_System("1.0"))), - ("SOURCES",("*.*",), False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Sources("1.0"))), - ("ALL",("*.*",), True, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_All("1.0"))), - ("ALL PRIVILEGES",("*.*",), True, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_All("1.0"))), #alias for all +@Examples("privilege on allow_column allow_introspection", [ + ("dictGet", ("db0.table0","db0.*","*.*","tb0","*"), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_DictGet("1.0"))), + ("INTROSPECTION", ("*.*",), False, True, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Introspection("1.0"))), + ("SELECT", ("db0.table0","db0.*","*.*","tb0","*"), True, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Select("1.0"))), + ("INSERT",("db0.table0","db0.*","*.*","tb0","*"), True, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Insert("1.0"))), + ("ALTER",("db0.table0","db0.*","*.*","tb0","*"), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Alter("1.0"))), + ("CREATE",("db0.table0","db0.*","*.*","tb0","*"), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Create("1.0"))), + ("DROP",("db0.table0","db0.*","*.*","tb0","*"), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Drop("1.0"))), + ("TRUNCATE",("db0.table0","db0.*","*.*","tb0","*"), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Truncate("1.0"))), + ("OPTIMIZE",("db0.table0","db0.*","*.*","tb0","*"), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Optimize("1.0"))), + ("SHOW",("db0.table0","db0.*","*.*","tb0","*"), True, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Show("1.0"))), + ("KILL QUERY",("*.*",), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_KillQuery("1.0"))), + ("ACCESS MANAGEMENT",("*.*",), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_AccessManagement("1.0"))), + ("SYSTEM",("db0.table0","db0.*","*.*","tb0","*"), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_System("1.0"))), + ("SOURCES",("*.*",), False, False, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_Sources("1.0"))), + ("ALL",("*.*",), True, True, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_All("1.0"))), + ("ALL PRIVILEGES",("*.*",), True, True, Requirements(RQ_SRS_006_RBAC_Grant_Privilege_All("1.0"))), #alias for all ],) -def grant_privileges(self, privilege, on, allow_introspection, node="clickhouse1"): - grant_privilege(privilege=privilege, on=on, allow_introspection=allow_introspection, node=node) +def grant_privileges(self, privilege, on, allow_column, allow_introspection, node="clickhouse1"): + grant_privilege(privilege=privilege, on=on, allow_column=allow_column, allow_introspection=allow_introspection, node=node) @TestOutline(Scenario) @Requirements(RQ_SRS_006_RBAC_Grant_Privilege_GrantOption("1.0")) -def grant_privilege(self, privilege, on, allow_introspection, node="clickhouse1"): +def grant_privilege(self, privilege, on, allow_column, allow_introspection, node="clickhouse1"): node = self.context.cluster.node(node) for on_ in on: @@ -58,9 +58,10 @@ def grant_privilege(self, privilege, on, allow_introspection, node="clickhouse1" with When("I grant privilege with grant option"): node.query(f"GRANT {privilege} ON {on_} TO user1 WITH GRANT OPTION", settings=settings) - #grant column specific for some column 'x' - with When("I grant privilege with columns"): - node.query(f"GRANT {privilege}(x) ON {on_} TO user0", settings=settings) + if allow_column and ('*' not in on_): + #grant column specific for some column 'x' + with When("I grant privilege with columns"): + node.query(f"GRANT {privilege}(x) ON {on_} TO user0", settings=settings) @TestFeature @Name("grant privilege") From 7ac4bd7d1efe26a7693e72752696092704483e4a Mon Sep 17 00:00:00 2001 From: Vitaly Baranov Date: Fri, 21 Aug 2020 18:47:37 +0300 Subject: [PATCH 24/73] Add storages from after ones from and . --- src/Access/AccessControlManager.cpp | 44 ++++++++----------- .../configs/local_directories.xml | 2 + .../test_user_directories/configs/memory.xml | 3 ++ .../configs/mixed_style.xml | 8 ++++ .../configs/old_style.xml | 1 + .../configs/relative_path.xml | 3 ++ .../integration/test_user_directories/test.py | 8 ++++ 7 files changed, 43 insertions(+), 26 deletions(-) create mode 100644 tests/integration/test_user_directories/configs/mixed_style.xml diff --git a/src/Access/AccessControlManager.cpp b/src/Access/AccessControlManager.cpp index 6158be1b603..1fa26c85354 100644 --- a/src/Access/AccessControlManager.cpp +++ b/src/Access/AccessControlManager.cpp @@ -281,41 +281,33 @@ void AccessControlManager::addStoragesFromMainConfig( String config_dir = std::filesystem::path{config_path}.remove_filename().string(); String dbms_dir = config.getString("path", DBMS_DEFAULT_PATH); String include_from_path = config.getString("include_from", "/etc/metrika.xml"); + bool has_user_directories = config.has("user_directories"); - if (config.has("user_directories")) + /// If path to users' config isn't absolute, try guess its root (current) dir. + /// At first, try to find it in dir of main config, after will use current dir. + String users_config_path = config.getString("users_config", ""); + if (users_config_path.empty()) { - if (config.has("users_config")) - LOG_WARNING(getLogger(), " is specified, the path from won't be used: " + config.getString("users_config")); - if (config.has("access_control_path")) - LOG_WARNING(getLogger(), " is specified, the path from won't be used: " + config.getString("access_control_path")); - - addStoragesFromUserDirectoriesConfig( - config, - "user_directories", - config_dir, - dbms_dir, - include_from_path, - get_zookeeper_function); - } - else - { - /// If path to users' config isn't absolute, try guess its root (current) dir. - /// At first, try to find it in dir of main config, after will use current dir. - String users_config_path = config.getString("users_config", ""); - if (users_config_path.empty()) + if (!has_user_directories) users_config_path = config_path; - else if (std::filesystem::path{users_config_path}.is_relative() && std::filesystem::exists(config_dir + users_config_path)) - users_config_path = config_dir + users_config_path; + } + else if (std::filesystem::path{users_config_path}.is_relative() && std::filesystem::exists(config_dir + users_config_path)) + users_config_path = config_dir + users_config_path; + if (!users_config_path.empty()) + { if (users_config_path != config_path) checkForUsersNotInMainConfig(config, config_path, users_config_path, getLogger()); addUsersConfigStorage(users_config_path, include_from_path, dbms_dir, get_zookeeper_function); - - String disk_storage_dir = config.getString("access_control_path", ""); - if (!disk_storage_dir.empty()) - addDiskStorage(disk_storage_dir); } + + String disk_storage_dir = config.getString("access_control_path", ""); + if (!disk_storage_dir.empty()) + addDiskStorage(disk_storage_dir); + + if (has_user_directories) + addStoragesFromUserDirectoriesConfig(config, "user_directories", config_dir, dbms_dir, include_from_path, get_zookeeper_function); } diff --git a/tests/integration/test_user_directories/configs/local_directories.xml b/tests/integration/test_user_directories/configs/local_directories.xml index e2cbcd135df..7b9601da982 100644 --- a/tests/integration/test_user_directories/configs/local_directories.xml +++ b/tests/integration/test_user_directories/configs/local_directories.xml @@ -12,4 +12,6 @@ /var/lib/clickhouse/access3-ro/ + + diff --git a/tests/integration/test_user_directories/configs/memory.xml b/tests/integration/test_user_directories/configs/memory.xml index 6e906d2b1d6..78da38ed0bc 100644 --- a/tests/integration/test_user_directories/configs/memory.xml +++ b/tests/integration/test_user_directories/configs/memory.xml @@ -5,4 +5,7 @@ + + + diff --git a/tests/integration/test_user_directories/configs/mixed_style.xml b/tests/integration/test_user_directories/configs/mixed_style.xml new file mode 100644 index 00000000000..d6ddecf6f5d --- /dev/null +++ b/tests/integration/test_user_directories/configs/mixed_style.xml @@ -0,0 +1,8 @@ + + + + + + /etc/clickhouse-server/users6.xml + /var/lib/clickhouse/access6/ + diff --git a/tests/integration/test_user_directories/configs/old_style.xml b/tests/integration/test_user_directories/configs/old_style.xml index a0ff36edaba..cc753006b22 100644 --- a/tests/integration/test_user_directories/configs/old_style.xml +++ b/tests/integration/test_user_directories/configs/old_style.xml @@ -1,5 +1,6 @@ /etc/clickhouse-server/users2.xml /var/lib/clickhouse/access2/ + diff --git a/tests/integration/test_user_directories/configs/relative_path.xml b/tests/integration/test_user_directories/configs/relative_path.xml index 8906478959e..c4ef3c5fd79 100644 --- a/tests/integration/test_user_directories/configs/relative_path.xml +++ b/tests/integration/test_user_directories/configs/relative_path.xml @@ -4,4 +4,7 @@ users4.xml + + + diff --git a/tests/integration/test_user_directories/test.py b/tests/integration/test_user_directories/test.py index 8b7f34cf999..218330cb1a5 100644 --- a/tests/integration/test_user_directories/test.py +++ b/tests/integration/test_user_directories/test.py @@ -16,6 +16,7 @@ def started_cluster(): node.exec_in_container("cp /etc/clickhouse-server/users.xml /etc/clickhouse-server/users3.xml") node.exec_in_container("cp /etc/clickhouse-server/users.xml /etc/clickhouse-server/users4.xml") node.exec_in_container("cp /etc/clickhouse-server/users.xml /etc/clickhouse-server/users5.xml") + node.exec_in_container("cp /etc/clickhouse-server/users.xml /etc/clickhouse-server/users6.xml") yield cluster @@ -49,3 +50,10 @@ def test_memory(): node.restart_clickhouse() assert node.query("SELECT * FROM system.user_directories") == TSV([["users.xml", "users.xml", "/etc/clickhouse-server/users5.xml", 1, 1], ["memory", "memory", "", 0, 2]]) + +def test_mixed_style(): + node.copy_file_to_container(os.path.join(SCRIPT_DIR, "configs/mixed_style.xml"), '/etc/clickhouse-server/config.d/z.xml') + node.restart_clickhouse() + assert node.query("SELECT * FROM system.user_directories") == TSV([["users.xml", "users.xml", "/etc/clickhouse-server/users6.xml", 1, 1], + ["local directory", "local directory", "/var/lib/clickhouse/access6/", 0, 2], + ["memory", "memory", "", 0, 3]]) From e2574da1f5b39ad610dec0fb565860172095150e Mon Sep 17 00:00:00 2001 From: Gao Qiang <30835199+dreamerfable@users.noreply.github.com> Date: Thu, 27 Aug 2020 21:21:43 +0800 Subject: [PATCH 25/73] Update mergetree.md MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update all content in this article，fix wrong formats, fix wrong translation,unified description of main concept, remove deprecated content,add the new features. --- .../mergetree-family/mergetree.md | 427 ++++++++++++++---- 1 file changed, 338 insertions(+), 89 deletions(-) diff --git a/docs/zh/engines/table-engines/mergetree-family/mergetree.md b/docs/zh/engines/table-engines/mergetree-family/mergetree.md index e92621c12df..e733994b73d 100644 --- a/docs/zh/engines/table-engines/mergetree-family/mergetree.md +++ b/docs/zh/engines/table-engines/mergetree-family/mergetree.md @@ -2,44 +2,47 @@ Clickhouse 中最强大的表引擎当属 `MergeTree` （合并树）引擎及该系列（`*MergeTree`）中的其他引擎。 -`MergeTree` 引擎系列的基本理念如下。当你有巨量数据要插入到表中，你要高效地一批批写入数据片段，并希望这些数据片段在后台按照一定规则合并。相比在插入时不断修改（重写）数据进存储，这种策略会高效很多。 +`MergeTree` 系列的引擎被设计用于插入极大量的数据到一张表当中。数据可以以数据片段的形式一个接着一个的快速写入，数据片段在后台按照一定的规则进行合并。相比在插入时不断修改（重写）已存储的数据，这种策略会高效很多。 主要特点: - 存储的数据按主键排序。 - 这让你可以创建一个用于快速检索数据的小稀疏索引。 + 这使得你能够创建一个小型的稀疏索引来加快数据检索。 -- 允许使用分区，如果指定了 [分区键](custom-partitioning-key.md) 的话。 +- 支持数据分区，如果指定了 [分区键](custom-partitioning-key.md) 的话。 在相同数据集和相同结果集的情况下 ClickHouse 中某些带分区的操作会比普通操作更快。查询中指定了分区键时 ClickHouse 会自动截取分区数据。这也有效增加了查询性能。 - 支持数据副本。 - `ReplicatedMergeTree` 系列的表便是用于此。更多信息，请参阅 [数据副本](replication.md) 一节。 + `ReplicatedMergeTree` 系列的表提供了数据副本功能。更多信息，请参阅 [数据副本](replication.md) 一节。 - 支持数据采样。 需要的话，你可以给表设置一个采样方法。 -!!! 注意 "注意" +!!! note "注意" [合并](../special/merge.md#merge) 引擎并不属于 `*MergeTree` 系列。 ## 建表 {#table_engine-mergetree-creating-a-table} - CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] - ( - name1 [type1] [DEFAULT|MATERIALIZED|ALIAS expr1], - name2 [type2] [DEFAULT|MATERIALIZED|ALIAS expr2], - ... - INDEX index_name1 expr1 TYPE type1(...) GRANULARITY value1, - INDEX index_name2 expr2 TYPE type2(...) GRANULARITY value2 - ) ENGINE = MergeTree() - [PARTITION BY expr] - [ORDER BY expr] - [PRIMARY KEY expr] - [SAMPLE BY expr] - [SETTINGS name=value, ...] +``` sql +CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] +( + name1 [type1] [DEFAULT|MATERIALIZED|ALIAS expr1] [TTL expr1], + name2 [type2] [DEFAULT|MATERIALIZED|ALIAS expr2] [TTL expr2], + ... + INDEX index_name1 expr1 TYPE type1(...) GRANULARITY value1, + INDEX index_name2 expr2 TYPE type2(...) GRANULARITY value2 +) ENGINE = MergeTree() +ORDER BY expr +[PARTITION BY expr] +[PRIMARY KEY expr] +[SAMPLE BY expr] +[TTL expr [DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'], ...] +[SETTINGS name=value, ...] +``` 对于以上参数的描述，可参考 [CREATE 语句 的描述](../../../engines/table-engines/mergetree-family/mergetree.md) 。 @@ -62,7 +65,7 @@ Clickhouse 中最强大的表引擎当属 `MergeTree` （合并树）引擎及 要按月分区，可以使用表达式 `toYYYYMM(date_column)` ，这里的 `date_column` 是一个 [Date](../../../engines/table-engines/mergetree-family/mergetree.md) 类型的列。分区名的格式会是 `"YYYYMM"` 。 -- `PRIMARY KEY` - 主键，如果要设成 [跟排序键不相同](#xuan-ze-gen-pai-xu-jian-bu-yi-yang-zhu-jian)，可选。 +- `PRIMARY KEY` - 主键，如果要 [选择与排序键不同的主键](#choosing-a-primary-key-that-differs-from-the-sorting-key)，可选。 默认情况下主键跟排序键（由 `ORDER BY` 子句指定）相同。 因此，大部分情况下不需要再专门指定一个 `PRIMARY KEY` 子句。 @@ -72,17 +75,19 @@ Clickhouse 中最强大的表引擎当属 `MergeTree` （合并树）引擎及 如果要用抽样表达式，主键中必须包含这个表达式。例如： `SAMPLE BY intHash32(UserID) ORDER BY (CounterID, EventDate, intHash32(UserID))` 。 -- TTL 指定行存储的持续时间并定义 PART 在硬盘和卷上的移动逻辑的规则列表，可选。 +- TTL 指定行存储的持续时间并定义数据片段在硬盘和卷上的移动逻辑的规则列表，可选。 表达式中必须存在至少一个 `Date` 或 `DateTime` 类型的列，比如： `TTL date + INTERVAl 1 DAY` - 规则的类型 `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'`指定了当满足条件（到达当前时间）时所要执行的动作：移除过期的行，还是将 PART （如果PART中的所有行都满足表达式的话）移动到指定的磁盘（`TO DISK 'xxx'`) 或 卷（`TO VOLUME 'xxx'`）。默认的规则是移除（`DELETE`）。可以在列表中指定多个规则，但最多只能有一个`DELETE`的规则。 + 规则的类型 `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'`指定了当满足条件（到达指定时间）时所要执行的动作：移除过期的行，还是将数据片段（如果数据片段中的所有行都满足表达式的话）移动到指定的磁盘（`TO DISK 'xxx'`) 或 卷（`TO VOLUME 'xxx'`）。默认的规则是移除（`DELETE`）。可以在列表中指定多个规则，但最多只能有一个`DELETE`的规则。 + + 更多细节，请查看 [表和列的 TTL](#table_engine-mergetree-ttl) -- `SETTINGS` — 影响 `MergeTree` 性能的额外参数： +- `SETTINGS` — 控制 `MergeTree` 行为的额外参数： - - `index_granularity` — 索引粒度。索引中相邻的『标记』间的数据行数。默认值，8192 。参考[Data Storage](#mergetree-data-storage)。 + - `index_granularity` — 索引粒度。索引中相邻的『标记』间的数据行数。默认值，8192 。参考[数据存储](#mergetree-data-storage)。 - `index_granularity_bytes` — 索引粒度，以字节为单位，默认值: 10Mb。如果想要仅按数据行数限制索引粒度, 请设置为0(不建议)。 - `enable_mixed_granularity_parts` — 是否启用通过 `index_granularity_bytes` 控制索引粒度的大小。在19.11版本之前, 只有 `index_granularity` 配置能够用于限制索引粒度的大小。当从具有很大的行（几十上百兆字节）的表中查询数据时候，`index_granularity_bytes` 配置能够提升ClickHouse的性能。如果你的表里有很大的行，可以开启这项配置来提升`SELECT` 查询的性能。 - `use_minimalistic_part_header_in_zookeeper` — 是否在 ZooKeeper 中启用最小的数据片段头 。如果设置了 `use_minimalistic_part_header_in_zookeeper=1` ，ZooKeeper 会存储更少的数据。更多信息参考『服务配置参数』这章中的 [设置描述](../../../operations/server-configuration-parameters/settings.md#server-settings-use_minimalistic_part_header_in_zookeeper) 。 @@ -90,18 +95,21 @@ Clickhouse 中最强大的表引擎当属 `MergeTree` （合并树）引擎及 - `merge_with_ttl_timeout` — TTL合并频率的最小间隔时间，单位：秒。默认值: 86400 (1 天)。 - `write_final_mark` — 是否启用在数据片段尾部写入最终索引标记。默认值: 1（不建议更改）。 - - `storage_policy` — 存储策略。 参见 [使用多个区块装置进行数据存储](#table_engine-mergetree-multiple-volumes). - - `min_bytes_for_wide_part`,`min_rows_for_wide_part` 在数据分段中可以使用`Wide`格式进行存储的最小字节数/行数。你可以不设置、只设置一个，或全都设置。参考：[Data Storage](#mergetree-data-storage) + - `merge_max_block_size` — 在块中进行合并操作时的最大行数限制。默认值：8192 + - `storage_policy` — 存储策略。 参见 [使用具有多个块的设备进行数据存储](#table_engine-mergetree-multiple-volumes). + - `min_bytes_for_wide_part`,`min_rows_for_wide_part` 在数据片段中可以使用`Wide`格式进行存储的最小字节数/行数。你可以不设置、只设置一个，或全都设置。参考：[数据存储](#mergetree-data-storage) **示例配置** - ENGINE MergeTree() PARTITION BY toYYYYMM(EventDate) ORDER BY (CounterID, EventDate, intHash32(UserID)) SAMPLE BY intHash32(UserID) SETTINGS index_granularity=8192 +``` sql +ENGINE MergeTree() PARTITION BY toYYYYMM(EventDate) ORDER BY (CounterID, EventDate, intHash32(UserID)) SAMPLE BY intHash32(UserID) SETTINGS index_granularity=8192 +``` -示例中，我们设为按月分区。 +在这个例子中，我们设置了按月进行分区。 -同时我们设置了一个按用户ID哈希的抽样表达式。这让你可以有该表中每个 `CounterID` 和 `EventDate` 下面的数据的伪随机分布。如果你在查询时指定了 [SAMPLE](../../../engines/table-engines/mergetree-family/mergetree.md#select-sample-clause) 子句。 ClickHouse会返回对于用户子集的一个均匀的伪随机数据采样。 +同时我们设置了一个按用户 ID 哈希的抽样表达式。这使得你可以对该表中每个 `CounterID` 和 `EventDate` 的数据伪随机分布。如果你在查询时指定了 [SAMPLE](../../../engines/table-engines/mergetree-family/mergetree.md#select-sample-clause) 子句。 ClickHouse会返回对于用户子集的一个均匀的伪随机数据采样。 -`index_granularity` 可省略，默认值为 8192 。 +`index_granularity` 可省略因为 8192 是默认设置 。
@@ -133,15 +141,20 @@ Clickhouse 中最强大的表引擎当属 `MergeTree` （合并树）引擎及 ## 数据存储 {#mergetree-data-storage} -表由按主键排序的数据 *片段* 组成。 +表由按主键排序的数据片段（DATA PART）组成。 -当数据被插入到表中时，会分成数据片段并按主键的字典序排序。例如，主键是 `(CounterID, Date)` 时，片段中数据按 `CounterID` 排序，具有相同 `CounterID` 的部分按 `Date` 排序。 +当数据被插入到表中时，会创建多个数据片段并按主键的字典序排序。例如，主键是 `(CounterID, Date)` 时，片段中数据首先按 `CounterID` 排序，具有相同 `CounterID` 的部分按 `Date` 排序。 -不同分区的数据会被分成不同的片段，ClickHouse 在后台合并数据片段以便更高效存储。不会合并来自不同分区的数据片段。这个合并机制并不保证相同主键的所有行都会合并到同一个数据片段中。 +不同分区的数据会被分成不同的片段，ClickHouse 在后台合并数据片段以便更高效存储。不同分区的数据片段不会进行合并。合并机制并不保证具有相同主键的行全都合并到同一个数据片段中。 -ClickHouse 会为每个数据片段创建一个索引文件，索引文件包含每个索引行（『标记』）的主键值。索引行号定义为 `n * index_granularity` 。最大的 `n` 等于总行数除以 `index_granularity` 的值的整数部分。对于每列，跟主键相同的索引行处也会写入『标记』。这些『标记』让你可以直接找到数据所在的列。 +数据片段可以以 `Wide` 或 `Compact` 格式存储。在 `Wide` 格式下，每一列都会在文件系统中存储为单独的文件，在 `Compact` 格式下所有列都存储在一个文件中。`Compact` 格式可以提高插入量少插入频率频繁时的性能。 -你可以只用一单一大表并不断地一块块往里面加入数据 – `MergeTree` 引擎的就是为了这样的场景。 +数据存储格式由 `min_bytes_for_wide_part` 和 `min_rows_for_wide_part` 表引擎参数控制。如果数据片段中的字节数或行数少于相应的设置值，数据片段会以 `Compact` 格式存储，否则会以 `Wide` 格式存储。 + +每个数据片段被逻辑的分割成颗粒（granules）。颗粒是 ClickHouse 中进行数据查询时的最小不可分割数据集。ClickHouse 不会对行或值进行拆分，所以每个颗粒总是包含整数个行。每个颗粒的第一行通过该行的主键值进行标记， +ClickHouse 会为每个数据片段创建一个索引文件来存储这些标记。对于每列，无论它是否包含在主键当中，ClickHouse 都会存储类似标记。这些标记让你可以在列文件中直接找到数据。 + +颗粒的大小通过表引擎参数 `index_granularity` 和 `index_granularity_bytes` 控制。取决于行的大小，颗粒的行数的在 `[1, index_granularity]` 范围中。如果单行的大小超过了 `index_granularity_bytes` 设置的值，那么一个颗粒的大小会超过 `index_granularity_bytes`。在这种情况下，颗粒的大小等于该行的大小。 ## 主键和索引在查询中的表现 {#primary-keys-and-indexes-in-queries} @@ -162,56 +175,53 @@ ClickHouse 会为每个数据片段创建一个索引文件，索引文件包含 上面例子可以看出使用索引通常会比全表描述要高效。 -稀疏索引会引起额外的数据读取。当读取主键单个区间范围的数据时，每个数据块中最多会多读 `index_granularity * 2` 行额外的数据。大部分情况下，当 `index_granularity = 8192` 时，ClickHouse的性能并不会降级。 +稀疏索引会引起额外的数据读取。当读取主键单个区间范围的数据时，每个数据块中最多会多读 `index_granularity * 2` 行额外的数据。 -稀疏索引让你能操作有巨量行的表。因为这些索引是常驻内存（RAM）的。 +稀疏索引使得你可以处理极大量的行，因为大多数情况下，这些索引常驻与内存（RAM）中。 -ClickHouse 不要求主键惟一。所以，你可以插入多条具有相同主键的行。 +ClickHouse 不要求主键惟一，所以你可以插入多条具有相同主键的行。 ### 主键的选择 {#zhu-jian-de-xuan-ze} -主键中列的数量并没有明确的限制。依据数据结构，你应该让主键包含多些或少些列。这样可以： +主键中列的数量并没有明确的限制。依据数据结构，你可以在主键包含多些或少些列。这样可以： - 改善索引的性能。 - 如果当前主键是 `(a, b)` ，然后加入另一个 `c` 列，满足下面条件时，则可以改善性能： - - 有带有 `c` 列条件的查询。 - - 很长的数据范围（ `index_granularity` 的数倍）里 `(a, b)` 都是相同的值，并且这种的情况很普遍。换言之，就是加入另一列后，可以让你的查询略过很长的数据范围。 + 如果当前主键是 `(a, b)` ，在下列情况下添加另一个 `c` 列会提升性能： + + - 查询会使用 `c` 列作为条件 + - 很长的数据范围（ `index_granularity` 的数倍）里 `(a, b)` 都是相同的值，并且这样的情况很普遍。换言之，就是加入另一列后，可以让你的查询略过很长的数据范围。 - 改善数据压缩。 - ClickHouse 以主键排序片段数据，所以，数据的一致性越高，压缩越好。 + ClickHouse 以主键排序片段数据，所以，数据的一致性越高，压缩越好。 -- [折叠树](collapsingmergetree.md#table_engine-collapsingmergetree) 和 [SummingMergeTree](summingmergetree.md) 引擎里，数据合并时，会有额外的处理逻辑。 +- 在[CollapsingMergeTree](collapsingmergetree.md#table_engine-collapsingmergetree) 和 [SummingMergeTree](summingmergetree.md) 引擎里进行数据合并时会提供额外的处理逻辑。 - 在这种情况下，指定一个跟主键不同的 *排序键* 也是有意义的。 + 在这种情况下，指定与主键不同的 *排序键* 也是有意义的。 长的主键会对插入性能和内存消耗有负面影响，但主键中额外的列并不影响 `SELECT` 查询的性能。 -### 选择跟排序键不一样主键 {#xuan-ze-gen-pai-xu-jian-bu-yi-yang-zhu-jian} +可以使用 `ORDER BY tuple()` 语法创建没有主键的表。在这种情况下 ClickHouse 根据数据插入的顺序存储。如果在使用 `INSERT ... SELECT` 时希望保持数据的排序，请设置 [max\_insert\_threads = 1](../../../operations/settings/settings.md#settings-max-insert-threads)。 -指定一个跟排序键（用于排序数据片段中行的表达式） -不一样的主键（用于计算写到索引文件的每个标记值的表达式）是可以的。 -这种情况下，主键表达式元组必须是排序键表达式元组的一个前缀。 +想要根据初始顺序进行数据查询，使用 [单线程查询](../../../operations/settings/settings.md#settings-max_threads) -当使用 [SummingMergeTree](summingmergetree.md) 和 -[AggregatingMergeTree](aggregatingmergetree.md) 引擎时，这个特性非常有用。 -通常，使用这类引擎时，表里列分两种：*维度* 和 *度量* 。 -典型的查询是在 `GROUP BY` 并过虑维度的情况下统计度量列的值。 -像 SummingMergeTree 和 AggregatingMergeTree ，用相同的排序键值统计行时， -通常会加上所有的维度。结果就是，这键的表达式会是一长串的列组成， -并且这组列还会因为新加维度必须频繁更新。 +### 选择与排序键不同主键 {#choosing-a-primary-key-that-differs-from-the-sorting-key} -这种情况下，主键中仅预留少量列保证高效范围扫描， -剩下的维度列放到排序键元组里。这样是合理的。 +指定一个跟排序键不一样的主键是可以的，此时排序键用于在数据片段中进行排序，主键用于在索引文件中进行标记的写入。这种情况下，主键表达式元组必须是排序键表达式元组的前缀。 -[排序键的修改](../../../engines/table-engines/mergetree-family/mergetree.md) 是轻量级的操作，因为一个新列同时被加入到表里和排序键后时，已存在的数据片段并不需要修改。由于旧的排序键是新排序键的前缀，并且刚刚添加的列中没有数据，因此在表修改时的数据对于新旧的排序键来说都是有序的。 +当使用 [SummingMergeTree](summingmergetree.md) 和 [AggregatingMergeTree](aggregatingmergetree.md) 引擎时，这个特性非常有用。通常在使用这类引擎时，表里的列分两种：*维度* 和 *度量* 。典型的查询会通过任意的 `GROUP BY` 对度量列进行聚合并通过维度列进行过滤。由于 SummingMergeTree 和 AggregatingMergeTree 会对排序键相同的行进行聚合，所以把所有的维度放进排序键是很自然的做法。但这将导致排序键中包含大量的列，并且排序键会伴随着新添加的维度不断的更新。 -### 索引和分区在查询中的应用 {#suo-yin-he-fen-qu-zai-cha-xun-zhong-de-ying-yong} +在这种情况下合理的做法是，只保留少量的列在主键当中用于提升扫描效率，将维度列添加到排序键中。 -对于 `SELECT` 查询，ClickHouse 分析是否可以使用索引。如果 `WHERE/PREWHERE` 子句具有下面这些表达式（作为谓词链接一子项或整个）则可以使用索引：基于主键或分区键的列或表达式的部分的等式或比较运算表达式；基于主键或分区键的列或表达式的固定前缀的 `IN` 或 `LIKE` 表达式；基于主键或分区键的列的某些函数；基于主键或分区键的表达式的逻辑表达式。 +对排序键进行 [ALTER](../../../sql-reference/statements/alter/index.md) 是轻量级的操作，因为当一个新列同时被加入到表里和排序键里时，已存在的数据片段并不需要修改。由于旧的排序键是新排序键的前缀，并且新添加的列中没有数据，因此在表修改时的数据对于新旧的排序键来说都是有序的。 -因此，在索引键的一个或多个区间上快速地跑查询都是可能的。下面例子中，指定标签；指定标签和日期范围；指定标签和日期；指定多个标签和日期范围等运行查询，都会非常快。 +### 索引和分区在查询中的应用 {#use-of-indexes-and-partitions-in-queries} + +对于 `SELECT` 查询，ClickHouse 分析是否可以使用索引。如果 `WHERE/PREWHERE` 子句具有下面这些表达式（作为谓词链接一子项或整个）则可以使用索引：包含一个表示与主键/分区键中的部分字段或全部字段相等/不等的比较表达式；基于主键/分区键的字段上的 `IN` 或 固定前缀的`LIKE` 表达式；基于主键/分区键的字段上的某些函数；基于主键/分区键的表达式的逻辑表达式。 + + +因此，在索引键的一个或多个区间上快速地执行查询都是可能的。下面例子中，指定标签；指定标签和日期范围；指定标签和日期；指定多个标签和日期范围等执行查询，都会非常快。 当引擎配置如下时： @@ -237,11 +247,18 @@ SELECT count() FROM table WHERE CounterID = 34 OR URL LIKE '%upyachka%' 要检查 ClickHouse 执行一个查询时能否使用索引，可设置 [force\_index\_by\_date](../../../operations/settings/settings.md#settings-force_index_by_date) 和 [force\_primary\_key](../../../operations/settings/settings.md) 。 -按月分区的分区键是只能读取包含适当范围日期的数据块。这种情况下，数据块会包含很多天（最多整月）的数据。在块中，数据按主键排序，主键第一列可能不包含日期。因此，仅使用日期而没有带主键前缀条件的查询将会导致读取超过这个日期范围。 +按月分区的分区键是只能读取包含适当范围日期的数据块。这种情况下，数据块会包含很多天（最多整月）的数据。在块中，数据按主键排序，主键第一列可能不包含日期。因此，仅使用日期而没有带主键前几个字段作为条件的查询将会导致需要读取超过这个指定日期以外的数据。 -### 跳数索引（分段汇总索引，实验性的） {#tiao-shu-suo-yin-fen-duan-hui-zong-suo-yin-shi-yan-xing-de} +### 部分单调主键的使用 -需要设置 `allow_experimental_data_skipping_indices` 为 1 才能使用此索引。（执行 `SET allow_experimental_data_skipping_indices = 1`）。 +考虑这样的场景，比如一个月中的几天。它们在一个月的范围内形成一个[单调序列](https://zh.wikipedia.org/wiki/单调函数) ，但如果扩展到更大的时间范围它们就不再单调了。这就是一个部分单调序列。如果用户使用部分单调的主键创建表，ClickHouse同样会创建一个稀疏索引。当用户从这类表中查询数据时，ClickHouse 会对查询条件进行分析。如果用户希望获取两个索引标记之间的数据并且这两个标记在一个月以内，ClickHouse 可以在这种特殊情况下使用到索引，因为它可以计算出查询参数与索引标记之间的距离。 + +如果查询参数范围内的主键不是单调序列，那么 ClickHouse 无法使用索引。在这种情况下，ClickHouse 会进行全表扫描。 + +ClickHouse 在任何主键代表一个部分单调序列的情况下都会使用这个逻辑。 + + +### 跳数索引 {#tiao-shu-suo-yin-fen-duan-hui-zong-suo-yin-shi-yan-xing-de} 此索引在 `CREATE` 语句的列部分里定义。 @@ -249,12 +266,14 @@ SELECT count() FROM table WHERE CounterID = 34 OR URL LIKE '%upyachka%' INDEX index_name expr TYPE type(...) GRANULARITY granularity_value ``` -`*MergeTree` 系列的表都能指定跳数索引。 +`*MergeTree` 系列的表可以指定跳数索引。 这些索引是由数据块按粒度分割后的每部分在指定表达式上汇总信息 `granularity_value` 组成（粒度大小用表引擎里 `index_granularity` 的指定）。 这些汇总信息有助于用 `where` 语句跳过大片不满足的数据，从而减少 `SELECT` 查询从磁盘读取的数据量， -示例 +这些索引会在数据块上聚合指定表达式的信息，这些信息以 granularity_value 指定的粒度组成 （粒度的大小通过在表引擎中定义 index_granularity 定义）。这些汇总信息有助于跳过大片不满足 `where` 条件的数据，从而减少 `SELECT` 查询从磁盘读取的数据量。 + +**示例** ``` sql CREATE TABLE table_name @@ -282,19 +301,27 @@ SELECT count() FROM table WHERE u64 * i32 == 10 AND u64 * length(s) >= 1234 存储指定表达式的极值（如果表达式是 `tuple` ，则存储 `tuple` 中每个元素的极值），这些信息用于跳过数据块，类似主键。 - `set(max_rows)` - 存储指定表达式的惟一值（不超过 `max_rows` 个，`max_rows=0` 则表示『无限制』）。这些信息可用于检查 `WHERE` 表达式是否满足某个数据块。 + 存储指定表达式的不重复值（不超过 `max_rows` 个，`max_rows=0` 则表示『无限制』）。这些信息可用于检查 数据块是否满足 `WHERE` 条件。 - `ngrambf_v1(n, size_of_bloom_filter_in_bytes, number_of_hash_functions, random_seed)` - 存储包含数据块中所有 n 元短语的 [布隆过滤器](https://en.wikipedia.org/wiki/Bloom_filter) 。只可用在字符串上。 + 存储一个包含数据块中所有 n元短语（ngram） 的 [布隆过滤器](https://en.wikipedia.org/wiki/Bloom_filter) 。只可用在字符串上。 可用于优化 `equals` ， `like` 和 `in` 表达式的性能。 `n` – 短语长度。 - `size_of_bloom_filter_in_bytes` – 布隆过滤器大小，单位字节。（因为压缩得好，可以指定比较大的值，如256或512）。 - `number_of_hash_functions` – 布隆过滤器中使用的 hash 函数的个数。 - `random_seed` – hash 函数的随机种子。 + `size_of_bloom_filter_in_bytes` – 布隆过滤器大小，单位字节。（因为压缩得好，可以指定比较大的值，如 256 或 512）。 + `number_of_hash_functions` – 布隆过滤器中使用的哈希函数的个数。 + `random_seed` – 哈希函数的随机种子。 - `tokenbf_v1(size_of_bloom_filter_in_bytes, number_of_hash_functions, random_seed)` - 跟 `ngrambf_v1` 类似，不同于 ngrams 存储字符串指定长度的所有片段。它只存储被非字母数据字符分割的片段。 + 跟 `ngrambf_v1` 类似，不同于 ngrams 存储字符串指定长度的所有片段。它只存储被非字母数字字符分割的片段。 +- `bloom_filter(bloom_filter([false_positive])` – 为指定的列存储布隆过滤器 + + 可选的参数 false_positive 用来指定从布隆过滤器收到错误响应的几率。取值范围是 (0,1)，默认值：0.025 + + 支持的数据类型：`Int*`, `UInt*`, `Float*`, `Enum`, `Date`, `DateTime`, `String`, `FixedString`, `Array`, `LowCardinality`, `Nullable`。 + + 以下函数会用到这个索引： [equals](../../../sql-reference/functions/comparison-functions.md), [notEquals](../../../sql-reference/functions/comparison-functions.md), [in](../../../sql-reference/functions/in-functions.md), [notIn](../../../sql-reference/functions/in-functions.md), [has](../../../sql-reference/functions/array-functions.md) + ``` sql @@ -303,17 +330,62 @@ INDEX sample_index2 (u64 * length(str), i32 + f64 * 100, date, str) TYPE set(100 INDEX sample_index3 (lower(str), str) TYPE ngrambf_v1(3, 256, 2, 0) GRANULARITY 4 ``` -## 并发数据访问 {#bing-fa-shu-ju-fang-wen} +#### 函数支持 {#functions-support} + +WHERE 子句中的条件包含对列的函数调用，如果列是索引的一部分，ClickHouse 会在执行函数时尝试使用索引。不同的函数对索引的支持是不同的。 + +`set` 索引会对所有函数生效，其他索引对函数的生效情况见下表 + +| 函数 (操作符) / 索引 | primary key | minmax | ngrambf\_v1 | tokenbf\_v1 | bloom\_filter | +|------------------------------------------------------------------------------------------------------------|-------------|--------|-------------|-------------|---------------| +| [equals (=, ==)](../../../sql-reference/functions/comparison-functions.md#function-equals) | ✔ | ✔ | ✔ | ✔ | ✔ | +| [notEquals(!=, \<\>)](../../../sql-reference/functions/comparison-functions.md#function-notequals) | ✔ | ✔ | ✔ | ✔ | ✔ | +| [like](../../../sql-reference/functions/string-search-functions.md#function-like) | ✔ | ✔ | ✔ | ✔ | ✔ | +| [notLike](../../../sql-reference/functions/string-search-functions.md#function-notlike) | ✔ | ✔ | ✗ | ✗ | ✗ | +| [startsWith](../../../sql-reference/functions/string-functions.md#startswith) | ✔ | ✔ | ✔ | ✔ | ✗ | +| [endsWith](../../../sql-reference/functions/string-functions.md#endswith) | ✗ | ✗ | ✔ | ✔ | ✗ | +| [multiSearchAny](../../../sql-reference/functions/string-search-functions.md#function-multisearchany) | ✗ | ✗ | ✔ | ✗ | ✗ | +| [in](../../../sql-reference/functions/in-functions.md#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ | +| [notIn](../../../sql-reference/functions/in-functions.md#in-functions) | ✔ | ✔ | ✔ | ✔ | ✔ | +| [less (\<)](../../../sql-reference/functions/comparison-functions.md#function-less) | ✔ | ✔ | ✗ | ✗ | ✗ | +| [greater (\>)](../../../sql-reference/functions/comparison-functions.md#function-greater) | ✔ | ✔ | ✗ | ✗ | ✗ | +| [lessOrEquals (\<=)](../../../sql-reference/functions/comparison-functions.md#function-lessorequals) | ✔ | ✔ | ✗ | ✗ | ✗ | +| [greaterOrEquals (\>=)](../../../sql-reference/functions/comparison-functions.md#function-greaterorequals) | ✔ | ✔ | ✗ | ✗ | ✗ | +| [empty](../../../sql-reference/functions/array-functions.md#function-empty) | ✔ | ✔ | ✗ | ✗ | ✗ | +| [notEmpty](../../../sql-reference/functions/array-functions.md#function-notempty) | ✔ | ✔ | ✗ | ✗ | ✗ | +| hasToken | ✗ | ✗ | ✗ | ✔ | ✗ | + +常量参数小于 ngram 大小的函数不能使用 `ngrambf_v1` 进行查询优化。 + +!!! note "注意" +布隆过滤器可能会包含不符合条件的匹配，所以 `ngrambf_v1`, `tokenbf_v1` 和 `bloom_filter` 索引不能用于负向的函数，例如： + +- 可以用来优化的场景 + - `s LIKE '%test%'` + - `NOT s NOT LIKE '%test%'` + - `s = 1` + - `NOT s != 1` + - `startsWith(s, 'test')` +- 不能用来优化的场景 + - `NOT s LIKE '%test%'` + - `s NOT LIKE '%test%'` + - `NOT s = 1` + - `s != 1` + - `NOT startsWith(s, 'test')` + +## 并发数据访问 {#concurrent-data-access} 应对表的并发访问，我们使用多版本机制。换言之，当同时读和更新表时，数据从当前查询到的一组片段中读取。没有冗长的的锁。插入不会阻碍读取。 对表的读操作是自动并行的。 -## 列和表的TTL {#table_engine-mergetree-ttl} +## 列和表的 TTL {#table_engine-mergetree-ttl} -TTL可以设置值的生命周期，它既可以为整张表设置，也可以为每个列字段单独设置。如果`TTL`同时作用于表和字段，ClickHouse会使用先到期的那个。 +TTL 可以设置值的生命周期，它既可以为整张表设置，也可以为每个列字段单独设置。表级别的 TTL 还会指定数据在磁盘和卷上自动转移的逻辑。 -被设置TTL的表，必须拥有[日期](../../../engines/table-engines/mergetree-family/mergetree.md) 或 [日期时间](../../../engines/table-engines/mergetree-family/mergetree.md) 类型的字段。要定义数据的生命周期，需要在这个日期字段上使用操作符，例如: +TTL 表达式的计算结果必须是 [日期](../../../engines/table-engines/mergetree-family/mergetree.md) 或 [日期时间](../../../engines/table-engines/mergetree-family/mergetree.md) 类型的字段。 + +示例： ``` sql TTL time_column @@ -327,15 +399,15 @@ TTL date_time + INTERVAL 1 MONTH TTL date_time + INTERVAL 15 HOUR ``` -### 列字段 TTL {#mergetree-column-ttl} +### 列 TTL {#mergetree-column-ttl} -当列字段中的值过期时, ClickHouse会将它们替换成数据类型的默认值。如果分区内，某一列的所有值均已过期，则ClickHouse会从文件系统中删除这个分区目录下的列文件。 +当列中的值过期时, ClickHouse会将它们替换成该列数据类型的默认值。如果数据片段中列的所有值均已过期，则ClickHouse 会从文件系统中的数据片段中此列。 `TTL`子句不能被用于主键字段。 -示例说明: +示例: -创建一张包含 `TTL` 的表 +创建表时指定 `TTL` ``` sql CREATE TABLE example_table @@ -368,11 +440,21 @@ ALTER TABLE example_table ### 表 TTL {#mergetree-table-ttl} -当表内的数据过期时, ClickHouse会删除所有对应的行。 +表可以设置一个用于移除过期行的表达式，以及多个用于在磁盘或卷上自动转移数据片段的表达式。当表中的行过期时，ClickHouse 会删除所有对应的行。对于数据片段的转移特性，必须所有的行都满足转移条件。 -举例说明: +``` sql +TTL expr [DELETE|TO DISK 'aaa'|TO VOLUME 'bbb'], ... +``` -创建一张包含 `TTL` 的表 +TTL 规则的类型紧跟在每个 TTL 表达式后面，它会影响满足表达式时（到达指定时间时）应当执行的操作： + +- `DELETE` - 删除过期的行（默认操作）; +- `TO DISK 'aaa'` - 将数据片段移动到磁盘 `aaa`; +- `TO VOLUME 'bbb'` - 将数据片段移动到卷 `bbb`. + +示例: + +创建时指定 TTL ``` sql CREATE TABLE example_table @@ -383,7 +465,9 @@ CREATE TABLE example_table ENGINE = MergeTree PARTITION BY toYYYYMM(d) ORDER BY d -TTL d + INTERVAL 1 MONTH; +TTL d + INTERVAL 1 MONTH [DELETE], + d + INTERVAL 1 WEEK TO VOLUME 'aaa', + d + INTERVAL 2 WEEK TO DISK 'bbb'; ``` 修改表的 `TTL` @@ -395,14 +479,179 @@ ALTER TABLE example_table **删除数据** -当ClickHouse合并数据分区时, 会删除TTL过期的数据。 +ClickHouse 在数据片段合并时会删除掉过期的数据。 -当ClickHouse发现数据过期时, 它将会执行一个计划外的合并。要控制这类合并的频率, 你可以设置 `merge_with_ttl_timeout`。如果该值被设置的太低, 它将导致执行许多的计划外合并，这可能会消耗大量资源。 +当ClickHouse发现数据过期时, 它将会执行一个计划外的合并。要控制这类合并的频率, 你可以设置 `merge_with_ttl_timeout`。如果该值被设置的太低, 它将引发大量计划外的合并，这可能会消耗大量资源。 -如果在合并的时候执行`SELECT` 查询, 则可能会得到过期的数据。为了避免这种情况，可以在`SELECT`之前使用 [OPTIMIZE](../../../engines/table-engines/mergetree-family/mergetree.md#misc_operations-optimize) 查询。 +如果在合并的过程中执行 `SELECT` 查询, 则可能会得到过期的数据。为了避免这种情况，可以在 `SELECT` 之前使用 [OPTIMIZE](../../../engines/table-engines/mergetree-family/mergetree.md#misc_operations-optimize) 查询。 -## 使用多个块设备进行数据存储 {#table_engine-mergetree-multiple-volumes} +## 使用具有多个块的设备进行数据存储 {#table_engine-mergetree-multiple-volumes} + +### 介绍 {#introduction} + +MergeTree 系列表引擎可以将数据存储在多块设备上。这对某些可以潜在被划分为“冷”“热”的表来说是很有用的。近期数据被定期的查询但只需要很小的空间。相反，详尽的历史数据很少被用到。如果有多块磁盘可用，那么“热”的数据可以放置在快速的磁盘上（比如 NVMe 固态硬盘或内存），“冷”的数据可以放在相对较慢的磁盘上（比如机械硬盘）。 + +数据片段是 `MergeTree` 引擎表的最小可移动单元。属于同一个数据片段的数据被存储在同一块磁盘上。数据片段会在后台自动的在磁盘间移动，也可以通过 [ALTER](../../../sql-reference/statements/alter/partition.md#alter_move-partition) 查询来移动。 + +### 术语 {#terms} + +- 磁盘 — 挂载到文件系统的块设备 +- 默认磁盘 — 在服务器设置中通过 [path](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-path) 参数指定的数据存储 +- 卷 — 磁盘的等效有序集合 （类似于 [JBOD](https://en.wikipedia.org/wiki/Non-RAID_drive_architectures)） +- 存储策略 — 卷的集合及他们之间的数据移动规则 ### 配置 {#table_engine-mergetree-multiple-volumes_configure} -[来源文章](https://clickhouse.tech/docs/en/operations/table_engines/mergetree/) +磁盘、卷和存储策略应当在主文件 `config.xml` 或 `config.d` 目录中的独立文件中的 `` 标签内定义。 + +配置结构： + +``` xml + + + + /mnt/fast_ssd/clickhouse/ + + + /mnt/hdd1/clickhouse/ + 10485760 + + + /mnt/hdd2/clickhouse/ + 10485760 + + + ... + + + ... + +``` + +标签： + +- `` — 磁盘名，名称必须与其他磁盘不同. +- `path` — 服务器将用来存储数据 (`data` 和 `shadow` 目录) 的路径, 应当以 ‘/’ 结尾. +- `keep_free_space_bytes` — 需要保留的剩余磁盘空间. + +磁盘定义的顺序无关紧要。 + +存储策略配置： + +``` xml + + ... + + + + + disk_name_from_disks_configuration + 1073741824 + + + + + + + 0.2 + + + + + + + + ... + +``` + +标签： + +- `policy_name_N` — 策略名称，不能重复。 +- `volume_name_N` — 卷名称，不能重复。 +- `disk` — 卷中的磁盘。 +- `max_data_part_size_bytes` — 任意卷上的磁盘可以存储的数据片段的最大大小。 +- `move_factor` — 当可用空间少于这个因子时，数据将自动的向下一个卷（如果有的话）移动 (默认值为 0.1)。 + +配置示例： + +``` xml + + ... + + + + + disk1 + disk2 + + + + + + + + fast_ssd + 1073741824 + + + disk1 + + + 0.2 + + + ... + +``` + +在给出的例子中， `hdd_in_order` 策略实现了 [循环制](https://zh.wikipedia.org/wiki/循环制) 方法。因此这个策略只定义了一个卷（`single`），数据片段会以循环的顺序全部存储到它的磁盘上。当有多个类似的磁盘挂载到系统上，但没有配置 RAID 时，这种策略非常有用。请注意一个每个独立的磁盘驱动都并不可靠，你可能需要用 3 或更大的复制因此来补偿它。 + +如果在系统中有不同类型的磁盘可用，可以使用 `moving_from_ssd_to_hdd`。`hot` 卷由 SSD 磁盘（`fast_ssd`）组成，这个卷上可以存储的数据片段的最大大小为 1GB。所有大于 1GB 的数据片段都会被直接存储到 `cold` 卷上，`cold` 卷包含一个名为 `disk1` 的 HDD 磁盘。 +同样，一旦 `fast_ssd` 被填充超过 80%，数据会通过后台进程向 `disk1` 进行转移。 + +存储策略中卷的枚举顺序是很重要的。因为当一个卷被充满时，数据会向下一个卷转移。磁盘的枚举顺序同样重要，因为数据是依次存储在磁盘上的。 + +在创建表时，可以将一个配置好的策略应用到表： + +``` sql +CREATE TABLE table_with_non_default_policy ( + EventDate Date, + OrderID UInt64, + BannerID UInt64, + SearchPhrase String +) ENGINE = MergeTree +ORDER BY (OrderID, BannerID) +PARTITION BY toYYYYMM(EventDate) +SETTINGS storage_policy = 'moving_from_ssd_to_hdd' +``` + +`default` 存储策略意味着只使用一个卷，这个卷只包含一个在 `` 中定义的磁盘。表创建后，它的存储策略就不能改变了。 + +可以通过 [background\_move\_pool\_size](../../../operations/settings/settings.md#background_move_pool_size) 设置调整执行后台任务的线程数。 + +### 详细说明 {#details} + +对于 `MergeTree` 表，数据通过以下不同的方式写入到磁盘当中： + +- 作为插入（`INSERT`查询）的结果 +- 在后台合并和[数据变异](../../../sql-reference/statements/alter/index.md#alter-mutations)期间 +- 当从另一个副本下载时 +- 作为 [ALTER TABLE … FREEZE PARTITION](../../../sql-reference/statements/alter/partition.md#alter_freeze-partition) 冻结分区的结果 + +除了数据变异和冻结分区以外的情况下，数据按照以下逻辑存储到卷或磁盘上： + +1. 首个卷（按定义顺序）拥有足够的磁盘空间存储数据片段（`unreserved_space > current_part_size`）并且允许存储给定数据片段的大小（`max_data_part_size_bytes > current_part_size`） +2. 在这个数据卷内，紧挨着先前存储数据的那块磁盘之后的磁盘，拥有比数据片段大的剩余空间。（`unreserved_space - keep_free_space_bytes > current_part_size`） + +更进一步，数据变异和分区冻结使用的是 [硬链接](https://en.wikipedia.org/wiki/Hard_link)。不同磁盘之间的硬链接是不支持的，所以在这种情况下数据片段都会被存储到初始化的那一块磁盘上。 + +在后台，数据片段基于剩余空间（`move_factor`参数）根据卷在配置文件中定义的顺序进行转移。数据永远不会从最后一个移出也不会从第一个移入。可以通过系统表 [system.part\_log](../../../operations/system-tables/part_log.md#system_tables-part-log) (字段 `type = MOVE_PART`) 和 [system.parts](../../../operations/system-tables/parts.md#system_tables-parts) (字段 `path` 和 `disk`) 来监控后台的移动情况。同时，具体细节可以通过服务器日志查看。 + +用户可以通过 [ALTER TABLE … MOVE PART\|PARTITION … TO VOLUME\|DISK …](../../../sql-reference/statements/alter/partition.md#alter_move-partition) 强制移动一个数据片段或分区到另外一个卷，所有后台移动的限制都会被考虑在内。这个查询会自行启动，无需等待后台操作完成。如果没有足够的可用空间或任何必须条件没有被满足，用户会收到报错信息。 + +数据移动不会妨碍到数据复制。也就是说，同一张表的不同副本可以指定不同的存储策略。 + +在后台合并和数据变异之后，就的数据片段会在一定时间后被移除 (`old_parts_lifetime`)。在这期间，他们不能被移动到其他的卷或磁盘。也就是说，直到数据片段被完全移除，它们仍然会被磁盘占用空间计算在内。 + +[原始文章](https://clickhouse.tech/docs/en/operations/table_engines/mergetree/) From 00c8dce39c3d9644c6bd7e8e3e1939ef06e0b432 Mon Sep 17 00:00:00 2001 From: Sergei Shtykov Date: Fri, 28 Aug 2020 14:01:33 +0300 Subject: [PATCH 26/73] CLICKHOUSEDOCS-744: Fixed VersionedCollapsingMergeTree description. --- .../mergetree-family/versionedcollapsingmergetree.md | 2 +- .../mergetree-family/versionedcollapsingmergetree.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/en/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md b/docs/en/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md index a010a395c64..b23139b402b 100644 --- a/docs/en/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md +++ b/docs/en/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md @@ -121,7 +121,7 @@ To find out why we need two rows for each change, see [Algorithm](#table_engines **Notes on Usage** -1. The program that writes the data should remember the state of an object in order to cancel it. The “cancel” string should be a copy of the “state” string with the opposite `Sign`. This increases the initial size of storage but allows to write the data quickly. +1. The program that writes the data should remember the state of an object to be able to cancel it. “Cancel” string should contain copies of the primary key fields and the version of the “state” string and the opposite `Sign`. It increases the initial size of storage but allows to write the data quickly. 2. Long growing arrays in columns reduce the efficiency of the engine due to the load for writing. The more straightforward the data, the better the efficiency. 3. `SELECT` results depend strongly on the consistency of the history of object changes. Be accurate when preparing data for inserting. You can get unpredictable results with inconsistent data, such as negative values for non-negative metrics like session depth. diff --git a/docs/ru/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md b/docs/ru/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md index 5dc9589bef5..bf280eb52bc 100644 --- a/docs/ru/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md +++ b/docs/ru/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md @@ -116,7 +116,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] **Примечания по использованию** -1. Программа, которая записывает данные, должна помнить состояние объекта, чтобы иметь возможность отменить его. Строка отмены состояния должна быть копией предыдущей строки состояния с противоположным значением `Sign`. Это увеличивает начальный размер хранилища, но позволяет быстро записывать данные. +1. Программа, которая записывает данные, должна помнить состояние объекта, чтобы иметь возможность отменить его. Строка отмены состояния должна содержать копии полей первичного ключа и копию версии строки состояния и противоположное значение `Sign`. Это увеличивает начальный размер хранилища, но позволяет быстро записывать данные. 2. Длинные растущие массивы в столбцах снижают эффективность работы движка за счёт нагрузки на запись. Чем проще данные, тем выше эффективность. 3. `SELECT` результаты сильно зависят от согласованности истории изменений объекта. Будьте точны при подготовке данных для вставки. Вы можете получить непредсказуемые результаты с несогласованными данными, такими как отрицательные значения для неотрицательных метрик, таких как глубина сеанса. From bd9c01e4c0579af6b2d066cc2d5dfbe96efc24c1 Mon Sep 17 00:00:00 2001 From: Gao Qiang <30835199+dreamerfable@users.noreply.github.com> Date: Fri, 28 Aug 2020 22:54:30 +0800 Subject: [PATCH 27/73] Update mergetree.md --- .../table-engines/mergetree-family/mergetree.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/zh/engines/table-engines/mergetree-family/mergetree.md b/docs/zh/engines/table-engines/mergetree-family/mergetree.md index e733994b73d..0b886547229 100644 --- a/docs/zh/engines/table-engines/mergetree-family/mergetree.md +++ b/docs/zh/engines/table-engines/mergetree-family/mergetree.md @@ -214,7 +214,7 @@ ClickHouse 不要求主键惟一，所以你可以插入多条具有相同主键 在这种情况下合理的做法是，只保留少量的列在主键当中用于提升扫描效率，将维度列添加到排序键中。 -对排序键进行 [ALTER](../../../sql-reference/statements/alter/index.md) 是轻量级的操作，因为当一个新列同时被加入到表里和排序键里时，已存在的数据片段并不需要修改。由于旧的排序键是新排序键的前缀，并且新添加的列中没有数据，因此在表修改时的数据对于新旧的排序键来说都是有序的。 +对排序键进行 [ALTER](../../../sql-reference/statements/alter.md) 是轻量级的操作，因为当一个新列同时被加入到表里和排序键里时，已存在的数据片段并不需要修改。由于旧的排序键是新排序键的前缀，并且新添加的列中没有数据，因此在表修改时的数据对于新旧的排序键来说都是有序的。 ### 索引和分区在查询中的应用 {#use-of-indexes-and-partitions-in-queries} @@ -491,7 +491,7 @@ ClickHouse 在数据片段合并时会删除掉过期的数据。 MergeTree 系列表引擎可以将数据存储在多块设备上。这对某些可以潜在被划分为“冷”“热”的表来说是很有用的。近期数据被定期的查询但只需要很小的空间。相反，详尽的历史数据很少被用到。如果有多块磁盘可用，那么“热”的数据可以放置在快速的磁盘上（比如 NVMe 固态硬盘或内存），“冷”的数据可以放在相对较慢的磁盘上（比如机械硬盘）。 -数据片段是 `MergeTree` 引擎表的最小可移动单元。属于同一个数据片段的数据被存储在同一块磁盘上。数据片段会在后台自动的在磁盘间移动，也可以通过 [ALTER](../../../sql-reference/statements/alter/partition.md#alter_move-partition) 查询来移动。 +数据片段是 `MergeTree` 引擎表的最小可移动单元。属于同一个数据片段的数据被存储在同一块磁盘上。数据片段会在后台自动的在磁盘间移动，也可以通过 [ALTER](../../../sql-reference/statements/alter.md#alter_move-partition) 查询来移动。 ### 术语 {#terms} @@ -635,9 +635,9 @@ SETTINGS storage_policy = 'moving_from_ssd_to_hdd' 对于 `MergeTree` 表，数据通过以下不同的方式写入到磁盘当中： - 作为插入（`INSERT`查询）的结果 -- 在后台合并和[数据变异](../../../sql-reference/statements/alter/index.md#alter-mutations)期间 +- 在后台合并和[数据变异](../../../sql-reference/statements/alter.md#alter-mutations)期间 - 当从另一个副本下载时 -- 作为 [ALTER TABLE … FREEZE PARTITION](../../../sql-reference/statements/alter/partition.md#alter_freeze-partition) 冻结分区的结果 +- 作为 [ALTER TABLE … FREEZE PARTITION](../../../sql-reference/statements/alter.md#alter_freeze-partition) 冻结分区的结果 除了数据变异和冻结分区以外的情况下，数据按照以下逻辑存储到卷或磁盘上： @@ -648,7 +648,7 @@ SETTINGS storage_policy = 'moving_from_ssd_to_hdd' 在后台，数据片段基于剩余空间（`move_factor`参数）根据卷在配置文件中定义的顺序进行转移。数据永远不会从最后一个移出也不会从第一个移入。可以通过系统表 [system.part\_log](../../../operations/system-tables/part_log.md#system_tables-part-log) (字段 `type = MOVE_PART`) 和 [system.parts](../../../operations/system-tables/parts.md#system_tables-parts) (字段 `path` 和 `disk`) 来监控后台的移动情况。同时，具体细节可以通过服务器日志查看。 -用户可以通过 [ALTER TABLE … MOVE PART\|PARTITION … TO VOLUME\|DISK …](../../../sql-reference/statements/alter/partition.md#alter_move-partition) 强制移动一个数据片段或分区到另外一个卷，所有后台移动的限制都会被考虑在内。这个查询会自行启动，无需等待后台操作完成。如果没有足够的可用空间或任何必须条件没有被满足，用户会收到报错信息。 +用户可以通过 [ALTER TABLE … MOVE PART\|PARTITION … TO VOLUME\|DISK …](../../../sql-reference/statements/alter.md#alter_move-partition) 强制移动一个数据片段或分区到另外一个卷，所有后台移动的限制都会被考虑在内。这个查询会自行启动，无需等待后台操作完成。如果没有足够的可用空间或任何必须条件没有被满足，用户会收到报错信息。 数据移动不会妨碍到数据复制。也就是说，同一张表的不同副本可以指定不同的存储策略。 From e22ee38a353fd19785ff6106f33a4ce382c4b01c Mon Sep 17 00:00:00 2001 From: Dao Minh Thuc Date: Sun, 30 Aug 2020 22:48:43 +0700 Subject: [PATCH 28/73] Fix build for AppleClang --- contrib/capnproto-cmake/CMakeLists.txt | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/contrib/capnproto-cmake/CMakeLists.txt b/contrib/capnproto-cmake/CMakeLists.txt index 8bdac0beec0..e5d62c59327 100644 --- a/contrib/capnproto-cmake/CMakeLists.txt +++ b/contrib/capnproto-cmake/CMakeLists.txt @@ -29,6 +29,10 @@ set (KJ_SRCS ${CAPNPROTO_SOURCE_DIR}/kj/parse/char.c++ ) +if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang") + set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-char8_t") +endif () + add_library(kj ${KJ_SRCS}) target_include_directories(kj SYSTEM PUBLIC ${CAPNPROTO_SOURCE_DIR}) From 8fa61f785faa3b21f913b6780fbb5bb667eec1ad Mon Sep 17 00:00:00 2001 From: Alexey Milovidov Date: Tue, 1 Sep 2020 01:52:12 +0300 Subject: [PATCH 29/73] Better check for tuple size in complex key external dictionaries --- src/Dictionaries/ExternalQueryBuilder.cpp | 8 ++++++-- .../SSDComplexKeyCacheDictionary.cpp | 6 ++++++ src/Dictionaries/SSDComplexKeyCacheDictionary.h | 10 ++++------ src/Functions/FunctionsExternalDictionaries.h | 16 ++++++++++++++++ 4 files changed, 32 insertions(+), 8 deletions(-) diff --git a/src/Dictionaries/ExternalQueryBuilder.cpp b/src/Dictionaries/ExternalQueryBuilder.cpp index b682aaeb557..e8d71b1fd85 100644 --- a/src/Dictionaries/ExternalQueryBuilder.cpp +++ b/src/Dictionaries/ExternalQueryBuilder.cpp @@ -13,6 +13,7 @@ namespace DB namespace ErrorCodes { extern const int UNSUPPORTED_METHOD; + extern const int LOGICAL_ERROR; } @@ -239,12 +240,15 @@ std::string ExternalQueryBuilder::composeLoadIdsQuery(const std::vector } -std::string -ExternalQueryBuilder::composeLoadKeysQuery(const Columns & key_columns, const std::vector & requested_rows, LoadKeysMethod method, size_t partition_key_prefix) +std::string ExternalQueryBuilder::composeLoadKeysQuery( + const Columns & key_columns, const std::vector & requested_rows, LoadKeysMethod method, size_t partition_key_prefix) { if (!dict_struct.key) throw Exception{"Composite key required for method", ErrorCodes::UNSUPPORTED_METHOD}; + if (key_columns.size() != dict_struct.key->size()) + throw Exception{"The size of key_columns does not equal to the size of dictionary key", ErrorCodes::LOGICAL_ERROR}; + WriteBufferFromOwnString out; writeString("SELECT ", out); diff --git a/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp b/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp index 826a61f7312..b1e4686e938 100644 --- a/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp +++ b/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp @@ -1120,6 +1120,8 @@ void SSDComplexKeyCacheStorage::update( AbsentIdHandler && on_key_not_found, const DictionaryLifetime lifetime) { + assert(key_columns.size() == key_types.size()); + auto append_block = [&key_types, this]( const Columns & new_keys, const SSDComplexKeyCachePartition::Attributes & new_attributes, @@ -1447,6 +1449,10 @@ void SSDComplexKeyCacheDictionary::getItemsNumberImpl( const Columns & key_columns, const DataTypes & key_types, ResultArrayType & out, DefaultGetter && get_default) const { + assert(dict_struct.key); + assert(key_columns.size() == key_types.size()); + assert(key_columns.size() == dict_struct.key->size()); + const auto now = std::chrono::system_clock::now(); TemporalComplexKeysPool not_found_pool; diff --git a/src/Dictionaries/SSDComplexKeyCacheDictionary.h b/src/Dictionaries/SSDComplexKeyCacheDictionary.h index 89e88982eee..af9a0c0a7ee 100644 --- a/src/Dictionaries/SSDComplexKeyCacheDictionary.h +++ b/src/Dictionaries/SSDComplexKeyCacheDictionary.h @@ -427,9 +427,8 @@ private: using SSDComplexKeyCachePartitionPtr = std::shared_ptr; -/* - Class for managing SSDCachePartition and getting data from source. -*/ +/** Class for managing SSDCachePartition and getting data from source. + */ class SSDComplexKeyCacheStorage { public: @@ -515,9 +514,8 @@ private: }; -/* - Dictionary interface -*/ +/** Dictionary interface + */ class SSDComplexKeyCacheDictionary final : public IDictionaryBase { public: diff --git a/src/Functions/FunctionsExternalDictionaries.h b/src/Functions/FunctionsExternalDictionaries.h index 609c247ce42..5472f0eebf8 100644 --- a/src/Functions/FunctionsExternalDictionaries.h +++ b/src/Functions/FunctionsExternalDictionaries.h @@ -971,6 +971,14 @@ private: const auto & key_columns = assert_cast(*key_col).getColumnsCopy(); const auto & key_types = static_cast(*key_col_with_type.type).getElements(); + assert(key_columns.size() == key_types.size()); + const auto & structure = dict->getStructure(); + assert(structure.key); + size_t key_size = structure.key->size(); + if (key_columns.size() != key_size) + throw Exception{ErrorCodes::TYPE_MISMATCH, + "Wrong size of tuple at the third argument of function {} must be {}", getName(), key_size}; + typename ColVec::MutablePtr out; if constexpr (IsDataTypeDecimal) out = ColVec::create(key_columns.front()->size(), decimal_scale); @@ -1294,6 +1302,14 @@ private: const auto & key_columns = typeid_cast(*key_col).getColumnsCopy(); const auto & key_types = static_cast(*key_col_with_type.type).getElements(); + assert(key_columns.size() == key_types.size()); + const auto & structure = dict->getStructure(); + assert(structure.key); + size_t key_size = structure.key->size(); + if (key_columns.size() != key_size) + throw Exception{ErrorCodes::TYPE_MISMATCH, + "Wrong size of tuple at the third argument of function {} must be {}", getName(), key_size}; + /// @todo detect when all key columns are constant const auto rows = key_col->size(); typename ColVec::MutablePtr out; From 142a5bcede36257a37905bbf50047eca09b20f88 Mon Sep 17 00:00:00 2001 From: Alexey Milovidov Date: Tue, 1 Sep 2020 02:10:04 +0300 Subject: [PATCH 30/73] Added validation of key types to SSD Cache dictionary --- src/Dictionaries/SSDComplexKeyCacheDictionary.cpp | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp b/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp index b1e4686e938..972d10da24d 100644 --- a/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp +++ b/src/Dictionaries/SSDComplexKeyCacheDictionary.cpp @@ -1453,6 +1453,8 @@ void SSDComplexKeyCacheDictionary::getItemsNumberImpl( assert(key_columns.size() == key_types.size()); assert(key_columns.size() == dict_struct.key->size()); + dict_struct.validateKeyTypes(key_types); + const auto now = std::chrono::system_clock::now(); TemporalComplexKeysPool not_found_pool; @@ -1533,6 +1535,8 @@ void SSDComplexKeyCacheDictionary::getItemsStringImpl( ColumnString * out, DefaultGetter && get_default) const { + dict_struct.validateKeyTypes(key_types); + const auto now = std::chrono::system_clock::now(); TemporalComplexKeysPool not_found_pool; From 33c5815eb307fee81f59f405a87b0276dc05521d Mon Sep 17 00:00:00 2001 From: Alexander Kuzmenkov Date: Tue, 1 Sep 2020 02:33:42 +0300 Subject: [PATCH 31/73] Add a HTML report for AST Fuzzer --- docker/test/fuzzer/run-fuzzer.sh | 56 ++++++++++++++++++++++++++++++-- programs/client/Client.cpp | 15 ++------- 2 files changed, 57 insertions(+), 14 deletions(-) diff --git a/docker/test/fuzzer/run-fuzzer.sh b/docker/test/fuzzer/run-fuzzer.sh index 8cfe1a87408..5c1f2fdb586 100755 --- a/docker/test/fuzzer/run-fuzzer.sh +++ b/docker/test/fuzzer/run-fuzzer.sh @@ -91,7 +91,7 @@ function fuzz ./clickhouse-client --query "select elapsed, query from system.processes" ||: killall clickhouse-server ||: - for x in {1..10} + for _ in {1..10} do if ! pgrep -f clickhouse-server then @@ -172,8 +172,60 @@ case "$stage" in echo "failure" > status.txt echo "Fuzzer failed ($fuzzer_exit_code). See the logs" > description.txt fi + ;& +"report") +cat > report.html < + + + + AST Fuzzer for PR #${PR_TO_TEST} @ ${SHA_TO_TEST} + + +
+ +

AST Fuzzer for PR #${PR_TO_TEST} @ ${SHA_TO_TEST}

+

+fuzzer.log +server.log +main.log +

+ + + +
Test nameTest statusDescription
AST Fuzzer$(cat status.txt)$(cat description.txt)
+ + + +EOF ;& esac +exit $task_exit_code + diff --git a/programs/client/Client.cpp b/programs/client/Client.cpp index db5a677e0e1..eb95b3634ca 100644 --- a/programs/client/Client.cpp +++ b/programs/client/Client.cpp @@ -847,30 +847,24 @@ private: } // Parse and execute what we've read. - fprintf(stderr, "will now parse '%s'\n", text.c_str()); - const auto * new_end = processWithFuzzing(text); if (new_end > &text[0]) { const auto rest_size = text.size() - (new_end - &text[0]); - fprintf(stderr, "total %zd, rest %zd\n", text.size(), rest_size); - memcpy(&text[0], new_end, rest_size); text.resize(rest_size); } else { - fprintf(stderr, "total %zd, can't parse\n", text.size()); + // We didn't read enough text to parse a query. Will read more. } - if (!connection->isConnected()) + if (!connection->ping()) { // Uh-oh... - std::cerr << "Lost connection to the server." << std::endl; - last_exception_received_from_server - = std::make_unique(210, "~"); + last_exception_received_from_server = std::make_unique(210, "Lost connection to the server."); return; } @@ -880,9 +874,6 @@ private: // and we still cannot parse a single query in it. Abort. std::cerr << "Read too much text and still can't parse a query." " Aborting." << std::endl; - last_exception_received_from_server - = std::make_unique(1, "~"); - // return; exit(1); } } From 9cf2a38eb8198a473357f7ceeb2ba56ac4561b4b Mon Sep 17 00:00:00 2001 From: Alexander Kuzmenkov Date: Tue, 1 Sep 2020 03:22:06 +0300 Subject: [PATCH 32/73] fixup --- programs/client/Client.cpp | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/programs/client/Client.cpp b/programs/client/Client.cpp index eb95b3634ca..c9701950dc5 100644 --- a/programs/client/Client.cpp +++ b/programs/client/Client.cpp @@ -861,12 +861,12 @@ private: // We didn't read enough text to parse a query. Will read more. } - if (!connection->ping()) - { - // Uh-oh... - last_exception_received_from_server = std::make_unique(210, "Lost connection to the server."); - return; - } + // Ensure that we're still connected to the server. If the server died, + // the reconnect is going to fail with an exception, and the fuzzer + // will exit. The ping() would be the best match here, but it's + // private, probably for a good reason that the protocol doesn't allow + // pings at any possible moment. + connection->forceConnected(connection_parameters.timeouts); if (text.size() > 4 * 1024) { From c3dd968931e31db7bc59483b85e67acc961dbafd Mon Sep 17 00:00:00 2001 From: bharatnc Date: Mon, 31 Aug 2020 21:42:27 -0700 Subject: [PATCH 33/73] fix ALTER LIVE VIEW lock issue This PR fixes a lock issue that happens while executing `ALTER LIVE VIEW` query with the `REFRESH` command that results in a exception. The problem is that lock is currently being acquired in `InterpreterALterQuery.cpp` in the `InterpreterAlterQuery::execute()` method and lock is again being reacquired in `StorageLiveView.cpp` in the ` StorageLiveView::refresh` method. This removes that extra lock. Before fix: ```sql --create table CREATE TABLE test0 ( c0 UInt64 ) ENGINE = MergeTree() PARTITION BY c0 ORDER BY c0; -- enable experimental_live_view :) SET allow_experimental_live_view=1 -- create live view; :) CREATE LIVE VIEW live1 AS SELECT * FROM table0; -- alter live view results in exception :) ALTER LIVE VIEW live1 REFRESH; ... ... Received exception from server (version 20.8.1): Code: 49. DB::Exception: Received from localhost:9000. DB::Exception: RWLockImpl::getLock(): RWLock is already locked in exclusive mode. ``` After fix: ```sql :) ALTER LIVE VIEW live1 REFRESH; ALTER LIVE VIEW live1 REFRESH Ok. 0 rows in set. Elapsed: 0.016 sec. ``` --- src/Interpreters/InterpreterAlterQuery.cpp | 2 +- src/Storages/LiveView/StorageLiveView.cpp | 5 +++-- src/Storages/LiveView/StorageLiveView.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/src/Interpreters/InterpreterAlterQuery.cpp b/src/Interpreters/InterpreterAlterQuery.cpp index e0313803e9a..8cf581eb463 100644 --- a/src/Interpreters/InterpreterAlterQuery.cpp +++ b/src/Interpreters/InterpreterAlterQuery.cpp @@ -101,7 +101,7 @@ BlockIO InterpreterAlterQuery::execute() switch (command.type) { case LiveViewCommand::REFRESH: - live_view->refresh(context); + live_view->refresh(); break; } } diff --git a/src/Storages/LiveView/StorageLiveView.cpp b/src/Storages/LiveView/StorageLiveView.cpp index 54ac5bcc791..4da02365232 100644 --- a/src/Storages/LiveView/StorageLiveView.cpp +++ b/src/Storages/LiveView/StorageLiveView.cpp @@ -518,9 +518,10 @@ void StorageLiveView::drop() condition.notify_all(); } -void StorageLiveView::refresh(const Context & context) +void StorageLiveView::refresh() { - auto table_lock = lockExclusively(context.getCurrentQueryId(), context.getSettingsRef().lock_acquire_timeout); + // Lock is already acquired exclusively from InterperterAlterQuery.cpp InterpreterAlterQuery::execute() method. + // So, reacquiring lock is not needed and will result in an exception. { std::lock_guard lock(mutex); if (getNewBlocks()) diff --git a/src/Storages/LiveView/StorageLiveView.h b/src/Storages/LiveView/StorageLiveView.h index 43afd169a92..0c099d01a29 100644 --- a/src/Storages/LiveView/StorageLiveView.h +++ b/src/Storages/LiveView/StorageLiveView.h @@ -122,7 +122,7 @@ public: void startup() override; void shutdown() override; - void refresh(const Context & context); + void refresh(); Pipe read( const Names & column_names, From 49095e81692214b45aa4681f0de5a3bea724ea17 Mon Sep 17 00:00:00 2001 From: BohuTANG Date: Tue, 1 Sep 2020 13:27:13 +0800 Subject: [PATCH 34/73] ISSUES-14235 add one integration test for empty GTID transaction --- .../test_materialize_mysql_database/test.py | 34 +++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/tests/integration/test_materialize_mysql_database/test.py b/tests/integration/test_materialize_mysql_database/test.py index bfda4e7e840..c86b9850f44 100644 --- a/tests/integration/test_materialize_mysql_database/test.py +++ b/tests/integration/test_materialize_mysql_database/test.py @@ -120,3 +120,37 @@ def test_materialize_database_ddl_with_mysql_8_0(started_cluster, started_mysql_ materialize_with_ddl.alter_rename_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") materialize_with_ddl.alter_modify_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") +def test_materialize_database_ddl_with_empty_transaction(started_cluster, started_mysql_5_7): + mysql_node = started_mysql_5_7.alloc_connection() + mysql_node.query("CREATE DATABASE test_database") + + + mysql_node.query("RESET MASTER") + mysql_node.query("CREATE TABLE test_database.t1(a INT NOT NULL PRIMARY KEY, b VARCHAR(255) DEFAULT 'BEGIN')") + mysql_node.query("INSERT INTO test_database.t1(a) VALUES(1)") + + clickhouse_node.query( + "CREATE DATABASE test_database ENGINE = MaterializeMySQL('{}:3306', 'test_database', 'root', 'clickhouse')".format( + "mysql5_7")) + + # Reject one empty GTID QUERY event with 'BEGIN' and 'COMMIT' + mysql_cursor = mysql_node.cursor(pymysql.cursors.DictCursor) + mysql_cursor.execute("SHOW MASTER STATUS") + (uuid, seqs) = mysql_cursor.fetchall()[0]["Executed_Gtid_Set"].split(":") + (seq_begin, seq_end) = seqs.split("-") + assert int(seq_begin) == 1 + assert int(seq_end) == 3 + next_gtid = uuid + ":" + str(int(seq_end) + 1) + mysql_node.query("SET gtid_next='" + next_gtid + "'") + mysql_node.query("BEGIN") + mysql_node.query("COMMIT") + mysql_node.query("SET gtid_next='AUTOMATIC'") + + # Reject one 'BEGIN' QUERY event and 'COMMIT' XID event. + mysql_node.query("/* start */ begin /* end */") + mysql_node.query("INSERT INTO test_database.t1(a) VALUES(2)") + mysql_node.query("/* start */ commit /* end */") + + materialize_with_ddl.check_query(clickhouse_node, "SELECT * FROM test_database.t1 ORDER BY a FORMAT TSV", "1\tBEGIN\n2\tBEGIN\n") + clickhouse_node.query("DROP DATABASE test_database") + mysql_node.query("DROP DATABASE test_database") From 2c0353587eb754fc5dc7c3efb7c223b05ec34a95 Mon Sep 17 00:00:00 2001 From: bharatnc Date: Mon, 31 Aug 2020 22:04:40 -0700 Subject: [PATCH 35/73] add tests --- .../0_stateless/01463_test_alter_live_view_refresh.sql | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql diff --git a/tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql b/tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql new file mode 100644 index 00000000000..36e8c9a9785 --- /dev/null +++ b/tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql @@ -0,0 +1,9 @@ +CREATE TABLE test0 ( + c0 UInt64 + ) ENGINE = MergeTree() PARTITION BY c0 ORDER BY c0; + +SET allow_experimental_live_view=1; + +CREATE LIVE VIEW live1 AS SELECT * FROM test0; + +ALTER LIVE VIEW live1 REFRESH; -- success From d04cda03677b5d3151f6d2eb24f63f181892e8e2 Mon Sep 17 00:00:00 2001 From: Azat Khuzhin Date: Tue, 1 Sep 2020 02:22:33 +0300 Subject: [PATCH 36/73] Fix QueryPlan lifetime (for EXPLAIN PIPELINE graph=1) for queries with nested interpreter Example of such queries are distributed queries, which creates local InterpreterSelectQuery, which will have it's own QueryPlan but returns Pipes that has that IQueryPlanStep attached. After EXPLAIN PIPELINE graph=1 tries to use them, and will get SIGSEGV. - TSAN:
``` ==2782113==ERROR: AddressSanitizer: heap-use-after-free on address 0x6120000223c0 at pc 0x00002b8f3f3e bp 0x7fff18cfbff0 sp 0x7fff18cfbfe8 READ of size 8 at 0x6120000223c0 thread T22 (TCPHandler) #0 0x2b8f3f3d in DB::printPipelineCompact(std::__1::vector, std::__1::allocator > > const&, DB::WriteBuffer&, bool) /build/obj-x86_64-linux-gnu/../src/Processors/printPipeline.cpp:116:53 #1 0x29ee698c in DB::InterpreterExplainQuery::executeImpl() /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterExplainQuery.cpp:275:17 #2 0x29ee2e40 in DB::InterpreterExplainQuery::execute() /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterExplainQuery.cpp:73:14 #3 0x2a7b44a2 in DB::executeQueryImpl(char const*, char const*, DB::Context&, bool, DB::QueryProcessingStage::Enum, bool, DB::ReadBuffer*) /build/obj-x86_64-linux-gnu/../src/Interpreters/executeQuery.cpp:389:28 #4 0x2a7b1cb3 in DB::executeQuery(std::__1::basic_string, std::__1::allocator > const&, DB::Context&, bool, DB::QueryProcessingStage::Enum, bool) /build/obj-x86_64-linux-gnu/../src/Interpreters/executeQuery.cpp:675:30 #5 0x2b7993b2 in DB::TCPHandler::runImpl() /build/obj-x86_64-linux-gnu/../src/Server/TCPHandler.cpp:253:24 #6 0x2b7b649a in DB::TCPHandler::run() /build/obj-x86_64-linux-gnu/../src/Server/TCPHandler.cpp:1217:9 #7 0x31d9c57e in Poco::Net::TCPServerConnection::start() /build/obj-x86_64-linux-gnu/../contrib/poco/Net/src/TCPServerConnection.cpp:43:3 #8 0x31d9d281 in Poco::Net::TCPServerDispatcher::run() /build/obj-x86_64-linux-gnu/../contrib/poco/Net/src/TCPServerDispatcher.cpp:114:20 #9 0x3206b5d5 in Poco::PooledThread::run() /build/obj-x86_64-linux-gnu/../contrib/poco/Foundation/src/ThreadPool.cpp:199:14 #10 0x320657ad in Poco::ThreadImpl::runnableEntry(void*) /build/obj-x86_64-linux-gnu/../contrib/poco/Foundation/src/Thread_POSIX.cpp:345:27 #11 0x7ffff7f853e8 in start_thread (/usr/lib/libpthread.so.0+0x93e8) #12 0x7ffff7ea2292 in clone (/usr/lib/libc.so.6+0x100292) 0x6120000223c0 is located 0 bytes inside of 272-byte region [0x6120000223c0,0x6120000224d0) freed by thread T22 (TCPHandler) here: #0 0x122f3b62 in operator delete(void*, unsigned long) (/src/ch/tmp/master-20200831/clickhouse+0x122f3b62) #1 0x2bd9e9fa in std::__1::default_delete::operator()(DB::IQueryPlanStep*) const /build/obj-x86_64-linux-gnu/../contrib/libcxx/include/memory:2363:5 #2 0x2bd9e9fa in std::__1::unique_ptr >::reset(DB::IQueryPlanStep*) /build/obj-x86_64-linux-gnu/../contrib/libcxx/include/memory:2618:7 #3 0x2bd9e9fa in std::__1::unique_ptr >::~unique_ptr() /build/obj-x86_64-linux-gnu/../contrib/libcxx/include/memory:2572:19 #4 0x2bd9e9fa in DB::QueryPlan::Node::~Node() /build/obj-x86_64-linux-gnu/../src/Processors/QueryPlan/QueryPlan.h:66:12 #5 0x2bd9e9fa in void std::__1::allocator_traits > >::__destroy(std::__1::integral_constant, std::__1::allocator >&, DB::QueryPlan::Node*) /build/obj-x86_64-linux-gnu/../contrib/libcxx/include/memory:1798:23 #6 0x2bd9e9fa in void std::__1::allocator_traits > >::destroy(std::__1::allocator >&, DB::QueryPlan::Node*) /build/obj-x86_64-lin ux-gnu/../contrib/libcxx/include/memory:1630:14 #7 0x2bd9e9fa in std::__1::__list_imp >::clear() /build/obj-x86_64-linux-gnu/../contrib/libcxx/include/list:762:13 #8 0x29fece08 in DB::InterpreterSelectQuery::execute() /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterSelectQuery.cpp:492:1 #9 0x2abf7484 in DB::ClusterProxy::(anonymous namespace)::createLocalStream(std::__1::shared_ptr const&, DB::Block const&, DB::Context const&, DB::QueryProcessingStage::Enum) /build/obj-x86_64-linux-gnu/../src/Interpreters/ClusterProxy/SelectStreamFactory.cpp: 78:33 #10 0x2abea85d in DB::ClusterProxy::SelectStreamFactory::createForShard(DB::Cluster::ShardInfo const&, std::__1::basic_string, std::__1::allocator > const&, std::__1::shared_ptr const&, DB::Context const&, std::__1::shar ed_ptr const&, DB::SelectQueryInfo const&, std::__1::vector >&)::$_0::operator()() const /build/obj-x86_64-linux-gnu/../src/Interpreters/ClusterProxy/SelectStreamFactory.cpp:133:51 #11 0x2abea85d in DB::ClusterProxy::SelectStreamFactory::createForShard(DB::Cluster::ShardInfo const&, std::__1::basic_string, std::__1::allocator > const&, std::__1::shared_ptr const&, DB::Context const&, std::__1::shar ed_ptr const&, DB::SelectQueryInfo const&, std::__1::vector >&) /build/obj-x86_64-linux-gnu/../src/Interpreters/ClusterProxy/SelectStreamFactory.cpp:189:13 #12 0x2abe6d99 in DB::ClusterProxy::executeQuery(DB::ClusterProxy::IStreamFactory&, std::__1::shared_ptr const&, Poco::Logger*, std::__1::shared_ptr const&, DB::Context const&, DB::Settings const&, DB::SelectQueryInfo const&) /build/obj-x86_64-lin ux-gnu/../src/Interpreters/ClusterProxy/executeQuery.cpp:107:24 #13 0x2abc4b74 in DB::StorageDistributed::read(std::__1::vector, std::__1::allocator >, std::__1::allocator, std::__1::allocator > > > const&, s td::__1::shared_ptr const&, DB::SelectQueryInfo const&, DB::Context const&, DB::QueryProcessingStage::Enum, unsigned long, unsigned int) /build/obj-x86_64-linux-gnu/../src/Storages/StorageDistributed.cpp:514:12 #14 0x2bda1c5a in DB::ReadFromStorageStep::ReadFromStorageStep(std::__1::shared_ptr, std::__1::shared_ptr&, DB::SelectQueryOptions, std::__1::shared_ptr, std::__1::vector, std::__1::allocator >, std::__1::allocator, std::__1::allocator > > > const&, DB::SelectQueryInfo const&, std::__1::shared_ptr, DB::QueryProcessingStage ::Enum, unsigned long, unsigned long) /build/obj-x86_64-linux-gnu/../src/Processors/QueryPlan/ReadFromStorageStep.cpp:39:26 #15 0x2a01ca70 in std::__1::__unique_if::__unique_single std::__1::make_unique&, std::__1::shared_ptr&, DB::SelectQueryOptions&, std ::__1::shared_ptr&, std::__1::vector, std::__1::allocator >, std::__1::allocator, std::__1::allocator > > >&, DB::SelectQueryInfo&, st d::__1::shared_ptr&, DB::QueryProcessingStage::Enum&, unsigned long&, unsigned long&>(std::__1::shared_ptr&, std::__1::shared_ptr&, DB::SelectQueryOptions&, std::__1::shared_ptr&, std::__1::vector, std::__1::allocator >, std::__1::allocator, std::__1::allocator > > >&, DB::SelectQueryInfo&, std::__1::shared_ptr&, DB::QueryProcessingStage::Enum&, unsigned long&, unsigned long&) /build/obj-x86_64-linux-gnu/../contrib/libcxx/include/memory:3028:32 #16 0x29ff556a in DB::InterpreterSelectQuery::executeFetchColumns(DB::QueryProcessingStage::Enum, DB::QueryPlan&, std::__1::shared_ptr const&, std::__1::vector, std::__1::allocator >, std:: __1::allocator, std::__1::allocator > > > const&) /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterSelectQuery.cpp:1383:26 #17 0x29fe6b83 in DB::InterpreterSelectQuery::executeImpl(DB::QueryPlan&, std::__1::shared_ptr const&, std::__1::optional) /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterSelectQuery.cpp:795:9 #18 0x29fe5771 in DB::InterpreterSelectQuery::buildQueryPlan(DB::QueryPlan&) /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterSelectQuery.cpp:473:5 #19 0x2a47d370 in DB::InterpreterSelectWithUnionQuery::buildQueryPlan(DB::QueryPlan&) /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterSelectWithUnionQuery.cpp:182:38 #20 0x29ee5bff in DB::InterpreterExplainQuery::executeImpl() /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterExplainQuery.cpp:265:21 #21 0x29ee2e40 in DB::InterpreterExplainQuery::execute() /build/obj-x86_64-linux-gnu/../src/Interpreters/InterpreterExplainQuery.cpp:73:14 #22 0x2a7b44a2 in DB::executeQueryImpl(char const*, char const*, DB::Context&, bool, DB::QueryProcessingStage::Enum, bool, DB::ReadBuffer*) /build/obj-x86_64-linux-gnu/../src/Interpreters/executeQuery.cpp:389:28 #23 0x2a7b1cb3 in DB::executeQuery(std::__1::basic_string, std::__1::allocator > const&, DB::Context&, bool, DB::QueryProcessingStage::Enum, bool) /build/obj-x86_64-linux-gnu/../src/Interpreters/executeQuery.cpp:675:30 #24 0x2b7993b2 in DB::TCPHandler::runImpl() /build/obj-x86_64-linux-gnu/../src/Server/TCPHandler.cpp:253:24 #25 0x2b7b649a in DB::TCPHandler::run() /build/obj-x86_64-linux-gnu/../src/Server/TCPHandler.cpp:1217:9 #26 0x31d9c57e in Poco::Net::TCPServerConnection::start() /build/obj-x86_64-linux-gnu/../contrib/poco/Net/src/TCPServerConnection.cpp:43:3 #27 0x31d9d281 in Poco::Net::TCPServerDispatcher::run() /build/obj-x86_64-linux-gnu/../contrib/poco/Net/src/TCPServerDispatcher.cpp:114:20 #28 0x3206b5d5 in Poco::PooledThread::run() /build/obj-x86_64-linux-gnu/../contrib/poco/Foundation/src/ThreadPool.cpp:199:14 #29 0x320657ad in Poco::ThreadImpl::runnableEntry(void*) /build/obj-x86_64-linux-gnu/../contrib/poco/Foundation/src/Thread_POSIX.cpp:345:27 #30 0x7ffff7f853e8 in start_thread (/usr/lib/libpthread.so.0+0x93e8) ```
--- .../ClusterProxy/SelectStreamFactory.cpp | 18 ++++++++++++------ src/Interpreters/InterpreterExplainQuery.cpp | 4 +++- src/Processors/Pipe.cpp | 2 ++ src/Processors/Pipe.h | 8 ++++++++ src/Processors/QueryPipeline.h | 3 +++ .../0_stateless/01470_explain.reference | 0 tests/queries/0_stateless/01470_explain.sql | 6 ++++++ 7 files changed, 34 insertions(+), 7 deletions(-) create mode 100644 tests/queries/0_stateless/01470_explain.reference create mode 100644 tests/queries/0_stateless/01470_explain.sql diff --git a/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp b/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp index 986de85d712..ed7bd2cf71f 100644 --- a/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp +++ b/src/Interpreters/ClusterProxy/SelectStreamFactory.cpp @@ -13,6 +13,7 @@ #include #include #include +#include namespace ProfileEvents { @@ -68,14 +69,19 @@ SelectStreamFactory::SelectStreamFactory( namespace { -QueryPipeline createLocalStream( +auto createLocalPipe( const ASTPtr & query_ast, const Block & header, const Context & context, QueryProcessingStage::Enum processed_stage) { checkStackSize(); - InterpreterSelectQuery interpreter{query_ast, context, SelectQueryOptions(processed_stage)}; + InterpreterSelectQuery interpreter(query_ast, context, SelectQueryOptions(processed_stage)); + auto query_plan = std::make_unique(); - auto pipeline = interpreter.execute().pipeline; + interpreter.buildQueryPlan(*query_plan); + auto pipeline = std::move(*query_plan->buildQueryPipeline()); + + /// Avoid going it out-of-scope for EXPLAIN + pipeline.addQueryPlan(std::move(query_plan)); pipeline.addSimpleTransform([&](const Block & source_header) { @@ -94,7 +100,7 @@ QueryPipeline createLocalStream( /// return std::make_shared(stream); pipeline.setMaxThreads(1); - return pipeline; + return QueryPipeline::getPipe(std::move(pipeline)); } String formattedAST(const ASTPtr & ast) @@ -130,7 +136,7 @@ void SelectStreamFactory::createForShard( auto emplace_local_stream = [&]() { - pipes.emplace_back(QueryPipeline::getPipe(createLocalStream(modified_query_ast, header, context, processed_stage))); + pipes.emplace_back(createLocalPipe(modified_query_ast, header, context, processed_stage)); }; String modified_query = formattedAST(modified_query_ast); @@ -270,7 +276,7 @@ void SelectStreamFactory::createForShard( } if (try_results.empty() || local_delay < max_remote_delay) - return QueryPipeline::getPipe(createLocalStream(modified_query_ast, header, context, stage)); + return createLocalPipe(modified_query_ast, header, context, stage); else { std::vector connections; diff --git a/src/Interpreters/InterpreterExplainQuery.cpp b/src/Interpreters/InterpreterExplainQuery.cpp index 9960509a5d7..c936556ce39 100644 --- a/src/Interpreters/InterpreterExplainQuery.cpp +++ b/src/Interpreters/InterpreterExplainQuery.cpp @@ -269,7 +269,9 @@ BlockInputStreamPtr InterpreterExplainQuery::executeImpl() if (settings.graph) { - auto processors = Pipe::detachProcessors(QueryPipeline::getPipe(std::move(*pipeline))); + /// Pipe holds QueryPlan, should not go out-of-scope + auto pipe = QueryPipeline::getPipe(std::move(*pipeline)); + const auto & processors = pipe.getProcessors(); if (settings.compact) printPipelineCompact(processors, buffer, settings.query_pipeline_options.header); diff --git a/src/Processors/Pipe.cpp b/src/Processors/Pipe.cpp index 93dcd561c00..d28e54dae58 100644 --- a/src/Processors/Pipe.cpp +++ b/src/Processors/Pipe.cpp @@ -102,6 +102,8 @@ Pipe::Holder & Pipe::Holder::operator=(Holder && rhs) storage_holders.insert(storage_holders.end(), rhs.storage_holders.begin(), rhs.storage_holders.end()); interpreter_context.insert(interpreter_context.end(), rhs.interpreter_context.begin(), rhs.interpreter_context.end()); + for (auto & plan : rhs.query_plans) + query_plans.emplace_back(std::move(plan)); return *this; } diff --git a/src/Processors/Pipe.h b/src/Processors/Pipe.h index 28b64937aeb..f5f8b117db9 100644 --- a/src/Processors/Pipe.h +++ b/src/Processors/Pipe.h @@ -1,6 +1,7 @@ #pragma once #include #include +#include namespace DB { @@ -8,6 +9,8 @@ namespace DB class Pipe; using Pipes = std::vector; +class QueryPipeline; + class IStorage; using StoragePtr = std::shared_ptr; @@ -86,6 +89,8 @@ public: /// Get processors from Pipe. Use it with cautious, it is easy to loss totals and extremes ports. static Processors detachProcessors(Pipe pipe) { return std::move(pipe.processors); } + /// Get processors from Pipe w/o destroying pipe (used for EXPLAIN to keep QueryPlan). + const Processors & getProcessors() const { return processors; } /// Specify quotas and limits for every ISourceWithProgress. void setLimits(const SourceWithProgress::LocalLimits & limits); @@ -96,6 +101,8 @@ public: /// This methods are from QueryPipeline. Needed to make conversion from pipeline to pipe possible. void addInterpreterContext(std::shared_ptr context) { holder.interpreter_context.emplace_back(std::move(context)); } void addStorageHolder(StoragePtr storage) { holder.storage_holders.emplace_back(std::move(storage)); } + /// For queries with nested interpreters (i.e. StorageDistributed) + void addQueryPlan(std::unique_ptr plan) { holder.query_plans.emplace_back(std::move(plan)); } private: /// Destruction order: processors, header, locks, temporary storages, local contexts @@ -113,6 +120,7 @@ private: std::vector> interpreter_context; std::vector storage_holders; std::vector table_locks; + std::vector> query_plans; }; Holder holder; diff --git a/src/Processors/QueryPipeline.h b/src/Processors/QueryPipeline.h index 385cf77198e..94de753bebc 100644 --- a/src/Processors/QueryPipeline.h +++ b/src/Processors/QueryPipeline.h @@ -21,6 +21,8 @@ class QueryPipelineProcessorsCollector; struct AggregatingTransformParams; using AggregatingTransformParamsPtr = std::shared_ptr; +class QueryPlan; + class QueryPipeline { public: @@ -93,6 +95,7 @@ public: void addTableLock(const TableLockHolder & lock) { pipe.addTableLock(lock); } void addInterpreterContext(std::shared_ptr context) { pipe.addInterpreterContext(std::move(context)); } void addStorageHolder(StoragePtr storage) { pipe.addStorageHolder(std::move(storage)); } + void addQueryPlan(std::unique_ptr plan) { pipe.addQueryPlan(std::move(plan)); } /// For compatibility with IBlockInputStream. void setProgressCallback(const ProgressCallback & callback); diff --git a/tests/queries/0_stateless/01470_explain.reference b/tests/queries/0_stateless/01470_explain.reference new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/queries/0_stateless/01470_explain.sql b/tests/queries/0_stateless/01470_explain.sql new file mode 100644 index 00000000000..8fd145e7f65 --- /dev/null +++ b/tests/queries/0_stateless/01470_explain.sql @@ -0,0 +1,6 @@ +-- +-- regressions +-- + +-- SIGSEGV regression due to QueryPlan lifetime +EXPLAIN PIPELINE graph=1 SELECT * FROM remote('127.{1,2}', system.one) FORMAT Null; From 679afe5ff2bc792c6eadafa8a705113a42ac2c1b Mon Sep 17 00:00:00 2001 From: Ivan Blinkov Date: Tue, 1 Sep 2020 10:06:23 +0300 Subject: [PATCH 37/73] Revert "Documentation about ReplacingMergeTree extended with type DateTime64 for column (#13498)" This reverts commit 896b561523fb54361ef2e6748219f2bcbf625e4b. --- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- .../table-engines/mergetree-family/replacingmergetree.md | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md index 109ae6c4601..684e7e28112 100644 --- a/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/en/engines/table-engines/mergetree-family/replacingmergetree.md @@ -31,7 +31,7 @@ For a description of request parameters, see [statement description](../../../sq **ReplacingMergeTree Parameters** -- `ver` — column with version. Type `UInt*`, `Date`, `DateTime` or `DateTime64`. Optional parameter. +- `ver` — column with version. Type `UInt*`, `Date` or `DateTime`. Optional parameter. When merging, `ReplacingMergeTree` from all the rows with the same sorting key leaves only one: diff --git a/docs/es/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/es/engines/table-engines/mergetree-family/replacingmergetree.md index cb3c6aea34b..a1e95c5b5f4 100644 --- a/docs/es/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/es/engines/table-engines/mergetree-family/replacingmergetree.md @@ -33,7 +33,7 @@ Para obtener una descripción de los parámetros de solicitud, consulte [descrip **ReplacingMergeTree Parámetros** -- `ver` — column with version. Type `UInt*`, `Date`, `DateTime` o `DateTime64`. Parámetro opcional. +- `ver` — column with version. Type `UInt*`, `Date` o `DateTime`. Parámetro opcional. Al fusionar, `ReplacingMergeTree` de todas las filas con la misma clave primaria deja solo una: diff --git a/docs/fa/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/fa/engines/table-engines/mergetree-family/replacingmergetree.md index 4ece20461cb..0ace0e05afc 100644 --- a/docs/fa/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/fa/engines/table-engines/mergetree-family/replacingmergetree.md @@ -33,7 +33,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] **پارامترهای جایگزین** -- `ver` — column with version. Type `UInt*`, `Date`, `DateTime` یا `DateTime64`. پارامتر اختیاری. +- `ver` — column with version. Type `UInt*`, `Date` یا `DateTime`. پارامتر اختیاری. هنگام ادغام, `ReplacingMergeTree` از تمام ردیف ها با همان کلید اصلی تنها یک برگ دارد: diff --git a/docs/fr/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/fr/engines/table-engines/mergetree-family/replacingmergetree.md index 755249c1a38..ac3c0f3b021 100644 --- a/docs/fr/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/fr/engines/table-engines/mergetree-family/replacingmergetree.md @@ -33,7 +33,7 @@ Pour une description des paramètres de requête, voir [demande de description]( **ReplacingMergeTree Paramètres** -- `ver` — column with version. Type `UInt*`, `Date`, `DateTime` ou `DateTime64`. Paramètre facultatif. +- `ver` — column with version. Type `UInt*`, `Date` ou `DateTime`. Paramètre facultatif. Lors de la fusion, `ReplacingMergeTree` de toutes les lignes avec la même clé primaire ne laisse qu'un: diff --git a/docs/ja/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/ja/engines/table-engines/mergetree-family/replacingmergetree.md index e2cce893e3a..c3df9559415 100644 --- a/docs/ja/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/ja/engines/table-engines/mergetree-family/replacingmergetree.md @@ -33,7 +33,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] **ReplacingMergeTreeパラメータ** -- `ver` — column with version. Type `UInt*`, `Date`, `DateTime` または `DateTime64`. 任意パラメータ。 +- `ver` — column with version. Type `UInt*`, `Date` または `DateTime`. 任意パラメータ。 マージ時, `ReplacingMergeTree` 同じ主キーを持つすべての行から、一つだけを残します: diff --git a/docs/ru/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/ru/engines/table-engines/mergetree-family/replacingmergetree.md index fefc3c65b38..4aa1eb556f3 100644 --- a/docs/ru/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/ru/engines/table-engines/mergetree-family/replacingmergetree.md @@ -25,7 +25,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] **Параметры ReplacingMergeTree** -- `ver` — столбец с версией, тип `UInt*`, `Date`, `DateTime` или `DateTime64`. Необязательный параметр. +- `ver` — столбец с версией, тип `UInt*`, `Date` или `DateTime`. Необязательный параметр. При слиянии, из всех строк с одинаковым значением ключа сортировки `ReplacingMergeTree` оставляет только одну: diff --git a/docs/tr/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/tr/engines/table-engines/mergetree-family/replacingmergetree.md index f586b97cb2f..a24c84e9a16 100644 --- a/docs/tr/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/tr/engines/table-engines/mergetree-family/replacingmergetree.md @@ -33,7 +33,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] **ReplacingMergeTree Parametreleri** -- `ver` — column with version. Type `UInt*`, `Date`, `DateTime` veya `DateTime64`. İsteğe bağlı parametre. +- `ver` — column with version. Type `UInt*`, `Date` veya `DateTime`. İsteğe bağlı parametre. Birleş whenirken, `ReplacingMergeTree` aynı birincil anahtara sahip tüm satırlardan sadece bir tane bırakır: diff --git a/docs/zh/engines/table-engines/mergetree-family/replacingmergetree.md b/docs/zh/engines/table-engines/mergetree-family/replacingmergetree.md index 03b47172400..626597eeaf0 100644 --- a/docs/zh/engines/table-engines/mergetree-family/replacingmergetree.md +++ b/docs/zh/engines/table-engines/mergetree-family/replacingmergetree.md @@ -25,7 +25,7 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] **参数** -- `ver` — 版本列。类型为 `UInt*`, `Date`, `DateTime` 或 `DateTime64`。可选参数。 +- `ver` — 版本列。类型为 `UInt*`, `Date` 或 `DateTime`。可选参数。 合并的时候，`ReplacingMergeTree` 从所有具有相同主键的行中选择一行留下： - 如果 `ver` 列未指定，选择最后一条。 