Merge remote-tracking branch 'origin' into integration-2

contrib/libunwind

@@ -1 +1 @@
-Subproject commit 8fe25d7dc70f2a4ea38c3e5a33fa9d4199b67a5a
+Subproject commit 1e4a2e5ce77be1af12e918a3c15dccf2bbac587d

docker/test/performance-comparison/perf.py

@@ -44,7 +44,7 @@ parser.add_argument('--port', nargs='*', default=[9000], help="Space-separated l
 parser.add_argument('--runs', type=int, default=1, help='Number of query runs per server.')
 parser.add_argument('--max-queries', type=int, default=None, help='Test no more than this number of queries, chosen at random.')
 parser.add_argument('--queries-to-run', nargs='*', type=int, default=None, help='Space-separated list of indexes of queries to test.')
-parser.add_argument('--max-query-seconds', type=int, default=10, help='For how many seconds at most a query is allowed to run. The script finishes with error if this time is exceeded.')
+parser.add_argument('--max-query-seconds', type=int, default=15, help='For how many seconds at most a query is allowed to run. The script finishes with error if this time is exceeded.')
 parser.add_argument('--profile-seconds', type=int, default=0, help='For how many seconds to profile a query for which the performance has changed.')
 parser.add_argument('--long', action='store_true', help='Do not skip the tests tagged as long.')
 parser.add_argument('--print-queries', action='store_true', help='Print test queries and exit.')
@@ -273,8 +273,14 @@ for query_index in queries_to_run:
             prewarm_id = f'{query_prefix}.prewarm0'
 
             try:
-                # Will also detect too long queries during warmup stage
-                res = c.execute(q, query_id = prewarm_id, settings = {'max_execution_time': args.max_query_seconds})
+                # During the warmup runs, we will also:
+                # * detect queries that are exceedingly long, to fail fast,
+                # * collect profiler traces, which might be helpful for analyzing
+                #   test coverage. We disable profiler for normal runs because
+                #   it makes the results unstable.
+                res = c.execute(q, query_id = prewarm_id,
+                    settings = {'max_execution_time': args.max_query_seconds,
+                        'query_profiler_real_time_period_ns': 10000000})
             except clickhouse_driver.errors.Error as e:
                 # Add query id to the exception to make debugging easier.
                 e.args = (prewarm_id, *e.args)
@@ -359,10 +365,11 @@ for query_index in queries_to_run:
         # For very short queries we have a special mode where we run them for at
         # least some time. The recommended lower bound of run time for "normal"
         # queries is about 0.1 s, and we run them about 10 times, giving the
-        # time per query per server of about one second. Use this value as a
-        # reference for "short" queries.
+        # time per query per server of about one second. Run "short" queries
+        # for longer time, because they have a high percentage of overhead and
+        # might give less stable results.
         if is_short[query_index]:
-            if server_seconds >= 2 * len(this_query_connections):
+            if server_seconds >= 8 * len(this_query_connections):
                 break
             # Also limit the number of runs, so that we don't go crazy processing
             # the results -- 'eqmed.sql' is really suboptimal.

docker/test/performance-comparison/report.py

@@ -446,6 +446,9 @@ if args.report == 'main':
                 attrs[3] = f'style="background: {color_bad}"'
             else:
                 attrs[3] = ''
+                # Just don't add the slightly unstable queries we don't consider
+                # errors. It's not clear what the user should do with them.
+                continue
 
             text += tableRow(r, attrs, anchor)
 
@@ -553,12 +556,11 @@ if args.report == 'main':
         error_tests += unstable_partial_queries
         status = 'failure'
 
-    if unstable_queries:
-        message_array.append(str(unstable_queries) + ' unstable')
-
-#    Disabled before fix.
-#    if very_unstable_queries:
-#        status = 'failure'
+    # Don't show mildly unstable queries, only the very unstable ones we
+    # treat as errors.
+    if very_unstable_queries:
+        status = 'failure'
+        message_array.append(str(very_unstable_queries) + ' unstable')
 
     error_tests += slow_average_tests
     if error_tests:

docs/en/operations/configuration-files.md

@@ -57,7 +57,7 @@ $ cat /etc/clickhouse-server/users.d/alice.xml
 
 ## YAML examples {#example}
 
-Here you can see default config written in YAML: [config-example.yaml](https://github.com/ClickHouse/ClickHouse/blob/master/programs/server/config-example.yaml).
+Here you can see default config written in YAML: [config.yaml.example](https://github.com/ClickHouse/ClickHouse/blob/master/programs/server/config.yaml.example).
 
 There are some differences between YAML and XML formats in terms of ClickHouse configurations. Here are some tips for writing a configuration in YAML format.
 

docs/ru/operations/configuration-files.md

@@ -6,9 +6,9 @@ toc_title: "Конфигурационные файлы"
 
 # Конфигурационные файлы {#configuration_files}
 
-Основной конфигурационный файл сервера - `config.xml`. Он расположен в директории `/etc/clickhouse-server/`.
+Основной конфигурационный файл сервера - `config.xml` или `config.yaml`. Он расположен в директории `/etc/clickhouse-server/`.
 
-Отдельные настройки могут быть переопределены в файлах `*.xml` и `*.conf` из директории `config.d` рядом с конфигом.
+Отдельные настройки могут быть переопределены в файлах `*.xml` и `*.conf`, а также `.yaml` (для файлов в формате YAML) из директории `config.d` рядом с конфигом.
 
 У элементов этих конфигурационных файлов могут быть указаны атрибуты `replace` или `remove`.
 
@@ -25,7 +25,7 @@ toc_title: "Конфигурационные файлы"
 В элементе `users_config` файла `config.xml` можно указать относительный путь к конфигурационному файлу с настройками пользователей, профилей и квот. Значение `users_config` по умолчанию — `users.xml`. Если `users_config` не указан, то настройки пользователей, профилей и квот можно задать непосредственно в `config.xml`.
 
 Настройки пользователя могут быть разделены в несколько отдельных файлов аналогичных `config.xml` и `config.d\`. Имя директории задаётся также как `users_config`.
-Имя директории задаётся так же, как имя файла в `users_config`, с подстановкой `.d` вместо `.xml`.
+Имя директории задаётся так же, как имя файла в `users_config`, с подстановкой `.d` вместо `.xml`/`.yaml`.
 Директория `users.d` используется по умолчанию, также как `users.xml` используется для `users_config`.
 Например, можно иметь по отдельному конфигурационному файлу для каждого пользователя:
 
@@ -52,3 +52,66 @@ $ cat /etc/clickhouse-server/users.d/alice.xml
 
 Сервер следит за изменениями конфигурационных файлов, а также файлов и ZooKeeper-узлов, которые были использованы при выполнении подстановок и переопределений, и перезагружает настройки пользователей и кластеров на лету. То есть, можно изменять кластера, пользователей и их настройки без перезапуска сервера.
 
+## Примеры записи конфигурации на YAML {#example}
+
+Здесь можно рассмотреть пример реальной конфигурации записанной на YAML: [config.yaml.example](https://github.com/ClickHouse/ClickHouse/blob/master/programs/server/config.yaml.example).
+
+Между стандартами XML и YAML имеются различия, поэтому в этом разделе будут перечислены некоторые подсказки для написания конфигурации на YMAL.
+
+Для записи обычной пары ключ-значение следует использовать Scalar:
+``` yaml
+key: value
+```
+
+Для создания тега, содержащего подтеги следует использовать Map:
+``` yaml
+map_key:
+  key1: val1
+  key2: val2
+  key3: val3
+```
+
+Для создания списка значений или подтегов, расположенных по определенному ключу, следует использовать Sequence:
+``` yaml
+seq_key:
+  - val1
+  - val2
+  - key1: val3
+  - map:
+      key2: val4
+      key3: val5
+```
+
+В случае, усли необходимо объявить тег, аналогичный XML-атрибуту, необходимо задать скаляр, имеющий ключ с префиксом @ и заключенный в кавычки:
+
+``` yaml
+map:
+  "@attr1": value1
+  "@attr2": value2
+  key: 123
+```
+
+Из такой Map мы получим после конвертации:
+
+``` xml
+<map attr1="value1" attr2="value2">
+    <key>123</key>
+</map>
+```
+
+Помимо Map, можно задавать атрибуты для Sequence:
+
+``` yaml
+seq:
+  - "@attr1": value1
+  - "@attr2": value2
+  - 123
+  - abc
+```
+
+Таким образом получая аналог следующей записи на XML:
+
+``` xml
+<seq attr1="value1" attr2="value2">123</seq>
+<seq attr1="value1" attr2="value2">abc</seq>
+```

programs/server/config.yaml.example

@@ -1,4 +1,8 @@
-# NOTE: User and query level settings are set up in "users.xml" file.
+# This is an example of a configuration file "config.xml" rewritten in YAML
+# You can read this documentation for detailed information about YAML configuration:
+# https://clickhouse.tech/docs/en/operations/configuration-files/
+
+# NOTE: User and query level settings are set up in "users.yaml" file.
 # If you have accidentally specified user-level settings here, server won't start.
 # You can either move the settings to the right place inside "users.xml" file
 # or add skip_check_for_incorrect_settings: 1 here.