From 2d7cb031202ae1cdbee29d11048dfe89bb3d5acc Mon Sep 17 00:00:00 2001 From: Azat Khuzhin Date: Tue, 1 Sep 2020 10:08:54 +0300 Subject: [PATCH 38/73] Suppress superfluous wget (-nv) output Since for dowloading some of files wget logging may take 50% of overall log [1]. [1]: https://clickhouse-builds.s3.yandex.net/14315/c32ff4c98cb3b83a12f945eadd180415b7a3b269/clickhouse_build_check/build_log_761119955_1598923036.txt --- docker/builder/Dockerfile | 2 +- docker/packager/binary/Dockerfile | 9 ++++----- docker/packager/deb/Dockerfile | 4 ++-- docker/test/base/Dockerfile | 2 +- docker/test/codebrowser/Dockerfile | 2 +- docker/test/fasttest/Dockerfile | 5 ++--- docker/test/fuzzer/run-fuzzer.sh | 4 ++-- docker/test/integration/runner/Dockerfile | 2 +- docker/test/pvs/Dockerfile | 8 ++++---- docker/test/stateless/Dockerfile | 2 +- docker/test/stateless_unbundled/Dockerfile | 2 +- docker/test/stateless_with_coverage/Dockerfile | 2 +- docker/test/testflows/runner/Dockerfile | 2 +- docs/en/interfaces/http.md | 2 +- docs/es/interfaces/http.md | 2 +- docs/fa/interfaces/http.md | 2 +- docs/fr/interfaces/http.md | 2 +- docs/ja/interfaces/http.md | 2 +- docs/ru/interfaces/http.md | 2 +- docs/tr/interfaces/http.md | 2 +- docs/zh/interfaces/http.md | 2 +- src/Functions/URL/tldLookup.sh | 2 +- utils/build/build_no_submodules.sh | 2 +- utils/ci/build-gcc-from-sources.sh | 2 +- utils/ci/docker-multiarch/update.sh | 10 +++++----- utils/clickhouse-docker | 2 +- 26 files changed, 39 insertions(+), 41 deletions(-) diff --git a/docker/builder/Dockerfile b/docker/builder/Dockerfile index b7dadc3ec6d..d4a121d13eb 100644 --- a/docker/builder/Dockerfile +++ b/docker/builder/Dockerfile @@ -6,7 +6,7 @@ RUN apt-get update \ && apt-get install ca-certificates lsb-release wget gnupg apt-transport-https \ --yes --no-install-recommends --verbose-versions \ && export LLVM_PUBKEY_HASH="bda960a8da687a275a2078d43c111d66b1c6a893a3275271beedf266c1ff4a0cdecb429c7a5cccf9f486ea7aa43fd27f" \ - && wget -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ + && wget -nv -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ && echo "${LLVM_PUBKEY_HASH} /tmp/llvm-snapshot.gpg.key" | sha384sum -c \ && apt-key add /tmp/llvm-snapshot.gpg.key \ && export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \ diff --git a/docker/packager/binary/Dockerfile b/docker/packager/binary/Dockerfile index b8650b945e1..e1133f337a9 100644 --- a/docker/packager/binary/Dockerfile +++ b/docker/packager/binary/Dockerfile @@ -7,7 +7,7 @@ RUN apt-get update \ && apt-get install ca-certificates lsb-release wget gnupg apt-transport-https \ --yes --no-install-recommends --verbose-versions \ && export LLVM_PUBKEY_HASH="bda960a8da687a275a2078d43c111d66b1c6a893a3275271beedf266c1ff4a0cdecb429c7a5cccf9f486ea7aa43fd27f" \ - && wget -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ + && wget -nv -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ && echo "${LLVM_PUBKEY_HASH} /tmp/llvm-snapshot.gpg.key" | sha384sum -c \ && apt-key add /tmp/llvm-snapshot.gpg.key \ && export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \ @@ -55,7 +55,6 @@ RUN apt-get update \ cmake \ gdb \ rename \ - wget \ build-essential \ --yes --no-install-recommends @@ -83,14 +82,14 @@ RUN git clone https://github.com/tpoechtrager/cctools-port.git \ && rm -rf cctools-port # Download toolchain for Darwin -RUN wget https://github.com/phracker/MacOSX-SDKs/releases/download/10.14-beta4/MacOSX10.14.sdk.tar.xz +RUN wget -nv https://github.com/phracker/MacOSX-SDKs/releases/download/10.14-beta4/MacOSX10.14.sdk.tar.xz # Download toolchain for ARM # It contains all required headers and libraries. Note that it's named as "gcc" but actually we are using clang for cross compiling. -RUN wget "https://developer.arm.com/-/media/Files/downloads/gnu-a/8.3-2019.03/binrel/gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu.tar.xz?revision=2e88a73f-d233-4f96-b1f4-d8b36e9bb0b9&la=en" -O gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu.tar.xz +RUN wget -nv "https://developer.arm.com/-/media/Files/downloads/gnu-a/8.3-2019.03/binrel/gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu.tar.xz?revision=2e88a73f-d233-4f96-b1f4-d8b36e9bb0b9&la=en" -O gcc-arm-8.3-2019.03-x86_64-aarch64-linux-gnu.tar.xz # Download toolchain for FreeBSD 11.3 -RUN wget https://clickhouse-datasets.s3.yandex.net/toolchains/toolchains/freebsd-11.3-toolchain.tar.xz +RUN wget -nv https://clickhouse-datasets.s3.yandex.net/toolchains/toolchains/freebsd-11.3-toolchain.tar.xz COPY build.sh / CMD ["/bin/bash", "/build.sh"] diff --git a/docker/packager/deb/Dockerfile b/docker/packager/deb/Dockerfile index 6d0fdca2310..87f4582f8e2 100644 --- a/docker/packager/deb/Dockerfile +++ b/docker/packager/deb/Dockerfile @@ -7,7 +7,7 @@ RUN apt-get update \ && apt-get install ca-certificates lsb-release wget gnupg apt-transport-https \ --yes --no-install-recommends --verbose-versions \ && export LLVM_PUBKEY_HASH="bda960a8da687a275a2078d43c111d66b1c6a893a3275271beedf266c1ff4a0cdecb429c7a5cccf9f486ea7aa43fd27f" \ - && wget -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ + && wget -nv -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ && echo "${LLVM_PUBKEY_HASH} /tmp/llvm-snapshot.gpg.key" | sha384sum -c \ && apt-key add /tmp/llvm-snapshot.gpg.key \ && export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \ @@ -34,7 +34,7 @@ RUN curl -O https://clickhouse-builds.s3.yandex.net/utils/1/dpkg-deb \ ENV APACHE_PUBKEY_HASH="bba6987b63c63f710fd4ed476121c588bc3812e99659d27a855f8c4d312783ee66ad6adfce238765691b04d62fa3688f" RUN export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \ - && wget -O /tmp/arrow-keyring.deb "https://apache.bintray.com/arrow/ubuntu/apache-arrow-archive-keyring-latest-${CODENAME}.deb" \ + && wget -nv -O /tmp/arrow-keyring.deb "https://apache.bintray.com/arrow/ubuntu/apache-arrow-archive-keyring-latest-${CODENAME}.deb" \ && echo "${APACHE_PUBKEY_HASH} /tmp/arrow-keyring.deb" | sha384sum -c \ && dpkg -i /tmp/arrow-keyring.deb diff --git a/docker/test/base/Dockerfile b/docker/test/base/Dockerfile index c9b0700ecfc..8117d2907bc 100644 --- a/docker/test/base/Dockerfile +++ b/docker/test/base/Dockerfile @@ -7,7 +7,7 @@ RUN apt-get update \ && apt-get install ca-certificates lsb-release wget gnupg apt-transport-https \ --yes --no-install-recommends --verbose-versions \ && export LLVM_PUBKEY_HASH="bda960a8da687a275a2078d43c111d66b1c6a893a3275271beedf266c1ff4a0cdecb429c7a5cccf9f486ea7aa43fd27f" \ - && wget -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ + && wget -nv -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ && echo "${LLVM_PUBKEY_HASH} /tmp/llvm-snapshot.gpg.key" | sha384sum -c \ && apt-key add /tmp/llvm-snapshot.gpg.key \ && export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \ diff --git a/docker/test/codebrowser/Dockerfile b/docker/test/codebrowser/Dockerfile index f9d239ef8ef..cb3462cad0e 100644 --- a/docker/test/codebrowser/Dockerfile +++ b/docker/test/codebrowser/Dockerfile @@ -15,7 +15,7 @@ RUN apt-get --allow-unauthenticated update -y \ gpg-agent \ git -RUN wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | sudo apt-key add - +RUN wget -nv -O - https://apt.kitware.com/keys/kitware-archive-latest.asc | sudo apt-key add - RUN sudo apt-add-repository 'deb https://apt.kitware.com/ubuntu/ bionic main' RUN sudo echo "deb [trusted=yes] http://apt.llvm.org/bionic/ llvm-toolchain-bionic-8 main" >> /etc/apt/sources.list diff --git a/docker/test/fasttest/Dockerfile b/docker/test/fasttest/Dockerfile index 49845d72f1d..9b4bb574f8f 100644 --- a/docker/test/fasttest/Dockerfile +++ b/docker/test/fasttest/Dockerfile @@ -7,7 +7,7 @@ RUN apt-get update \ && apt-get install ca-certificates lsb-release wget gnupg apt-transport-https \ --yes --no-install-recommends --verbose-versions \ && export LLVM_PUBKEY_HASH="bda960a8da687a275a2078d43c111d66b1c6a893a3275271beedf266c1ff4a0cdecb429c7a5cccf9f486ea7aa43fd27f" \ - && wget -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ + && wget -nv -O /tmp/llvm-snapshot.gpg.key https://apt.llvm.org/llvm-snapshot.gpg.key \ && echo "${LLVM_PUBKEY_HASH} /tmp/llvm-snapshot.gpg.key" | sha384sum -c \ && apt-key add /tmp/llvm-snapshot.gpg.key \ && export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \ @@ -61,7 +61,6 @@ RUN apt-get update \ software-properties-common \ tzdata \ unixodbc \ - wget \ --yes --no-install-recommends # This symlink required by gcc to find lld compiler @@ -70,7 +69,7 @@ RUN ln -s /usr/bin/lld-${LLVM_VERSION} /usr/bin/ld.lld ARG odbc_driver_url="https://github.com/ClickHouse/clickhouse-odbc/releases/download/v1.1.4.20200302/clickhouse-odbc-1.1.4-Linux.tar.gz" RUN mkdir -p /tmp/clickhouse-odbc-tmp \ - && wget --quiet -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ + && wget -nv -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ && cp /tmp/clickhouse-odbc-tmp/lib64/*.so /usr/local/lib/ \ && odbcinst -i -d -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbcinst.ini.sample \ && odbcinst -i -s -l -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbc.ini.sample \ diff --git a/docker/test/fuzzer/run-fuzzer.sh b/docker/test/fuzzer/run-fuzzer.sh index 8cfe1a87408..a319033a232 100755 --- a/docker/test/fuzzer/run-fuzzer.sh +++ b/docker/test/fuzzer/run-fuzzer.sh @@ -32,10 +32,10 @@ function clone function download { -# wget -O- -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/performance/performance.tgz" \ +# wget -nv -O- -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/performance/performance.tgz" \ # | tar --strip-components=1 -zxv - wget -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-10_debug_none_bundled_unsplitted_disable_False_binary/clickhouse" + wget -nv -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-10_debug_none_bundled_unsplitted_disable_False_binary/clickhouse" chmod +x clickhouse ln -s ./clickhouse ./clickhouse-server ln -s ./clickhouse ./clickhouse-client diff --git a/docker/test/integration/runner/Dockerfile b/docker/test/integration/runner/Dockerfile index 95ab516cdaa..bfbe8da816f 100644 --- a/docker/test/integration/runner/Dockerfile +++ b/docker/test/integration/runner/Dockerfile @@ -46,7 +46,7 @@ RUN set -eux; \ \ # this "case" statement is generated via "update.sh" \ - if ! wget -O docker.tgz "https://download.docker.com/linux/static/${DOCKER_CHANNEL}/x86_64/docker-${DOCKER_VERSION}.tgz"; then \ + if ! wget -nv -O docker.tgz "https://download.docker.com/linux/static/${DOCKER_CHANNEL}/x86_64/docker-${DOCKER_VERSION}.tgz"; then \ echo >&2 "error: failed to download 'docker-${DOCKER_VERSION}' from '${DOCKER_CHANNEL}' for '${x86_64}'"; \ exit 1; \ fi; \ diff --git a/docker/test/pvs/Dockerfile b/docker/test/pvs/Dockerfile index ebd9c105705..0aedb67e572 100644 --- a/docker/test/pvs/Dockerfile +++ b/docker/test/pvs/Dockerfile @@ -12,8 +12,8 @@ RUN apt-get update --yes \ strace \ --yes --no-install-recommends -#RUN wget -q -O - http://files.viva64.com/etc/pubkey.txt | sudo apt-key add - -#RUN sudo wget -O /etc/apt/sources.list.d/viva64.list http://files.viva64.com/etc/viva64.list +#RUN wget -nv -O - http://files.viva64.com/etc/pubkey.txt | sudo apt-key add - +#RUN sudo wget -nv -O /etc/apt/sources.list.d/viva64.list http://files.viva64.com/etc/viva64.list # #RUN apt-get --allow-unauthenticated update -y \ # && env DEBIAN_FRONTEND=noninteractive \ @@ -24,10 +24,10 @@ ENV PKG_VERSION="pvs-studio-latest" RUN set -x \ && export PUBKEY_HASHSUM="486a0694c7f92e96190bbfac01c3b5ac2cb7823981db510a28f744c99eabbbf17a7bcee53ca42dc6d84d4323c2742761" \ - && wget https://files.viva64.com/etc/pubkey.txt -O /tmp/pubkey.txt \ + && wget -nv https://files.viva64.com/etc/pubkey.txt -O /tmp/pubkey.txt \ && echo "${PUBKEY_HASHSUM} /tmp/pubkey.txt" | sha384sum -c \ && apt-key add /tmp/pubkey.txt \ - && wget "https://files.viva64.com/${PKG_VERSION}.deb" \ + && wget -nv "https://files.viva64.com/${PKG_VERSION}.deb" \ && { debsig-verify ${PKG_VERSION}.deb \ || echo "WARNING: Some file was just downloaded from the internet without any validation and we are installing it into the system"; } \ && dpkg -i "${PKG_VERSION}.deb" diff --git a/docker/test/stateless/Dockerfile b/docker/test/stateless/Dockerfile index d3bc03a8f92..409a1b07bef 100644 --- a/docker/test/stateless/Dockerfile +++ b/docker/test/stateless/Dockerfile @@ -26,7 +26,7 @@ RUN apt-get update -y \ zookeeperd RUN mkdir -p /tmp/clickhouse-odbc-tmp \ - && wget --quiet -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ + && wget -nv -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ && cp /tmp/clickhouse-odbc-tmp/lib64/*.so /usr/local/lib/ \ && odbcinst -i -d -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbcinst.ini.sample \ && odbcinst -i -s -l -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbc.ini.sample \ diff --git a/docker/test/stateless_unbundled/Dockerfile b/docker/test/stateless_unbundled/Dockerfile index 7de29fede72..b05e46406da 100644 --- a/docker/test/stateless_unbundled/Dockerfile +++ b/docker/test/stateless_unbundled/Dockerfile @@ -71,7 +71,7 @@ RUN apt-get --allow-unauthenticated update -y \ zookeeperd RUN mkdir -p /tmp/clickhouse-odbc-tmp \ - && wget --quiet -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ + && wget -nv -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ && cp /tmp/clickhouse-odbc-tmp/lib64/*.so /usr/local/lib/ \ && odbcinst -i -d -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbcinst.ini.sample \ && odbcinst -i -s -l -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbc.ini.sample \ diff --git a/docker/test/stateless_with_coverage/Dockerfile b/docker/test/stateless_with_coverage/Dockerfile index f3539804852..77357d5142f 100644 --- a/docker/test/stateless_with_coverage/Dockerfile +++ b/docker/test/stateless_with_coverage/Dockerfile @@ -33,7 +33,7 @@ RUN apt-get update -y \ qemu-user-static RUN mkdir -p /tmp/clickhouse-odbc-tmp \ - && wget --quiet -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ + && wget -nv -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ && cp /tmp/clickhouse-odbc-tmp/lib64/*.so /usr/local/lib/ \ && odbcinst -i -d -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbcinst.ini.sample \ && odbcinst -i -s -l -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbc.ini.sample \ diff --git a/docker/test/testflows/runner/Dockerfile b/docker/test/testflows/runner/Dockerfile index 6b4ec12b80c..898552ade56 100644 --- a/docker/test/testflows/runner/Dockerfile +++ b/docker/test/testflows/runner/Dockerfile @@ -44,7 +44,7 @@ RUN set -eux; \ \ # this "case" statement is generated via "update.sh" \ - if ! wget -O docker.tgz "https://download.docker.com/linux/static/${DOCKER_CHANNEL}/x86_64/docker-${DOCKER_VERSION}.tgz"; then \ + if ! wget -nv -O docker.tgz "https://download.docker.com/linux/static/${DOCKER_CHANNEL}/x86_64/docker-${DOCKER_VERSION}.tgz"; then \ echo >&2 "error: failed to download 'docker-${DOCKER_VERSION}' from '${DOCKER_CHANNEL}' for '${x86_64}'"; \ exit 1; \ fi; \ diff --git a/docs/en/interfaces/http.md b/docs/en/interfaces/http.md index a5e7ef22558..35c79b5ee02 100644 --- a/docs/en/interfaces/http.md +++ b/docs/en/interfaces/http.md @@ -36,7 +36,7 @@ Examples: $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ echo -ne 'GET /?query=SELECT%201 HTTP/1.0\r\n\r\n' | nc localhost 8123 diff --git a/docs/es/interfaces/http.md b/docs/es/interfaces/http.md index abc5cf63188..ebce0ec7a51 100644 --- a/docs/es/interfaces/http.md +++ b/docs/es/interfaces/http.md @@ -38,7 +38,7 @@ Ejemplos: $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ echo -ne 'GET /?query=SELECT%201 HTTP/1.0\r\n\r\n' | nc localhost 8123 diff --git a/docs/fa/interfaces/http.md b/docs/fa/interfaces/http.md index 774980cf8fb..9ce40c17e6f 100644 --- a/docs/fa/interfaces/http.md +++ b/docs/fa/interfaces/http.md @@ -38,7 +38,7 @@ Ok. $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ echo -ne 'GET /?query=SELECT%201 HTTP/1.0\r\n\r\n' | nc localhost 8123 diff --git a/docs/fr/interfaces/http.md b/docs/fr/interfaces/http.md index 2de32747d4a..a414bba2c2f 100644 --- a/docs/fr/interfaces/http.md +++ b/docs/fr/interfaces/http.md @@ -38,7 +38,7 @@ Exemple: $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ echo -ne 'GET /?query=SELECT%201 HTTP/1.0\r\n\r\n' | nc localhost 8123 diff --git a/docs/ja/interfaces/http.md b/docs/ja/interfaces/http.md index c76b1ba0827..31f2b54af6d 100644 --- a/docs/ja/interfaces/http.md +++ b/docs/ja/interfaces/http.md @@ -38,7 +38,7 @@ GETメソッドを使用する場合, ‘readonly’ 設定されています。 $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ echo -ne 'GET /?query=SELECT%201 HTTP/1.0\r\n\r\n' | nc localhost 8123 diff --git a/docs/ru/interfaces/http.md b/docs/ru/interfaces/http.md index afd4d083365..b1cc4c79b25 100644 --- a/docs/ru/interfaces/http.md +++ b/docs/ru/interfaces/http.md @@ -31,7 +31,7 @@ Ok. $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ echo -ne 'GET /?query=SELECT%201 HTTP/1.0\r\n\r\n' | nc localhost 8123 diff --git a/docs/tr/interfaces/http.md b/docs/tr/interfaces/http.md index 2b92dd0ed9b..49d20ef6655 100644 --- a/docs/tr/interfaces/http.md +++ b/docs/tr/interfaces/http.md @@ -38,7 +38,7 @@ GET yöntemini kullanırken, ‘readonly’ ayar .lanmıştır. Başka bir deyi $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ echo -ne 'GET /?query=SELECT%201 HTTP/1.0\r\n\r\n' | nc localhost 8123 diff --git a/docs/zh/interfaces/http.md b/docs/zh/interfaces/http.md index 0fecb1873db..9feb8c5d69d 100644 --- a/docs/zh/interfaces/http.md +++ b/docs/zh/interfaces/http.md @@ -23,7 +23,7 @@ Ok. $ curl 'http://localhost:8123/?query=SELECT%201' 1 -$ wget -O- -q 'http://localhost:8123/?query=SELECT 1' +$ wget -nv -O- 'http://localhost:8123/?query=SELECT 1' 1 $ GET 'http://localhost:8123/?query=SELECT 1' diff --git a/src/Functions/URL/tldLookup.sh b/src/Functions/URL/tldLookup.sh index a61f2b09660..a7893c3a168 100755 --- a/src/Functions/URL/tldLookup.sh +++ b/src/Functions/URL/tldLookup.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash -[ ! -f public_suffix_list.dat ] && wget -O public_suffix_list.dat https://publicsuffix.org/list/public_suffix_list.dat +[ ! -f public_suffix_list.dat ] && wget -nv -O public_suffix_list.dat https://publicsuffix.org/list/public_suffix_list.dat echo '%language=C++ %define lookup-function-name is_valid diff --git a/utils/build/build_no_submodules.sh b/utils/build/build_no_submodules.sh index 4bcbe0b2a17..f9e2b6032a5 100755 --- a/utils/build/build_no_submodules.sh +++ b/utils/build/build_no_submodules.sh @@ -11,7 +11,7 @@ ROOT_DIR=${CUR_DIR}/../../build_no_submodules mkdir -p $ROOT_DIR cd $ROOT_DIR URL=`git remote get-url origin | sed 's/.git$//'` -wget -O ch.zip $URL/archive/${BRANCH}.zip +wget -nv -O ch.zip $URL/archive/${BRANCH}.zip unzip -ou ch.zip # TODO: make disableable lz4 zstd diff --git a/utils/ci/build-gcc-from-sources.sh b/utils/ci/build-gcc-from-sources.sh index 06d9820a022..8886bb7afd7 100755 --- a/utils/ci/build-gcc-from-sources.sh +++ b/utils/ci/build-gcc-from-sources.sh @@ -18,7 +18,7 @@ THREADS=$(grep -c ^processor /proc/cpuinfo) mkdir "${WORKSPACE}/gcc" pushd "${WORKSPACE}/gcc" -wget https://ftpmirror.gnu.org/gcc/${GCC_SOURCES_VERSION}/${GCC_SOURCES_VERSION}.tar.xz +wget -nv https://ftpmirror.gnu.org/gcc/${GCC_SOURCES_VERSION}/${GCC_SOURCES_VERSION}.tar.xz tar xf ${GCC_SOURCES_VERSION}.tar.xz pushd ${GCC_SOURCES_VERSION} ./contrib/download_prerequisites diff --git a/utils/ci/docker-multiarch/update.sh b/utils/ci/docker-multiarch/update.sh index 6abcf339607..1348631bdcf 100755 --- a/utils/ci/docker-multiarch/update.sh +++ b/utils/ci/docker-multiarch/update.sh @@ -29,7 +29,7 @@ baseUrl="https://partner-images.canonical.com/core/$VERSION" # install qemu-user-static if [ -n "${QEMU_ARCH}" ]; then if [ ! -f x86_64_qemu-${QEMU_ARCH}-static.tar.gz ]; then - wget -N https://github.com/multiarch/qemu-user-static/releases/download/${QEMU_VER}/x86_64_qemu-${QEMU_ARCH}-static.tar.gz + wget -nv -N https://github.com/multiarch/qemu-user-static/releases/download/${QEMU_VER}/x86_64_qemu-${QEMU_ARCH}-static.tar.gz fi tar -xvf x86_64_qemu-${QEMU_ARCH}-static.tar.gz -C $ROOTFS/usr/bin/ fi @@ -37,13 +37,13 @@ fi # get the image if \ - wget -q --spider "$baseUrl/current" \ - && wget -q --spider "$baseUrl/current/$thisTar" \ + wget -nv --spider "$baseUrl/current" \ + && wget -nv --spider "$baseUrl/current/$thisTar" \ ; then baseUrl+='/current' fi -wget -qN "$baseUrl/"{{MD5,SHA{1,256}}SUMS{,.gpg},"$thisTarBase.manifest",'unpacked/build-info.txt'} || true -wget -N "$baseUrl/$thisTar" +wget -nv -N "$baseUrl/"{{MD5,SHA{1,256}}SUMS{,.gpg},"$thisTarBase.manifest",'unpacked/build-info.txt'} || true +wget -nv -N "$baseUrl/$thisTar" # check checksum if [ -f SHA256SUMS ]; then diff --git a/utils/clickhouse-docker b/utils/clickhouse-docker index a3354aadacb..383a82e6d2c 100755 --- a/utils/clickhouse-docker +++ b/utils/clickhouse-docker @@ -24,7 +24,7 @@ param="$1" if [ "${param}" = "list" ] then # https://stackoverflow.com/a/39454426/1555175 - wget -q https://registry.hub.docker.com/v1/repositories/yandex/clickhouse-server/tags -O - | sed -e 's/[][]//g' -e 's/"//g' -e 's/ //g' | tr '}' '\n' | awk -F: '{print $3}' + wget -nv https://registry.hub.docker.com/v1/repositories/yandex/clickhouse-server/tags -O - | sed -e 's/[][]//g' -e 's/"//g' -e 's/ //g' | tr '}' '\n' | awk -F: '{print $3}' else docker pull yandex/clickhouse-server:${param} tmp_dir=$(mktemp -d -t ci-XXXXXXXXXX) # older version require /nonexistent folder to exist to run clickhouse client :D From a0b4cc78d6451a319eb191bdd2cf19ad104430c7 Mon Sep 17 00:00:00 2001 From: alesapin Date: Tue, 1 Sep 2020 10:26:31 +0300 Subject: [PATCH 39/73] Throw exception on alter for storages created from table functions --- src/Databases/DatabaseOrdinary.cpp | 8 +++++ .../01461_alter_table_function.reference | 7 ++++ .../01461_alter_table_function.sql | 33 +++++++++++++++++++ 3 files changed, 48 insertions(+) create mode 100644 tests/queries/0_stateless/01461_alter_table_function.reference create mode 100644 tests/queries/0_stateless/01461_alter_table_function.sql diff --git a/src/Databases/DatabaseOrdinary.cpp b/src/Databases/DatabaseOrdinary.cpp index cb9f817cc3c..0512a155418 100644 --- a/src/Databases/DatabaseOrdinary.cpp +++ b/src/Databases/DatabaseOrdinary.cpp @@ -33,6 +33,11 @@ static constexpr size_t PRINT_MESSAGE_EACH_N_OBJECTS = 256; static constexpr size_t PRINT_MESSAGE_EACH_N_SECONDS = 5; static constexpr size_t METADATA_FILE_BUFFER_SIZE = 32768; +namespace ErrorCodes +{ + extern const int NOT_IMPLEMENTED; +} + namespace { void tryAttachTable( @@ -249,6 +254,9 @@ void DatabaseOrdinary::alterTable(const Context & context, const StorageID & tab auto & ast_create_query = ast->as(); + if (ast_create_query.as_table_function) + throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Cannot alter table {} because it was created AS table function", backQuote(table_name)); + ASTPtr new_columns = InterpreterCreateQuery::formatColumns(metadata.columns); ASTPtr new_indices = InterpreterCreateQuery::formatIndices(metadata.secondary_indices); ASTPtr new_constraints = InterpreterCreateQuery::formatConstraints(metadata.constraints); diff --git a/tests/queries/0_stateless/01461_alter_table_function.reference b/tests/queries/0_stateless/01461_alter_table_function.reference new file mode 100644 index 00000000000..395155967a9 --- /dev/null +++ b/tests/queries/0_stateless/01461_alter_table_function.reference @@ -0,0 +1,7 @@ +CREATE TABLE default.table_from_remote AS remote(\'localhost\', \'system\', \'numbers\') +CREATE TABLE default.table_from_remote AS remote(\'localhost\', \'system\', \'numbers\') +CREATE TABLE default.table_from_numbers AS numbers(1000) +CREATE TABLE default.table_from_numbers AS numbers(1000) +CREATE TABLE default.table_from_select\n(\n `number` UInt64\n)\nENGINE = MergeTree()\nORDER BY tuple()\nSETTINGS index_granularity = 8192 +CREATE TABLE default.table_from_select\n(\n `number` UInt64,\n `col` UInt8\n)\nENGINE = MergeTree()\nORDER BY tuple()\nSETTINGS index_granularity = 8192 +1 diff --git a/tests/queries/0_stateless/01461_alter_table_function.sql b/tests/queries/0_stateless/01461_alter_table_function.sql new file mode 100644 index 00000000000..e242d1f0b7b --- /dev/null +++ b/tests/queries/0_stateless/01461_alter_table_function.sql @@ -0,0 +1,33 @@ +DROP TABLE IF EXISTS table_from_remote; +DROP TABLE IF EXISTS table_from_select; +DROP TABLE IF EXISTS table_from_numbers; + +CREATE TABLE table_from_remote AS remote('localhost', 'system', 'numbers'); + +SHOW CREATE TABLE table_from_remote; + +ALTER TABLE table_from_remote ADD COLUMN col UInt8; --{serverError 48} + +SHOW CREATE TABLE table_from_remote; + +CREATE TABLE table_from_numbers AS numbers(1000); + +SHOW CREATE TABLE table_from_numbers; + +ALTER TABLE table_from_numbers ADD COLUMN col UInt8; --{serverError 48} + +SHOW CREATE TABLE table_from_numbers; + +CREATE TABLE table_from_select ENGINE = MergeTree() ORDER BY tuple() AS SELECT number from system.numbers LIMIT 1; + +SHOW CREATE TABLE table_from_select; + +ALTER TABLE table_from_select ADD COLUMN col UInt8; + +SHOW CREATE TABLE table_from_select; + +SELECT 1; + +DROP TABLE IF EXISTS table_from_remote; +DROP TABLE IF EXISTS table_from_select; +DROP TABLE IF EXISTS table_from_numbers; From 453fb837d8416d7886358fb23488608f72d40c3c Mon Sep 17 00:00:00 2001 From: BohuTANG Date: Tue, 1 Sep 2020 16:25:15 +0800 Subject: [PATCH 40/73] ISSUES-14235 change string.rfind to stringstarts_with --- src/Core/MySQL/MySQLReplication.cpp | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/src/Core/MySQL/MySQLReplication.cpp b/src/Core/MySQL/MySQLReplication.cpp index 41afe3cde6a..f26436440b8 100644 --- a/src/Core/MySQL/MySQLReplication.cpp +++ b/src/Core/MySQL/MySQLReplication.cpp @@ -103,17 +103,17 @@ namespace MySQLReplication = header.event_size - EVENT_HEADER_LENGTH - 4 - 4 - 1 - 2 - 2 - status_len - schema_len - 1 - CHECKSUM_CRC32_SIGNATURE_LENGTH; query.resize(len); payload.readStrict(reinterpret_cast(query.data()), len); - if (query.rfind("BEGIN", 0) == 0 || query.rfind("COMMIT") == 0) + if (query.starts_with("BEGIN") || query.starts_with("COMMIT")) { typ = QUERY_EVENT_MULTI_TXN_FLAG; } - else if (query.rfind("XA", 0) == 0) + else if (query.starts_with("XA")) { - if (query.rfind("XA ROLLBACK", 0) == 0) + if (query.starts_with("XA ROLLBACK")) throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::UNKNOWN_EXCEPTION); typ = QUERY_EVENT_XA; } - else if (query.rfind("SAVEPOINT", 0) == 0) + else if (query.starts_with("SAVEPOINT")) { throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::UNKNOWN_EXCEPTION); } From d604e84df3214d4c9cf5f329f19c792af685f42b Mon Sep 17 00:00:00 2001 From: BohuTANG Date: Tue, 1 Sep 2020 16:37:58 +0800 Subject: [PATCH 41/73] ISSUES-14235 add mysql_5_7 and mysql_8_0 empty transaction tests --- .../materialize_with_ddl.py | 36 ++++++++++++++++++ .../test_materialize_mysql_database/test.py | 37 ++----------------- 2 files changed, 40 insertions(+), 33 deletions(-) diff --git a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py index 18695f40e53..0dff05df3a1 100644 --- a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py +++ b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py @@ -1,4 +1,5 @@ import time +import pymysql.cursors def check_query(clickhouse_node, query, result_set, retry_count=3, interval_seconds=3): @@ -321,3 +322,38 @@ def alter_rename_table_with_materialize_mysql_database(clickhouse_node, mysql_no clickhouse_node.query("DROP DATABASE test_database") mysql_node.query("DROP DATABASE test_database") + + +def query_event_with_empty_transaction(clickhouse_node, mysql_node, service_name): + mysql_node.query("CREATE DATABASE test_database") + + mysql_node.query("RESET MASTER") + mysql_node.query("CREATE TABLE test_database.t1(a INT NOT NULL PRIMARY KEY, b VARCHAR(255) DEFAULT 'BEGIN')") + mysql_node.query("INSERT INTO test_database.t1(a) VALUES(1)") + + clickhouse_node.query( + "CREATE DATABASE test_database ENGINE = MaterializeMySQL('{}:3306', 'test_database', 'root', 'clickhouse')".format( + service_name)) + + # Reject one empty GTID QUERY event with 'BEGIN' and 'COMMIT' + mysql_cursor = mysql_node.cursor(pymysql.cursors.DictCursor) + mysql_cursor.execute("SHOW MASTER STATUS") + (uuid, seqs) = mysql_cursor.fetchall()[0]["Executed_Gtid_Set"].split(":") + (seq_begin, seq_end) = seqs.split("-") + assert int(seq_begin) == 1 + assert int(seq_end) == 3 + next_gtid = uuid + ":" + str(int(seq_end) + 1) + mysql_node.query("SET gtid_next='" + next_gtid + "'") + mysql_node.query("BEGIN") + mysql_node.query("COMMIT") + mysql_node.query("SET gtid_next='AUTOMATIC'") + + # Reject one 'BEGIN' QUERY event and 'COMMIT' XID event. + mysql_node.query("/* start */ begin /* end */") + mysql_node.query("INSERT INTO test_database.t1(a) VALUES(2)") + mysql_node.query("/* start */ commit /* end */") + + check_query(clickhouse_node, "SELECT * FROM test_database.t1 ORDER BY a FORMAT TSV", + "1\tBEGIN\n2\tBEGIN\n") + clickhouse_node.query("DROP DATABASE test_database") + mysql_node.query("DROP DATABASE test_database") diff --git a/tests/integration/test_materialize_mysql_database/test.py b/tests/integration/test_materialize_mysql_database/test.py index c86b9850f44..d45a5e3ceaf 100644 --- a/tests/integration/test_materialize_mysql_database/test.py +++ b/tests/integration/test_materialize_mysql_database/test.py @@ -120,37 +120,8 @@ def test_materialize_database_ddl_with_mysql_8_0(started_cluster, started_mysql_ materialize_with_ddl.alter_rename_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") materialize_with_ddl.alter_modify_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") -def test_materialize_database_ddl_with_empty_transaction(started_cluster, started_mysql_5_7): - mysql_node = started_mysql_5_7.alloc_connection() - mysql_node.query("CREATE DATABASE test_database") +def test_materialize_database_ddl_with_empty_transaction_5_7(started_cluster, started_mysql_5_7): + materialize_with_ddl.query_event_with_empty_transaction(clickhouse_node, started_mysql_5_7.alloc_connection(), "mysql5_7") - - mysql_node.query("RESET MASTER") - mysql_node.query("CREATE TABLE test_database.t1(a INT NOT NULL PRIMARY KEY, b VARCHAR(255) DEFAULT 'BEGIN')") - mysql_node.query("INSERT INTO test_database.t1(a) VALUES(1)") - - clickhouse_node.query( - "CREATE DATABASE test_database ENGINE = MaterializeMySQL('{}:3306', 'test_database', 'root', 'clickhouse')".format( - "mysql5_7")) - - # Reject one empty GTID QUERY event with 'BEGIN' and 'COMMIT' - mysql_cursor = mysql_node.cursor(pymysql.cursors.DictCursor) - mysql_cursor.execute("SHOW MASTER STATUS") - (uuid, seqs) = mysql_cursor.fetchall()[0]["Executed_Gtid_Set"].split(":") - (seq_begin, seq_end) = seqs.split("-") - assert int(seq_begin) == 1 - assert int(seq_end) == 3 - next_gtid = uuid + ":" + str(int(seq_end) + 1) - mysql_node.query("SET gtid_next='" + next_gtid + "'") - mysql_node.query("BEGIN") - mysql_node.query("COMMIT") - mysql_node.query("SET gtid_next='AUTOMATIC'") - - # Reject one 'BEGIN' QUERY event and 'COMMIT' XID event. - mysql_node.query("/* start */ begin /* end */") - mysql_node.query("INSERT INTO test_database.t1(a) VALUES(2)") - mysql_node.query("/* start */ commit /* end */") - - materialize_with_ddl.check_query(clickhouse_node, "SELECT * FROM test_database.t1 ORDER BY a FORMAT TSV", "1\tBEGIN\n2\tBEGIN\n") - clickhouse_node.query("DROP DATABASE test_database") - mysql_node.query("DROP DATABASE test_database") +def test_materialize_database_ddl_with_empty_transaction_8_0(started_cluster, started_mysql_8_0): + materialize_with_ddl.query_event_with_empty_transaction(clickhouse_node, started_mysql_8_0.alloc_connection(), "mysql8_0") From 8fac595428606115066647bc2f3b8a394931e16b Mon Sep 17 00:00:00 2001 From: Nikolai Kochetov Date: Tue, 1 Sep 2020 13:29:10 +0300 Subject: [PATCH 42/73] Stop query execution if exception happened in PipelineExecutor itself. --- src/Processors/Executors/PipelineExecutor.cpp | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/src/Processors/Executors/PipelineExecutor.cpp b/src/Processors/Executors/PipelineExecutor.cpp index cacd8fced8d..d445177f28e 100644 --- a/src/Processors/Executors/PipelineExecutor.cpp +++ b/src/Processors/Executors/PipelineExecutor.cpp @@ -469,7 +469,16 @@ void PipelineExecutor::wakeUpExecutor(size_t thread_num) void PipelineExecutor::executeSingleThread(size_t thread_num, size_t num_threads) { - executeStepImpl(thread_num, num_threads); + try + { + executeStepImpl(thread_num, num_threads); + } + catch (...) + { + /// In case of exception from executor itself, stop other threads. + finish(); + throw; + } #ifndef NDEBUG auto & context = executor_contexts[thread_num]; From 4e58f003053ba82053e61e620e6758014aa826d8 Mon Sep 17 00:00:00 2001 From: Alexander Kuzmenkov <36882414+akuzm@users.noreply.github.com> Date: Tue, 1 Sep 2020 16:57:13 +0300 Subject: [PATCH 43/73] Update docker/test/fuzzer/run-fuzzer.sh --- docker/test/fuzzer/run-fuzzer.sh | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/docker/test/fuzzer/run-fuzzer.sh b/docker/test/fuzzer/run-fuzzer.sh index a319033a232..0ac4859a1e2 100755 --- a/docker/test/fuzzer/run-fuzzer.sh +++ b/docker/test/fuzzer/run-fuzzer.sh @@ -35,7 +35,7 @@ function download # wget -nv -O- -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/performance/performance.tgz" \ # | tar --strip-components=1 -zxv - wget -nv -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-10_debug_none_bundled_unsplitted_disable_False_binary/clickhouse" + wget -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-10_debug_none_bundled_unsplitted_disable_False_binary/clickhouse" chmod +x clickhouse ln -s ./clickhouse ./clickhouse-server ln -s ./clickhouse ./clickhouse-client @@ -176,4 +176,3 @@ case "$stage" in exit $task_exit_code ;& esac - From 4620ac4c0d4d839aaf0554f6db94ea0ac24c214e Mon Sep 17 00:00:00 2001 From: Alexander Kuzmenkov <36882414+akuzm@users.noreply.github.com> Date: Tue, 1 Sep 2020 16:57:20 +0300 Subject: [PATCH 44/73] Update docker/test/fuzzer/run-fuzzer.sh --- docker/test/fuzzer/run-fuzzer.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docker/test/fuzzer/run-fuzzer.sh b/docker/test/fuzzer/run-fuzzer.sh index 0ac4859a1e2..66d3e840c4f 100755 --- a/docker/test/fuzzer/run-fuzzer.sh +++ b/docker/test/fuzzer/run-fuzzer.sh @@ -32,7 +32,7 @@ function clone function download { -# wget -nv -O- -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/performance/performance.tgz" \ +# wget -O- -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/performance/performance.tgz" \ # | tar --strip-components=1 -zxv wget -nv -nd -c "https://clickhouse-builds.s3.yandex.net/$PR_TO_TEST/$SHA_TO_TEST/clickhouse_build_check/clang-10_debug_none_bundled_unsplitted_disable_False_binary/clickhouse" From 34a2beab7c54cd5d726aa78f4efbbc8825f2ee20 Mon Sep 17 00:00:00 2001 From: Evgeniia Sudarikova Date: Tue, 1 Sep 2020 18:03:43 +0300 Subject: [PATCH 45/73] Edited EN description --- docs/en/engines/table-engines/integrations/rabbitmq.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/en/engines/table-engines/integrations/rabbitmq.md b/docs/en/engines/table-engines/integrations/rabbitmq.md index 7d09c6f72a5..7fe99ca3678 100644 --- a/docs/en/engines/table-engines/integrations/rabbitmq.md +++ b/docs/en/engines/table-engines/integrations/rabbitmq.md @@ -7,7 +7,7 @@ toc_title: RabbitMQ This engine allows integrating ClickHouse with [RabbitMQ](https://www.rabbitmq.com). -RabbitMQ lets you: +`RabbitMQ` lets you: - Publish or subscribe to data flows. - Process streams as they become available. @@ -44,7 +44,7 @@ Optional parameters: - `rabbitmq_routing_key_list` – A comma-separated list of routing keys. - `rabbitmq_row_delimiter` – Delimiter character, which ends the message. - `rabbitmq_num_consumers` – The number of consumers per table. Default: `1`. Specify more consumers if the throughput of one consumer is insufficient. -- `rabbitmq_num_queues` – The number of queues per consumer. Default: `1`. Specify more queues if the capacity of one queue per consumer is insufficient. Single queue can contain up to 50K messages at the same time. +- `rabbitmq_num_queues` – The number of queues per consumer. Default: `1`. Specify more queues if the capacity of one queue per consumer is insufficient. A single queue can contain up to 50K messages at the same time. - `rabbitmq_transactional_channel` – Wrap insert queries in transactions. Default: `0`. Required configuration: @@ -86,13 +86,13 @@ There can be no more than one exchange per table. One exchange can be shared bet Exchange type options: -- `direct` - Routing is based on exact matching of keys. Example table key list: `key1,key2,key3,key4,key5`, message key can eqaul any of them. +- `direct` - Routing is based on the exact matching of keys. Example table key list: `key1,key2,key3,key4,key5`, message key can equal any of them. - `fanout` - Routing to all tables (where exchange name is the same) regardless of the keys. - `topic` - Routing is based on patterns with dot-separated keys. Examples: `*.logs`, `records.*.*.2020`, `*.2018,*.2019,*.2020`. - `headers` - Routing is based on `key=value` matches with a setting `x-match=all` or `x-match=any`. Example table key list: `x-match=all,format=logs,type=report,year=2020`. -- `consistent-hash` - Data is evenly distributed between all bound tables (where exchange name is the same). Note that this exchange type must be enabled with RabbitMQ plugin: `rabbitmq-plugins enable rabbitmq_consistent_hash_exchange`. +- `consistent-hash` - Data is evenly distributed between all bound tables (where the exchange name is the same). Note that this exchange type must be enabled with RabbitMQ plugin: `rabbitmq-plugins enable rabbitmq_consistent_hash_exchange`. -If exchange type is not specified, then default is `fanout` and routing keys for data publishing must be randomized in range `[1, num_consumers]` for every message/batch (or in range `[1, num_consumers * num_queues]` if `rabbitmq_num_queues` is set). This table configuration works quicker then any other, especially when `rabbitmq_num_consumers` and/or `rabbitmq_num_queues` parameters are set. +If exchange type is not specified, then default is `fanout` and routing keys for data publishing must be randomized in range `[1, num_consumers]` for every message/batch (or in range `[1, num_consumers * num_queues]` if `rabbitmq_num_queues` is set). This table configuration works quicker than any other, especially when `rabbitmq_num_consumers` and/or `rabbitmq_num_queues` parameters are set. If `rabbitmq_num_consumers` and/or `rabbitmq_num_queues` parameters are specified along with `rabbitmq_exchange_type`, then: From 0b70abe54235b53cd1c909f56562cf32791eb344 Mon Sep 17 00:00:00 2001 From: Alexander Kuzmenkov Date: Tue, 1 Sep 2020 18:51:46 +0300 Subject: [PATCH 46/73] Don't let the fuzzer change max_execution_time --- docker/test/fuzzer/query-fuzzer-tweaks-users.xml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/docker/test/fuzzer/query-fuzzer-tweaks-users.xml b/docker/test/fuzzer/query-fuzzer-tweaks-users.xml index 8d430aa5c54..356d3212932 100644 --- a/docker/test/fuzzer/query-fuzzer-tweaks-users.xml +++ b/docker/test/fuzzer/query-fuzzer-tweaks-users.xml @@ -2,6 +2,15 @@ 10 + + + + 10 + + From 120962b61a98ef1cafc043c51304070e727cde28 Mon Sep 17 00:00:00 2001 From: bharatnc Date: Tue, 1 Sep 2020 05:09:48 -0700 Subject: [PATCH 47/73] fix tests --- .../0_stateless/01463_test_alter_live_view_refresh.reference | 1 + tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql | 1 + 2 files changed, 2 insertions(+) create mode 100644 tests/queries/0_stateless/01463_test_alter_live_view_refresh.reference diff --git a/tests/queries/0_stateless/01463_test_alter_live_view_refresh.reference b/tests/queries/0_stateless/01463_test_alter_live_view_refresh.reference new file mode 100644 index 00000000000..4d98c7b6838 --- /dev/null +++ b/tests/queries/0_stateless/01463_test_alter_live_view_refresh.reference @@ -0,0 +1 @@ +ALTER LIVE VIEW live1 REFRESH diff --git a/tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql b/tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql index 36e8c9a9785..ab316a377fd 100644 --- a/tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql +++ b/tests/queries/0_stateless/01463_test_alter_live_view_refresh.sql @@ -6,4 +6,5 @@ SET allow_experimental_live_view=1; CREATE LIVE VIEW live1 AS SELECT * FROM test0; +select 'ALTER LIVE VIEW live1 REFRESH'; ALTER LIVE VIEW live1 REFRESH; -- success From d646ca1d0cd3f0f22226cd40e291625061f70d8e Mon Sep 17 00:00:00 2001 From: Dao Minh Thuc Date: Tue, 1 Sep 2020 23:07:26 +0700 Subject: [PATCH 48/73] Disable -fchar8_t for capnproto only --- contrib/capnproto-cmake/CMakeLists.txt | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/contrib/capnproto-cmake/CMakeLists.txt b/contrib/capnproto-cmake/CMakeLists.txt index e5d62c59327..b655ad3e5d9 100644 --- a/contrib/capnproto-cmake/CMakeLists.txt +++ b/contrib/capnproto-cmake/CMakeLists.txt @@ -29,10 +29,6 @@ set (KJ_SRCS ${CAPNPROTO_SOURCE_DIR}/kj/parse/char.c++ ) -if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang") - set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-char8_t") -endif () - add_library(kj ${KJ_SRCS}) target_include_directories(kj SYSTEM PUBLIC ${CAPNPROTO_SOURCE_DIR}) @@ -82,8 +78,9 @@ if (COMPILER_GCC) -Wno-deprecated-declarations -Wno-class-memaccess) elseif (COMPILER_CLANG) set (SUPPRESS_WARNINGS -Wno-non-virtual-dtor -Wno-sign-compare -Wno-strict-aliasing -Wno-deprecated-declarations) + set (CAPNP_PRIVATE_CXX_FLAGS -fno-char8_t) endif () -target_compile_options(kj PRIVATE ${SUPPRESS_WARNINGS}) -target_compile_options(capnp PRIVATE ${SUPPRESS_WARNINGS}) -target_compile_options(capnpc PRIVATE ${SUPPRESS_WARNINGS}) +target_compile_options(kj PRIVATE ${SUPPRESS_WARNINGS} ${CAPNP_PRIVATE_CXX_FLAGS}) +target_compile_options(capnp PRIVATE ${SUPPRESS_WARNINGS} ${CAPNP_PRIVATE_CXX_FLAGS}) +target_compile_options(capnpc PRIVATE ${SUPPRESS_WARNINGS} ${CAPNP_PRIVATE_CXX_FLAGS}) From b67fde2b0415194978ab989e53c1443676e6a4e5 Mon Sep 17 00:00:00 2001 From: romanzhukov Date: Tue, 1 Sep 2020 19:20:42 +0300 Subject: [PATCH 49/73] DOCSUP-2031: Update by PR#1130 Added description of the partial_merge_join_optimizations and partial_merge_join_rows_in_right_blocks settings. --- docs/ru/operations/settings/settings.md | 29 +++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/docs/ru/operations/settings/settings.md b/docs/ru/operations/settings/settings.md index ab64fb757f1..a6c868876ed 100644 --- a/docs/ru/operations/settings/settings.md +++ b/docs/ru/operations/settings/settings.md @@ -406,6 +406,35 @@ INSERT INTO test VALUES (lower('Hello')), (lower('world')), (lower('INSERT')), ( - 0 — пустые ячейки заполняются значением по умолчанию соответствующего типа поля. - 1 — `JOIN` ведёт себя как в стандартном SQL. Тип соответствующего поля преобразуется в [Nullable](../../sql-reference/data-types/nullable.md#data_type-nullable), а пустые ячейки заполняются значениями [NULL](../../sql-reference/syntax.md). +## partial_merge_join_optimizations {#partial_merge_join_optimizations} + +Отключает все оптимизации для запросов [JOIN](../../sql-reference/statements/select/join.md) с частичным MergeJoin алгоритмом. + +По умолчанию оптимизации включены, что может привести к неправильным результатам. Если вы видите подозрительные результаты в своих запросах, отключите оптимизацию с помощью этого параметра. В различных версиях сервера ClickHouse, оптимизация может отличаться. + +Возможные значения: + +- 0 — Оптимизация отключена. +- 1 — Оптимизация включена. + +Значение по умолчанию: 1. + +## partial_merge_join_rows_in_right_blocks {#partial_merge_join_rows_in_right_blocks} + +Устанавливает предельные размеры блоков данных «правого» соединения, для запросов [JOIN](../../sql-reference/statements/select/join.md) с частичным MergeJoin алгоритмом. + +Сервер ClickHouse: + +1. Разделяет данные правого соединения на блоки с заданным числом строк. +2. Индексирует для каждого блока минимальное и максимальное значение. +3. Выгружает подготовленные блоки на диск, если это возможно. + +Возможные значения: + +- Положительное целое число. Рекомендуемый диапазон значений [1000, 100000]. + +Значение по умолчанию: 65536. + ## join_on_disk_max_files_to_merge {#join_on_disk_max_files_to_merge} Устанавливет количество файлов, разрешенных для параллельной сортировки, при выполнении операций MergeJoin на диске. From 9591ae59cc538100c9aa4440738abf47183cab15 Mon Sep 17 00:00:00 2001 From: romanzhukov Date: Tue, 1 Sep 2020 20:46:40 +0300 Subject: [PATCH 50/73] DOCSUP-2031: Update by PR#11065 Disable ANY RIGHT and ANY FULL JOINs by default --- docs/ru/operations/settings/settings.md | 28 +++++++++++++++++++ .../sql-reference/statements/select/join.md | 4 ++- 2 files changed, 31 insertions(+), 1 deletion(-) diff --git a/docs/ru/operations/settings/settings.md b/docs/ru/operations/settings/settings.md index a6c868876ed..6f5f7ccf965 100644 --- a/docs/ru/operations/settings/settings.md +++ b/docs/ru/operations/settings/settings.md @@ -458,6 +458,34 @@ INSERT INTO test VALUES (lower('Hello')), (lower('world')), (lower('INSERT')), ( Значение по умолчанию: LZ4. +## any_join_distinct_right_table_keys {#any_join_distinct_right_table_keys} + +Включает устаревшее поведение сервера ClickHouse при выполнении операций `ANY INNER|LEFT JOIN`. + +!!! note "Внимание" + Используйте этот параметр только в целях обратной совместимости, если ваши варианты использования требуют устаревшего поведения `JOIN`. + +Когда включено устаревшее поведение: + +- Результаты операций "t1 ANY LEFT JOIN t2" и "t2 ANY RIGHT JOIN t1" не равны, поскольку ClickHouse использует логику с сопоставлением ключей таблицы "многие к одному слева направо". +- Результаты операций `ANY INNER JOIN` содержат все строки из левой таблицы, аналогично операции `SEMI LEFT JOIN`. + +Когда устаревшее поведение отключено: + +- Результаты операций `t1 ANY LEFT JOIN t2` и `t2 ANY RIGHT JOIN t1` равно, потому что ClickHouse использует логику сопоставления ключей один-ко-многим в операциях `ANY RIGHT JOIN`. +- Результаты операций `ANY INNER JOIN` содержат по одной строке на ключ из левой и правой таблиц. + +Возможные значения: + +- 0 — Устаревшее поведение отключено. +- 1 — Устаревшее поведение включено. + +Значение по умолчанию: 0. + +См. также: + +- [JOIN strictness](../../sql-reference/statements/select/join.md#select-join-strictness) + ## max\_block\_size {#setting-max_block_size} Данные в ClickHouse обрабатываются по блокам (наборам кусочков столбцов). Внутренние циклы обработки для одного блока достаточно эффективны, но есть заметные издержки на каждый блок. Настройка `max_block_size` — это рекомендация, какой размер блока (в количестве строк) загружать из таблиц. Размер блока не должен быть слишком маленьким, чтобы затраты на каждый блок были заметны, но не слишком велики, чтобы запрос с LIMIT, который завершается после первого блока, обрабатывался быстро. Цель состоит в том, чтобы не использовалось слишком много оперативки при вынимании большого количества столбцов в несколько потоков; чтобы оставалась хоть какая-нибудь кэш-локальность. diff --git a/docs/ru/sql-reference/statements/select/join.md b/docs/ru/sql-reference/statements/select/join.md index 2a5bcff0cbb..800f07a7c66 100644 --- a/docs/ru/sql-reference/statements/select/join.md +++ b/docs/ru/sql-reference/statements/select/join.md @@ -36,7 +36,9 @@ FROM !!! note "Примечание" Значение строгости по умолчанию может быть переопределено с помощью настройки [join\_default\_strictness](../../../operations/settings/settings.md#settings-join_default_strictness). - + +Поведение сервера ClickHouse для операций `ANY JOIN` зависит от параметра [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys). + ### Использование ASOF JOIN {#asof-join-usage} `ASOF JOIN` применим в том случае, когда необходимо объединять записи, которые не имеют точного совпадения. From f93edc5defd1141b2292614eab105b6b4371d9a2 Mon Sep 17 00:00:00 2001 From: Evgeniia Sudarikova Date: Tue, 1 Sep 2020 21:59:27 +0300 Subject: [PATCH 51/73] Edit more text in EN version --- docs/en/engines/table-engines/integrations/rabbitmq.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/en/engines/table-engines/integrations/rabbitmq.md b/docs/en/engines/table-engines/integrations/rabbitmq.md index 7fe99ca3678..1bf1c1d3754 100644 --- a/docs/en/engines/table-engines/integrations/rabbitmq.md +++ b/docs/en/engines/table-engines/integrations/rabbitmq.md @@ -45,7 +45,7 @@ Optional parameters: - `rabbitmq_row_delimiter` – Delimiter character, which ends the message. - `rabbitmq_num_consumers` – The number of consumers per table. Default: `1`. Specify more consumers if the throughput of one consumer is insufficient. - `rabbitmq_num_queues` – The number of queues per consumer. Default: `1`. Specify more queues if the capacity of one queue per consumer is insufficient. A single queue can contain up to 50K messages at the same time. -- `rabbitmq_transactional_channel` – Wrap insert queries in transactions. Default: `0`. +- `rabbitmq_transactional_channel` – Wrap `INSERT` queries in transactions. Default: `0`. Required configuration: @@ -72,7 +72,7 @@ Example: ## Description {#description} -`SELECT` is not particularly useful for reading messages (except for debugging), because each message can be read only once. It is more practical to create real-time threads using materialized views. To do this: +`SELECT` is not particularly useful for reading messages (except for debugging), because each message can be read only once. It is more practical to create real-time threads using [materialized views](../../../sql-reference/statements/create/view.md). To do this: 1. Use the engine to create a RabbitMQ consumer and consider it a data stream. 2. Create a table with the desired structure. From 1259ded322fd27ae43c59423fb88a7639edd77b9 Mon Sep 17 00:00:00 2001 From: Evgeniia Sudarikova Date: Tue, 1 Sep 2020 22:02:11 +0300 Subject: [PATCH 52/73] Add RU version --- .../table-engines/integrations/rabbitmq.md | 122 ++++++++++++++++++ 1 file changed, 122 insertions(+) create mode 100644 docs/ru/engines/table-engines/integrations/rabbitmq.md diff --git a/docs/ru/engines/table-engines/integrations/rabbitmq.md b/docs/ru/engines/table-engines/integrations/rabbitmq.md new file mode 100644 index 00000000000..b6b239f0eee --- /dev/null +++ b/docs/ru/engines/table-engines/integrations/rabbitmq.md @@ -0,0 +1,122 @@ +--- +toc_priority: 6 +toc_title: RabbitMQ +--- + +# RabbitMQ {#rabbitmq-engine} + +Движок работает с [RabbitMQ](https://www.rabbitmq.com). + +`RabbitMQ` позволяет: + +- Публиковать/подписываться на потоки данных. +- Обрабатывать потоки по мере их появления. + +## Создание таблицы {#table_engine-rabbitmq-creating-a-table} + +``` sql +CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] +( + name1 [type1] [DEFAULT|MATERIALIZED|ALIAS expr1], + name2 [type2] [DEFAULT|MATERIALIZED|ALIAS expr2], + ... +) ENGINE = RabbitMQ SETTINGS + rabbitmq_host_port = 'host:port', + rabbitmq_exchange_name = 'exchange_name', + rabbitmq_format = 'data_format'[,] + [rabbitmq_exchange_type = 'exchange_type',] + [rabbitmq_routing_key_list = 'key1,key2,...',] + [rabbitmq_row_delimiter = 'delimiter_symbol',] + [rabbitmq_num_consumers = N,] + [rabbitmq_num_queues = N,] + [rabbitmq_transactional_channel = 0] +``` + +Обязательные параметры: + +- `rabbitmq_host_port` – адрес сервера (`хост:порт`). Например: `localhost:5672`. +- `rabbitmq_exchange_name` – имя точки обмена в RabbitMQ. +- `rabbitmq_format` – формат сообщения. Используется такое же обозначение, как и в функции `FORMAT` в SQL, например, `JSONEachRow`. Подробнее см. в разделе [Форматы входных и выходных данных](../../../interfaces/formats.md). + +Дополнительные параметры: + +- `rabbitmq_exchange_type` – тип точки обмена в RabbitMQ: `direct`, `fanout`, `topic`, `headers`, `consistent-hash`. По умолчанию: `fanout`. +- `rabbitmq_routing_key_list` – список ключей маршрутизации, через запятую. +- `rabbitmq_row_delimiter` – символ-разделитель, который завершает сообщение. +- `rabbitmq_num_consumers` – количество потребителей на таблицу. По умолчанию: `1`. Укажите больше потребителей, если пропускная способность одного потребителя недостаточна. +- `rabbitmq_num_queues` – количество очередей на потребителя. По умолчанию: `1`. Укажите больше потребителей, если пропускная способность одной очереди на потребителя недостаточна. Одна очередь поддерживает до 50 тысяч сообщений одновременно. +- `rabbitmq_transactional_channel` – обернутые запросы `INSERT` в транзакциях. По умолчанию: `0`. + +Требуемая конфигурация: + +Конфигурация сервера RabbitMQ добавляется с помощью конфигурационного файла ClickHouse. + +``` xml + + root + clickhouse + +``` + +Example: + +``` sql + CREATE TABLE queue ( + key UInt64, + value UInt64 + ) ENGINE = RabbitMQ SETTINGS rabbitmq_host_port = 'localhost:5672', + rabbitmq_exchange_name = 'exchange1', + rabbitmq_format = 'JSONEachRow', + rabbitmq_num_consumers = 5; +``` + +## Описание {#description} + +Запрос `SELECT` не очень полезен для чтения сообщений (за исключением отладки), поскольку каждое сообщение может быть прочитано только один раз. Практичнее создавать потоки реального времени с помощью [материализованных преставлений](../../../sql-reference/statements/create/view.md). Для этого: + +1. Создайте потребителя RabbitMQ с помощью движка и рассматривайте его как поток данных. +2. Создайте таблицу с необходимой структурой. +3. Создайте материализованное представление, которое преобразует данные от движка и помещает их в ранее созданную таблицу. + +Когда к движку присоединяется материализованное представление, оно начинает в фоновом режиме собирать данные. Это позволяет непрерывно получать сообщения от RabbitMQ и преобразовывать их в необходимый формат с помощью `SELECT`. +У одной таблицы RabbitMQ может быть неограниченное количество материализованных представлений. + +Данные передаются с помощью параметров `rabbitmq_exchange_type` и `rabbitmq_routing_key_list`. +Может быть не более одной точки обмена на таблицу. Одна точка обмена может использоваться несколькими таблицами: это позволяет выполнять маршрутизацию по нескольким таблицам одновременно. + +Параметры точек обмена: + +- `direct` - маршрутизация основана на точном совпадении ключей. Пример списка ключей: `key1,key2,key3,key4,key5`. Ключ сообщения может совпадать с одним из них. +- `fanout` - маршрутизация по всем таблицам, где имя точки обмена совпадает, независимо от ключей. +- `topic` - маршрутизация основана на правилах с ключами, разделенными точками. Например: `*.logs`, `records.*.*.2020`, `*.2018,*.2019,*.2020`. +- `headers` - маршрутизация основана на совпадении `key=value` с настройкой `x-match=all` или `x-match=any`. Пример списка ключей таблицы: `x-match=all,format=logs,type=report,year=2020`. +- `consistent-hash` - данные равномерно распределяются между всеми связанными таблицами, где имя точки обмена совпадает. Обратите внимание, что этот тип обмена должен быть включен с помощью плагина RabbitMQ: `rabbitmq-plugins enable rabbitmq_consistent_hash_exchange`. + +Если тип точки обмена не задан, по умолчанию используется `fanout`. В таком случае ключи маршрутизации для публикации данных должны быть рандомизированы в диапазоне `[1, num_consumers]` за каждое сообщение/пакет (или в диапазоне `[1, num_consumers * num_queues]`, если `rabbitmq_num_queues` задано). Эта конфигурация таблицы работает быстрее, чем любая другая, особенно когда заданы параметры `rabbitmq_num_consumers` и/или `rabbitmq_num_queues`. + +Если параметры`rabbitmq_num_consumers` и/или `rabbitmq_num_queues` заданы вместе с параметром `rabbitmq_exchange_type`: + +- плагин `rabbitmq-consistent-hash-exchange` должен быть включен. +- свойство `message_id` должно быть определено (уникальное для каждого сообщения/пакета). + +Пример: + +``` sql + CREATE TABLE queue ( + key UInt64, + value UInt64 + ) ENGINE = RabbitMQ SETTINGS rabbitmq_host_port = 'localhost:5672', + rabbitmq_exchange_name = 'exchange1', + rabbitmq_exchange_type = 'headers', + rabbitmq_routing_key_list = 'format=logs,type=report,year=2020', + rabbitmq_format = 'JSONEachRow', + rabbitmq_num_consumers = 5; + + CREATE TABLE daily (key UInt64, value UInt64) + ENGINE = MergeTree(); + + CREATE MATERIALIZED VIEW consumer TO daily + AS SELECT key, value FROM queue; + + SELECT key, value FROM daily ORDER BY key; +``` From a6486490a2b39488c6d2a20dd09b0bc39a5f3d2e Mon Sep 17 00:00:00 2001 From: Alexander Kuzmenkov Date: Tue, 1 Sep 2020 22:05:57 +0300 Subject: [PATCH 53/73] performance comparison --- docker/test/performance-comparison/compare.sh | 9 +++++++-- docker/test/performance-comparison/report.py | 11 +++-------- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/docker/test/performance-comparison/compare.sh b/docker/test/performance-comparison/compare.sh index d3b9fc2214e..4384f5b7827 100755 --- a/docker/test/performance-comparison/compare.sh +++ b/docker/test/performance-comparison/compare.sh @@ -536,7 +536,9 @@ create table queries engine File(TSVWithNamesAndTypes, 'report/queries.tsv') left join query_display_names on query_metric_stats.test = query_display_names.test and query_metric_stats.query_index = query_display_names.query_index - where metric_name = 'server_time' + -- 'server_time' is rounded down to ms, which might be bad for very short queries. + -- Use 'client_time' instead. + where metric_name = 'client_time' order by test, query_index, metric_name ; @@ -888,7 +890,10 @@ for log in *-err.log do test=$(basename "$log" "-err.log") { - grep -H -m2 -i '\(Exception\|Error\):[^:]' "$log" \ + # The second grep is a heuristic for error messages like + # "socket.timeout: timed out". + grep -h -m2 -i '\(Exception\|Error\):[^:]' "$log" \ + || grep -h -m2 -i '^[^ ]\+: ' "$log" \ || head -2 "$log" } | sed "s/^/$test\t/" >> run-errors.tsv ||: done diff --git a/docker/test/performance-comparison/report.py b/docker/test/performance-comparison/report.py index ecf9c7a45e5..d7fc2a9707b 100755 --- a/docker/test/performance-comparison/report.py +++ b/docker/test/performance-comparison/report.py @@ -168,12 +168,6 @@ def nextRowAnchor(): global table_anchor return f'{table_anchor}.{row_anchor + 1}' -def setRowAnchor(anchor_row_part): - global row_anchor - global table_anchor - row_anchor = anchor_row_part - return currentRowAnchor() - def advanceRowAnchor(): global row_anchor global table_anchor @@ -480,11 +474,12 @@ if args.report == 'main': total_runs = (nominal_runs + 1) * 2 # one prewarm run, two servers attrs = ['' for c in columns] for r in rows: + anchor = f'{currentTableAnchor()}.{r[0]}' if float(r[6]) > 1.5 * total_runs: # FIXME should be 15s max -- investigate parallel_insert slow_average_tests += 1 attrs[6] = f'style="background: {color_bad}"' - errors_explained.append([f'The test \'{r[0]}\' is too slow to run as a whole. Investigate whether the create and fill queries can be sped up']) + errors_explained.append([f'The test \'{r[0]}\' is too slow to run as a whole. Investigate whether the create and fill queries can be sped up']) else: attrs[6] = '' @@ -495,7 +490,7 @@ if args.report == 'main': else: attrs[5] = '' - text += tableRow(r, attrs) + text += tableRow(r, attrs, anchor) text += tableEnd() tables.append(text) From fa04b39d32e566c641009da6724a2b9dc4a5e1f6 Mon Sep 17 00:00:00 2001 From: Alexander Kuzmenkov <36882414+akuzm@users.noreply.github.com> Date: Wed, 2 Sep 2020 02:06:53 +0300 Subject: [PATCH 54/73] Revert "Change query event filter and add integration test for empty GTID transaction" --- src/Core/MySQL/MySQLReplication.cpp | 8 ++--- .../materialize_with_ddl.py | 36 ------------------- .../test_materialize_mysql_database/test.py | 5 --- 3 files changed, 4 insertions(+), 45 deletions(-) diff --git a/src/Core/MySQL/MySQLReplication.cpp b/src/Core/MySQL/MySQLReplication.cpp index f26436440b8..41afe3cde6a 100644 --- a/src/Core/MySQL/MySQLReplication.cpp +++ b/src/Core/MySQL/MySQLReplication.cpp @@ -103,17 +103,17 @@ namespace MySQLReplication = header.event_size - EVENT_HEADER_LENGTH - 4 - 4 - 1 - 2 - 2 - status_len - schema_len - 1 - CHECKSUM_CRC32_SIGNATURE_LENGTH; query.resize(len); payload.readStrict(reinterpret_cast(query.data()), len); - if (query.starts_with("BEGIN") || query.starts_with("COMMIT")) + if (query.rfind("BEGIN", 0) == 0 || query.rfind("COMMIT") == 0) { typ = QUERY_EVENT_MULTI_TXN_FLAG; } - else if (query.starts_with("XA")) + else if (query.rfind("XA", 0) == 0) { - if (query.starts_with("XA ROLLBACK")) + if (query.rfind("XA ROLLBACK", 0) == 0) throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::UNKNOWN_EXCEPTION); typ = QUERY_EVENT_XA; } - else if (query.starts_with("SAVEPOINT")) + else if (query.rfind("SAVEPOINT", 0) == 0) { throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::UNKNOWN_EXCEPTION); } diff --git a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py index 0dff05df3a1..18695f40e53 100644 --- a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py +++ b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py @@ -1,5 +1,4 @@ import time -import pymysql.cursors def check_query(clickhouse_node, query, result_set, retry_count=3, interval_seconds=3): @@ -322,38 +321,3 @@ def alter_rename_table_with_materialize_mysql_database(clickhouse_node, mysql_no clickhouse_node.query("DROP DATABASE test_database") mysql_node.query("DROP DATABASE test_database") - - -def query_event_with_empty_transaction(clickhouse_node, mysql_node, service_name): - mysql_node.query("CREATE DATABASE test_database") - - mysql_node.query("RESET MASTER") - mysql_node.query("CREATE TABLE test_database.t1(a INT NOT NULL PRIMARY KEY, b VARCHAR(255) DEFAULT 'BEGIN')") - mysql_node.query("INSERT INTO test_database.t1(a) VALUES(1)") - - clickhouse_node.query( - "CREATE DATABASE test_database ENGINE = MaterializeMySQL('{}:3306', 'test_database', 'root', 'clickhouse')".format( - service_name)) - - # Reject one empty GTID QUERY event with 'BEGIN' and 'COMMIT' - mysql_cursor = mysql_node.cursor(pymysql.cursors.DictCursor) - mysql_cursor.execute("SHOW MASTER STATUS") - (uuid, seqs) = mysql_cursor.fetchall()[0]["Executed_Gtid_Set"].split(":") - (seq_begin, seq_end) = seqs.split("-") - assert int(seq_begin) == 1 - assert int(seq_end) == 3 - next_gtid = uuid + ":" + str(int(seq_end) + 1) - mysql_node.query("SET gtid_next='" + next_gtid + "'") - mysql_node.query("BEGIN") - mysql_node.query("COMMIT") - mysql_node.query("SET gtid_next='AUTOMATIC'") - - # Reject one 'BEGIN' QUERY event and 'COMMIT' XID event. - mysql_node.query("/* start */ begin /* end */") - mysql_node.query("INSERT INTO test_database.t1(a) VALUES(2)") - mysql_node.query("/* start */ commit /* end */") - - check_query(clickhouse_node, "SELECT * FROM test_database.t1 ORDER BY a FORMAT TSV", - "1\tBEGIN\n2\tBEGIN\n") - clickhouse_node.query("DROP DATABASE test_database") - mysql_node.query("DROP DATABASE test_database") diff --git a/tests/integration/test_materialize_mysql_database/test.py b/tests/integration/test_materialize_mysql_database/test.py index d45a5e3ceaf..bfda4e7e840 100644 --- a/tests/integration/test_materialize_mysql_database/test.py +++ b/tests/integration/test_materialize_mysql_database/test.py @@ -120,8 +120,3 @@ def test_materialize_database_ddl_with_mysql_8_0(started_cluster, started_mysql_ materialize_with_ddl.alter_rename_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") materialize_with_ddl.alter_modify_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") -def test_materialize_database_ddl_with_empty_transaction_5_7(started_cluster, started_mysql_5_7): - materialize_with_ddl.query_event_with_empty_transaction(clickhouse_node, started_mysql_5_7.alloc_connection(), "mysql5_7") - -def test_materialize_database_ddl_with_empty_transaction_8_0(started_cluster, started_mysql_8_0): - materialize_with_ddl.query_event_with_empty_transaction(clickhouse_node, started_mysql_8_0.alloc_connection(), "mysql8_0") From 6dfab8815660e967aec922ce5b6aaa1c11536933 Mon Sep 17 00:00:00 2001 From: BohuTANG Date: Wed, 2 Sep 2020 08:31:51 +0800 Subject: [PATCH 55/73] ISSUES-14235 change string.rfind to string starts_with and add some tests --- src/Core/MySQL/MySQLReplication.cpp | 13 +++---- .../materialize_with_ddl.py | 35 +++++++++++++++++++ .../test_materialize_mysql_database/test.py | 5 +++ 3 files changed, 47 insertions(+), 6 deletions(-) diff --git a/src/Core/MySQL/MySQLReplication.cpp b/src/Core/MySQL/MySQLReplication.cpp index 41afe3cde6a..104d2159f60 100644 --- a/src/Core/MySQL/MySQLReplication.cpp +++ b/src/Core/MySQL/MySQLReplication.cpp @@ -13,6 +13,7 @@ namespace DB namespace ErrorCodes { extern const int UNKNOWN_EXCEPTION; + extern const int LOGICAL_ERROR; } namespace MySQLReplication @@ -103,19 +104,19 @@ namespace MySQLReplication = header.event_size - EVENT_HEADER_LENGTH - 4 - 4 - 1 - 2 - 2 - status_len - schema_len - 1 - CHECKSUM_CRC32_SIGNATURE_LENGTH; query.resize(len); payload.readStrict(reinterpret_cast(query.data()), len); - if (query.rfind("BEGIN", 0) == 0 || query.rfind("COMMIT") == 0) + if (query.starts_with("BEGIN") || query.starts_with("COMMIT")) { typ = QUERY_EVENT_MULTI_TXN_FLAG; } - else if (query.rfind("XA", 0) == 0) + else if (query.starts_with("XA")) { - if (query.rfind("XA ROLLBACK", 0) == 0) - throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::UNKNOWN_EXCEPTION); + if (query.starts_with("XA ROLLBACK")) + throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::LOGICAL_ERROR); typ = QUERY_EVENT_XA; } - else if (query.rfind("SAVEPOINT", 0) == 0) + else if (query.starts_with("SAVEPOINT")) { - throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::UNKNOWN_EXCEPTION); + throw ReplicationError("ParseQueryEvent: Unsupported query event:" + query, ErrorCodes::LOGICAL_ERROR); } } diff --git a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py index 18695f40e53..eb3b0cdda4f 100644 --- a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py +++ b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py @@ -1,4 +1,5 @@ import time +import pymysql.cursors def check_query(clickhouse_node, query, result_set, retry_count=3, interval_seconds=3): @@ -321,3 +322,37 @@ def alter_rename_table_with_materialize_mysql_database(clickhouse_node, mysql_no clickhouse_node.query("DROP DATABASE test_database") mysql_node.query("DROP DATABASE test_database") + +def query_event_with_empty_transaction(clickhouse_node, mysql_node, service_name): + mysql_node.query("CREATE DATABASE test_database") + + mysql_node.query("RESET MASTER") + mysql_node.query("CREATE TABLE test_database.t1(a INT NOT NULL PRIMARY KEY, b VARCHAR(255) DEFAULT 'BEGIN')") + mysql_node.query("INSERT INTO test_database.t1(a) VALUES(1)") + + clickhouse_node.query( + "CREATE DATABASE test_database ENGINE = MaterializeMySQL('{}:3306', 'test_database', 'root', 'clickhouse')".format( + service_name)) + + # Reject one empty GTID QUERY event with 'BEGIN' and 'COMMIT' + mysql_cursor = mysql_node.alloc_connection().cursor(pymysql.cursors.DictCursor) + mysql_cursor.execute("SHOW MASTER STATUS") + (uuid, seqs) = mysql_cursor.fetchall()[0]["Executed_Gtid_Set"].split(":") + (seq_begin, seq_end) = seqs.split("-") + assert int(seq_begin) == 1 + assert int(seq_end) == 3 + next_gtid = uuid + ":" + str(int(seq_end) + 1) + mysql_node.query("SET gtid_next='" + next_gtid + "'") + mysql_node.query("BEGIN") + mysql_node.query("COMMIT") + mysql_node.query("SET gtid_next='AUTOMATIC'") + + # Reject one 'BEGIN' QUERY event and 'COMMIT' XID event. + mysql_node.query("/* start */ begin /* end */") + mysql_node.query("INSERT INTO test_database.t1(a) VALUES(2)") + mysql_node.query("/* start */ commit /* end */") + + check_query(clickhouse_node, "SELECT * FROM test_database.t1 ORDER BY a FORMAT TSV", + "1\tBEGIN\n2\tBEGIN\n") + clickhouse_node.query("DROP DATABASE test_database") + mysql_node.query("DROP DATABASE test_database") diff --git a/tests/integration/test_materialize_mysql_database/test.py b/tests/integration/test_materialize_mysql_database/test.py index bfda4e7e840..cc955da92a4 100644 --- a/tests/integration/test_materialize_mysql_database/test.py +++ b/tests/integration/test_materialize_mysql_database/test.py @@ -120,3 +120,8 @@ def test_materialize_database_ddl_with_mysql_8_0(started_cluster, started_mysql_ materialize_with_ddl.alter_rename_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") materialize_with_ddl.alter_modify_column_with_materialize_mysql_database(clickhouse_node, started_mysql_8_0, "mysql8_0") +def test_materialize_database_ddl_with_empty_transaction_5_7(started_cluster, started_mysql_5_7): + materialize_with_ddl.query_event_with_empty_transaction(clickhouse_node, started_mysql_5_7, "mysql5_7") + +def test_materialize_database_ddl_with_empty_transaction_8_0(started_cluster, started_mysql_8_0): + materialize_with_ddl.query_event_with_empty_transaction(clickhouse_node, started_mysql_8_0, "mysql8_0") From 443ed33ab3def36559ace9f4d74b476faf193853 Mon Sep 17 00:00:00 2001 From: Alexey Milovidov Date: Wed, 2 Sep 2020 04:26:35 +0300 Subject: [PATCH 56/73] Less number of threads in builder --- debian/rules | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/debian/rules b/debian/rules index 5b271a8691f..e9882a09e76 100755 --- a/debian/rules +++ b/debian/rules @@ -18,7 +18,7 @@ ifeq ($(CCACHE_PREFIX),distcc) THREADS_COUNT=$(shell distcc -j) endif ifeq ($(THREADS_COUNT),) - THREADS_COUNT=$(shell nproc || grep -c ^processor /proc/cpuinfo || sysctl -n hw.ncpu || echo 4) + THREADS_COUNT=$(shell $$(( $$(nproc || grep -c ^processor /proc/cpuinfo || sysctl -n hw.ncpu || echo 8) / 2 )) ) endif DEB_BUILD_OPTIONS+=parallel=$(THREADS_COUNT) From 56bbac1569e8cc7b6853b3268ce451b791bf48c9 Mon Sep 17 00:00:00 2001 From: Alexey Milovidov Date: Wed, 2 Sep 2020 04:28:52 +0300 Subject: [PATCH 57/73] Trigger CI --- src/Dictionaries/BucketCache.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/src/Dictionaries/BucketCache.h b/src/Dictionaries/BucketCache.h index 381110066a6..c7dec12c3e4 100644 --- a/src/Dictionaries/BucketCache.h +++ b/src/Dictionaries/BucketCache.h @@ -30,12 +30,13 @@ struct Int64Hasher }; -/* - Class for storing cache index. - It consists of two arrays. - The first one is split into buckets (each stores 8 elements (cells)) determined by hash of the element key. - The second one is split into 4bit numbers, which are positions in bucket for next element write (So cache uses FIFO eviction algorithm inside each bucket). -*/ +/** + * Class for storing cache index. + * It consists of two arrays. + * The first one is split into buckets (each stores 8 elements (cells)) determined by hash of the element key. + * The second one is split into 4bit numbers, which are positions in bucket for next element write + * (So cache uses FIFO eviction algorithm inside each bucket). + */ template class BucketCacheIndex { From 04c88ca9e434ade639889a3a1be244be71a07710 Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Wed, 2 Sep 2020 05:06:21 +0300 Subject: [PATCH 58/73] Update AccessFlags.h --- src/Access/AccessFlags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/Access/AccessFlags.h b/src/Access/AccessFlags.h index 11d39585238..3cb92b6b855 100644 --- a/src/Access/AccessFlags.h +++ b/src/Access/AccessFlags.h @@ -100,7 +100,7 @@ public: /// The same as allFlags(). static AccessFlags allFlagsGrantableOnGlobalLevel(); - /// Returns all the flags which could be granted on the global level. + /// Returns all the flags which could be granted on the database level. /// Returns allDatabaseFlags() | allTableFlags() | allDictionaryFlags() | allColumnFlags(). static AccessFlags allFlagsGrantableOnDatabaseLevel(); From 1f908af189d2693f87fa0aec6422ee9767f9958d Mon Sep 17 00:00:00 2001 From: zhang2014 Date: Wed, 2 Sep 2020 13:05:09 +0800 Subject: [PATCH 59/73] ISSUES-14114 fix create parse failure when mysql nullable primary key --- .../MySQL/InterpretersMySQLDDLQuery.cpp | 86 ++++++++++++------- .../MySQL/tests/gtest_create_rewritten.cpp | 52 ++++++++--- src/Parsers/MySQL/ASTDeclareColumn.cpp | 4 +- 3 files changed, 100 insertions(+), 42 deletions(-) diff --git a/src/Interpreters/MySQL/InterpretersMySQLDDLQuery.cpp b/src/Interpreters/MySQL/InterpretersMySQLDDLQuery.cpp index 461dd997cd1..70916fe386d 100644 --- a/src/Interpreters/MySQL/InterpretersMySQLDDLQuery.cpp +++ b/src/Interpreters/MySQL/InterpretersMySQLDDLQuery.cpp @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -124,8 +125,37 @@ static NamesAndTypesList getNames(const ASTFunction & expr, const Context & cont return expression->getRequiredColumnsWithTypes(); } +static NamesAndTypesList modifyPrimaryKeysToNonNullable(const NamesAndTypesList & primary_keys, NamesAndTypesList & columns) +{ + /// https://dev.mysql.com/doc/refman/5.7/en/create-table.html#create-table-indexes-keys + /// PRIMARY KEY: + /// A unique index where all key columns must be defined as NOT NULL. + /// If they are not explicitly declared as NOT NULL, MySQL declares them so implicitly (and silently). + /// A table can have only one PRIMARY KEY. The name of a PRIMARY KEY is always PRIMARY, + /// which thus cannot be used as the name for any other kind of index. + NamesAndTypesList non_nullable_primary_keys; + for (const auto & primary_key : primary_keys) + { + if (!primary_key.type->isNullable()) + non_nullable_primary_keys.emplace_back(primary_key); + else + { + non_nullable_primary_keys.emplace_back( + NameAndTypePair(primary_key.name, assert_cast(primary_key.type.get())->getNestedType())); + + for (auto & column : columns) + { + if (column.name == primary_key.name) + column.type = assert_cast(column.type.get())->getNestedType(); + } + } + } + + return non_nullable_primary_keys; +} + static inline std::tuple getKeys( - ASTExpressionList * columns_define, ASTExpressionList * indices_define, const Context & context, const NamesAndTypesList & columns) + ASTExpressionList * columns_define, ASTExpressionList * indices_define, const Context & context, NamesAndTypesList & columns) { NameSet increment_columns; auto keys = makeASTFunction("tuple"); @@ -171,8 +201,9 @@ static inline std::tuple ASTPtr { - ASTPtr column = std::make_shared(column_name); + if (type_max_size <= 1000) + return std::make_shared(column_name); - if (is_nullable) - column = makeASTFunction("assumeNotNull", column); - - return makeASTFunction("intDiv", column, std::make_shared(UInt64(type_max_size / 1000))); + return makeASTFunction("intDiv", std::make_shared(column_name), + std::make_shared(UInt64(type_max_size / 1000))); }; ASTPtr best_partition; @@ -219,16 +249,12 @@ static ASTPtr getPartitionPolicy(const NamesAndTypesList & primary_keys) WhichDataType which(type); if (which.isNullable()) - { - type = (static_cast(*type)).getNestedType(); - which = WhichDataType(type); - } + throw Exception("LOGICAL ERROR: MySQL primary key must be not null, it is a bug.", ErrorCodes::LOGICAL_ERROR); if (which.isDateOrDateTime()) { /// In any case, date or datetime is always the best partitioning key - ASTPtr res = std::make_shared(primary_key.name); - return makeASTFunction("toYYYYMM", primary_key.type->isNullable() ? makeASTFunction("assumeNotNull", res) : res); + return makeASTFunction("toYYYYMM", std::make_shared(primary_key.name)); } if (type->haveMaximumSizeOfValue() && (!best_size || type->getSizeOfValueInMemory() < best_size)) @@ -236,25 +262,22 @@ static ASTPtr getPartitionPolicy(const NamesAndTypesList & primary_keys) if (which.isInt8() || which.isUInt8()) { best_size = type->getSizeOfValueInMemory(); - best_partition = std::make_shared(primary_key.name); - - if (primary_key.type->isNullable()) - best_partition = makeASTFunction("assumeNotNull", best_partition); + best_partition = numbers_partition(primary_key.name, std::numeric_limits::max()); } else if (which.isInt16() || which.isUInt16()) { best_size = type->getSizeOfValueInMemory(); - best_partition = numbers_partition(primary_key.name, primary_key.type->isNullable(), std::numeric_limits::max()); + best_partition = numbers_partition(primary_key.name, std::numeric_limits::max()); } else if (which.isInt32() || which.isUInt32()) { best_size = type->getSizeOfValueInMemory(); - best_partition = numbers_partition(primary_key.name, primary_key.type->isNullable(), std::numeric_limits::max()); + best_partition = numbers_partition(primary_key.name, std::numeric_limits::max()); } else if (which.isInt64() || which.isUInt64()) { best_size = type->getSizeOfValueInMemory(); - best_partition = numbers_partition(primary_key.name, primary_key.type->isNullable(), std::numeric_limits::max()); + best_partition = numbers_partition(primary_key.name, std::numeric_limits::max()); } } } @@ -266,12 +289,12 @@ static ASTPtr getOrderByPolicy( const NamesAndTypesList & primary_keys, const NamesAndTypesList & unique_keys, const NamesAndTypesList & keys, const NameSet & increment_columns) { NameSet order_by_columns_set; - std::deque> order_by_columns_list; + std::deque order_by_columns_list; const auto & add_order_by_expression = [&](const NamesAndTypesList & names_and_types) { - std::vector increment_keys; - std::vector non_increment_keys; + NamesAndTypesList increment_keys; + NamesAndTypesList non_increment_keys; for (const auto & [name, type] : names_and_types) { @@ -280,13 +303,13 @@ static ASTPtr getOrderByPolicy( if (increment_columns.count(name)) { - increment_keys.emplace_back(name); order_by_columns_set.emplace(name); + increment_keys.emplace_back(NameAndTypePair(name, type)); } else { order_by_columns_set.emplace(name); - non_increment_keys.emplace_back(name); + non_increment_keys.emplace_back(NameAndTypePair(name, type)); } } @@ -305,8 +328,13 @@ static ASTPtr getOrderByPolicy( for (const auto & order_by_columns : order_by_columns_list) { - for (const auto & order_by_column : order_by_columns) - order_by_expression->arguments->children.emplace_back(std::make_shared(order_by_column)); + for (const auto & [name, type] : order_by_columns) + { + order_by_expression->arguments->children.emplace_back(std::make_shared(name)); + + if (type->isNullable()) + order_by_expression->arguments->children.back() = makeASTFunction("assumeNotNull", order_by_expression->arguments->children.back()); + } } return order_by_expression; diff --git a/src/Interpreters/MySQL/tests/gtest_create_rewritten.cpp b/src/Interpreters/MySQL/tests/gtest_create_rewritten.cpp index b9bfe28ea1b..b940e4e0c95 100644 --- a/src/Interpreters/MySQL/tests/gtest_create_rewritten.cpp +++ b/src/Interpreters/MySQL/tests/gtest_create_rewritten.cpp @@ -103,21 +103,12 @@ TEST(MySQLCreateRewritten, PartitionPolicy) {"TIMESTAMP", "DateTime", " PARTITION BY toYYYYMM(key)"}, {"BOOLEAN", "Int8", " PARTITION BY key"} }; - const auto & replace_string = [](const String & str, const String & old_str, const String & new_str) - { - String new_string = str; - size_t pos = new_string.find(old_str); - if (pos != std::string::npos) - new_string = new_string.replace(pos, old_str.size(), new_str); - return new_string; - }; - for (const auto & [test_type, mapped_type, partition_policy] : test_types) { EXPECT_EQ(queryToString(tryRewrittenCreateQuery( "CREATE TABLE `test_database`.`test_table_1` (`key` " + test_type + " PRIMARY KEY)", context_holder.context)), - "CREATE TABLE test_database.test_table_1 (`key` Nullable(" + mapped_type + "), `_sign` Int8() MATERIALIZED 1, " - "`_version` UInt64() MATERIALIZED 1) ENGINE = ReplacingMergeTree(_version)" + replace_string(partition_policy, "key", "assumeNotNull(key)") + " ORDER BY tuple(key)"); + "CREATE TABLE test_database.test_table_1 (`key` " + mapped_type + ", `_sign` Int8() MATERIALIZED 1, " + "`_version` UInt64() MATERIALIZED 1) ENGINE = ReplacingMergeTree(_version)" + partition_policy + " ORDER BY tuple(key)"); EXPECT_EQ(queryToString(tryRewrittenCreateQuery( "CREATE TABLE `test_database`.`test_table_1` (`key` " + test_type + " NOT NULL PRIMARY KEY)", context_holder.context)), @@ -126,6 +117,45 @@ TEST(MySQLCreateRewritten, PartitionPolicy) } } +TEST(MySQLCreateRewritten, OrderbyPolicy) +{ + tryRegisterFunctions(); + const auto & context_holder = getContext(); + + std::vector> test_types + { + {"TINYINT", "Int8", " PARTITION BY key"}, {"SMALLINT", "Int16", " PARTITION BY intDiv(key, 65)"}, + {"MEDIUMINT", "Int32", " PARTITION BY intDiv(key, 4294967)"}, {"INT", "Int32", " PARTITION BY intDiv(key, 4294967)"}, + {"INTEGER", "Int32", " PARTITION BY intDiv(key, 4294967)"}, {"BIGINT", "Int64", " PARTITION BY intDiv(key, 18446744073709551)"}, + {"FLOAT", "Float32", ""}, {"DOUBLE", "Float64", ""}, {"VARCHAR(10)", "String", ""}, {"CHAR(10)", "String", ""}, + {"Date", "Date", " PARTITION BY toYYYYMM(key)"}, {"DateTime", "DateTime", " PARTITION BY toYYYYMM(key)"}, + {"TIMESTAMP", "DateTime", " PARTITION BY toYYYYMM(key)"}, {"BOOLEAN", "Int8", " PARTITION BY key"} + }; + + for (const auto & [test_type, mapped_type, partition_policy] : test_types) + { + EXPECT_EQ(queryToString(tryRewrittenCreateQuery( + "CREATE TABLE `test_database`.`test_table_1` (`key` " + test_type + " PRIMARY KEY, `key2` " + test_type + " UNIQUE KEY)", context_holder.context)), + "CREATE TABLE test_database.test_table_1 (`key` " + mapped_type + ", `key2` Nullable(" + mapped_type + "), `_sign` Int8() MATERIALIZED 1, " + "`_version` UInt64() MATERIALIZED 1) ENGINE = ReplacingMergeTree(_version)" + partition_policy + " ORDER BY (key, assumeNotNull(key2))"); + + EXPECT_EQ(queryToString(tryRewrittenCreateQuery( + "CREATE TABLE `test_database`.`test_table_1` (`key` " + test_type + " NOT NULL PRIMARY KEY, `key2` " + test_type + " NOT NULL UNIQUE KEY)", context_holder.context)), + "CREATE TABLE test_database.test_table_1 (`key` " + mapped_type + ", `key2` " + mapped_type + ", `_sign` Int8() MATERIALIZED 1, " + "`_version` UInt64() MATERIALIZED 1) ENGINE = ReplacingMergeTree(_version)" + partition_policy + " ORDER BY (key, key2)"); + + EXPECT_EQ(queryToString(tryRewrittenCreateQuery( + "CREATE TABLE `test_database`.`test_table_1` (`key` " + test_type + " KEY UNIQUE KEY)", context_holder.context)), + "CREATE TABLE test_database.test_table_1 (`key` " + mapped_type + ", `_sign` Int8() MATERIALIZED 1, " + "`_version` UInt64() MATERIALIZED 1) ENGINE = ReplacingMergeTree(_version)" + partition_policy + " ORDER BY tuple(key)"); + + EXPECT_EQ(queryToString(tryRewrittenCreateQuery( + "CREATE TABLE `test_database`.`test_table_1` (`key` " + test_type + ", `key2` " + test_type + " UNIQUE KEY, PRIMARY KEY(`key`, `key2`))", context_holder.context)), + "CREATE TABLE test_database.test_table_1 (`key` " + mapped_type + ", `key2` " + mapped_type + ", `_sign` Int8() MATERIALIZED 1, " + "`_version` UInt64() MATERIALIZED 1) ENGINE = ReplacingMergeTree(_version)" + partition_policy + " ORDER BY (key, key2)"); + } +} + TEST(MySQLCreateRewritten, RewrittenQueryWithPrimaryKey) { tryRegisterFunctions(); diff --git a/src/Parsers/MySQL/ASTDeclareColumn.cpp b/src/Parsers/MySQL/ASTDeclareColumn.cpp index 56a92291f06..6d21f934858 100644 --- a/src/Parsers/MySQL/ASTDeclareColumn.cpp +++ b/src/Parsers/MySQL/ASTDeclareColumn.cpp @@ -46,10 +46,10 @@ static inline bool parseColumnDeclareOptions(IParser::Pos & pos, ASTPtr & node, OptionDescribe("DEFAULT", "default", std::make_unique()), OptionDescribe("ON UPDATE", "on_update", std::make_unique()), OptionDescribe("AUTO_INCREMENT", "auto_increment", std::make_unique()), - OptionDescribe("UNIQUE", "unique_key", std::make_unique()), OptionDescribe("UNIQUE KEY", "unique_key", std::make_unique()), - OptionDescribe("KEY", "primary_key", std::make_unique()), OptionDescribe("PRIMARY KEY", "primary_key", std::make_unique()), + OptionDescribe("UNIQUE", "unique_key", std::make_unique()), + OptionDescribe("KEY", "primary_key", std::make_unique()), OptionDescribe("COMMENT", "comment", std::make_unique()), OptionDescribe("CHARACTER SET", "charset_name", std::make_unique()), OptionDescribe("COLLATE", "collate", std::make_unique()), From be925f8d9c004aa8de4c6b1548916c7e2bd719f1 Mon Sep 17 00:00:00 2001 From: Amos Bird Date: Sat, 29 Aug 2020 13:33:46 +0800 Subject: [PATCH 60/73] Introduce columns transformers. --- .../TranslateQualifiedNamesVisitor.cpp | 19 ++- src/Parsers/ASTAsterisk.cpp | 7 +- src/Parsers/ASTAsterisk.h | 3 + src/Parsers/ASTColumnsMatcher.cpp | 7 +- src/Parsers/ASTColumnsMatcher.h | 1 + src/Parsers/ASTColumnsTransformers.cpp | 158 ++++++++++++++++++ src/Parsers/ASTColumnsTransformers.h | 85 ++++++++++ src/Parsers/ASTQualifiedAsterisk.cpp | 5 + src/Parsers/ASTQualifiedAsterisk.h | 1 + src/Parsers/ExpressionElementParsers.cpp | 126 +++++++++++++- src/Parsers/ExpressionElementParsers.h | 9 + src/Parsers/ya.make | 1 + .../01470_columns_transformers.reference | 63 +++++++ .../01470_columns_transformers.sql | 36 ++++ 14 files changed, 515 insertions(+), 6 deletions(-) create mode 100644 src/Parsers/ASTColumnsTransformers.cpp create mode 100644 src/Parsers/ASTColumnsTransformers.h create mode 100644 tests/queries/0_stateless/01470_columns_transformers.reference create mode 100644 tests/queries/0_stateless/01470_columns_transformers.sql diff --git a/src/Interpreters/TranslateQualifiedNamesVisitor.cpp b/src/Interpreters/TranslateQualifiedNamesVisitor.cpp index fcc4948d88a..e28997f0ad6 100644 --- a/src/Interpreters/TranslateQualifiedNamesVisitor.cpp +++ b/src/Interpreters/TranslateQualifiedNamesVisitor.cpp @@ -18,6 +18,7 @@ #include #include #include +#include namespace DB @@ -135,8 +136,8 @@ void TranslateQualifiedNamesMatcher::visit(ASTFunction & node, const ASTPtr &, D void TranslateQualifiedNamesMatcher::visit(const ASTQualifiedAsterisk &, const ASTPtr & ast, Data & data) { - if (ast->children.size() != 1) - throw Exception("Logical error: qualified asterisk must have exactly one child", ErrorCodes::LOGICAL_ERROR); + if (ast->children.empty()) + throw Exception("Logical error: qualified asterisk must have children", ErrorCodes::LOGICAL_ERROR); auto & ident = ast->children[0]; @@ -242,6 +243,10 @@ void TranslateQualifiedNamesMatcher::visit(ASTExpressionList & node, const ASTPt first_table = false; } + for (const auto & transformer : asterisk->children) + { + IASTColumnsTransformer::transform(transformer, node.children); + } } else if (const auto * asterisk_pattern = child->as()) { @@ -258,6 +263,11 @@ void TranslateQualifiedNamesMatcher::visit(ASTExpressionList & node, const ASTPt first_table = false; } + // ColumnsMatcher's transformers start to appear at child 1 + for (auto it = asterisk_pattern->children.begin() + 1; it != asterisk_pattern->children.end(); ++it) + { + IASTColumnsTransformer::transform(*it, node.children); + } } else if (const auto * qualified_asterisk = child->as()) { @@ -274,6 +284,11 @@ void TranslateQualifiedNamesMatcher::visit(ASTExpressionList & node, const ASTPt break; } } + // QualifiedAsterisk's transformers start to appear at child 1 + for (auto it = qualified_asterisk->children.begin() + 1; it != qualified_asterisk->children.end(); ++it) + { + IASTColumnsTransformer::transform(*it, node.children); + } } else node.children.emplace_back(child); diff --git a/src/Parsers/ASTAsterisk.cpp b/src/Parsers/ASTAsterisk.cpp index 9f38b955d00..95a63586685 100644 --- a/src/Parsers/ASTAsterisk.cpp +++ b/src/Parsers/ASTAsterisk.cpp @@ -13,9 +13,14 @@ ASTPtr ASTAsterisk::clone() const void ASTAsterisk::appendColumnName(WriteBuffer & ostr) const { ostr.write('*'); } -void ASTAsterisk::formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const +void ASTAsterisk::formatImpl(const FormatSettings & settings, FormatState & state, FormatStateStacked frame) const { settings.ostr << "*"; + for (const auto & child : children) + { + settings.ostr << ' '; + child->formatImpl(settings, state, frame); + } } } diff --git a/src/Parsers/ASTAsterisk.h b/src/Parsers/ASTAsterisk.h index 620394ec65a..9c4c9a2df6d 100644 --- a/src/Parsers/ASTAsterisk.h +++ b/src/Parsers/ASTAsterisk.h @@ -9,6 +9,9 @@ namespace DB struct AsteriskSemantic; struct AsteriskSemanticImpl; +/** SELECT * is expanded to all visible columns of the source table. + * Optional transformers can be attached to further manipulate these expanded columns. + */ class ASTAsterisk : public IAST { public: diff --git a/src/Parsers/ASTColumnsMatcher.cpp b/src/Parsers/ASTColumnsMatcher.cpp index b6eb4889a09..191ca52c0e8 100644 --- a/src/Parsers/ASTColumnsMatcher.cpp +++ b/src/Parsers/ASTColumnsMatcher.cpp @@ -28,10 +28,15 @@ void ASTColumnsMatcher::updateTreeHashImpl(SipHash & hash_state) const IAST::updateTreeHashImpl(hash_state); } -void ASTColumnsMatcher::formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const +void ASTColumnsMatcher::formatImpl(const FormatSettings & settings, FormatState & state, FormatStateStacked frame) const { settings.ostr << (settings.hilite ? hilite_keyword : "") << "COLUMNS" << (settings.hilite ? hilite_none : "") << "(" << quoteString(original_pattern) << ")"; + for (ASTs::const_iterator it = children.begin() + 1; it != children.end(); ++it) + { + settings.ostr << ' '; + (*it)->formatImpl(settings, state, frame); + } } void ASTColumnsMatcher::setPattern(String pattern) diff --git a/src/Parsers/ASTColumnsMatcher.h b/src/Parsers/ASTColumnsMatcher.h index 3fa85769712..47a9b86a519 100644 --- a/src/Parsers/ASTColumnsMatcher.h +++ b/src/Parsers/ASTColumnsMatcher.h @@ -23,6 +23,7 @@ struct AsteriskSemanticImpl; /** SELECT COLUMNS('regexp') is expanded to multiple columns like * (asterisk). + * Optional transformers can be attached to further manipulate these expanded columns. */ class ASTColumnsMatcher : public IAST { diff --git a/src/Parsers/ASTColumnsTransformers.cpp b/src/Parsers/ASTColumnsTransformers.cpp new file mode 100644 index 00000000000..29bc8420066 --- /dev/null +++ b/src/Parsers/ASTColumnsTransformers.cpp @@ -0,0 +1,158 @@ +#include "ASTColumnsTransformers.h" +#include +#include +#include +#include +#include + + +namespace DB +{ +namespace ErrorCodes +{ + extern const int ILLEGAL_TYPE_OF_ARGUMENT; +} + +void IASTColumnsTransformer::transform(const ASTPtr & transformer, ASTs & nodes) +{ + if (const auto * apply = transformer->as()) + { + apply->transform(nodes); + } + else if (const auto * except = transformer->as()) + { + except->transform(nodes); + } + else if (const auto * replace = transformer->as()) + { + replace->transform(nodes); + } +} + +void ASTColumnsApplyTransformer::formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const +{ + settings.ostr << (settings.hilite ? hilite_keyword : "") << "APPLY" << (settings.hilite ? hilite_none : "") << "(" << func_name << ")"; +} + +void ASTColumnsApplyTransformer::transform(ASTs & nodes) const +{ + for (auto & column : nodes) + { + column = makeASTFunction(func_name, column); + } +} + +void ASTColumnsExceptTransformer::formatImpl(const FormatSettings & settings, FormatState & state, FormatStateStacked frame) const +{ + settings.ostr << (settings.hilite ? hilite_keyword : "") << "EXCEPT" << (settings.hilite ? hilite_none : "") << "("; + + for (ASTs::const_iterator it = children.begin(); it != children.end(); ++it) + { + if (it != children.begin()) + { + settings.ostr << ", "; + } + (*it)->formatImpl(settings, state, frame); + } + + settings.ostr << ")"; +} + +void ASTColumnsExceptTransformer::transform(ASTs & nodes) const +{ + nodes.erase( + std::remove_if( + nodes.begin(), + nodes.end(), + [this](const ASTPtr & node_child) + { + if (const auto * id = node_child->as()) + { + for (const auto & except_child : children) + { + if (except_child->as().name == id->shortName()) + return true; + } + } + return false; + }), + nodes.end()); +} + +void ASTColumnsReplaceTransformer::Replacement::formatImpl( + const FormatSettings & settings, FormatState & state, FormatStateStacked frame) const +{ + expr->formatImpl(settings, state, frame); + settings.ostr << (settings.hilite ? hilite_keyword : "") << " AS " << (settings.hilite ? hilite_none : "") << name; +} + +void ASTColumnsReplaceTransformer::formatImpl(const FormatSettings & settings, FormatState & state, FormatStateStacked frame) const +{ + settings.ostr << (settings.hilite ? hilite_keyword : "") << "REPLACE" << (settings.hilite ? hilite_none : "") << "("; + + for (ASTs::const_iterator it = children.begin(); it != children.end(); ++it) + { + if (it != children.begin()) + { + settings.ostr << ", "; + } + (*it)->formatImpl(settings, state, frame); + } + + settings.ostr << ")"; +} + +void ASTColumnsReplaceTransformer::replaceChildren(ASTPtr & node, const ASTPtr & replacement, const String & name) +{ + for (auto & child : node->children) + { + if (const auto * id = child->as()) + { + if (id->shortName() == name) + child = replacement; + } + else + replaceChildren(child, replacement, name); + } +} + +void ASTColumnsReplaceTransformer::transform(ASTs & nodes) const +{ + std::map replace_map; + for (const auto & replace_child : children) + { + auto & replacement = replace_child->as(); + if (replace_map.find(replacement.name) != replace_map.end()) + throw Exception( + "Expressions in columns transformer REPLACE should not contain the same replacement more than once", + ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT); + replace_map.emplace(replacement.name, replacement.expr); + } + + for (auto & column : nodes) + { + if (const auto * id = column->as()) + { + auto replace_it = replace_map.find(id->shortName()); + if (replace_it != replace_map.end()) + { + column = replace_it->second; + column->setAlias(replace_it->first); + } + } + else if (auto * ast_with_alias = dynamic_cast(column.get())) + { + auto replace_it = replace_map.find(ast_with_alias->alias); + if (replace_it != replace_map.end()) + { + auto new_ast = replace_it->second->clone(); + ast_with_alias->alias = ""; // remove the old alias as it's useless after replace transformation + replaceChildren(new_ast, column, replace_it->first); + column = new_ast; + column->setAlias(replace_it->first); + } + } + } +} + +} diff --git a/src/Parsers/ASTColumnsTransformers.h b/src/Parsers/ASTColumnsTransformers.h new file mode 100644 index 00000000000..ddf0d70dc35 --- /dev/null +++ b/src/Parsers/ASTColumnsTransformers.h @@ -0,0 +1,85 @@ +#pragma once + +#include + +namespace DB +{ +class IASTColumnsTransformer : public IAST +{ +public: + virtual void transform(ASTs & nodes) const = 0; + static void transform(const ASTPtr & transformer, ASTs & nodes); +}; + +class ASTColumnsApplyTransformer : public IASTColumnsTransformer +{ +public: + String getID(char) const override { return "ColumnsApplyTransformer"; } + ASTPtr clone() const override + { + auto res = std::make_shared(*this); + return res; + } + void transform(ASTs & nodes) const override; + String func_name; + +protected: + void formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const override; +}; + +class ASTColumnsExceptTransformer : public IASTColumnsTransformer +{ +public: + String getID(char) const override { return "ColumnsExceptTransformer"; } + ASTPtr clone() const override + { + auto clone = std::make_shared(*this); + clone->cloneChildren(); + return clone; + } + void transform(ASTs & nodes) const override; + +protected: + void formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const override; +}; + +class ASTColumnsReplaceTransformer : public IASTColumnsTransformer +{ +public: + class Replacement : public IAST + { + public: + String getID(char) const override { return "ColumnsReplaceTransformer::Replacement"; } + ASTPtr clone() const override + { + auto replacement = std::make_shared(*this); + replacement->name = name; + replacement->expr = expr->clone(); + replacement->children.push_back(replacement->expr); + return replacement; + } + + String name; + ASTPtr expr; + + protected: + void formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const override; + }; + + String getID(char) const override { return "ColumnsReplaceTransformer"; } + ASTPtr clone() const override + { + auto clone = std::make_shared(*this); + clone->cloneChildren(); + return clone; + } + void transform(ASTs & nodes) const override; + +protected: + void formatImpl(const FormatSettings & settings, FormatState &, FormatStateStacked) const override; + +private: + static void replaceChildren(ASTPtr & node, const ASTPtr & replacement, const String & name); +}; + +} diff --git a/src/Parsers/ASTQualifiedAsterisk.cpp b/src/Parsers/ASTQualifiedAsterisk.cpp index cbde6d4f15d..0cda01cecac 100644 --- a/src/Parsers/ASTQualifiedAsterisk.cpp +++ b/src/Parsers/ASTQualifiedAsterisk.cpp @@ -16,6 +16,11 @@ void ASTQualifiedAsterisk::formatImpl(const FormatSettings & settings, FormatSta const auto & qualifier = children.at(0); qualifier->formatImpl(settings, state, frame); settings.ostr << ".*"; + for (ASTs::const_iterator it = children.begin() + 1; it != children.end(); ++it) + { + settings.ostr << ' '; + (*it)->formatImpl(settings, state, frame); + } } } diff --git a/src/Parsers/ASTQualifiedAsterisk.h b/src/Parsers/ASTQualifiedAsterisk.h index 2cead406647..2c3689d0ace 100644 --- a/src/Parsers/ASTQualifiedAsterisk.h +++ b/src/Parsers/ASTQualifiedAsterisk.h @@ -11,6 +11,7 @@ struct AsteriskSemanticImpl; /** Something like t.* * It will have qualifier as its child ASTIdentifier. + * Optional transformers can be attached to further manipulate these expanded columns. */ class ASTQualifiedAsterisk : public IAST { diff --git a/src/Parsers/ExpressionElementParsers.cpp b/src/Parsers/ExpressionElementParsers.cpp index e24bb9c4129..eee46c599b1 100644 --- a/src/Parsers/ExpressionElementParsers.cpp +++ b/src/Parsers/ExpressionElementParsers.cpp @@ -20,7 +20,9 @@ #include #include #include +#include +#include #include #include #include @@ -1172,17 +1174,131 @@ bool ParserColumnsMatcher::parseImpl(Pos & pos, ASTPtr & node, Expected & expect auto res = std::make_shared(); res->setPattern(regex_node->as().value.get()); res->children.push_back(regex_node); + ParserColumnsTransformers transformers_p; + ASTPtr transformer; + while (transformers_p.parse(pos, transformer, expected)) + { + res->children.push_back(transformer); + } node = std::move(res); return true; } -bool ParserAsterisk::parseImpl(Pos & pos, ASTPtr & node, Expected &) +bool ParserColumnsTransformers::parseImpl(Pos & pos, ASTPtr & node, Expected & expected) +{ + ParserKeyword apply("APPLY"); + ParserKeyword except("EXCEPT"); + ParserKeyword replace("REPLACE"); + ParserKeyword as("AS"); + + if (apply.ignore(pos, expected)) + { + if (pos->type != TokenType::OpeningRoundBracket) + return false; + ++pos; + + String func_name; + if (!parseIdentifierOrStringLiteral(pos, expected, func_name)) + return false; + + if (pos->type != TokenType::ClosingRoundBracket) + return false; + ++pos; + + auto res = std::make_shared(); + res->func_name = func_name; + node = std::move(res); + return true; + } + else if (except.ignore(pos, expected)) + { + if (pos->type != TokenType::OpeningRoundBracket) + return false; + ++pos; + + ASTs identifiers; + auto parse_id = [&identifiers, &pos, &expected] + { + ASTPtr identifier; + if (!ParserIdentifier().parse(pos, identifier, expected)) + return false; + + identifiers.emplace_back(std::move(identifier)); + return true; + }; + + if (!ParserList::parseUtil(pos, expected, parse_id, false)) + return false; + + if (pos->type != TokenType::ClosingRoundBracket) + return false; + ++pos; + + auto res = std::make_shared(); + res->children = std::move(identifiers); + node = std::move(res); + return true; + } + else if (replace.ignore(pos, expected)) + { + if (pos->type != TokenType::OpeningRoundBracket) + return false; + ++pos; + + ASTs replacements; + ParserExpression element_p; + ParserIdentifier ident_p; + auto parse_id = [&] + { + ASTPtr expr; + + if (!element_p.parse(pos, expr, expected)) + return false; + if (!as.ignore(pos, expected)) + return false; + + ASTPtr ident; + if (!ident_p.parse(pos, ident, expected)) + return false; + + auto replacement = std::make_shared(); + replacement->name = getIdentifierName(ident); + replacement->expr = std::move(expr); + replacements.emplace_back(std::move(replacement)); + return true; + }; + + if (!ParserList::parseUtil(pos, expected, parse_id, false)) + return false; + + if (pos->type != TokenType::ClosingRoundBracket) + return false; + ++pos; + + auto res = std::make_shared(); + res->children = std::move(replacements); + node = std::move(res); + return true; + } + + return false; +} + + +bool ParserAsterisk::parseImpl(Pos & pos, ASTPtr & node, Expected & expected) { if (pos->type == TokenType::Asterisk) { ++pos; - node = std::make_shared(); + auto asterisk = std::make_shared(); + ParserColumnsTransformers transformers_p; + ASTPtr transformer; + while (transformers_p.parse(pos, transformer, expected)) + { + asterisk->children.push_back(transformer); + } + node = asterisk; return true; } return false; @@ -1204,6 +1320,12 @@ bool ParserQualifiedAsterisk::parseImpl(Pos & pos, ASTPtr & node, Expected & exp auto res = std::make_shared(); res->children.push_back(node); + ParserColumnsTransformers transformers_p; + ASTPtr transformer; + while (transformers_p.parse(pos, transformer, expected)) + { + res->children.push_back(transformer); + } node = std::move(res); return true; } diff --git a/src/Parsers/ExpressionElementParsers.h b/src/Parsers/ExpressionElementParsers.h index 13e3febcebe..702d757761a 100644 --- a/src/Parsers/ExpressionElementParsers.h +++ b/src/Parsers/ExpressionElementParsers.h @@ -88,6 +88,15 @@ protected: bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override; }; +/** *, t.*, db.table.*, COLUMNS('') APPLY(...) or EXCEPT(...) or REPLACE(...) + */ +class ParserColumnsTransformers : public IParserBase +{ +protected: + const char * getName() const override { return "COLUMNS transformers"; } + bool parseImpl(Pos & pos, ASTPtr & node, Expected & expected) override; +}; + /** A function, for example, f(x, y + 1, g(z)). * Or an aggregate function: sum(x + f(y)), corr(x, y). The syntax is the same as the usual function. * Or a parametric aggregate function: quantile(0.9)(x + y). diff --git a/src/Parsers/ya.make b/src/Parsers/ya.make index 1b03bae100b..b6ef322e426 100644 --- a/src/Parsers/ya.make +++ b/src/Parsers/ya.make @@ -10,6 +10,7 @@ SRCS( ASTAsterisk.cpp ASTColumnDeclaration.cpp ASTColumnsMatcher.cpp + ASTColumnsTransformers.cpp ASTConstraintDeclaration.cpp ASTCreateQuery.cpp ASTCreateQuotaQuery.cpp diff --git a/tests/queries/0_stateless/01470_columns_transformers.reference b/tests/queries/0_stateless/01470_columns_transformers.reference new file mode 100644 index 00000000000..595d99b917f --- /dev/null +++ b/tests/queries/0_stateless/01470_columns_transformers.reference @@ -0,0 +1,63 @@ +220 18 347 +110 9 173.5 +1970-04-11 1970-01-11 1970-11-21 +2 3 +1 2 +18 347 +110 173.5 +1970-04-11 1970-01-11 1970-11-21 +222 18 347 +111 11 173.5 +1970-04-11 1970-01-11 1970-11-21 +SELECT + sum(i), + sum(j), + sum(k) +FROM columns_transformers +SELECT + avg(i), + avg(j), + avg(k) +FROM columns_transformers +SELECT + toDate(any(i)), + toDate(any(j)), + toDate(any(k)) +FROM columns_transformers AS a +SELECT + length(toString(j)), + length(toString(k)) +FROM columns_transformers +SELECT + sum(j), + sum(k) +FROM columns_transformers +SELECT + avg(i), + avg(k) +FROM columns_transformers +SELECT + toDate(any(i)), + toDate(any(j)), + toDate(any(k)) +FROM columns_transformers AS a +SELECT + sum(i + 1 AS i), + sum(j), + sum(k) +FROM columns_transformers +SELECT + avg(i + 1 AS i), + avg(j + 2 AS j), + avg(k) +FROM columns_transformers +SELECT + toDate(any(i)), + toDate(any(j)), + toDate(any(k)) +FROM columns_transformers AS a +SELECT + (i + 1) + 1 AS i, + j, + k +FROM columns_transformers diff --git a/tests/queries/0_stateless/01470_columns_transformers.sql b/tests/queries/0_stateless/01470_columns_transformers.sql new file mode 100644 index 00000000000..de6a1a89d81 --- /dev/null +++ b/tests/queries/0_stateless/01470_columns_transformers.sql @@ -0,0 +1,36 @@ +DROP TABLE IF EXISTS columns_transformers; + +CREATE TABLE columns_transformers (i Int64, j Int16, k Int64) Engine=TinyLog; +INSERT INTO columns_transformers VALUES (100, 10, 324), (120, 8, 23); + +SELECT * APPLY(sum) from columns_transformers; +SELECT columns_transformers.* APPLY(avg) from columns_transformers; +SELECT a.* APPLY(toDate) APPLY(any) from columns_transformers a; +SELECT COLUMNS('[jk]') APPLY(toString) APPLY(length) from columns_transformers; + +SELECT * EXCEPT(i) APPLY(sum) from columns_transformers; +SELECT columns_transformers.* EXCEPT(j) APPLY(avg) from columns_transformers; +-- EXCEPT after APPLY will not match anything +SELECT a.* APPLY(toDate) EXCEPT(i, j) APPLY(any) from columns_transformers a; + +SELECT * REPLACE(i + 1 AS i) APPLY(sum) from columns_transformers; +SELECT columns_transformers.* REPLACE(j + 2 AS j, i + 1 AS i) APPLY(avg) from columns_transformers; +SELECT columns_transformers.* REPLACE(j + 1 AS j, j + 2 AS j) APPLY(avg) from columns_transformers; -- { serverError 43 } +-- REPLACE after APPLY will not match anything +SELECT a.* APPLY(toDate) REPLACE(i + 1 AS i) APPLY(any) from columns_transformers a; + +EXPLAIN SYNTAX SELECT * APPLY(sum) from columns_transformers; +EXPLAIN SYNTAX SELECT columns_transformers.* APPLY(avg) from columns_transformers; +EXPLAIN SYNTAX SELECT a.* APPLY(toDate) APPLY(any) from columns_transformers a; +EXPLAIN SYNTAX SELECT COLUMNS('[jk]') APPLY(toString) APPLY(length) from columns_transformers; +EXPLAIN SYNTAX SELECT * EXCEPT(i) APPLY(sum) from columns_transformers; +EXPLAIN SYNTAX SELECT columns_transformers.* EXCEPT(j) APPLY(avg) from columns_transformers; +EXPLAIN SYNTAX SELECT a.* APPLY(toDate) EXCEPT(i, j) APPLY(any) from columns_transformers a; +EXPLAIN SYNTAX SELECT * REPLACE(i + 1 AS i) APPLY(sum) from columns_transformers; +EXPLAIN SYNTAX SELECT columns_transformers.* REPLACE(j + 2 AS j, i + 1 AS i) APPLY(avg) from columns_transformers; +EXPLAIN SYNTAX SELECT a.* APPLY(toDate) REPLACE(i + 1 AS i) APPLY(any) from columns_transformers a; + +-- Multiple REPLACE in a row +EXPLAIN SYNTAX SELECT * REPLACE(i + 1 AS i) REPLACE(i + 1 AS i) from columns_transformers; + +DROP TABLE columns_transformers; From 13fdcfada9f34f693595b117063caac156b9b47b Mon Sep 17 00:00:00 2001 From: BohuTANG Date: Wed, 2 Sep 2020 15:41:09 +0800 Subject: [PATCH 61/73] Try to fix query_event_with_empty_transaction failed --- .../test_materialize_mysql_database/materialize_with_ddl.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py index eb3b0cdda4f..f8111ae9508 100644 --- a/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py +++ b/tests/integration/test_materialize_mysql_database/materialize_with_ddl.py @@ -339,8 +339,6 @@ def query_event_with_empty_transaction(clickhouse_node, mysql_node, service_name mysql_cursor.execute("SHOW MASTER STATUS") (uuid, seqs) = mysql_cursor.fetchall()[0]["Executed_Gtid_Set"].split(":") (seq_begin, seq_end) = seqs.split("-") - assert int(seq_begin) == 1 - assert int(seq_end) == 3 next_gtid = uuid + ":" + str(int(seq_end) + 1) mysql_node.query("SET gtid_next='" + next_gtid + "'") mysql_node.query("BEGIN") From 6bd753d85d0a87a965f46317305348bdf7ec8556 Mon Sep 17 00:00:00 2001 From: Amos Bird Date: Fri, 28 Aug 2020 22:07:14 +0800 Subject: [PATCH 62/73] TableFunction view. --- src/Interpreters/QueryNormalizer.cpp | 8 ++++ src/Parsers/ASTFunction.cpp | 13 ++++++ src/Parsers/ASTFunction.h | 1 + src/Parsers/ExpressionElementParsers.cpp | 32 +++++++++++++ src/Storages/StorageView.cpp | 8 +++- src/TableFunctions/TableFunctionView.cpp | 45 +++++++++++++++++++ src/TableFunctions/TableFunctionView.h | 27 +++++++++++ src/TableFunctions/registerTableFunctions.cpp | 2 + src/TableFunctions/registerTableFunctions.h | 2 + src/TableFunctions/ya.make | 1 + .../01415_table_function_view.reference | 10 +++++ .../0_stateless/01415_table_function_view.sql | 5 +++ 12 files changed, 153 insertions(+), 1 deletion(-) create mode 100644 src/TableFunctions/TableFunctionView.cpp create mode 100644 src/TableFunctions/TableFunctionView.h create mode 100644 tests/queries/0_stateless/01415_table_function_view.reference create mode 100644 tests/queries/0_stateless/01415_table_function_view.sql diff --git a/src/Interpreters/QueryNormalizer.cpp b/src/Interpreters/QueryNormalizer.cpp index 324c401eb8a..59233218a50 100644 --- a/src/Interpreters/QueryNormalizer.cpp +++ b/src/Interpreters/QueryNormalizer.cpp @@ -20,6 +20,7 @@ namespace ErrorCodes extern const int TOO_DEEP_AST; extern const int CYCLIC_ALIASES; extern const int UNKNOWN_QUERY_PARAMETER; + extern const int BAD_ARGUMENTS; } @@ -151,6 +152,13 @@ void QueryNormalizer::visitChildren(const ASTPtr & node, Data & data) { if (const auto * func_node = node->as()) { + if (func_node->query) + { + if (func_node->name != "view") + throw Exception("Query argument can only be used in the `view` TableFunction", ErrorCodes::BAD_ARGUMENTS); + /// Don't go into query argument. + return; + } /// We skip the first argument. We also assume that the lambda function can not have parameters. size_t first_pos = 0; if (func_node->name == "lambda") diff --git a/src/Parsers/ASTFunction.cpp b/src/Parsers/ASTFunction.cpp index e8e6efc7fd9..07429c8104f 100644 --- a/src/Parsers/ASTFunction.cpp +++ b/src/Parsers/ASTFunction.cpp @@ -48,6 +48,7 @@ ASTPtr ASTFunction::clone() const auto res = std::make_shared(*this); res->children.clear(); + if (query) { res->query = query->clone(); res->children.push_back(res->query); } if (arguments) { res->arguments = arguments->clone(); res->children.push_back(res->arguments); } if (parameters) { res->parameters = parameters->clone(); res->children.push_back(res->parameters); } @@ -118,6 +119,18 @@ void ASTFunction::formatImplWithoutAlias(const FormatSettings & settings, Format nested_need_parens.need_parens = true; nested_dont_need_parens.need_parens = false; + if (query) + { + std::string nl_or_nothing = settings.one_line ? "" : "\n"; + std::string indent_str = settings.one_line ? "" : std::string(4u * frame.indent, ' '); + settings.ostr << (settings.hilite ? hilite_function : "") << name << "(" << nl_or_nothing; + FormatStateStacked frame_nested = frame; + frame_nested.need_parens = false; + ++frame_nested.indent; + query->formatImpl(settings, state, frame_nested); + settings.ostr << nl_or_nothing << indent_str << ")"; + return; + } /// Should this function to be written as operator? bool written = false; if (arguments && !parameters) diff --git a/src/Parsers/ASTFunction.h b/src/Parsers/ASTFunction.h index 127f50ee586..b94614426d8 100644 --- a/src/Parsers/ASTFunction.h +++ b/src/Parsers/ASTFunction.h @@ -13,6 +13,7 @@ class ASTFunction : public ASTWithAlias { public: String name; + ASTPtr query; // It's possible for a function to accept a query as its only argument. ASTPtr arguments; /// parameters - for parametric aggregate function. Example: quantile(0.9)(x) - what in first parens are 'parameters'. ASTPtr parameters; diff --git a/src/Parsers/ExpressionElementParsers.cpp b/src/Parsers/ExpressionElementParsers.cpp index e24bb9c4129..149d0195dff 100644 --- a/src/Parsers/ExpressionElementParsers.cpp +++ b/src/Parsers/ExpressionElementParsers.cpp @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include #include @@ -217,10 +219,12 @@ bool ParserFunction::parseImpl(Pos & pos, ASTPtr & node, Expected & expected) ParserIdentifier id_parser; ParserKeyword distinct("DISTINCT"); ParserExpressionList contents(false); + ParserSelectWithUnionQuery select; bool has_distinct_modifier = false; ASTPtr identifier; + ASTPtr query; ASTPtr expr_list_args; ASTPtr expr_list_params; @@ -231,8 +235,36 @@ bool ParserFunction::parseImpl(Pos & pos, ASTPtr & node, Expected & expected) return false; ++pos; + if (distinct.ignore(pos, expected)) has_distinct_modifier = true; + else + { + auto old_pos = pos; + auto maybe_an_subquery = pos->type == TokenType::OpeningRoundBracket; + + if (select.parse(pos, query, expected)) + { + auto & select_ast = query->as(); + if (select_ast.list_of_selects->children.size() == 1 && maybe_an_subquery) + { + // It's an subquery. Bail out. + pos = old_pos; + } + else + { + if (pos->type != TokenType::ClosingRoundBracket) + return false; + ++pos; + auto function_node = std::make_shared(); + tryGetIdentifierNameInto(identifier, function_node->name); + function_node->query = query; + function_node->children.push_back(function_node->query); + node = function_node; + return true; + } + } + } const char * contents_begin = pos->begin; if (!contents.parse(pos, expr_list_args, expected)) diff --git a/src/Storages/StorageView.cpp b/src/Storages/StorageView.cpp index 1a95b7ea21f..4b7733c1cd2 100644 --- a/src/Storages/StorageView.cpp +++ b/src/Storages/StorageView.cpp @@ -104,7 +104,13 @@ void StorageView::replaceWithSubquery(ASTSelectQuery & outer_query, ASTPtr view_ ASTTableExpression * table_expression = getFirstTableExpression(outer_query); if (!table_expression->database_and_table_name) - throw Exception("Logical error: incorrect table expression", ErrorCodes::LOGICAL_ERROR); + { + // If it's a view table function, add a fake db.table name. + if (table_expression->table_function && table_expression->table_function->as()->name == "view") + table_expression->database_and_table_name = std::make_shared("__view"); + else + throw Exception("Logical error: incorrect table expression", ErrorCodes::LOGICAL_ERROR); + } DatabaseAndTableWithAlias db_table(table_expression->database_and_table_name); String alias = db_table.alias.empty() ? db_table.table : db_table.alias; diff --git a/src/TableFunctions/TableFunctionView.cpp b/src/TableFunctions/TableFunctionView.cpp new file mode 100644 index 00000000000..6166fa56f47 --- /dev/null +++ b/src/TableFunctions/TableFunctionView.cpp @@ -0,0 +1,45 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include "registerTableFunctions.h" + + +namespace DB +{ +namespace ErrorCodes +{ + extern const int BAD_ARGUMENTS; +} + +StoragePtr TableFunctionView::executeImpl(const ASTPtr & ast_function, const Context & context, const std::string & table_name) const +{ + if (const auto * function = ast_function->as()) + { + if (function->query) + { + if (auto * select = function->query->as()) + { + auto sample = InterpreterSelectWithUnionQuery::getSampleBlock(function->query, context); + auto columns = ColumnsDescription(sample.getNamesAndTypesList()); + ASTCreateQuery create; + create.select = select; + auto res = StorageView::create(StorageID(getDatabaseName(), table_name), create, columns); + res->startup(); + return res; + } + } + } + throw Exception("Table function '" + getName() + "' requires a query argument.", ErrorCodes::BAD_ARGUMENTS); +} + +void registerTableFunctionView(TableFunctionFactory & factory) +{ + factory.registerFunction(); +} + +} diff --git a/src/TableFunctions/TableFunctionView.h b/src/TableFunctions/TableFunctionView.h new file mode 100644 index 00000000000..49f51823735 --- /dev/null +++ b/src/TableFunctions/TableFunctionView.h @@ -0,0 +1,27 @@ +#pragma once + +#include +#include + + +namespace DB +{ + +/* view(query) + * Turning subquery into a table. + * Useful for passing subquery around. + */ +class TableFunctionView : public ITableFunction +{ +public: + static constexpr auto name = "view"; + std::string getName() const override { return name; } +private: + StoragePtr executeImpl(const ASTPtr & ast_function, const Context & context, const std::string & table_name) const override; + const char * getStorageTypeName() const override { return "View"; } + + UInt64 evaluateArgument(const Context & context, ASTPtr & argument) const; +}; + + +} diff --git a/src/TableFunctions/registerTableFunctions.cpp b/src/TableFunctions/registerTableFunctions.cpp index d312fa2085d..25a495a9185 100644 --- a/src/TableFunctions/registerTableFunctions.cpp +++ b/src/TableFunctions/registerTableFunctions.cpp @@ -30,6 +30,8 @@ void registerTableFunctions() registerTableFunctionODBC(factory); registerTableFunctionJDBC(factory); + registerTableFunctionView(factory); + #if USE_MYSQL registerTableFunctionMySQL(factory); #endif diff --git a/src/TableFunctions/registerTableFunctions.h b/src/TableFunctions/registerTableFunctions.h index a695c1926a0..8ff64a22fea 100644 --- a/src/TableFunctions/registerTableFunctions.h +++ b/src/TableFunctions/registerTableFunctions.h @@ -30,6 +30,8 @@ void registerTableFunctionHDFS(TableFunctionFactory & factory); void registerTableFunctionODBC(TableFunctionFactory & factory); void registerTableFunctionJDBC(TableFunctionFactory & factory); +void registerTableFunctionView(TableFunctionFactory & factory); + #if USE_MYSQL void registerTableFunctionMySQL(TableFunctionFactory & factory); #endif diff --git a/src/TableFunctions/ya.make b/src/TableFunctions/ya.make index 3f73df7e3e2..e87c96073bd 100644 --- a/src/TableFunctions/ya.make +++ b/src/TableFunctions/ya.make @@ -21,6 +21,7 @@ SRCS( TableFunctionRemote.cpp TableFunctionURL.cpp TableFunctionValues.cpp + TableFunctionView.cpp TableFunctionZeros.cpp ) diff --git a/tests/queries/0_stateless/01415_table_function_view.reference b/tests/queries/0_stateless/01415_table_function_view.reference new file mode 100644 index 00000000000..2b5eef0300e --- /dev/null +++ b/tests/queries/0_stateless/01415_table_function_view.reference @@ -0,0 +1,10 @@ +1 +1 +SELECT `1` +FROM view( + SELECT 1 +) +SELECT `1` +FROM remote(\'127.0.0.1\', view( + SELECT 1 +)) diff --git a/tests/queries/0_stateless/01415_table_function_view.sql b/tests/queries/0_stateless/01415_table_function_view.sql new file mode 100644 index 00000000000..0beeb64c02d --- /dev/null +++ b/tests/queries/0_stateless/01415_table_function_view.sql @@ -0,0 +1,5 @@ +SELECT * FROM view(SELECT 1); +SELECT * FROM remote('127.0.0.1', view(SELECT 1)); + +EXPLAIN SYNTAX SELECT * FROM view(SELECT 1); +EXPLAIN SYNTAX SELECT * FROM remote('127.0.0.1', view(SELECT 1)); From 09850dbdbc3e2fb5b0150a74d06f6cbcf473d371 Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Wed, 2 Sep 2020 15:39:34 +0300 Subject: [PATCH 63/73] Update ASTColumnsTransformers.cpp --- src/Parsers/ASTColumnsTransformers.cpp | 1 + 1 file changed, 1 insertion(+) diff --git a/src/Parsers/ASTColumnsTransformers.cpp b/src/Parsers/ASTColumnsTransformers.cpp index 29bc8420066..2625a03830b 100644 --- a/src/Parsers/ASTColumnsTransformers.cpp +++ b/src/Parsers/ASTColumnsTransformers.cpp @@ -1,3 +1,4 @@ +#include #include "ASTColumnsTransformers.h" #include #include From 95493352fee2edb0de47fc32d9172f4acfc548e7 Mon Sep 17 00:00:00 2001 From: Alexey Milovidov Date: Wed, 2 Sep 2020 17:07:25 +0300 Subject: [PATCH 64/73] Remove wrong checks --- src/Functions/FunctionsExternalDictionaries.h | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/src/Functions/FunctionsExternalDictionaries.h b/src/Functions/FunctionsExternalDictionaries.h index 5472f0eebf8..609c247ce42 100644 --- a/src/Functions/FunctionsExternalDictionaries.h +++ b/src/Functions/FunctionsExternalDictionaries.h @@ -971,14 +971,6 @@ private: const auto & key_columns = assert_cast(*key_col).getColumnsCopy(); const auto & key_types = static_cast(*key_col_with_type.type).getElements(); - assert(key_columns.size() == key_types.size()); - const auto & structure = dict->getStructure(); - assert(structure.key); - size_t key_size = structure.key->size(); - if (key_columns.size() != key_size) - throw Exception{ErrorCodes::TYPE_MISMATCH, - "Wrong size of tuple at the third argument of function {} must be {}", getName(), key_size}; - typename ColVec::MutablePtr out; if constexpr (IsDataTypeDecimal) out = ColVec::create(key_columns.front()->size(), decimal_scale); @@ -1302,14 +1294,6 @@ private: const auto & key_columns = typeid_cast(*key_col).getColumnsCopy(); const auto & key_types = static_cast(*key_col_with_type.type).getElements(); - assert(key_columns.size() == key_types.size()); - const auto & structure = dict->getStructure(); - assert(structure.key); - size_t key_size = structure.key->size(); - if (key_columns.size() != key_size) - throw Exception{ErrorCodes::TYPE_MISMATCH, - "Wrong size of tuple at the third argument of function {} must be {}", getName(), key_size}; - /// @todo detect when all key columns are constant const auto rows = key_col->size(); typename ColVec::MutablePtr out; From 8e8d5fb89fda276b62811154b8e0c3258b8df6c4 Mon Sep 17 00:00:00 2001 From: Alexander Kazakov Date: Wed, 2 Sep 2020 23:25:50 +0300 Subject: [PATCH 65/73] Updated Changelog.md with description for 20.7 --- CHANGELOG.md | 204 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 204 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 4e1c1d59b99..94fb9641958 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,207 @@ +## ClickHouse release 20.7 + +### ClickHouse release v20.7.2.30-stable, 2020-08-31 + +#### Backward Incompatible Change + +* Function `modulo` (operator `%`) with at least one floating point number as argument will calculate remainder of division directly on floating point numbers without converting both arguments to integers. It makes behaviour compatible with most of DBMS. This also applicable for Date and DateTime data types. Added alias `mod`. This closes [#7323](https://github.com/ClickHouse/ClickHouse/issues/7323). [#12585](https://github.com/ClickHouse/ClickHouse/pull/12585) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Deprecate special printing of zero Date/DateTime values as `0000-00-00` and `0000-00-00 00:00:00`. [#12442](https://github.com/ClickHouse/ClickHouse/pull/12442) ([alexey-milovidov](https://github.com/alexey-milovidov)). + +#### New Feature + +* Added support for user-declared settings, which can be accessed from inside queries. [#13013](https://github.com/ClickHouse/ClickHouse/pull/13013) ([Vitaly Baranov](https://github.com/vitlibar)). +* Added http headers `X-ClickHouse-Database` and `X-ClickHouse-Format` which may be used to set default database and output format. [#12981](https://github.com/ClickHouse/ClickHouse/pull/12981) ([hcz](https://github.com/hczhcz)). +* Add `minMap` and `maxMap` functions support to `SimpleAggregateFunction`. [#12662](https://github.com/ClickHouse/ClickHouse/pull/12662) ([Ildus Kurbangaliev](https://github.com/ildus)). +* Add setting `allow_non_metadata_alters` which restricts to execute `ALTER` queries which modify data on disk. Disabled be default. Closes [#11547](https://github.com/ClickHouse/ClickHouse/issues/11547). [#12635](https://github.com/ClickHouse/ClickHouse/pull/12635) ([alesapin](https://github.com/alesapin)). +* A function `formatRow` is added to support turning arbitrary expressions into a string via given format. It's useful for manipulating SQL outputs and is quite versatile combined with the `columns` function. [#12574](https://github.com/ClickHouse/ClickHouse/pull/12574) ([Amos Bird](https://github.com/amosbird)). +* - Add FROM_UNIXTIME function, related to [12149](https://github.com/ClickHouse/ClickHouse/issues/12149). [#12484](https://github.com/ClickHouse/ClickHouse/pull/12484) ([flynn](https://github.com/ucasFL)). +* Allow Nullable types as keys in MergeTree tables. https://github.com/ClickHouse/ClickHouse/issues/5319. [#12433](https://github.com/ClickHouse/ClickHouse/pull/12433) ([Amos Bird](https://github.com/amosbird)). +* Integration with [COS](https://intl.cloud.tencent.com/product/cos). [#12386](https://github.com/ClickHouse/ClickHouse/pull/12386) ([fastio](https://github.com/fastio)). +* Add `bayesAB` function for bayesian-ab-testing. [#12327](https://github.com/ClickHouse/ClickHouse/pull/12327) ([achimbab](https://github.com/achimbab)). +* Added `system.crash_log` table into which stack traces for fatal errors are collected. [#12316](https://github.com/ClickHouse/ClickHouse/pull/12316) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add mapAdd and mapSubtract functions for adding/subtracting key-mapped values. [#11735](https://github.com/ClickHouse/ClickHouse/pull/11735) ([Ildus Kurbangaliev](https://github.com/ildus)). +* - Added support of LDAP authentication for preconfigured users ("Simple Bind" method). [#11234](https://github.com/ClickHouse/ClickHouse/pull/11234) ([Denis Glazachev](https://github.com/traceon)). + +#### Bug Fix + +* Fix crash in mark inclusion search introduced in https://github.com/ClickHouse/ClickHouse/pull/12277 . [#14225](https://github.com/ClickHouse/ClickHouse/pull/14225) ([Amos Bird](https://github.com/amosbird)). +* Fixed incorrect sorting order for LowCardinality columns. This fixes [#13958](https://github.com/ClickHouse/ClickHouse/issues/13958). [#14223](https://github.com/ClickHouse/ClickHouse/pull/14223) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Removed hardcoded timeout, which wrongly overruled `query_wait_timeout_milliseconds` setting for cache-dictionary. [#14105](https://github.com/ClickHouse/ClickHouse/pull/14105) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Fixed wrong mount point in extra info for `Poco::Exception: no space left on device`. [#14050](https://github.com/ClickHouse/ClickHouse/pull/14050) ([tavplubix](https://github.com/tavplubix)). +* Fix wrong results in select queries with `DISTINCT` keyword in case `optimize_duplicate_order_by_and_distinct` setting is enabled. [#13925](https://github.com/ClickHouse/ClickHouse/pull/13925) ([Artem Zuikov](https://github.com/4ertus2)). +* Fixed potential deadlock when renaming `Distributed` table. [#13922](https://github.com/ClickHouse/ClickHouse/pull/13922) ([tavplubix](https://github.com/tavplubix)). +* Fix incorrect sorting for `FixedString` columns. Fixes [#13182](https://github.com/ClickHouse/ClickHouse/issues/13182). [#13887](https://github.com/ClickHouse/ClickHouse/pull/13887) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix topK/topKWeighted merge (with non-default parameters). [#13817](https://github.com/ClickHouse/ClickHouse/pull/13817) ([Azat Khuzhin](https://github.com/azat)). +* Fix reading from MergeTree table with INDEX of type SET fails when compared against NULL. This fixes [#13686](https://github.com/ClickHouse/ClickHouse/issues/13686). [#13793](https://github.com/ClickHouse/ClickHouse/pull/13793) ([Amos Bird](https://github.com/amosbird)). +* Fix step overflow in function `range()`. [#13790](https://github.com/ClickHouse/ClickHouse/pull/13790) ([Azat Khuzhin](https://github.com/azat)). +* Fixed `Directory not empty` error when concurrently executing `DROP DATABASE` and `CREATE TABLE`. [#13756](https://github.com/ClickHouse/ClickHouse/pull/13756) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add range check for `h3KRing` function. This fixes [#13633](https://github.com/ClickHouse/ClickHouse/issues/13633). [#13752](https://github.com/ClickHouse/ClickHouse/pull/13752) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix race condition between DETACH and background merges. Parts may revive after detach. This is continuation of [#8602](https://github.com/ClickHouse/ClickHouse/issues/8602) that did not fix the issue but introduced a test that started to fail in very rare cases, demonstrating the issue. [#13746](https://github.com/ClickHouse/ClickHouse/pull/13746) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix logging Settings.Names/Values when log_queries_min_type > QUERY_START. [#13737](https://github.com/ClickHouse/ClickHouse/pull/13737) ([Azat Khuzhin](https://github.com/azat)). +* Fix incorrect message in `clickhouse-server.init` while checking user and group. [#13711](https://github.com/ClickHouse/ClickHouse/pull/13711) ([ylchou](https://github.com/ylchou)). +* Fix visible data clobbering by progress bar in client in interactive mode. This fixes [#12562](https://github.com/ClickHouse/ClickHouse/issues/12562) and [#13369](https://github.com/ClickHouse/ClickHouse/issues/13369) and [#13584](https://github.com/ClickHouse/ClickHouse/issues/13584) and fixes [#12964](https://github.com/ClickHouse/ClickHouse/issues/12964). [#13691](https://github.com/ClickHouse/ClickHouse/pull/13691) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Do not optimize any(arrayJoin()) -> arrayJoin() under `optimize_move_functions_out_of_any`. [#13681](https://github.com/ClickHouse/ClickHouse/pull/13681) ([Azat Khuzhin](https://github.com/azat)). +* Fix typo in error message about `The value of 'number_of_free_entries_in_pool_to_lower_max_size_of_merge' setting`. [#13678](https://github.com/ClickHouse/ClickHouse/pull/13678) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fixed possible deadlock in concurrent `ALTER ... REPLACE/MOVE PARTITION ...` queries. [#13626](https://github.com/ClickHouse/ClickHouse/pull/13626) ([tavplubix](https://github.com/tavplubix)). +* Fixed the behaviour when sometimes cache-dictionary returned default value instead of present value from source. [#13624](https://github.com/ClickHouse/ClickHouse/pull/13624) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Fix secondary indices corruption in compact parts. [#13538](https://github.com/ClickHouse/ClickHouse/pull/13538) ([Anton Popov](https://github.com/CurtizJ)). +* Fix premature `ON CLUSTER` timeouts for queries that must be executed on a single replica. Fixes [#6704](https://github.com/ClickHouse/ClickHouse/issues/6704), [#7228](https://github.com/ClickHouse/ClickHouse/issues/7228), [#13361](https://github.com/ClickHouse/ClickHouse/issues/13361), [#11884](https://github.com/ClickHouse/ClickHouse/issues/11884). [#13450](https://github.com/ClickHouse/ClickHouse/pull/13450) ([alesapin](https://github.com/alesapin)). +* Fix wrong code in function `netloc`. This fixes [#13335](https://github.com/ClickHouse/ClickHouse/issues/13335). [#13446](https://github.com/ClickHouse/ClickHouse/pull/13446) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix error in `parseDateTimeBestEffort` function when unix timestamp was passed as an argument. This fixes [#13362](https://github.com/ClickHouse/ClickHouse/issues/13362). [#13441](https://github.com/ClickHouse/ClickHouse/pull/13441) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix invalid return type for comparison of tuples with `NULL` elements. Fixes [#12461](https://github.com/ClickHouse/ClickHouse/issues/12461). [#13420](https://github.com/ClickHouse/ClickHouse/pull/13420) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix `aggregate function any(x) is found inside another aggregate function in query` error with `SET optimize_move_functions_out_of_any = 1` and aliases inside `any()`. [#13419](https://github.com/ClickHouse/ClickHouse/pull/13419) ([Artem Zuikov](https://github.com/4ertus2)). +* Fix possible race in `StorageMemory`. [#13416](https://github.com/ClickHouse/ClickHouse/pull/13416) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix empty output for `Arrow` and `Parquet` formats in case if query return zero rows. It was done because empty output is not valid for this formats. [#13399](https://github.com/ClickHouse/ClickHouse/pull/13399) ([hcz](https://github.com/hczhcz)). +* Fix select queries with constant columns and prefix of primary key in `ORDER BY` clause. [#13396](https://github.com/ClickHouse/ClickHouse/pull/13396) ([Anton Popov](https://github.com/CurtizJ)). +* Fix PrettyCompactMonoBlock for clickhouse-local. Fix extremes/totals with PrettyCompactMonoBlock. Fixes [#7746](https://github.com/ClickHouse/ClickHouse/issues/7746). [#13394](https://github.com/ClickHouse/ClickHouse/pull/13394) ([Azat Khuzhin](https://github.com/azat)). +* Fixed deadlock in system.text_log. It is a part of [#12339](https://github.com/ClickHouse/ClickHouse/issues/12339). This fixes [#12325](https://github.com/ClickHouse/ClickHouse/issues/12325). [#13386](https://github.com/ClickHouse/ClickHouse/pull/13386) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Fixed `File(TSVWithNames*)` (header was written multiple times), fixed `clickhouse-local --format CSVWithNames*` (lacks header, broken after [#12197](https://github.com/ClickHouse/ClickHouse/issues/12197)), fixed `clickhouse-local --format CSVWithNames*` with zero rows (lacks header). [#13343](https://github.com/ClickHouse/ClickHouse/pull/13343) ([Azat Khuzhin](https://github.com/azat)). +* Fix segfault when function `groupArrayMovingSum` deserializes empty state. Fixes [#13339](https://github.com/ClickHouse/ClickHouse/issues/13339). [#13341](https://github.com/ClickHouse/ClickHouse/pull/13341) ([alesapin](https://github.com/alesapin)). +* Throw error on `arrayJoin()` function in `JOIN ON` section. [#13330](https://github.com/ClickHouse/ClickHouse/pull/13330) ([Artem Zuikov](https://github.com/4ertus2)). +* Fix crash in `LEFT ASOF JOIN` with `join_use_nulls=1`. [#13291](https://github.com/ClickHouse/ClickHouse/pull/13291) ([Artem Zuikov](https://github.com/4ertus2)). +* Fix possible error `Totals having transform was already added to pipeline` in case of a query from delayed replica. [#13290](https://github.com/ClickHouse/ClickHouse/pull/13290) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* The server may crash if user passed specifically crafted arguments to the function `h3ToChildren`. This fixes [#13275](https://github.com/ClickHouse/ClickHouse/issues/13275). [#13277](https://github.com/ClickHouse/ClickHouse/pull/13277) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix potentially low performance and slightly incorrect result for `uniqExact`, `topK`, `sumDistinct` and similar aggregate functions called on Float types with NaN values. It also triggered assert in debug build. This fixes [#12491](https://github.com/ClickHouse/ClickHouse/issues/12491). [#13254](https://github.com/ClickHouse/ClickHouse/pull/13254) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix assertion in KeyCondition when primary key contains expression with monotonic function and query contains comparison with constant whose type is different. This fixes [#12465](https://github.com/ClickHouse/ClickHouse/issues/12465). [#13251](https://github.com/ClickHouse/ClickHouse/pull/13251) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Return passed number for numbers with MSB set in function roundUpToPowerOfTwoOrZero(). [#13234](https://github.com/ClickHouse/ClickHouse/pull/13234) ([Azat Khuzhin](https://github.com/azat)). +* Fix function if with nullable constexpr as cond that is not literal NULL. Fixes [#12463](https://github.com/ClickHouse/ClickHouse/issues/12463). [#13226](https://github.com/ClickHouse/ClickHouse/pull/13226) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix assert in `arrayElement` function in case of array elements are Nullable and array subscript is also Nullable. This fixes [#12172](https://github.com/ClickHouse/ClickHouse/issues/12172). [#13224](https://github.com/ClickHouse/ClickHouse/pull/13224) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix DateTime64 conversion functions with constant argument. [#13205](https://github.com/ClickHouse/ClickHouse/pull/13205) ([Azat Khuzhin](https://github.com/azat)). +* AvroConfluent: Skip Kafka tombstone records - Support skipping broken records ... [#13203](https://github.com/ClickHouse/ClickHouse/pull/13203) ([Andrew Onyshchuk](https://github.com/oandrew)). +* Fix parsing row policies from users.xml when names of databases or tables contain dots. This fixes https://github.com/ClickHouse/ClickHouse/issues/5779, https://github.com/ClickHouse/ClickHouse/issues/12527. [#13199](https://github.com/ClickHouse/ClickHouse/pull/13199) ([Vitaly Baranov](https://github.com/vitlibar)). +* Fix segfault when mutation is killed and the server tries to send the exception to the client. [#13169](https://github.com/ClickHouse/ClickHouse/pull/13169) ([alesapin](https://github.com/alesapin)). +* Fix access to redis dictionary after connection was dropped once. It may happen with `cache` and `direct` dictionary layouts. [#13082](https://github.com/ClickHouse/ClickHouse/pull/13082) ([Anton Popov](https://github.com/CurtizJ)). +* Fix wrong index analysis with functions. It could lead to some data parts being skipped when reading from `MergeTree` tables. Fixes [#13060](https://github.com/ClickHouse/ClickHouse/issues/13060). Fixes [#12406](https://github.com/ClickHouse/ClickHouse/issues/12406). [#13081](https://github.com/ClickHouse/ClickHouse/pull/13081) ([Anton Popov](https://github.com/CurtizJ)). +* Fix error `Cannot convert column because it is constant but values of constants are different in source and result` for remote queries which use deterministic functions in scope of query, but not deterministic between queries, like `now()`, `now64()`, `randConstant()`. Fixes [#11327](https://github.com/ClickHouse/ClickHouse/issues/11327). [#13075](https://github.com/ClickHouse/ClickHouse/pull/13075) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix crash which was possible for queries with `ORDER BY` tuple and small `LIMIT`. Fixes [#12623](https://github.com/ClickHouse/ClickHouse/issues/12623). [#13009](https://github.com/ClickHouse/ClickHouse/pull/13009) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix `Block structure mismatch` error for queries with `UNION` and `JOIN`. Fixes [#12602](https://github.com/ClickHouse/ClickHouse/issues/12602). [#12989](https://github.com/ClickHouse/ClickHouse/pull/12989) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Corrected merge_with_ttl_timeout logic which did not work well when expiration affected more than one partition over one time interval. (Authored by @excitoon). [#12982](https://github.com/ClickHouse/ClickHouse/pull/12982) ([Alexander Kazakov](https://github.com/Akazz)). +* Fix columns duplication for range hashed dictionary created from DDL query. This fixes [#10605](https://github.com/ClickHouse/ClickHouse/issues/10605). [#12857](https://github.com/ClickHouse/ClickHouse/pull/12857) ([alesapin](https://github.com/alesapin)). +* Fix unnecessary limiting for the number of threads for selects from local replica. [#12840](https://github.com/ClickHouse/ClickHouse/pull/12840) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix rare bug when `ALTER DELETE` and `ALTER MODIFY COLUMN` queries executed simultaneously as a single mutation. Bug leads to an incorrect amount of rows in `count.txt` and as a consequence incorrect data in part. Also, fix a small bug with simultaneous `ALTER RENAME COLUMN` and `ALTER ADD COLUMN`. [#12760](https://github.com/ClickHouse/ClickHouse/pull/12760) ([alesapin](https://github.com/alesapin)). +* Removed wrong auth access check when using ClickHouseDictionarySource to query remote tables. [#12756](https://github.com/ClickHouse/ClickHouse/pull/12756) ([sundyli](https://github.com/sundy-li)). +* Fix CAST(Nullable(String), Enum()). [#12745](https://github.com/ClickHouse/ClickHouse/pull/12745) ([Azat Khuzhin](https://github.com/azat)). +* Fix performance with large tuples, which are interpreted as functions in `IN` section. The case when user writes `WHERE x IN tuple(1, 2, ...)` instead of `WHERE x IN (1, 2, ...)` for some obscure reason. [#12700](https://github.com/ClickHouse/ClickHouse/pull/12700) ([Anton Popov](https://github.com/CurtizJ)). +* Fix memory tracking for input_format_parallel_parsing (by attaching thread to group). [#12672](https://github.com/ClickHouse/ClickHouse/pull/12672) ([Azat Khuzhin](https://github.com/azat)). +* Fix optimization `optimize_move_functions_out_of_any=1` in case of `any(func())`. [#12664](https://github.com/ClickHouse/ClickHouse/pull/12664) ([Artem Zuikov](https://github.com/4ertus2)). +* Fixed [#12293](https://github.com/ClickHouse/ClickHouse/issues/12293) allow push predicate when subquery contains `WITH` clause. [#12663](https://github.com/ClickHouse/ClickHouse/pull/12663) ([Winter Zhang](https://github.com/zhang2014)). +* Fixed [#10572](https://github.com/ClickHouse/ClickHouse/issues/10572) fix bloom filter index with const expression. [#12659](https://github.com/ClickHouse/ClickHouse/pull/12659) ([Winter Zhang](https://github.com/zhang2014)). +* Fix SIGSEGV in StorageKafka when broker is unavailable (and not only). [#12658](https://github.com/ClickHouse/ClickHouse/pull/12658) ([Azat Khuzhin](https://github.com/azat)). +* Add support for function `if` with `Array(UUID)` arguments. This fixes [#11066](https://github.com/ClickHouse/ClickHouse/issues/11066). [#12648](https://github.com/ClickHouse/ClickHouse/pull/12648) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* CREATE USER IF NOT EXISTS now doesn't throw exception if the user exists. This fixes https://github.com/ClickHouse/ClickHouse/issues/12507. [#12646](https://github.com/ClickHouse/ClickHouse/pull/12646) ([Vitaly Baranov](https://github.com/vitlibar)). +* Exception `There is no supertype...` can be thrown during `ALTER ... UPDATE` in unexpected cases (e.g. when subtracting from UInt64 column). This fixes [#7306](https://github.com/ClickHouse/ClickHouse/issues/7306). This fixes [#4165](https://github.com/ClickHouse/ClickHouse/issues/4165). [#12633](https://github.com/ClickHouse/ClickHouse/pull/12633) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Better exception message in disk access storage. [#12625](https://github.com/ClickHouse/ClickHouse/pull/12625) ([alesapin](https://github.com/alesapin)). +* Fix error message about adaptive granularity. [#12624](https://github.com/ClickHouse/ClickHouse/pull/12624) ([alesapin](https://github.com/alesapin)). +* The function `groupArrayMoving*` was not working for distributed queries. It's result was calculated within incorrect data type (without promotion to the largest type). The function `groupArrayMovingAvg` was returning integer number that was inconsistent with the `avg` function. This fixes [#12568](https://github.com/ClickHouse/ClickHouse/issues/12568). [#12622](https://github.com/ClickHouse/ClickHouse/pull/12622) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix possible `Pipeline stuck` error for queries with external sorting. Fixes [#12617](https://github.com/ClickHouse/ClickHouse/issues/12617). [#12618](https://github.com/ClickHouse/ClickHouse/pull/12618) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix error `Output of TreeExecutor is not sorted` for `OPTIMIZE DEDUPLICATE`. Fixes [#11572](https://github.com/ClickHouse/ClickHouse/issues/11572). [#12613](https://github.com/ClickHouse/ClickHouse/pull/12613) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix lack of aliases with function `any`. [#12593](https://github.com/ClickHouse/ClickHouse/pull/12593) ([Anton Popov](https://github.com/CurtizJ)). +* Fix race condition in external dictionaries with cache layout which can lead server crash. [#12566](https://github.com/ClickHouse/ClickHouse/pull/12566) ([alesapin](https://github.com/alesapin)). +* Remove data for Distributed tables (blocks from async INSERTs) on DROP TABLE. [#12556](https://github.com/ClickHouse/ClickHouse/pull/12556) ([Azat Khuzhin](https://github.com/azat)). +* Now ClickHouse will recalculate checksums for parts when file `checksums.txt` is absent. Broken since [#9827](https://github.com/ClickHouse/ClickHouse/issues/9827). [#12545](https://github.com/ClickHouse/ClickHouse/pull/12545) ([alesapin](https://github.com/alesapin)). +* Fix bug which lead to broken old parts after `ALTER DELETE` query when `enable_mixed_granularity_parts=1`. Fixes [#12536](https://github.com/ClickHouse/ClickHouse/issues/12536). [#12543](https://github.com/ClickHouse/ClickHouse/pull/12543) ([alesapin](https://github.com/alesapin)). +* Better exception for function `in` with invalid number of arguments. [#12529](https://github.com/ClickHouse/ClickHouse/pull/12529) ([Anton Popov](https://github.com/CurtizJ)). +* Fixing race condition in live view tables which could cause data duplication. [#12519](https://github.com/ClickHouse/ClickHouse/pull/12519) ([vzakaznikov](https://github.com/vzakaznikov)). +* Fixed performance issue, while reading from compact parts. [#12492](https://github.com/ClickHouse/ClickHouse/pull/12492) ([Anton Popov](https://github.com/CurtizJ)). +* Fix backwards compatibility in binary format of `AggregateFunction(avg, ...)` values. This fixes [#12342](https://github.com/ClickHouse/ClickHouse/issues/12342). [#12486](https://github.com/ClickHouse/ClickHouse/pull/12486) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix SETTINGS parse after FORMAT. [#12480](https://github.com/ClickHouse/ClickHouse/pull/12480) ([Azat Khuzhin](https://github.com/azat)). +* Fix crash in JOIN with dictionary when we are joining over expression of dictionary key: `t JOIN dict ON expr(dict.id) = t.id`. Disable dictionary join optimisation for this case. [#12458](https://github.com/ClickHouse/ClickHouse/pull/12458) ([Artem Zuikov](https://github.com/4ertus2)). +* SystemLog: do not write to ordinary server log under mutex. This can lead to deadlock if `text_log` is enabled. [#12452](https://github.com/ClickHouse/ClickHouse/pull/12452) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix UBSan report in base64 if tests were run on server with AVX-512. This fixes [#12318](https://github.com/ClickHouse/ClickHouse/issues/12318). Author: @qoega. [#12441](https://github.com/ClickHouse/ClickHouse/pull/12441) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix overflow when very large LIMIT or OFFSET is specified. This fixes [#10470](https://github.com/ClickHouse/ClickHouse/issues/10470). This fixes [#11372](https://github.com/ClickHouse/ClickHouse/issues/11372). [#12427](https://github.com/ClickHouse/ClickHouse/pull/12427) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* If MergeTree table does not contain ORDER BY or PARTITION BY, it was possible to request ALTER to CLEAR all the columns and ALTER will stuck. Fixed [#7941](https://github.com/ClickHouse/ClickHouse/issues/7941). [#12382](https://github.com/ClickHouse/ClickHouse/pull/12382) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* kafka: fix SIGSEGV if there is a message with error in the middle of the batch. [#12302](https://github.com/ClickHouse/ClickHouse/pull/12302) ([Azat Khuzhin](https://github.com/azat)). + +#### Improvement + +* Fix wrong error for long queries. It was possible to get syntax error other than `Max query size exceeded` for correct query. [#13928](https://github.com/ClickHouse/ClickHouse/pull/13928) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix data race in `lgamma` function. This race was caught only in `tsan`, no side effects really happened. [#13842](https://github.com/ClickHouse/ClickHouse/pull/13842) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Updated gitignore-files. [#13447](https://github.com/ClickHouse/ClickHouse/pull/13447) ([vladimir-golovchenko](https://github.com/vladimir-golovchenko)). +* Fix a 'Week'-interval formatting for ATTACH/ALTER/CREATE QUOTA-statements. [#13417](https://github.com/ClickHouse/ClickHouse/pull/13417) ([vladimir-golovchenko](https://github.com/vladimir-golovchenko)). +* Now broken parts are also reported when encountered in compact part processing. [#13282](https://github.com/ClickHouse/ClickHouse/pull/13282) ([Amos Bird](https://github.com/amosbird)). +* Fix assert in geohashesInBox. This fixes [#12554](https://github.com/ClickHouse/ClickHouse/issues/12554). [#13229](https://github.com/ClickHouse/ClickHouse/pull/13229) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix assert in parseDateTimeBestEffort. This fixes [#12649](https://github.com/ClickHouse/ClickHouse/issues/12649). [#13227](https://github.com/ClickHouse/ClickHouse/pull/13227) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Allow *Map aggregate functions to work on Arrays with NULLs. Fixes [#13157](https://github.com/ClickHouse/ClickHouse/issues/13157). [#13225](https://github.com/ClickHouse/ClickHouse/pull/13225) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add sanity check for MergeTree settings. If the settings are incorrect, the server will refuse to start or to create a table, printing detailed explanation to the user. [#13153](https://github.com/ClickHouse/ClickHouse/pull/13153) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Keep smaller amount of logs in ZooKeeper. Avoid excessive growing of ZooKeeper nodes in case of offline replicas when having many servers/tables/inserts. [#13100](https://github.com/ClickHouse/ClickHouse/pull/13100) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Minor optimization in Processors/PipelineExecutor: breaking out of a loop because it makes sense to do so. [#13058](https://github.com/ClickHouse/ClickHouse/pull/13058) ([Mark Papadakis](https://github.com/markpapadakis)). +* Add QueryTimeMicroseconds, SelectQueryTimeMicroseconds and InsertQueryTimeMicroseconds to system.events. [#13028](https://github.com/ClickHouse/ClickHouse/pull/13028) ([ianton-ru](https://github.com/ianton-ru)). +* Introduce setting `alter_partition_verbose_result` which outputs information about touched parts for some types of `ALTER TABLE ... PARTITION ...` queries (currently `ATTACH` and `FREEZE`). Closes [#8076](https://github.com/ClickHouse/ClickHouse/issues/8076). [#13017](https://github.com/ClickHouse/ClickHouse/pull/13017) ([alesapin](https://github.com/alesapin)). +* Protect from the cases when user may set `background_pool_size` to value lower than `number_of_free_entries_in_pool_to_execute_mutation` or `number_of_free_entries_in_pool_to_lower_max_size_of_merge`. In these cases ALTERs won't work or the maximum size of merge will be too limited. Saturate values instead. This closes [#10897](https://github.com/ClickHouse/ClickHouse/issues/10897). [#12728](https://github.com/ClickHouse/ClickHouse/pull/12728) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Now exceptions forwarded to the client if an error happened during ALTER or mutation. Closes [#11329](https://github.com/ClickHouse/ClickHouse/issues/11329). [#12666](https://github.com/ClickHouse/ClickHouse/pull/12666) ([alesapin](https://github.com/alesapin)). +* Support truncate table without table keyword. [#12653](https://github.com/ClickHouse/ClickHouse/pull/12653) ([Winter Zhang](https://github.com/zhang2014)). +* Added `current_database` information to `system.query_log`. [#12652](https://github.com/ClickHouse/ClickHouse/pull/12652) ([Amos Bird](https://github.com/amosbird)). +* Added SelectedRows and SelectedBytes events to ProfileEvents. [#12638](https://github.com/ClickHouse/ClickHouse/pull/12638) ([ianton-ru](https://github.com/ianton-ru)). +* Fix explain query format overwrite by default, issue https://github.com/ClickHouse/ClickHouse/issues/12432. [#12541](https://github.com/ClickHouse/ClickHouse/pull/12541) ([BohuTANG](https://github.com/BohuTANG)). +* Allow to set JOIN kind and type in more standad way: `LEFT SEMI JOIN` instead of `SEMI LEFT JOIN`. For now both are correct. [#12520](https://github.com/ClickHouse/ClickHouse/pull/12520) ([Artem Zuikov](https://github.com/4ertus2)). +* Changes default value for `multiple_joins_rewriter_version` to 2. It enables new multiple joins rewriter that knows about column names. [#12469](https://github.com/ClickHouse/ClickHouse/pull/12469) ([Artem Zuikov](https://github.com/4ertus2)). +* Add several metrics for requests to S3 storages. [#12464](https://github.com/ClickHouse/ClickHouse/pull/12464) ([ianton-ru](https://github.com/ianton-ru)). +* Avoid overflow in parsing of DateTime values that will lead to negative unix timestamp in their timezone (for example, `1970-01-01 00:00:00` in Moscow). Saturate to zero instead. This fixes [#3470](https://github.com/ClickHouse/ClickHouse/issues/3470). This fixes [#4172](https://github.com/ClickHouse/ClickHouse/issues/4172). [#12443](https://github.com/ClickHouse/ClickHouse/pull/12443) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Use correct default secure port for clickhouse-benchmark with `--secure` argument. This fixes [#11044](https://github.com/ClickHouse/ClickHouse/issues/11044). [#12440](https://github.com/ClickHouse/ClickHouse/pull/12440) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Rollback insertion errors in `Log`, `TinyLog`, `StripeLog` engines. In previous versions insertion error lead to inconsisent table state (this works as documented and it is normal for these table engines). This fixes [#12402](https://github.com/ClickHouse/ClickHouse/issues/12402). [#12426](https://github.com/ClickHouse/ClickHouse/pull/12426) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Now joinGet supports multi-key lookup. [#12418](https://github.com/ClickHouse/ClickHouse/pull/12418) ([Amos Bird](https://github.com/amosbird)). +* - Implement `RENAME DATABASE` and `RENAME DICTIONARY` for `Atomic` database engine - Add implicit `{uuid}` macro, which can be used in ZooKeeper path for `ReplicatedMergeTree`. It works with `CREATE ... ON CLUSTER ...` queries. Set `show_table_uuid_in_table_create_query_if_not_nil` to `true` to use it. - Make `ReplicatedMergeTree` engine arguments optional, `/clickhouse/tables/{uuid}/{shard}/` and `{replica}` are used by default. Closes [#12135](https://github.com/ClickHouse/ClickHouse/issues/12135). - Minor fixes. - These changes break backward compatibility of `Atomic` database engine. Previously created `Atomic` databases must be manually converted to new format. [#12343](https://github.com/ClickHouse/ClickHouse/pull/12343) ([tavplubix](https://github.com/tavplubix)). +* Separated `AWSAuthV4Signer` into different logger, removed excessive "AWSClient: AWSClient". [#12320](https://github.com/ClickHouse/ClickHouse/pull/12320) ([Vladimir Chebotarev](https://github.com/excitoon)). +* Allow TabSeparatedRaw as input format. [#12009](https://github.com/ClickHouse/ClickHouse/pull/12009) ([hcz](https://github.com/hczhcz)). +* Adds a new type of polygon dictionary which uses a recursively built grid to reduce the number of polygons which need to be checked for each point. [#9278](https://github.com/ClickHouse/ClickHouse/pull/9278) ([achulkov2](https://github.com/achulkov2)). + +#### Performance Improvement + +* Slightly optimize very short queries with LowCardinality. [#14129](https://github.com/ClickHouse/ClickHouse/pull/14129) ([Anton Popov](https://github.com/CurtizJ)). +* Slightly improve performance of aggregation by UInt8/UInt16 keys. [#13091](https://github.com/ClickHouse/ClickHouse/pull/13091) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Slightly improve performance of aggregation by UInt8/UInt16 keys. [#13055](https://github.com/ClickHouse/ClickHouse/pull/13055) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Push down `LIMIT` step for query plan. [#13016](https://github.com/ClickHouse/ClickHouse/pull/13016) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Parallel PK lookup and skipping index stages on parts, as described in [#11564](https://github.com/ClickHouse/ClickHouse/issues/11564). [#12589](https://github.com/ClickHouse/ClickHouse/pull/12589) ([Ivan Babrou](https://github.com/bobrik)). +* Converts String-type arguments of function "if" and "transform" into enum if `set optimize_if_transform_strings_to_enum = 1`. [#12515](https://github.com/ClickHouse/ClickHouse/pull/12515) ([Artem Zuikov](https://github.com/4ertus2)). +* Replaces monotonous functions with its argument in `ORDER BY` if `set optimize_monotonous_functions_in_order_by=1`. [#12467](https://github.com/ClickHouse/ClickHouse/pull/12467) ([Artem Zuikov](https://github.com/4ertus2)). +* Attempt to implement streaming optimization in `DiskS3`. [#12434](https://github.com/ClickHouse/ClickHouse/pull/12434) ([Vladimir Chebotarev](https://github.com/excitoon)). +* Lower memory usage for some operations up to 2 times. [#12424](https://github.com/ClickHouse/ClickHouse/pull/12424) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add order by optimisation that rewrites `ORDER BY x, f(x)` with `ORDER by x` if `set optimize_redundant_functions_in_order_by = 1`. [#12404](https://github.com/ClickHouse/ClickHouse/pull/12404) ([Artem Zuikov](https://github.com/4ertus2)). +* Optimize PK lookup for queries that match exact PK range. [#12277](https://github.com/ClickHouse/ClickHouse/pull/12277) ([Ivan Babrou](https://github.com/bobrik)). + +#### Build/Testing/Packaging Improvement + +* Ensure that all the submodules are from proper URLs. Continuation of [#13379](https://github.com/ClickHouse/ClickHouse/issues/13379). This fixes [#13378](https://github.com/ClickHouse/ClickHouse/issues/13378). [#13397](https://github.com/ClickHouse/ClickHouse/pull/13397) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Remove some of recursive submodules. See [#13378](https://github.com/ClickHouse/ClickHouse/issues/13378). [#13379](https://github.com/ClickHouse/ClickHouse/pull/13379) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* - Added testing for RBAC functionality of INSERT privilege in TestFlows. - Expanded tables on which SELECT is being tested. - Added Requirements to match new table engine tests. [#13340](https://github.com/ClickHouse/ClickHouse/pull/13340) ([MyroTk](https://github.com/MyroTk)). +* Fix timeout error during server restart in the stress test. [#13321](https://github.com/ClickHouse/ClickHouse/pull/13321) ([alesapin](https://github.com/alesapin)). +* Applying LDAP authentication test fixes. [#13310](https://github.com/ClickHouse/ClickHouse/pull/13310) ([vzakaznikov](https://github.com/vzakaznikov)). +* Now fast test will wait server with retries. [#13284](https://github.com/ClickHouse/ClickHouse/pull/13284) ([alesapin](https://github.com/alesapin)). +* Function `materialize()` (the function for ClickHouse testing) will work for NULL as expected - by transforming it to non-constant column. [#13212](https://github.com/ClickHouse/ClickHouse/pull/13212) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix libunwind build in AArch64. This fixes [#13204](https://github.com/ClickHouse/ClickHouse/issues/13204). [#13208](https://github.com/ClickHouse/ClickHouse/pull/13208) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Use `shellcheck` for sh tests linting. [#13200](https://github.com/ClickHouse/ClickHouse/pull/13200)[#13207](https://github.com/ClickHouse/ClickHouse/pull/13207) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add script which set labels for pull requests in GitHub hook. [#13183](https://github.com/ClickHouse/ClickHouse/pull/13183) ([alesapin](https://github.com/alesapin)). +* Even more retries in zkutil gtest to prevent test flakiness. [#13165](https://github.com/ClickHouse/ClickHouse/pull/13165) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Small fixes to the RBAC SRS. [#13152](https://github.com/ClickHouse/ClickHouse/pull/13152) ([vzakaznikov](https://github.com/vzakaznikov)). +* Fixing 00960_live_view_watch_events_live.py test. [#13108](https://github.com/ClickHouse/ClickHouse/pull/13108) ([vzakaznikov](https://github.com/vzakaznikov)). +* Improve cache purge in documentation deploy script. [#13107](https://github.com/ClickHouse/ClickHouse/pull/13107) ([alesapin](https://github.com/alesapin)). +* Rewrote Function tests to gtest. Removed useless includes from tests. [#13073](https://github.com/ClickHouse/ClickHouse/pull/13073) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Added tests for RBAC functionality of `SELECT` privilege in TestFlows. [#13061](https://github.com/ClickHouse/ClickHouse/pull/13061) ([Ritaank Tiwari](https://github.com/ritaank)). +* Adding extra xfails for some ldap tests. [#13054](https://github.com/ClickHouse/ClickHouse/pull/13054) ([vzakaznikov](https://github.com/vzakaznikov)). +* Rerun some tests in fast test check. [#12992](https://github.com/ClickHouse/ClickHouse/pull/12992) ([alesapin](https://github.com/alesapin)). +* Fix MSan error in "rdkafka" library. This closes [#12990](https://github.com/ClickHouse/ClickHouse/issues/12990). Updated `rdkafka` to version 1.5 (master). [#12991](https://github.com/ClickHouse/ClickHouse/pull/12991) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Check an ability that we able to restore the backup from an old version to the new version. This closes [#8979](https://github.com/ClickHouse/ClickHouse/issues/8979). [#12959](https://github.com/ClickHouse/ClickHouse/pull/12959) ([alesapin](https://github.com/alesapin)). +* Do not build helper_container image inside integrational tests. Build docker container in CI and use pre-built helper_container in integration tests. [#12953](https://github.com/ClickHouse/ClickHouse/pull/12953) ([Ilya Yatsishin](https://github.com/qoega)). +* Add a test for `ALTER TABLE CLEAR COLUMN` query for primary key columns. [#12951](https://github.com/ClickHouse/ClickHouse/pull/12951) ([alesapin](https://github.com/alesapin)). +* Increased timeouts in testflows tests. [#12949](https://github.com/ClickHouse/ClickHouse/pull/12949) ([vzakaznikov](https://github.com/vzakaznikov)). +* Fix build of test under Mac OS X. This closes [#12767](https://github.com/ClickHouse/ClickHouse/issues/12767). [#12772](https://github.com/ClickHouse/ClickHouse/pull/12772) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Connector-ODBC updated to mysql-connector-odbc-8.0.21. [#12739](https://github.com/ClickHouse/ClickHouse/pull/12739) ([Ilya Yatsishin](https://github.com/qoega)). +* Apply random query mutations (fuzzing) in stress tests. [#12734](https://github.com/ClickHouse/ClickHouse/pull/12734) ([Alexander Kuzmenkov](https://github.com/akuzm)). +* Adding RBAC syntax tests in TestFlows. [#12642](https://github.com/ClickHouse/ClickHouse/pull/12642) ([vzakaznikov](https://github.com/vzakaznikov)). +* Improve performance of TestKeeper. This will speedup tests with heavy usage of Replicated tables. [#12505](https://github.com/ClickHouse/ClickHouse/pull/12505) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Now we check that server is able to start after stress tests run. This fixes [#12473](https://github.com/ClickHouse/ClickHouse/issues/12473). [#12496](https://github.com/ClickHouse/ClickHouse/pull/12496) ([alesapin](https://github.com/alesapin)). +* Add PEERDIR(protoc) as protobuf format parses .proto file in runtime. [#12475](https://github.com/ClickHouse/ClickHouse/pull/12475) ([Yuriy Chernyshov](https://github.com/georgthegreat)). +* Fix UBSan report in HDFS library. This closes [#12330](https://github.com/ClickHouse/ClickHouse/issues/12330). [#12453](https://github.com/ClickHouse/ClickHouse/pull/12453) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Update fmtlib to master (7.0.1). [#12446](https://github.com/ClickHouse/ClickHouse/pull/12446) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add docker image for fast tests. [#12294](https://github.com/ClickHouse/ClickHouse/pull/12294) ([alesapin](https://github.com/alesapin)). +* Rework configuration paths for integration tests. [#12285](https://github.com/ClickHouse/ClickHouse/pull/12285) ([Ilya Yatsishin](https://github.com/qoega)). +* Add compiler option to control that stack frames are not too large. This will help to run the code in fibers with small stack size. [#11524](https://github.com/ClickHouse/ClickHouse/pull/11524) ([alexey-milovidov](https://github.com/alexey-milovidov)). + +#### Other + +* Avoid re-loading completion from the history file after each query (to avoid history overlaps with other client sessions). [#13086](https://github.com/ClickHouse/ClickHouse/pull/13086) ([Azat Khuzhin](https://github.com/azat)). + + ## ClickHouse release 20.6 ### ClickHouse release v20.6.3.28-stable From bda889e23463f1fd0dda56dda87b3fa18cdad1db Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Thu, 3 Sep 2020 00:24:58 +0300 Subject: [PATCH 66/73] Update CHANGELOG.md --- CHANGELOG.md | 165 ++++++++++++++++++++++++--------------------------- 1 file changed, 77 insertions(+), 88 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 94fb9641958..ec816caefe5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,200 +6,189 @@ * Function `modulo` (operator `%`) with at least one floating point number as argument will calculate remainder of division directly on floating point numbers without converting both arguments to integers. It makes behaviour compatible with most of DBMS. This also applicable for Date and DateTime data types. Added alias `mod`. This closes [#7323](https://github.com/ClickHouse/ClickHouse/issues/7323). [#12585](https://github.com/ClickHouse/ClickHouse/pull/12585) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Deprecate special printing of zero Date/DateTime values as `0000-00-00` and `0000-00-00 00:00:00`. [#12442](https://github.com/ClickHouse/ClickHouse/pull/12442) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* The function `groupArrayMoving*` was not working for distributed queries. It's result was calculated within incorrect data type (without promotion to the largest type). The function `groupArrayMovingAvg` was returning integer number that was inconsistent with the `avg` function. This fixes [#12568](https://github.com/ClickHouse/ClickHouse/issues/12568). [#12622](https://github.com/ClickHouse/ClickHouse/pull/12622) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add sanity check for MergeTree settings. If the settings are incorrect, the server will refuse to start or to create a table, printing detailed explanation to the user. [#13153](https://github.com/ClickHouse/ClickHouse/pull/13153) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Protect from the cases when user may set `background_pool_size` to value lower than `number_of_free_entries_in_pool_to_execute_mutation` or `number_of_free_entries_in_pool_to_lower_max_size_of_merge`. In these cases ALTERs won't work or the maximum size of merge will be too limited. Saturate values instead. This closes [#10897](https://github.com/ClickHouse/ClickHouse/issues/10897). [#12728](https://github.com/ClickHouse/ClickHouse/pull/12728) ([alexey-milovidov](https://github.com/alexey-milovidov)). #### New Feature -* Added support for user-declared settings, which can be accessed from inside queries. [#13013](https://github.com/ClickHouse/ClickHouse/pull/13013) ([Vitaly Baranov](https://github.com/vitlibar)). +* Polygon dictionary type that provides efficient "reverse geocoding" lookups - to find the region by coordinates in a dictionary of many polygons (world map). It is using carefully optimized algorithm with recursive grids to maintain low CPU and memory usage. [#9278](https://github.com/ClickHouse/ClickHouse/pull/9278) ([achulkov2](https://github.com/achulkov2)). +* Added support of LDAP authentication for preconfigured users ("Simple Bind" method). [#11234](https://github.com/ClickHouse/ClickHouse/pull/11234) ([Denis Glazachev](https://github.com/traceon)). +* Introduce setting `alter_partition_verbose_result` which outputs information about touched parts for some types of `ALTER TABLE ... PARTITION ...` queries (currently `ATTACH` and `FREEZE`). Closes [#8076](https://github.com/ClickHouse/ClickHouse/issues/8076). [#13017](https://github.com/ClickHouse/ClickHouse/pull/13017) ([alesapin](https://github.com/alesapin)). +* Add `bayesAB` function for bayesian-ab-testing. [#12327](https://github.com/ClickHouse/ClickHouse/pull/12327) ([achimbab](https://github.com/achimbab)). +* Added `system.crash_log` table into which stack traces for fatal errors are collected. This table should be empty. [#12316](https://github.com/ClickHouse/ClickHouse/pull/12316) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Added http headers `X-ClickHouse-Database` and `X-ClickHouse-Format` which may be used to set default database and output format. [#12981](https://github.com/ClickHouse/ClickHouse/pull/12981) ([hcz](https://github.com/hczhcz)). * Add `minMap` and `maxMap` functions support to `SimpleAggregateFunction`. [#12662](https://github.com/ClickHouse/ClickHouse/pull/12662) ([Ildus Kurbangaliev](https://github.com/ildus)). * Add setting `allow_non_metadata_alters` which restricts to execute `ALTER` queries which modify data on disk. Disabled be default. Closes [#11547](https://github.com/ClickHouse/ClickHouse/issues/11547). [#12635](https://github.com/ClickHouse/ClickHouse/pull/12635) ([alesapin](https://github.com/alesapin)). * A function `formatRow` is added to support turning arbitrary expressions into a string via given format. It's useful for manipulating SQL outputs and is quite versatile combined with the `columns` function. [#12574](https://github.com/ClickHouse/ClickHouse/pull/12574) ([Amos Bird](https://github.com/amosbird)). -* - Add FROM_UNIXTIME function, related to [12149](https://github.com/ClickHouse/ClickHouse/issues/12149). [#12484](https://github.com/ClickHouse/ClickHouse/pull/12484) ([flynn](https://github.com/ucasFL)). -* Allow Nullable types as keys in MergeTree tables. https://github.com/ClickHouse/ClickHouse/issues/5319. [#12433](https://github.com/ClickHouse/ClickHouse/pull/12433) ([Amos Bird](https://github.com/amosbird)). +* Add `FROM_UNIXTIME` function for compatibility with MySQL, related to [12149](https://github.com/ClickHouse/ClickHouse/issues/12149). [#12484](https://github.com/ClickHouse/ClickHouse/pull/12484) ([flynn](https://github.com/ucasFL)). +* Allow Nullable types as keys in MergeTree tables if `allow_nullable_key` table setting is enabled. https://github.com/ClickHouse/ClickHouse/issues/5319. [#12433](https://github.com/ClickHouse/ClickHouse/pull/12433) ([Amos Bird](https://github.com/amosbird)). * Integration with [COS](https://intl.cloud.tencent.com/product/cos). [#12386](https://github.com/ClickHouse/ClickHouse/pull/12386) ([fastio](https://github.com/fastio)). -* Add `bayesAB` function for bayesian-ab-testing. [#12327](https://github.com/ClickHouse/ClickHouse/pull/12327) ([achimbab](https://github.com/achimbab)). -* Added `system.crash_log` table into which stack traces for fatal errors are collected. [#12316](https://github.com/ClickHouse/ClickHouse/pull/12316) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Add mapAdd and mapSubtract functions for adding/subtracting key-mapped values. [#11735](https://github.com/ClickHouse/ClickHouse/pull/11735) ([Ildus Kurbangaliev](https://github.com/ildus)). -* - Added support of LDAP authentication for preconfigured users ("Simple Bind" method). [#11234](https://github.com/ClickHouse/ClickHouse/pull/11234) ([Denis Glazachev](https://github.com/traceon)). #### Bug Fix -* Fix crash in mark inclusion search introduced in https://github.com/ClickHouse/ClickHouse/pull/12277 . [#14225](https://github.com/ClickHouse/ClickHouse/pull/14225) ([Amos Bird](https://github.com/amosbird)). -* Fixed incorrect sorting order for LowCardinality columns. This fixes [#13958](https://github.com/ClickHouse/ClickHouse/issues/13958). [#14223](https://github.com/ClickHouse/ClickHouse/pull/14223) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Fix premature `ON CLUSTER` timeouts for queries that must be executed on a single replica. Fixes [#6704](https://github.com/ClickHouse/ClickHouse/issues/6704), [#7228](https://github.com/ClickHouse/ClickHouse/issues/7228), [#13361](https://github.com/ClickHouse/ClickHouse/issues/13361), [#11884](https://github.com/ClickHouse/ClickHouse/issues/11884). [#13450](https://github.com/ClickHouse/ClickHouse/pull/13450) ([alesapin](https://github.com/alesapin)). +* Fix crash in mark inclusion search introduced in https://github.com/ClickHouse/ClickHouse/pull/12277. [#14225](https://github.com/ClickHouse/ClickHouse/pull/14225) ([Amos Bird](https://github.com/amosbird)). +* Fix race condition in external dictionaries with cache layout which can lead server crash. [#12566](https://github.com/ClickHouse/ClickHouse/pull/12566) ([alesapin](https://github.com/alesapin)). +* Fix visible data clobbering by progress bar in client in interactive mode. This fixes [#12562](https://github.com/ClickHouse/ClickHouse/issues/12562) and [#13369](https://github.com/ClickHouse/ClickHouse/issues/13369) and [#13584](https://github.com/ClickHouse/ClickHouse/issues/13584) and fixes [#12964](https://github.com/ClickHouse/ClickHouse/issues/12964). [#13691](https://github.com/ClickHouse/ClickHouse/pull/13691) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fixed incorrect sorting order for `LowCardinality` columns when ORDER BY multiple columns is used. This fixes [#13958](https://github.com/ClickHouse/ClickHouse/issues/13958). [#14223](https://github.com/ClickHouse/ClickHouse/pull/14223) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). * Removed hardcoded timeout, which wrongly overruled `query_wait_timeout_milliseconds` setting for cache-dictionary. [#14105](https://github.com/ClickHouse/ClickHouse/pull/14105) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). * Fixed wrong mount point in extra info for `Poco::Exception: no space left on device`. [#14050](https://github.com/ClickHouse/ClickHouse/pull/14050) ([tavplubix](https://github.com/tavplubix)). -* Fix wrong results in select queries with `DISTINCT` keyword in case `optimize_duplicate_order_by_and_distinct` setting is enabled. [#13925](https://github.com/ClickHouse/ClickHouse/pull/13925) ([Artem Zuikov](https://github.com/4ertus2)). +* Fix wrong query optimization of select queries with `DISTINCT` keyword when subqueries also have `DISTINCT` in case `optimize_duplicate_order_by_and_distinct` setting is enabled. [#13925](https://github.com/ClickHouse/ClickHouse/pull/13925) ([Artem Zuikov](https://github.com/4ertus2)). * Fixed potential deadlock when renaming `Distributed` table. [#13922](https://github.com/ClickHouse/ClickHouse/pull/13922) ([tavplubix](https://github.com/tavplubix)). -* Fix incorrect sorting for `FixedString` columns. Fixes [#13182](https://github.com/ClickHouse/ClickHouse/issues/13182). [#13887](https://github.com/ClickHouse/ClickHouse/pull/13887) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). -* Fix topK/topKWeighted merge (with non-default parameters). [#13817](https://github.com/ClickHouse/ClickHouse/pull/13817) ([Azat Khuzhin](https://github.com/azat)). +* Fix incorrect sorting for `FixedString` columns when ORDER BY multiple columns is used. Fixes [#13182](https://github.com/ClickHouse/ClickHouse/issues/13182). [#13887](https://github.com/ClickHouse/ClickHouse/pull/13887) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Fix potentially lower precision of `topK`/`topKWeighted` aggregations (with non-default parameters). [#13817](https://github.com/ClickHouse/ClickHouse/pull/13817) ([Azat Khuzhin](https://github.com/azat)). * Fix reading from MergeTree table with INDEX of type SET fails when compared against NULL. This fixes [#13686](https://github.com/ClickHouse/ClickHouse/issues/13686). [#13793](https://github.com/ClickHouse/ClickHouse/pull/13793) ([Amos Bird](https://github.com/amosbird)). * Fix step overflow in function `range()`. [#13790](https://github.com/ClickHouse/ClickHouse/pull/13790) ([Azat Khuzhin](https://github.com/azat)). * Fixed `Directory not empty` error when concurrently executing `DROP DATABASE` and `CREATE TABLE`. [#13756](https://github.com/ClickHouse/ClickHouse/pull/13756) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Add range check for `h3KRing` function. This fixes [#13633](https://github.com/ClickHouse/ClickHouse/issues/13633). [#13752](https://github.com/ClickHouse/ClickHouse/pull/13752) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix race condition between DETACH and background merges. Parts may revive after detach. This is continuation of [#8602](https://github.com/ClickHouse/ClickHouse/issues/8602) that did not fix the issue but introduced a test that started to fail in very rare cases, demonstrating the issue. [#13746](https://github.com/ClickHouse/ClickHouse/pull/13746) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Fix logging Settings.Names/Values when log_queries_min_type > QUERY_START. [#13737](https://github.com/ClickHouse/ClickHouse/pull/13737) ([Azat Khuzhin](https://github.com/azat)). +* Fix logging Settings.Names/Values when `log_queries_min_type` greater than `QUERY_START`. [#13737](https://github.com/ClickHouse/ClickHouse/pull/13737) ([Azat Khuzhin](https://github.com/azat)). * Fix incorrect message in `clickhouse-server.init` while checking user and group. [#13711](https://github.com/ClickHouse/ClickHouse/pull/13711) ([ylchou](https://github.com/ylchou)). -* Fix visible data clobbering by progress bar in client in interactive mode. This fixes [#12562](https://github.com/ClickHouse/ClickHouse/issues/12562) and [#13369](https://github.com/ClickHouse/ClickHouse/issues/13369) and [#13584](https://github.com/ClickHouse/ClickHouse/issues/13584) and fixes [#12964](https://github.com/ClickHouse/ClickHouse/issues/12964). [#13691](https://github.com/ClickHouse/ClickHouse/pull/13691) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Do not optimize any(arrayJoin()) -> arrayJoin() under `optimize_move_functions_out_of_any`. [#13681](https://github.com/ClickHouse/ClickHouse/pull/13681) ([Azat Khuzhin](https://github.com/azat)). -* Fix typo in error message about `The value of 'number_of_free_entries_in_pool_to_lower_max_size_of_merge' setting`. [#13678](https://github.com/ClickHouse/ClickHouse/pull/13678) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Do not optimize `any(arrayJoin())` to `arrayJoin()` under `optimize_move_functions_out_of_any`. [#13681](https://github.com/ClickHouse/ClickHouse/pull/13681) ([Azat Khuzhin](https://github.com/azat)). * Fixed possible deadlock in concurrent `ALTER ... REPLACE/MOVE PARTITION ...` queries. [#13626](https://github.com/ClickHouse/ClickHouse/pull/13626) ([tavplubix](https://github.com/tavplubix)). * Fixed the behaviour when sometimes cache-dictionary returned default value instead of present value from source. [#13624](https://github.com/ClickHouse/ClickHouse/pull/13624) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). -* Fix secondary indices corruption in compact parts. [#13538](https://github.com/ClickHouse/ClickHouse/pull/13538) ([Anton Popov](https://github.com/CurtizJ)). -* Fix premature `ON CLUSTER` timeouts for queries that must be executed on a single replica. Fixes [#6704](https://github.com/ClickHouse/ClickHouse/issues/6704), [#7228](https://github.com/ClickHouse/ClickHouse/issues/7228), [#13361](https://github.com/ClickHouse/ClickHouse/issues/13361), [#11884](https://github.com/ClickHouse/ClickHouse/issues/11884). [#13450](https://github.com/ClickHouse/ClickHouse/pull/13450) ([alesapin](https://github.com/alesapin)). +* Fix secondary indices corruption in compact parts (compact parts is an experimental feature). [#13538](https://github.com/ClickHouse/ClickHouse/pull/13538) ([Anton Popov](https://github.com/CurtizJ)). * Fix wrong code in function `netloc`. This fixes [#13335](https://github.com/ClickHouse/ClickHouse/issues/13335). [#13446](https://github.com/ClickHouse/ClickHouse/pull/13446) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix error in `parseDateTimeBestEffort` function when unix timestamp was passed as an argument. This fixes [#13362](https://github.com/ClickHouse/ClickHouse/issues/13362). [#13441](https://github.com/ClickHouse/ClickHouse/pull/13441) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix invalid return type for comparison of tuples with `NULL` elements. Fixes [#12461](https://github.com/ClickHouse/ClickHouse/issues/12461). [#13420](https://github.com/ClickHouse/ClickHouse/pull/13420) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). -* Fix `aggregate function any(x) is found inside another aggregate function in query` error with `SET optimize_move_functions_out_of_any = 1` and aliases inside `any()`. [#13419](https://github.com/ClickHouse/ClickHouse/pull/13419) ([Artem Zuikov](https://github.com/4ertus2)). +* Fix wrong optimization caused `aggregate function any(x) is found inside another aggregate function in query` error with `SET optimize_move_functions_out_of_any = 1` and aliases inside `any()`. [#13419](https://github.com/ClickHouse/ClickHouse/pull/13419) ([Artem Zuikov](https://github.com/4ertus2)). * Fix possible race in `StorageMemory`. [#13416](https://github.com/ClickHouse/ClickHouse/pull/13416) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * Fix empty output for `Arrow` and `Parquet` formats in case if query return zero rows. It was done because empty output is not valid for this formats. [#13399](https://github.com/ClickHouse/ClickHouse/pull/13399) ([hcz](https://github.com/hczhcz)). -* Fix select queries with constant columns and prefix of primary key in `ORDER BY` clause. [#13396](https://github.com/ClickHouse/ClickHouse/pull/13396) ([Anton Popov](https://github.com/CurtizJ)). -* Fix PrettyCompactMonoBlock for clickhouse-local. Fix extremes/totals with PrettyCompactMonoBlock. Fixes [#7746](https://github.com/ClickHouse/ClickHouse/issues/7746). [#13394](https://github.com/ClickHouse/ClickHouse/pull/13394) ([Azat Khuzhin](https://github.com/azat)). -* Fixed deadlock in system.text_log. It is a part of [#12339](https://github.com/ClickHouse/ClickHouse/issues/12339). This fixes [#12325](https://github.com/ClickHouse/ClickHouse/issues/12325). [#13386](https://github.com/ClickHouse/ClickHouse/pull/13386) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Fix select queries with constant columns and prefix of primary key in `ORDER BY` clause. [#13396](https://github.com/ClickHouse/ClickHouse/pull/13396) ([Anton Popov](https://github.com/CurtizJ)). +* Fix `PrettyCompactMonoBlock` for clickhouse-local. Fix extremes/totals with `PrettyCompactMonoBlock`. Fixes [#7746](https://github.com/ClickHouse/ClickHouse/issues/7746). [#13394](https://github.com/ClickHouse/ClickHouse/pull/13394) ([Azat Khuzhin](https://github.com/azat)). +* Fixed deadlock in system.text_log. [#12452](https://github.com/ClickHouse/ClickHouse/pull/12452) ([alexey-milovidov](https://github.com/alexey-milovidov)). It is a part of [#12339](https://github.com/ClickHouse/ClickHouse/issues/12339). This fixes [#12325](https://github.com/ClickHouse/ClickHouse/issues/12325). [#13386](https://github.com/ClickHouse/ClickHouse/pull/13386) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). * Fixed `File(TSVWithNames*)` (header was written multiple times), fixed `clickhouse-local --format CSVWithNames*` (lacks header, broken after [#12197](https://github.com/ClickHouse/ClickHouse/issues/12197)), fixed `clickhouse-local --format CSVWithNames*` with zero rows (lacks header). [#13343](https://github.com/ClickHouse/ClickHouse/pull/13343) ([Azat Khuzhin](https://github.com/azat)). * Fix segfault when function `groupArrayMovingSum` deserializes empty state. Fixes [#13339](https://github.com/ClickHouse/ClickHouse/issues/13339). [#13341](https://github.com/ClickHouse/ClickHouse/pull/13341) ([alesapin](https://github.com/alesapin)). * Throw error on `arrayJoin()` function in `JOIN ON` section. [#13330](https://github.com/ClickHouse/ClickHouse/pull/13330) ([Artem Zuikov](https://github.com/4ertus2)). * Fix crash in `LEFT ASOF JOIN` with `join_use_nulls=1`. [#13291](https://github.com/ClickHouse/ClickHouse/pull/13291) ([Artem Zuikov](https://github.com/4ertus2)). * Fix possible error `Totals having transform was already added to pipeline` in case of a query from delayed replica. [#13290](https://github.com/ClickHouse/ClickHouse/pull/13290) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * The server may crash if user passed specifically crafted arguments to the function `h3ToChildren`. This fixes [#13275](https://github.com/ClickHouse/ClickHouse/issues/13275). [#13277](https://github.com/ClickHouse/ClickHouse/pull/13277) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Fix potentially low performance and slightly incorrect result for `uniqExact`, `topK`, `sumDistinct` and similar aggregate functions called on Float types with NaN values. It also triggered assert in debug build. This fixes [#12491](https://github.com/ClickHouse/ClickHouse/issues/12491). [#13254](https://github.com/ClickHouse/ClickHouse/pull/13254) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix potentially low performance and slightly incorrect result for `uniqExact`, `topK`, `sumDistinct` and similar aggregate functions called on Float types with `NaN` values. It also triggered assert in debug build. This fixes [#12491](https://github.com/ClickHouse/ClickHouse/issues/12491). [#13254](https://github.com/ClickHouse/ClickHouse/pull/13254) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix assertion in KeyCondition when primary key contains expression with monotonic function and query contains comparison with constant whose type is different. This fixes [#12465](https://github.com/ClickHouse/ClickHouse/issues/12465). [#13251](https://github.com/ClickHouse/ClickHouse/pull/13251) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Return passed number for numbers with MSB set in function roundUpToPowerOfTwoOrZero(). [#13234](https://github.com/ClickHouse/ClickHouse/pull/13234) ([Azat Khuzhin](https://github.com/azat)). +* Return passed number for numbers with MSB set in function roundUpToPowerOfTwoOrZero(). It prevents potential errors in case of overflow of array sizes. [#13234](https://github.com/ClickHouse/ClickHouse/pull/13234) ([Azat Khuzhin](https://github.com/azat)). * Fix function if with nullable constexpr as cond that is not literal NULL. Fixes [#12463](https://github.com/ClickHouse/ClickHouse/issues/12463). [#13226](https://github.com/ClickHouse/ClickHouse/pull/13226) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix assert in `arrayElement` function in case of array elements are Nullable and array subscript is also Nullable. This fixes [#12172](https://github.com/ClickHouse/ClickHouse/issues/12172). [#13224](https://github.com/ClickHouse/ClickHouse/pull/13224) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix DateTime64 conversion functions with constant argument. [#13205](https://github.com/ClickHouse/ClickHouse/pull/13205) ([Azat Khuzhin](https://github.com/azat)). -* AvroConfluent: Skip Kafka tombstone records - Support skipping broken records ... [#13203](https://github.com/ClickHouse/ClickHouse/pull/13203) ([Andrew Onyshchuk](https://github.com/oandrew)). * Fix parsing row policies from users.xml when names of databases or tables contain dots. This fixes https://github.com/ClickHouse/ClickHouse/issues/5779, https://github.com/ClickHouse/ClickHouse/issues/12527. [#13199](https://github.com/ClickHouse/ClickHouse/pull/13199) ([Vitaly Baranov](https://github.com/vitlibar)). -* Fix segfault when mutation is killed and the server tries to send the exception to the client. [#13169](https://github.com/ClickHouse/ClickHouse/pull/13169) ([alesapin](https://github.com/alesapin)). -* Fix access to redis dictionary after connection was dropped once. It may happen with `cache` and `direct` dictionary layouts. [#13082](https://github.com/ClickHouse/ClickHouse/pull/13082) ([Anton Popov](https://github.com/CurtizJ)). +* Fix access to `redis` dictionary after connection was dropped once. It may happen with `cache` and `direct` dictionary layouts. [#13082](https://github.com/ClickHouse/ClickHouse/pull/13082) ([Anton Popov](https://github.com/CurtizJ)). * Fix wrong index analysis with functions. It could lead to some data parts being skipped when reading from `MergeTree` tables. Fixes [#13060](https://github.com/ClickHouse/ClickHouse/issues/13060). Fixes [#12406](https://github.com/ClickHouse/ClickHouse/issues/12406). [#13081](https://github.com/ClickHouse/ClickHouse/pull/13081) ([Anton Popov](https://github.com/CurtizJ)). * Fix error `Cannot convert column because it is constant but values of constants are different in source and result` for remote queries which use deterministic functions in scope of query, but not deterministic between queries, like `now()`, `now64()`, `randConstant()`. Fixes [#11327](https://github.com/ClickHouse/ClickHouse/issues/11327). [#13075](https://github.com/ClickHouse/ClickHouse/pull/13075) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * Fix crash which was possible for queries with `ORDER BY` tuple and small `LIMIT`. Fixes [#12623](https://github.com/ClickHouse/ClickHouse/issues/12623). [#13009](https://github.com/ClickHouse/ClickHouse/pull/13009) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * Fix `Block structure mismatch` error for queries with `UNION` and `JOIN`. Fixes [#12602](https://github.com/ClickHouse/ClickHouse/issues/12602). [#12989](https://github.com/ClickHouse/ClickHouse/pull/12989) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). -* Corrected merge_with_ttl_timeout logic which did not work well when expiration affected more than one partition over one time interval. (Authored by @excitoon). [#12982](https://github.com/ClickHouse/ClickHouse/pull/12982) ([Alexander Kazakov](https://github.com/Akazz)). +* Corrected `merge_with_ttl_timeout` logic which did not work well when expiration affected more than one partition over one time interval. (Authored by @excitoon). [#12982](https://github.com/ClickHouse/ClickHouse/pull/12982) ([Alexander Kazakov](https://github.com/Akazz)). * Fix columns duplication for range hashed dictionary created from DDL query. This fixes [#10605](https://github.com/ClickHouse/ClickHouse/issues/10605). [#12857](https://github.com/ClickHouse/ClickHouse/pull/12857) ([alesapin](https://github.com/alesapin)). * Fix unnecessary limiting for the number of threads for selects from local replica. [#12840](https://github.com/ClickHouse/ClickHouse/pull/12840) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * Fix rare bug when `ALTER DELETE` and `ALTER MODIFY COLUMN` queries executed simultaneously as a single mutation. Bug leads to an incorrect amount of rows in `count.txt` and as a consequence incorrect data in part. Also, fix a small bug with simultaneous `ALTER RENAME COLUMN` and `ALTER ADD COLUMN`. [#12760](https://github.com/ClickHouse/ClickHouse/pull/12760) ([alesapin](https://github.com/alesapin)). -* Removed wrong auth access check when using ClickHouseDictionarySource to query remote tables. [#12756](https://github.com/ClickHouse/ClickHouse/pull/12756) ([sundyli](https://github.com/sundy-li)). -* Fix CAST(Nullable(String), Enum()). [#12745](https://github.com/ClickHouse/ClickHouse/pull/12745) ([Azat Khuzhin](https://github.com/azat)). +* Removed wrong credentials being used when using `clickhouse` dictionary source to query remote tables. [#12756](https://github.com/ClickHouse/ClickHouse/pull/12756) ([sundyli](https://github.com/sundy-li)). +* Fix `CAST(Nullable(String), Enum())`. [#12745](https://github.com/ClickHouse/ClickHouse/pull/12745) ([Azat Khuzhin](https://github.com/azat)). * Fix performance with large tuples, which are interpreted as functions in `IN` section. The case when user writes `WHERE x IN tuple(1, 2, ...)` instead of `WHERE x IN (1, 2, ...)` for some obscure reason. [#12700](https://github.com/ClickHouse/ClickHouse/pull/12700) ([Anton Popov](https://github.com/CurtizJ)). * Fix memory tracking for input_format_parallel_parsing (by attaching thread to group). [#12672](https://github.com/ClickHouse/ClickHouse/pull/12672) ([Azat Khuzhin](https://github.com/azat)). -* Fix optimization `optimize_move_functions_out_of_any=1` in case of `any(func())`. [#12664](https://github.com/ClickHouse/ClickHouse/pull/12664) ([Artem Zuikov](https://github.com/4ertus2)). -* Fixed [#12293](https://github.com/ClickHouse/ClickHouse/issues/12293) allow push predicate when subquery contains `WITH` clause. [#12663](https://github.com/ClickHouse/ClickHouse/pull/12663) ([Winter Zhang](https://github.com/zhang2014)). +* Fix wrong optimization `optimize_move_functions_out_of_any=1` in case of `any(func())`. [#12664](https://github.com/ClickHouse/ClickHouse/pull/12664) ([Artem Zuikov](https://github.com/4ertus2)). * Fixed [#10572](https://github.com/ClickHouse/ClickHouse/issues/10572) fix bloom filter index with const expression. [#12659](https://github.com/ClickHouse/ClickHouse/pull/12659) ([Winter Zhang](https://github.com/zhang2014)). * Fix SIGSEGV in StorageKafka when broker is unavailable (and not only). [#12658](https://github.com/ClickHouse/ClickHouse/pull/12658) ([Azat Khuzhin](https://github.com/azat)). * Add support for function `if` with `Array(UUID)` arguments. This fixes [#11066](https://github.com/ClickHouse/ClickHouse/issues/11066). [#12648](https://github.com/ClickHouse/ClickHouse/pull/12648) ([alexey-milovidov](https://github.com/alexey-milovidov)). * CREATE USER IF NOT EXISTS now doesn't throw exception if the user exists. This fixes https://github.com/ClickHouse/ClickHouse/issues/12507. [#12646](https://github.com/ClickHouse/ClickHouse/pull/12646) ([Vitaly Baranov](https://github.com/vitlibar)). * Exception `There is no supertype...` can be thrown during `ALTER ... UPDATE` in unexpected cases (e.g. when subtracting from UInt64 column). This fixes [#7306](https://github.com/ClickHouse/ClickHouse/issues/7306). This fixes [#4165](https://github.com/ClickHouse/ClickHouse/issues/4165). [#12633](https://github.com/ClickHouse/ClickHouse/pull/12633) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Better exception message in disk access storage. [#12625](https://github.com/ClickHouse/ClickHouse/pull/12625) ([alesapin](https://github.com/alesapin)). -* Fix error message about adaptive granularity. [#12624](https://github.com/ClickHouse/ClickHouse/pull/12624) ([alesapin](https://github.com/alesapin)). -* The function `groupArrayMoving*` was not working for distributed queries. It's result was calculated within incorrect data type (without promotion to the largest type). The function `groupArrayMovingAvg` was returning integer number that was inconsistent with the `avg` function. This fixes [#12568](https://github.com/ClickHouse/ClickHouse/issues/12568). [#12622](https://github.com/ClickHouse/ClickHouse/pull/12622) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix possible `Pipeline stuck` error for queries with external sorting. Fixes [#12617](https://github.com/ClickHouse/ClickHouse/issues/12617). [#12618](https://github.com/ClickHouse/ClickHouse/pull/12618) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * Fix error `Output of TreeExecutor is not sorted` for `OPTIMIZE DEDUPLICATE`. Fixes [#11572](https://github.com/ClickHouse/ClickHouse/issues/11572). [#12613](https://github.com/ClickHouse/ClickHouse/pull/12613) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). -* Fix lack of aliases with function `any`. [#12593](https://github.com/ClickHouse/ClickHouse/pull/12593) ([Anton Popov](https://github.com/CurtizJ)). -* Fix race condition in external dictionaries with cache layout which can lead server crash. [#12566](https://github.com/ClickHouse/ClickHouse/pull/12566) ([alesapin](https://github.com/alesapin)). +* Fix the issue when alias on result of function `any` can be lost during query optimization. [#12593](https://github.com/ClickHouse/ClickHouse/pull/12593) ([Anton Popov](https://github.com/CurtizJ)). * Remove data for Distributed tables (blocks from async INSERTs) on DROP TABLE. [#12556](https://github.com/ClickHouse/ClickHouse/pull/12556) ([Azat Khuzhin](https://github.com/azat)). * Now ClickHouse will recalculate checksums for parts when file `checksums.txt` is absent. Broken since [#9827](https://github.com/ClickHouse/ClickHouse/issues/9827). [#12545](https://github.com/ClickHouse/ClickHouse/pull/12545) ([alesapin](https://github.com/alesapin)). * Fix bug which lead to broken old parts after `ALTER DELETE` query when `enable_mixed_granularity_parts=1`. Fixes [#12536](https://github.com/ClickHouse/ClickHouse/issues/12536). [#12543](https://github.com/ClickHouse/ClickHouse/pull/12543) ([alesapin](https://github.com/alesapin)). -* Better exception for function `in` with invalid number of arguments. [#12529](https://github.com/ClickHouse/ClickHouse/pull/12529) ([Anton Popov](https://github.com/CurtizJ)). -* Fixing race condition in live view tables which could cause data duplication. [#12519](https://github.com/ClickHouse/ClickHouse/pull/12519) ([vzakaznikov](https://github.com/vzakaznikov)). -* Fixed performance issue, while reading from compact parts. [#12492](https://github.com/ClickHouse/ClickHouse/pull/12492) ([Anton Popov](https://github.com/CurtizJ)). +* Fixing race condition in live view tables which could cause data duplication. LIVE VIEW is an experimental feature. [#12519](https://github.com/ClickHouse/ClickHouse/pull/12519) ([vzakaznikov](https://github.com/vzakaznikov)). * Fix backwards compatibility in binary format of `AggregateFunction(avg, ...)` values. This fixes [#12342](https://github.com/ClickHouse/ClickHouse/issues/12342). [#12486](https://github.com/ClickHouse/ClickHouse/pull/12486) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Fix SETTINGS parse after FORMAT. [#12480](https://github.com/ClickHouse/ClickHouse/pull/12480) ([Azat Khuzhin](https://github.com/azat)). * Fix crash in JOIN with dictionary when we are joining over expression of dictionary key: `t JOIN dict ON expr(dict.id) = t.id`. Disable dictionary join optimisation for this case. [#12458](https://github.com/ClickHouse/ClickHouse/pull/12458) ([Artem Zuikov](https://github.com/4ertus2)). -* SystemLog: do not write to ordinary server log under mutex. This can lead to deadlock if `text_log` is enabled. [#12452](https://github.com/ClickHouse/ClickHouse/pull/12452) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Fix UBSan report in base64 if tests were run on server with AVX-512. This fixes [#12318](https://github.com/ClickHouse/ClickHouse/issues/12318). Author: @qoega. [#12441](https://github.com/ClickHouse/ClickHouse/pull/12441) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix overflow when very large LIMIT or OFFSET is specified. This fixes [#10470](https://github.com/ClickHouse/ClickHouse/issues/10470). This fixes [#11372](https://github.com/ClickHouse/ClickHouse/issues/11372). [#12427](https://github.com/ClickHouse/ClickHouse/pull/12427) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* If MergeTree table does not contain ORDER BY or PARTITION BY, it was possible to request ALTER to CLEAR all the columns and ALTER will stuck. Fixed [#7941](https://github.com/ClickHouse/ClickHouse/issues/7941). [#12382](https://github.com/ClickHouse/ClickHouse/pull/12382) ([alexey-milovidov](https://github.com/alexey-milovidov)). * kafka: fix SIGSEGV if there is a message with error in the middle of the batch. [#12302](https://github.com/ClickHouse/ClickHouse/pull/12302) ([Azat Khuzhin](https://github.com/azat)). #### Improvement +* Keep smaller amount of logs in ZooKeeper. Avoid excessive growing of ZooKeeper nodes in case of offline replicas when having many servers/tables/inserts. [#13100](https://github.com/ClickHouse/ClickHouse/pull/13100) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Now exceptions forwarded to the client if an error happened during ALTER or mutation. Closes [#11329](https://github.com/ClickHouse/ClickHouse/issues/11329). [#12666](https://github.com/ClickHouse/ClickHouse/pull/12666) ([alesapin](https://github.com/alesapin)). +* Add `QueryTimeMicroseconds`, `SelectQueryTimeMicroseconds` and `InsertQueryTimeMicroseconds` to `system.events`, along with system.metrics, processes, query_log, etc. [#13028](https://github.com/ClickHouse/ClickHouse/pull/13028) ([ianton-ru](https://github.com/ianton-ru)). +* Added `SelectedRows` and `SelectedBytes` to `system.events`, along with system.metrics, processes, query_log, etc. [#12638](https://github.com/ClickHouse/ClickHouse/pull/12638) ([ianton-ru](https://github.com/ianton-ru)). +* Added `current_database` information to `system.query_log`. [#12652](https://github.com/ClickHouse/ClickHouse/pull/12652) ([Amos Bird](https://github.com/amosbird)). +* Allow `TabSeparatedRaw` as input format. [#12009](https://github.com/ClickHouse/ClickHouse/pull/12009) ([hcz](https://github.com/hczhcz)). +* Now `joinGet` supports multi-key lookup. [#12418](https://github.com/ClickHouse/ClickHouse/pull/12418) ([Amos Bird](https://github.com/amosbird)). +* Allow `*Map` aggregate functions to work on Arrays with NULLs. Fixes [#13157](https://github.com/ClickHouse/ClickHouse/issues/13157). [#13225](https://github.com/ClickHouse/ClickHouse/pull/13225) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Avoid overflow in parsing of DateTime values that will lead to negative unix timestamp in their timezone (for example, `1970-01-01 00:00:00` in Moscow). Saturate to zero instead. This fixes [#3470](https://github.com/ClickHouse/ClickHouse/issues/3470). This fixes [#4172](https://github.com/ClickHouse/ClickHouse/issues/4172). [#12443](https://github.com/ClickHouse/ClickHouse/pull/12443) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* AvroConfluent: Skip Kafka tombstone records - Support skipping broken records [#13203](https://github.com/ClickHouse/ClickHouse/pull/13203) ([Andrew Onyshchuk](https://github.com/oandrew)). * Fix wrong error for long queries. It was possible to get syntax error other than `Max query size exceeded` for correct query. [#13928](https://github.com/ClickHouse/ClickHouse/pull/13928) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * Fix data race in `lgamma` function. This race was caught only in `tsan`, no side effects really happened. [#13842](https://github.com/ClickHouse/ClickHouse/pull/13842) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). -* Updated gitignore-files. [#13447](https://github.com/ClickHouse/ClickHouse/pull/13447) ([vladimir-golovchenko](https://github.com/vladimir-golovchenko)). * Fix a 'Week'-interval formatting for ATTACH/ALTER/CREATE QUOTA-statements. [#13417](https://github.com/ClickHouse/ClickHouse/pull/13417) ([vladimir-golovchenko](https://github.com/vladimir-golovchenko)). -* Now broken parts are also reported when encountered in compact part processing. [#13282](https://github.com/ClickHouse/ClickHouse/pull/13282) ([Amos Bird](https://github.com/amosbird)). -* Fix assert in geohashesInBox. This fixes [#12554](https://github.com/ClickHouse/ClickHouse/issues/12554). [#13229](https://github.com/ClickHouse/ClickHouse/pull/13229) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Fix assert in parseDateTimeBestEffort. This fixes [#12649](https://github.com/ClickHouse/ClickHouse/issues/12649). [#13227](https://github.com/ClickHouse/ClickHouse/pull/13227) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Allow *Map aggregate functions to work on Arrays with NULLs. Fixes [#13157](https://github.com/ClickHouse/ClickHouse/issues/13157). [#13225](https://github.com/ClickHouse/ClickHouse/pull/13225) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Add sanity check for MergeTree settings. If the settings are incorrect, the server will refuse to start or to create a table, printing detailed explanation to the user. [#13153](https://github.com/ClickHouse/ClickHouse/pull/13153) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Keep smaller amount of logs in ZooKeeper. Avoid excessive growing of ZooKeeper nodes in case of offline replicas when having many servers/tables/inserts. [#13100](https://github.com/ClickHouse/ClickHouse/pull/13100) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Now broken parts are also reported when encountered in compact part processing. Compact parts is an experimental feature. [#13282](https://github.com/ClickHouse/ClickHouse/pull/13282) ([Amos Bird](https://github.com/amosbird)). +* Fix assert in `geohashesInBox`. This fixes [#12554](https://github.com/ClickHouse/ClickHouse/issues/12554). [#13229](https://github.com/ClickHouse/ClickHouse/pull/13229) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix assert in `parseDateTimeBestEffort`. This fixes [#12649](https://github.com/ClickHouse/ClickHouse/issues/12649). [#13227](https://github.com/ClickHouse/ClickHouse/pull/13227) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Minor optimization in Processors/PipelineExecutor: breaking out of a loop because it makes sense to do so. [#13058](https://github.com/ClickHouse/ClickHouse/pull/13058) ([Mark Papadakis](https://github.com/markpapadakis)). -* Add QueryTimeMicroseconds, SelectQueryTimeMicroseconds and InsertQueryTimeMicroseconds to system.events. [#13028](https://github.com/ClickHouse/ClickHouse/pull/13028) ([ianton-ru](https://github.com/ianton-ru)). -* Introduce setting `alter_partition_verbose_result` which outputs information about touched parts for some types of `ALTER TABLE ... PARTITION ...` queries (currently `ATTACH` and `FREEZE`). Closes [#8076](https://github.com/ClickHouse/ClickHouse/issues/8076). [#13017](https://github.com/ClickHouse/ClickHouse/pull/13017) ([alesapin](https://github.com/alesapin)). -* Protect from the cases when user may set `background_pool_size` to value lower than `number_of_free_entries_in_pool_to_execute_mutation` or `number_of_free_entries_in_pool_to_lower_max_size_of_merge`. In these cases ALTERs won't work or the maximum size of merge will be too limited. Saturate values instead. This closes [#10897](https://github.com/ClickHouse/ClickHouse/issues/10897). [#12728](https://github.com/ClickHouse/ClickHouse/pull/12728) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Now exceptions forwarded to the client if an error happened during ALTER or mutation. Closes [#11329](https://github.com/ClickHouse/ClickHouse/issues/11329). [#12666](https://github.com/ClickHouse/ClickHouse/pull/12666) ([alesapin](https://github.com/alesapin)). -* Support truncate table without table keyword. [#12653](https://github.com/ClickHouse/ClickHouse/pull/12653) ([Winter Zhang](https://github.com/zhang2014)). -* Added `current_database` information to `system.query_log`. [#12652](https://github.com/ClickHouse/ClickHouse/pull/12652) ([Amos Bird](https://github.com/amosbird)). -* Added SelectedRows and SelectedBytes events to ProfileEvents. [#12638](https://github.com/ClickHouse/ClickHouse/pull/12638) ([ianton-ru](https://github.com/ianton-ru)). +* Support TRUNCATE table without TABLE keyword. [#12653](https://github.com/ClickHouse/ClickHouse/pull/12653) ([Winter Zhang](https://github.com/zhang2014)). * Fix explain query format overwrite by default, issue https://github.com/ClickHouse/ClickHouse/issues/12432. [#12541](https://github.com/ClickHouse/ClickHouse/pull/12541) ([BohuTANG](https://github.com/BohuTANG)). * Allow to set JOIN kind and type in more standad way: `LEFT SEMI JOIN` instead of `SEMI LEFT JOIN`. For now both are correct. [#12520](https://github.com/ClickHouse/ClickHouse/pull/12520) ([Artem Zuikov](https://github.com/4ertus2)). * Changes default value for `multiple_joins_rewriter_version` to 2. It enables new multiple joins rewriter that knows about column names. [#12469](https://github.com/ClickHouse/ClickHouse/pull/12469) ([Artem Zuikov](https://github.com/4ertus2)). * Add several metrics for requests to S3 storages. [#12464](https://github.com/ClickHouse/ClickHouse/pull/12464) ([ianton-ru](https://github.com/ianton-ru)). -* Avoid overflow in parsing of DateTime values that will lead to negative unix timestamp in their timezone (for example, `1970-01-01 00:00:00` in Moscow). Saturate to zero instead. This fixes [#3470](https://github.com/ClickHouse/ClickHouse/issues/3470). This fixes [#4172](https://github.com/ClickHouse/ClickHouse/issues/4172). [#12443](https://github.com/ClickHouse/ClickHouse/pull/12443) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Use correct default secure port for clickhouse-benchmark with `--secure` argument. This fixes [#11044](https://github.com/ClickHouse/ClickHouse/issues/11044). [#12440](https://github.com/ClickHouse/ClickHouse/pull/12440) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Rollback insertion errors in `Log`, `TinyLog`, `StripeLog` engines. In previous versions insertion error lead to inconsisent table state (this works as documented and it is normal for these table engines). This fixes [#12402](https://github.com/ClickHouse/ClickHouse/issues/12402). [#12426](https://github.com/ClickHouse/ClickHouse/pull/12426) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Now joinGet supports multi-key lookup. [#12418](https://github.com/ClickHouse/ClickHouse/pull/12418) ([Amos Bird](https://github.com/amosbird)). -* - Implement `RENAME DATABASE` and `RENAME DICTIONARY` for `Atomic` database engine - Add implicit `{uuid}` macro, which can be used in ZooKeeper path for `ReplicatedMergeTree`. It works with `CREATE ... ON CLUSTER ...` queries. Set `show_table_uuid_in_table_create_query_if_not_nil` to `true` to use it. - Make `ReplicatedMergeTree` engine arguments optional, `/clickhouse/tables/{uuid}/{shard}/` and `{replica}` are used by default. Closes [#12135](https://github.com/ClickHouse/ClickHouse/issues/12135). - Minor fixes. - These changes break backward compatibility of `Atomic` database engine. Previously created `Atomic` databases must be manually converted to new format. [#12343](https://github.com/ClickHouse/ClickHouse/pull/12343) ([tavplubix](https://github.com/tavplubix)). -* Separated `AWSAuthV4Signer` into different logger, removed excessive "AWSClient: AWSClient". [#12320](https://github.com/ClickHouse/ClickHouse/pull/12320) ([Vladimir Chebotarev](https://github.com/excitoon)). -* Allow TabSeparatedRaw as input format. [#12009](https://github.com/ClickHouse/ClickHouse/pull/12009) ([hcz](https://github.com/hczhcz)). -* Adds a new type of polygon dictionary which uses a recursively built grid to reduce the number of polygons which need to be checked for each point. [#9278](https://github.com/ClickHouse/ClickHouse/pull/9278) ([achulkov2](https://github.com/achulkov2)). +* Implement `RENAME DATABASE` and `RENAME DICTIONARY` for `Atomic` database engine - Add implicit `{uuid}` macro, which can be used in ZooKeeper path for `ReplicatedMergeTree`. It works with `CREATE ... ON CLUSTER ...` queries. Set `show_table_uuid_in_table_create_query_if_not_nil` to `true` to use it. - Make `ReplicatedMergeTree` engine arguments optional, `/clickhouse/tables/{uuid}/{shard}/` and `{replica}` are used by default. Closes [#12135](https://github.com/ClickHouse/ClickHouse/issues/12135). - Minor fixes. - These changes break backward compatibility of `Atomic` database engine. Previously created `Atomic` databases must be manually converted to new format. Atomic database is an experimental feature. [#12343](https://github.com/ClickHouse/ClickHouse/pull/12343) ([tavplubix](https://github.com/tavplubix)). +* Separated `AWSAuthV4Signer` into different logger, removed excessive `AWSClient: AWSClient` from log messages. [#12320](https://github.com/ClickHouse/ClickHouse/pull/12320) ([Vladimir Chebotarev](https://github.com/excitoon)). +* Better exception message in disk access storage. [#12625](https://github.com/ClickHouse/ClickHouse/pull/12625) ([alesapin](https://github.com/alesapin)). +* Better exception for function `in` with invalid number of arguments. [#12529](https://github.com/ClickHouse/ClickHouse/pull/12529) ([Anton Popov](https://github.com/CurtizJ)). +* Fix error message about adaptive granularity. [#12624](https://github.com/ClickHouse/ClickHouse/pull/12624) ([alesapin](https://github.com/alesapin)). +* Fix SETTINGS parse after FORMAT. [#12480](https://github.com/ClickHouse/ClickHouse/pull/12480) ([Azat Khuzhin](https://github.com/azat)). +* If MergeTree table does not contain ORDER BY or PARTITION BY, it was possible to request ALTER to CLEAR all the columns and ALTER will stuck. Fixed [#7941](https://github.com/ClickHouse/ClickHouse/issues/7941). [#12382](https://github.com/ClickHouse/ClickHouse/pull/12382) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Avoid re-loading completion from the history file after each query (to avoid history overlaps with other client sessions). [#13086](https://github.com/ClickHouse/ClickHouse/pull/13086) ([Azat Khuzhin](https://github.com/azat)). #### Performance Improvement -* Slightly optimize very short queries with LowCardinality. [#14129](https://github.com/ClickHouse/ClickHouse/pull/14129) ([Anton Popov](https://github.com/CurtizJ)). -* Slightly improve performance of aggregation by UInt8/UInt16 keys. [#13091](https://github.com/ClickHouse/ClickHouse/pull/13091) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Slightly improve performance of aggregation by UInt8/UInt16 keys. [#13055](https://github.com/ClickHouse/ClickHouse/pull/13055) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Push down `LIMIT` step for query plan. [#13016](https://github.com/ClickHouse/ClickHouse/pull/13016) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). -* Parallel PK lookup and skipping index stages on parts, as described in [#11564](https://github.com/ClickHouse/ClickHouse/issues/11564). [#12589](https://github.com/ClickHouse/ClickHouse/pull/12589) ([Ivan Babrou](https://github.com/bobrik)). -* Converts String-type arguments of function "if" and "transform" into enum if `set optimize_if_transform_strings_to_enum = 1`. [#12515](https://github.com/ClickHouse/ClickHouse/pull/12515) ([Artem Zuikov](https://github.com/4ertus2)). -* Replaces monotonous functions with its argument in `ORDER BY` if `set optimize_monotonous_functions_in_order_by=1`. [#12467](https://github.com/ClickHouse/ClickHouse/pull/12467) ([Artem Zuikov](https://github.com/4ertus2)). -* Attempt to implement streaming optimization in `DiskS3`. [#12434](https://github.com/ClickHouse/ClickHouse/pull/12434) ([Vladimir Chebotarev](https://github.com/excitoon)). * Lower memory usage for some operations up to 2 times. [#12424](https://github.com/ClickHouse/ClickHouse/pull/12424) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Add order by optimisation that rewrites `ORDER BY x, f(x)` with `ORDER by x` if `set optimize_redundant_functions_in_order_by = 1`. [#12404](https://github.com/ClickHouse/ClickHouse/pull/12404) ([Artem Zuikov](https://github.com/4ertus2)). * Optimize PK lookup for queries that match exact PK range. [#12277](https://github.com/ClickHouse/ClickHouse/pull/12277) ([Ivan Babrou](https://github.com/bobrik)). +* Slightly optimize very short queries with `LowCardinality`. [#14129](https://github.com/ClickHouse/ClickHouse/pull/14129) ([Anton Popov](https://github.com/CurtizJ)). +* Slightly improve performance of aggregation by UInt8/UInt16 keys. [#13091](https://github.com/ClickHouse/ClickHouse/pull/13091) and [#13055](https://github.com/ClickHouse/ClickHouse/pull/13055) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Push down `LIMIT` step for query plan (inside subqueries). [#13016](https://github.com/ClickHouse/ClickHouse/pull/13016) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). +* Parallel primary key lookup and skipping index stages on parts, as described in [#11564](https://github.com/ClickHouse/ClickHouse/issues/11564). [#12589](https://github.com/ClickHouse/ClickHouse/pull/12589) ([Ivan Babrou](https://github.com/bobrik)). +* Converting String-type arguments of function "if" and "transform" into enum if `set optimize_if_transform_strings_to_enum = 1`. [#12515](https://github.com/ClickHouse/ClickHouse/pull/12515) ([Artem Zuikov](https://github.com/4ertus2)). +* Replaces monotonic functions with its argument in `ORDER BY` if `set optimize_monotonous_functions_in_order_by=1`. [#12467](https://github.com/ClickHouse/ClickHouse/pull/12467) ([Artem Zuikov](https://github.com/4ertus2)). +* Add order by optimization that rewrites `ORDER BY x, f(x)` with `ORDER by x` if `set optimize_redundant_functions_in_order_by = 1`. [#12404](https://github.com/ClickHouse/ClickHouse/pull/12404) ([Artem Zuikov](https://github.com/4ertus2)). +* Allow pushdown predicate when subquery contains `WITH` clause. This fixes [#12293](https://github.com/ClickHouse/ClickHouse/issues/12293) [#12663](https://github.com/ClickHouse/ClickHouse/pull/12663) ([Winter Zhang](https://github.com/zhang2014)). +* Improve performance of reading from compact parts. Compact parts is an experimental feature. [#12492](https://github.com/ClickHouse/ClickHouse/pull/12492) ([Anton Popov](https://github.com/CurtizJ)). +* Attempt to implement streaming optimization in `DiskS3`. DiskS3 is an experimental feature. [#12434](https://github.com/ClickHouse/ClickHouse/pull/12434) ([Vladimir Chebotarev](https://github.com/excitoon)). #### Build/Testing/Packaging Improvement -* Ensure that all the submodules are from proper URLs. Continuation of [#13379](https://github.com/ClickHouse/ClickHouse/issues/13379). This fixes [#13378](https://github.com/ClickHouse/ClickHouse/issues/13378). [#13397](https://github.com/ClickHouse/ClickHouse/pull/13397) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Use `shellcheck` for sh tests linting. [#13200](https://github.com/ClickHouse/ClickHouse/pull/13200)[#13207](https://github.com/ClickHouse/ClickHouse/pull/13207) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Add script which set labels for pull requests in GitHub hook. [#13183](https://github.com/ClickHouse/ClickHouse/pull/13183) ([alesapin](https://github.com/alesapin)). * Remove some of recursive submodules. See [#13378](https://github.com/ClickHouse/ClickHouse/issues/13378). [#13379](https://github.com/ClickHouse/ClickHouse/pull/13379) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* - Added testing for RBAC functionality of INSERT privilege in TestFlows. - Expanded tables on which SELECT is being tested. - Added Requirements to match new table engine tests. [#13340](https://github.com/ClickHouse/ClickHouse/pull/13340) ([MyroTk](https://github.com/MyroTk)). +* Ensure that all the submodules are from proper URLs. Continuation of [#13379](https://github.com/ClickHouse/ClickHouse/issues/13379). This fixes [#13378](https://github.com/ClickHouse/ClickHouse/issues/13378). [#13397](https://github.com/ClickHouse/ClickHouse/pull/13397) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Added support for user-declared settings, which can be accessed from inside queries. This is needed when ClickHouse engine is used as a component of another system. [#13013](https://github.com/ClickHouse/ClickHouse/pull/13013) ([Vitaly Baranov](https://github.com/vitlibar)). +* Added testing for RBAC functionality of INSERT privilege in TestFlows. Expanded tables on which SELECT is being tested. Added Requirements to match new table engine tests. [#13340](https://github.com/ClickHouse/ClickHouse/pull/13340) ([MyroTk](https://github.com/MyroTk)). * Fix timeout error during server restart in the stress test. [#13321](https://github.com/ClickHouse/ClickHouse/pull/13321) ([alesapin](https://github.com/alesapin)). -* Applying LDAP authentication test fixes. [#13310](https://github.com/ClickHouse/ClickHouse/pull/13310) ([vzakaznikov](https://github.com/vzakaznikov)). * Now fast test will wait server with retries. [#13284](https://github.com/ClickHouse/ClickHouse/pull/13284) ([alesapin](https://github.com/alesapin)). * Function `materialize()` (the function for ClickHouse testing) will work for NULL as expected - by transforming it to non-constant column. [#13212](https://github.com/ClickHouse/ClickHouse/pull/13212) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Fix libunwind build in AArch64. This fixes [#13204](https://github.com/ClickHouse/ClickHouse/issues/13204). [#13208](https://github.com/ClickHouse/ClickHouse/pull/13208) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Use `shellcheck` for sh tests linting. [#13200](https://github.com/ClickHouse/ClickHouse/pull/13200)[#13207](https://github.com/ClickHouse/ClickHouse/pull/13207) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Add script which set labels for pull requests in GitHub hook. [#13183](https://github.com/ClickHouse/ClickHouse/pull/13183) ([alesapin](https://github.com/alesapin)). * Even more retries in zkutil gtest to prevent test flakiness. [#13165](https://github.com/ClickHouse/ClickHouse/pull/13165) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Small fixes to the RBAC SRS. [#13152](https://github.com/ClickHouse/ClickHouse/pull/13152) ([vzakaznikov](https://github.com/vzakaznikov)). -* Fixing 00960_live_view_watch_events_live.py test. [#13108](https://github.com/ClickHouse/ClickHouse/pull/13108) ([vzakaznikov](https://github.com/vzakaznikov)). +* Small fixes to the RBAC TestFlows. [#13152](https://github.com/ClickHouse/ClickHouse/pull/13152) ([vzakaznikov](https://github.com/vzakaznikov)). +* Fixing `00960_live_view_watch_events_live.py` test. [#13108](https://github.com/ClickHouse/ClickHouse/pull/13108) ([vzakaznikov](https://github.com/vzakaznikov)). * Improve cache purge in documentation deploy script. [#13107](https://github.com/ClickHouse/ClickHouse/pull/13107) ([alesapin](https://github.com/alesapin)). -* Rewrote Function tests to gtest. Removed useless includes from tests. [#13073](https://github.com/ClickHouse/ClickHouse/pull/13073) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). +* Rewrote some orphan tests to gtest. Removed useless includes from tests. [#13073](https://github.com/ClickHouse/ClickHouse/pull/13073) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)). * Added tests for RBAC functionality of `SELECT` privilege in TestFlows. [#13061](https://github.com/ClickHouse/ClickHouse/pull/13061) ([Ritaank Tiwari](https://github.com/ritaank)). -* Adding extra xfails for some ldap tests. [#13054](https://github.com/ClickHouse/ClickHouse/pull/13054) ([vzakaznikov](https://github.com/vzakaznikov)). * Rerun some tests in fast test check. [#12992](https://github.com/ClickHouse/ClickHouse/pull/12992) ([alesapin](https://github.com/alesapin)). * Fix MSan error in "rdkafka" library. This closes [#12990](https://github.com/ClickHouse/ClickHouse/issues/12990). Updated `rdkafka` to version 1.5 (master). [#12991](https://github.com/ClickHouse/ClickHouse/pull/12991) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix UBSan report in base64 if tests were run on server with AVX-512. This fixes [#12318](https://github.com/ClickHouse/ClickHouse/issues/12318). Author: @qoega. [#12441](https://github.com/ClickHouse/ClickHouse/pull/12441) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Fix UBSan report in HDFS library. This closes [#12330](https://github.com/ClickHouse/ClickHouse/issues/12330). [#12453](https://github.com/ClickHouse/ClickHouse/pull/12453) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Check an ability that we able to restore the backup from an old version to the new version. This closes [#8979](https://github.com/ClickHouse/ClickHouse/issues/8979). [#12959](https://github.com/ClickHouse/ClickHouse/pull/12959) ([alesapin](https://github.com/alesapin)). * Do not build helper_container image inside integrational tests. Build docker container in CI and use pre-built helper_container in integration tests. [#12953](https://github.com/ClickHouse/ClickHouse/pull/12953) ([Ilya Yatsishin](https://github.com/qoega)). * Add a test for `ALTER TABLE CLEAR COLUMN` query for primary key columns. [#12951](https://github.com/ClickHouse/ClickHouse/pull/12951) ([alesapin](https://github.com/alesapin)). * Increased timeouts in testflows tests. [#12949](https://github.com/ClickHouse/ClickHouse/pull/12949) ([vzakaznikov](https://github.com/vzakaznikov)). * Fix build of test under Mac OS X. This closes [#12767](https://github.com/ClickHouse/ClickHouse/issues/12767). [#12772](https://github.com/ClickHouse/ClickHouse/pull/12772) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Connector-ODBC updated to mysql-connector-odbc-8.0.21. [#12739](https://github.com/ClickHouse/ClickHouse/pull/12739) ([Ilya Yatsishin](https://github.com/qoega)). -* Apply random query mutations (fuzzing) in stress tests. [#12734](https://github.com/ClickHouse/ClickHouse/pull/12734) ([Alexander Kuzmenkov](https://github.com/akuzm)). * Adding RBAC syntax tests in TestFlows. [#12642](https://github.com/ClickHouse/ClickHouse/pull/12642) ([vzakaznikov](https://github.com/vzakaznikov)). * Improve performance of TestKeeper. This will speedup tests with heavy usage of Replicated tables. [#12505](https://github.com/ClickHouse/ClickHouse/pull/12505) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Now we check that server is able to start after stress tests run. This fixes [#12473](https://github.com/ClickHouse/ClickHouse/issues/12473). [#12496](https://github.com/ClickHouse/ClickHouse/pull/12496) ([alesapin](https://github.com/alesapin)). -* Add PEERDIR(protoc) as protobuf format parses .proto file in runtime. [#12475](https://github.com/ClickHouse/ClickHouse/pull/12475) ([Yuriy Chernyshov](https://github.com/georgthegreat)). -* Fix UBSan report in HDFS library. This closes [#12330](https://github.com/ClickHouse/ClickHouse/issues/12330). [#12453](https://github.com/ClickHouse/ClickHouse/pull/12453) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Update fmtlib to master (7.0.1). [#12446](https://github.com/ClickHouse/ClickHouse/pull/12446) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Add docker image for fast tests. [#12294](https://github.com/ClickHouse/ClickHouse/pull/12294) ([alesapin](https://github.com/alesapin)). * Rework configuration paths for integration tests. [#12285](https://github.com/ClickHouse/ClickHouse/pull/12285) ([Ilya Yatsishin](https://github.com/qoega)). * Add compiler option to control that stack frames are not too large. This will help to run the code in fibers with small stack size. [#11524](https://github.com/ClickHouse/ClickHouse/pull/11524) ([alexey-milovidov](https://github.com/alexey-milovidov)). - -#### Other - -* Avoid re-loading completion from the history file after each query (to avoid history overlaps with other client sessions). [#13086](https://github.com/ClickHouse/ClickHouse/pull/13086) ([Azat Khuzhin](https://github.com/azat)). +* Update gitignore-files. [#13447](https://github.com/ClickHouse/ClickHouse/pull/13447) ([vladimir-golovchenko](https://github.com/vladimir-golovchenko)). ## ClickHouse release 20.6 From 6e004ac26fe36dfe5498112dd7f65405dd3955e2 Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Thu, 3 Sep 2020 00:27:54 +0300 Subject: [PATCH 67/73] Update CHANGELOG.md --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index ec816caefe5..516fe99ddff 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -81,7 +81,7 @@ * Fix columns duplication for range hashed dictionary created from DDL query. This fixes [#10605](https://github.com/ClickHouse/ClickHouse/issues/10605). [#12857](https://github.com/ClickHouse/ClickHouse/pull/12857) ([alesapin](https://github.com/alesapin)). * Fix unnecessary limiting for the number of threads for selects from local replica. [#12840](https://github.com/ClickHouse/ClickHouse/pull/12840) ([Nikolai Kochetov](https://github.com/KochetovNicolai)). * Fix rare bug when `ALTER DELETE` and `ALTER MODIFY COLUMN` queries executed simultaneously as a single mutation. Bug leads to an incorrect amount of rows in `count.txt` and as a consequence incorrect data in part. Also, fix a small bug with simultaneous `ALTER RENAME COLUMN` and `ALTER ADD COLUMN`. [#12760](https://github.com/ClickHouse/ClickHouse/pull/12760) ([alesapin](https://github.com/alesapin)). -* Removed wrong credentials being used when using `clickhouse` dictionary source to query remote tables. [#12756](https://github.com/ClickHouse/ClickHouse/pull/12756) ([sundyli](https://github.com/sundy-li)). +* Wrong credentials being used when using `clickhouse` dictionary source to query remote tables. [#12756](https://github.com/ClickHouse/ClickHouse/pull/12756) ([sundyli](https://github.com/sundy-li)). * Fix `CAST(Nullable(String), Enum())`. [#12745](https://github.com/ClickHouse/ClickHouse/pull/12745) ([Azat Khuzhin](https://github.com/azat)). * Fix performance with large tuples, which are interpreted as functions in `IN` section. The case when user writes `WHERE x IN tuple(1, 2, ...)` instead of `WHERE x IN (1, 2, ...)` for some obscure reason. [#12700](https://github.com/ClickHouse/ClickHouse/pull/12700) ([Anton Popov](https://github.com/CurtizJ)). * Fix memory tracking for input_format_parallel_parsing (by attaching thread to group). [#12672](https://github.com/ClickHouse/ClickHouse/pull/12672) ([Azat Khuzhin](https://github.com/azat)). From 85cfebe47d82cb7017d91279d1384dc665272deb Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Thu, 3 Sep 2020 00:32:32 +0300 Subject: [PATCH 68/73] Update CHANGELOG.md --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 516fe99ddff..2d3f195f3a2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,7 +8,7 @@ * Deprecate special printing of zero Date/DateTime values as `0000-00-00` and `0000-00-00 00:00:00`. [#12442](https://github.com/ClickHouse/ClickHouse/pull/12442) ([alexey-milovidov](https://github.com/alexey-milovidov)). * The function `groupArrayMoving*` was not working for distributed queries. It's result was calculated within incorrect data type (without promotion to the largest type). The function `groupArrayMovingAvg` was returning integer number that was inconsistent with the `avg` function. This fixes [#12568](https://github.com/ClickHouse/ClickHouse/issues/12568). [#12622](https://github.com/ClickHouse/ClickHouse/pull/12622) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Add sanity check for MergeTree settings. If the settings are incorrect, the server will refuse to start or to create a table, printing detailed explanation to the user. [#13153](https://github.com/ClickHouse/ClickHouse/pull/13153) ([alexey-milovidov](https://github.com/alexey-milovidov)). -* Protect from the cases when user may set `background_pool_size` to value lower than `number_of_free_entries_in_pool_to_execute_mutation` or `number_of_free_entries_in_pool_to_lower_max_size_of_merge`. In these cases ALTERs won't work or the maximum size of merge will be too limited. Saturate values instead. This closes [#10897](https://github.com/ClickHouse/ClickHouse/issues/10897). [#12728](https://github.com/ClickHouse/ClickHouse/pull/12728) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Protect from the cases when user may set `background_pool_size` to value lower than `number_of_free_entries_in_pool_to_execute_mutation` or `number_of_free_entries_in_pool_to_lower_max_size_of_merge`. In these cases ALTERs won't work or the maximum size of merge will be too limited. It will throw exception explaining what to do. This closes [#10897](https://github.com/ClickHouse/ClickHouse/issues/10897). [#12728](https://github.com/ClickHouse/ClickHouse/pull/12728) ([alexey-milovidov](https://github.com/alexey-milovidov)). #### New Feature From 76aa1d15adcfc9745f730b1294d9378358f18de7 Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Thu, 3 Sep 2020 00:33:02 +0300 Subject: [PATCH 69/73] Update CHANGELOG.md --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 2d3f195f3a2..950bdc7e374 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -155,7 +155,7 @@ #### Build/Testing/Packaging Improvement -* Use `shellcheck` for sh tests linting. [#13200](https://github.com/ClickHouse/ClickHouse/pull/13200)[#13207](https://github.com/ClickHouse/ClickHouse/pull/13207) ([alexey-milovidov](https://github.com/alexey-milovidov)). +* Use `shellcheck` for sh tests linting. [#13200](https://github.com/ClickHouse/ClickHouse/pull/13200) [#13207](https://github.com/ClickHouse/ClickHouse/pull/13207) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Add script which set labels for pull requests in GitHub hook. [#13183](https://github.com/ClickHouse/ClickHouse/pull/13183) ([alesapin](https://github.com/alesapin)). * Remove some of recursive submodules. See [#13378](https://github.com/ClickHouse/ClickHouse/issues/13378). [#13379](https://github.com/ClickHouse/ClickHouse/pull/13379) ([alexey-milovidov](https://github.com/alexey-milovidov)). * Ensure that all the submodules are from proper URLs. Continuation of [#13379](https://github.com/ClickHouse/ClickHouse/issues/13379). This fixes [#13378](https://github.com/ClickHouse/ClickHouse/issues/13378). [#13397](https://github.com/ClickHouse/ClickHouse/pull/13397) ([alexey-milovidov](https://github.com/alexey-milovidov)). From 4b1b744644ad78c58acb5171d9738c77ade7f9b0 Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Thu, 3 Sep 2020 01:00:41 +0300 Subject: [PATCH 70/73] Revert "Less number of threads in builder" --- debian/rules | 2 +- src/Dictionaries/BucketCache.h | 13 ++++++------- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/debian/rules b/debian/rules index e9882a09e76..5b271a8691f 100755 --- a/debian/rules +++ b/debian/rules @@ -18,7 +18,7 @@ ifeq ($(CCACHE_PREFIX),distcc) THREADS_COUNT=$(shell distcc -j) endif ifeq ($(THREADS_COUNT),) - THREADS_COUNT=$(shell $$(( $$(nproc || grep -c ^processor /proc/cpuinfo || sysctl -n hw.ncpu || echo 8) / 2 )) ) + THREADS_COUNT=$(shell nproc || grep -c ^processor /proc/cpuinfo || sysctl -n hw.ncpu || echo 4) endif DEB_BUILD_OPTIONS+=parallel=$(THREADS_COUNT) diff --git a/src/Dictionaries/BucketCache.h b/src/Dictionaries/BucketCache.h index c7dec12c3e4..381110066a6 100644 --- a/src/Dictionaries/BucketCache.h +++ b/src/Dictionaries/BucketCache.h @@ -30,13 +30,12 @@ struct Int64Hasher }; -/** - * Class for storing cache index. - * It consists of two arrays. - * The first one is split into buckets (each stores 8 elements (cells)) determined by hash of the element key. - * The second one is split into 4bit numbers, which are positions in bucket for next element write - * (So cache uses FIFO eviction algorithm inside each bucket). - */ +/* + Class for storing cache index. + It consists of two arrays. + The first one is split into buckets (each stores 8 elements (cells)) determined by hash of the element key. + The second one is split into 4bit numbers, which are positions in bucket for next element write (So cache uses FIFO eviction algorithm inside each bucket). +*/ template class BucketCacheIndex { From b3addcd5cac93888fffde344dd5b36160502ed5e Mon Sep 17 00:00:00 2001 From: Alexey Milovidov Date: Thu, 3 Sep 2020 02:23:22 +0300 Subject: [PATCH 71/73] Fix error --- debian/rules | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/debian/rules b/debian/rules index e9882a09e76..ffe1f9e1228 100755 --- a/debian/rules +++ b/debian/rules @@ -18,7 +18,7 @@ ifeq ($(CCACHE_PREFIX),distcc) THREADS_COUNT=$(shell distcc -j) endif ifeq ($(THREADS_COUNT),) - THREADS_COUNT=$(shell $$(( $$(nproc || grep -c ^processor /proc/cpuinfo || sysctl -n hw.ncpu || echo 8) / 2 )) ) + THREADS_COUNT=$(shell echo $$(( $$(nproc || grep -c ^processor /proc/cpuinfo || sysctl -n hw.ncpu || echo 8) / 2 )) ) endif DEB_BUILD_OPTIONS+=parallel=$(THREADS_COUNT) From 821add088e4f4573656d6050ff585c9b04d5990e Mon Sep 17 00:00:00 2001 From: alexey-milovidov Date: Thu, 3 Sep 2020 09:57:01 +0300 Subject: [PATCH 72/73] Fix backport script; read the code (#14433) --- utils/github/backport.py | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/utils/github/backport.py b/utils/github/backport.py index 36f40d08623..3a33c3a563f 100644 --- a/utils/github/backport.py +++ b/utils/github/backport.py @@ -20,7 +20,7 @@ class Backport: def getPullRequests(self, from_commit): return self._gh.get_pull_requests(from_commit) - def execute(self, repo, til, number, run_cherrypick): + def execute(self, repo, until_commit, number, run_cherrypick): repo = LocalRepo(repo, 'origin', self.default_branch_name) branches = repo.get_release_branches()[-number:] # [(branch_name, base_commit)] @@ -31,9 +31,9 @@ class Backport: for branch in branches: logging.info('Found release branch: %s', branch[0]) - if not til: - til = branches[0][1] - prs = self.getPullRequests(til) + if not until_commit: + until_commit = branches[0][1] + pull_requests = self.getPullRequests(until_commit) backport_map = {} @@ -42,7 +42,7 @@ class Backport: RE_BACKPORTED = re.compile(r'^v(\d+\.\d+)-backported$') # pull-requests are sorted by ancestry from the least recent. - for pr in prs: + for pr in pull_requests: while repo.comparator(branches[-1][1]) >= repo.comparator(pr['mergeCommit']['oid']): logging.info("PR #{} is already inside {}. Dropping this branch for further PRs".format(pr['number'], branches[-1][0])) branches.pop() @@ -55,28 +55,28 @@ class Backport: # First pass. Find all must-backports for label in pr['labels']['nodes']: - if label['name'].startswith('pr-') and label['color'] == 'ff0000': + if label['name'] == 'pr-bugfix': backport_map[pr['number']] = branch_set.copy() continue - m = RE_MUST_BACKPORT.match(label['name']) - if m: + matched = RE_MUST_BACKPORT.match(label['name']) + if matched: if pr['number'] not in backport_map: backport_map[pr['number']] = set() - backport_map[pr['number']].add(m.group(1)) + backport_map[pr['number']].add(matched.group(1)) # Second pass. Find all no-backports for label in pr['labels']['nodes']: if label['name'] == 'pr-no-backport' and pr['number'] in backport_map: del backport_map[pr['number']] break - m1 = RE_NO_BACKPORT.match(label['name']) - m2 = RE_BACKPORTED.match(label['name']) - if m1 and pr['number'] in backport_map and m1.group(1) in backport_map[pr['number']]: - backport_map[pr['number']].remove(m1.group(1)) - logging.info('\tskipping %s because of forced no-backport', m1.group(1)) - elif m2 and pr['number'] in backport_map and m2.group(1) in backport_map[pr['number']]: - backport_map[pr['number']].remove(m2.group(1)) - logging.info('\tskipping %s because it\'s already backported manually', m2.group(1)) + matched_no_backport = RE_NO_BACKPORT.match(label['name']) + matched_backported = RE_BACKPORTED.match(label['name']) + if matched_no_backport and pr['number'] in backport_map and matched_no_backport.group(1) in backport_map[pr['number']]: + backport_map[pr['number']].remove(matched_no_backport.group(1)) + logging.info('\tskipping %s because of forced no-backport', matched_no_backport.group(1)) + elif matched_backported and pr['number'] in backport_map and matched_backported.group(1) in backport_map[pr['number']]: + backport_map[pr['number']].remove(matched_backported.group(1)) + logging.info('\tskipping %s because it\'s already backported manually', matched_backported.group(1)) for pr, branches in backport_map.items(): logging.info('PR #%s needs to be backported to:', pr) From acc0ee06575c2edf6cc6f48eb394462cb92554f1 Mon Sep 17 00:00:00 2001 From: alesapin Date: Thu, 3 Sep 2020 11:59:41 +0300 Subject: [PATCH 73/73] Apply TTL if it's not calculated for part --- src/Storages/MergeTree/IMergeTreeDataPart.cpp | 31 ++++++++++++++++ src/Storages/MergeTree/IMergeTreeDataPart.h | 5 +++ .../MergeTree/MergeTreeDataMergerMutator.cpp | 11 +++++- .../MergeTree/MergeTreeDataPartTTLInfo.h | 4 +- ...01471_calculate_ttl_during_merge.reference | 5 +++ .../01471_calculate_ttl_during_merge.sql | 37 +++++++++++++++++++ 6 files changed, 90 insertions(+), 3 deletions(-) create mode 100644 tests/queries/0_stateless/01471_calculate_ttl_during_merge.reference create mode 100644 tests/queries/0_stateless/01471_calculate_ttl_during_merge.sql diff --git a/src/Storages/MergeTree/IMergeTreeDataPart.cpp b/src/Storages/MergeTree/IMergeTreeDataPart.cpp index 66fcac49861..872e34adb83 100644 --- a/src/Storages/MergeTree/IMergeTreeDataPart.cpp +++ b/src/Storages/MergeTree/IMergeTreeDataPart.cpp @@ -1042,6 +1042,37 @@ void IMergeTreeDataPart::accumulateColumnSizes(ColumnToSize & column_to_size) co column_to_size[column_name] = size.data_compressed; } + +bool IMergeTreeDataPart::checkAllTTLCalculated(const StorageMetadataPtr & metadata_snapshot) const +{ + if (!metadata_snapshot->hasAnyTTL()) + return false; + + if (metadata_snapshot->hasRowsTTL()) + { + if (isEmpty()) /// All rows were finally deleted and we don't store TTL + return true; + else if (ttl_infos.table_ttl.min == 0) + return false; + } + + for (const auto & [column, desc] : metadata_snapshot->getColumnTTLs()) + { + /// Part has this column, but we don't calculated TTL for it + if (!ttl_infos.columns_ttl.count(column) && getColumns().contains(column)) + return false; + } + + for (const auto & move_desc : metadata_snapshot->getMoveTTLs()) + { + /// Move TTL is not calculated + if (!ttl_infos.moves_ttl.count(move_desc.result_column)) + return false; + } + + return true; +} + bool isCompactPart(const MergeTreeDataPartPtr & data_part) { return (data_part && data_part->getType() == MergeTreeDataPartType::COMPACT); diff --git a/src/Storages/MergeTree/IMergeTreeDataPart.h b/src/Storages/MergeTree/IMergeTreeDataPart.h index 35e82e0e94a..7df0468dc13 100644 --- a/src/Storages/MergeTree/IMergeTreeDataPart.h +++ b/src/Storages/MergeTree/IMergeTreeDataPart.h @@ -344,6 +344,11 @@ public: static inline constexpr auto DELETE_ON_DESTROY_MARKER_FILE_NAME = "delete-on-destroy.txt"; + /// Checks that all TTLs (table min/max, column ttls, so on) for part + /// calculated. Part without calculated TTL may exist if TTL was added after + /// part creation (using alter query with materialize_ttl setting). + bool checkAllTTLCalculated(const StorageMetadataPtr & metadata_snapshot) const; + protected: /// Total size of all columns, calculated once in calcuateColumnSizesOnDisk diff --git a/src/Storages/MergeTree/MergeTreeDataMergerMutator.cpp b/src/Storages/MergeTree/MergeTreeDataMergerMutator.cpp index 673ad02bfb6..c2c92d0a097 100644 --- a/src/Storages/MergeTree/MergeTreeDataMergerMutator.cpp +++ b/src/Storages/MergeTree/MergeTreeDataMergerMutator.cpp @@ -635,8 +635,17 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataMergerMutator::mergePartsToTempor new_data_part->is_temp = true; bool need_remove_expired_values = false; + bool force_ttl = false; for (const auto & part : parts) + { new_data_part->ttl_infos.update(part->ttl_infos); + if (metadata_snapshot->hasAnyTTL() && !part->checkAllTTLCalculated(metadata_snapshot)) + { + LOG_INFO(log, "Some TTL values were not calculated for part {}. Will calculate them forcefully during merge.", part->name); + need_remove_expired_values = true; + force_ttl = true; + } + } const auto & part_min_ttl = new_data_part->ttl_infos.part_min_ttl; if (part_min_ttl && part_min_ttl <= time_of_merge) @@ -809,7 +818,7 @@ MergeTreeData::MutableDataPartPtr MergeTreeDataMergerMutator::mergePartsToTempor merged_stream = std::make_shared(merged_stream, sort_description, SizeLimits(), 0 /*limit_hint*/, Names()); if (need_remove_expired_values) - merged_stream = std::make_shared(merged_stream, data, metadata_snapshot, new_data_part, time_of_merge, false); + merged_stream = std::make_shared(merged_stream, data, metadata_snapshot, new_data_part, time_of_merge, force_ttl); if (metadata_snapshot->hasSecondaryIndices()) diff --git a/src/Storages/MergeTree/MergeTreeDataPartTTLInfo.h b/src/Storages/MergeTree/MergeTreeDataPartTTLInfo.h index 209d7181b66..d7a6add8171 100644 --- a/src/Storages/MergeTree/MergeTreeDataPartTTLInfo.h +++ b/src/Storages/MergeTree/MergeTreeDataPartTTLInfo.h @@ -38,7 +38,7 @@ struct MergeTreeDataPartTTLInfos MergeTreeDataPartTTLInfo table_ttl; /// `part_min_ttl` and `part_max_ttl` are TTLs which are used for selecting parts - /// to merge in order to remove expired rows. + /// to merge in order to remove expired rows. time_t part_min_ttl = 0; time_t part_max_ttl = 0; @@ -58,7 +58,7 @@ struct MergeTreeDataPartTTLInfos part_max_ttl = time_max; } - bool empty() + bool empty() const { return !part_min_ttl && moves_ttl.empty(); } diff --git a/tests/queries/0_stateless/01471_calculate_ttl_during_merge.reference b/tests/queries/0_stateless/01471_calculate_ttl_during_merge.reference new file mode 100644 index 00000000000..1e682ec38a9 --- /dev/null +++ b/tests/queries/0_stateless/01471_calculate_ttl_during_merge.reference @@ -0,0 +1,5 @@ +3000 +3000 +2000 +2000 +1001 diff --git a/tests/queries/0_stateless/01471_calculate_ttl_during_merge.sql b/tests/queries/0_stateless/01471_calculate_ttl_during_merge.sql new file mode 100644 index 00000000000..901c47bc10f --- /dev/null +++ b/tests/queries/0_stateless/01471_calculate_ttl_during_merge.sql @@ -0,0 +1,37 @@ +DROP TABLE IF EXISTS table_for_ttl; + +CREATE TABLE table_for_ttl( + d DateTime, + key UInt64, + value String) +ENGINE = MergeTree() +ORDER BY tuple() +PARTITION BY key; + +INSERT INTO table_for_ttl SELECT now() - INTERVAL 2 YEAR, 1, toString(number) from numbers(1000); + +INSERT INTO table_for_ttl SELECT now() - INTERVAL 2 DAY, 3, toString(number) from numbers(2000, 1000); + +INSERT INTO table_for_ttl SELECT now(), 4, toString(number) from numbers(3000, 1000); + +SELECT count() FROM table_for_ttl; + +ALTER TABLE table_for_ttl MODIFY TTL d + INTERVAL 1 YEAR SETTINGS materialize_ttl_after_modify = 0; + +SELECT count() FROM table_for_ttl; + +OPTIMIZE TABLE table_for_ttl FINAL; + +SELECT count() FROM table_for_ttl; + +ALTER TABLE table_for_ttl MODIFY COLUMN value String TTL d + INTERVAL 1 DAY SETTINGS materialize_ttl_after_modify = 0; + +SELECT count(distinct value) FROM table_for_ttl; + +OPTIMIZE TABLE table_for_ttl FINAL; + +SELECT count(distinct value) FROM table_for_ttl; + +OPTIMIZE TABLE table_for_ttl FINAL; -- Just check in logs, that it doesn't run with force again + +DROP TABLE IF EXISTS table_for_ttl;