programs/server/users.yaml.example

@@ -0,0 +1,107 @@
+# Profiles of settings.
+profiles:
+    # Default settings.
+    default:
+        # Maximum memory usage for processing single query, in bytes.
+        max_memory_usage: 10000000000
+
+        # How to choose between replicas during distributed query processing.
+        # random - choose random replica from set of replicas with minimum number of errors
+        # nearest_hostname - from set of replicas with minimum number of errors, choose replica
+        # with minimum number of different symbols between replica's hostname and local hostname (Hamming distance).
+        # in_order - first live replica is chosen in specified order.
+        # first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
+        load_balancing: random
+
+        # Profile that allows only read queries.
+    readonly:
+        readonly: 1
+
+# Users and ACL.
+users:
+    # If user name was not specified, 'default' user is used.
+    default:
+        # Password could be specified in plaintext or in SHA256 (in hex format).
+        #
+        # If you want to specify password in plaintext (not recommended), place it in 'password' element.
+        # Example: password: qwerty
+        # Password could be empty.
+        #
+        # If you want to specify SHA256, place it in 'password_sha256_hex' element.
+        # Example: password_sha256_hex: 65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5
+        # Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
+        #
+        # If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
+        # Example: password_double_sha1_hex: e395796d6546b1b65db9d665cd43f0e858dd4303
+        #
+        # If you want to specify a previously defined LDAP server (see 'ldap_servers' in the main config) for authentication,
+        # place its name in 'server' element inside 'ldap' element.
+        # Example: ldap:
+                       # server: my_ldap_server
+        #
+        # If you want to authenticate the user via Kerberos (assuming Kerberos is enabled, see 'kerberos' in the main config),
+        # place 'kerberos' element instead of 'password' (and similar) elements.
+        # The name part of the canonical principal name of the initiator must match the user name for authentication to succeed.
+        # You can also place 'realm' element inside 'kerberos' element to further restrict authentication to only those requests
+        # whose initiator's realm matches it.
+        # Example: kerberos: ''
+        # Example: kerberos:
+                       # realm: EXAMPLE.COM
+        #
+        # How to generate decent password:
+        # Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
+        # In first line will be password and in second - corresponding SHA256.
+        #
+        # How to generate double SHA1:
+        # Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha1sum | tr -d '-' | xxd -r -p | sha1sum | tr -d '-'
+        # In first line will be password and in second - corresponding double SHA1.
+
+        password: ''
+
+        # List of networks with open access.
+        #
+        # To open access from everywhere, specify:
+        #    - ip: '::/0'
+        #
+        # To open access only from localhost, specify:
+        #    - ip: '::1'
+        #    - ip: 127.0.0.1
+        #
+        # Each element of list has one of the following forms:
+        # ip: IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
+        # 2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
+        # host: Hostname. Example: server01.yandex.ru.
+        # To check access, DNS query is performed, and all received addresses compared to peer address.
+        # host_regexp: Regular expression for host names. Example, ^server\d\d-\d\d-\d\.yandex\.ru$
+        # To check access, DNS PTR query is performed for peer address and then regexp is applied.
+        # Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
+        # Strongly recommended that regexp is ends with $ and take all expression in ''
+        # All results of DNS requests are cached till server restart.
+
+        networks:
+            ip: '::/0'
+
+        # Settings profile for user.
+        profile: default
+
+        # Quota for user.
+        quota: default
+
+        # User can create other users and grant rights to them.
+        # access_management: 1
+
+# Quotas.
+quotas:
+    # Name of quota.
+    default:
+        # Limits for time interval. You could specify many intervals with different limits.
+        interval:
+            # Length of interval.
+            duration: 3600
+
+            # No limits. Just calculate resource usage for time interval.
+            queries: 0
+            errors: 0
+            result_rows: 0
+            read_rows: 0
+            execution_time: 0

src/Common/tests/gtest_thread_pool_global_full.cpp

@@ -25,7 +25,7 @@ TEST(ThreadPool, GlobalFull1)
     std::atomic<size_t> counter = 0;
     static constexpr size_t num_jobs = capacity + 1;
 
-    auto func = [&] { ++counter; while (counter != num_jobs) {} };
+    auto func = [&] { ++counter; while (counter != num_jobs) {} }; //-V776
 
     ThreadPool pool(num_jobs);
 
@@ -63,7 +63,7 @@ TEST(ThreadPool, GlobalFull2)
     global_pool.wait();
 
     std::atomic<size_t> counter = 0;
-    auto func = [&] { ++counter; while (counter != capacity + 1) {} };
+    auto func = [&] { ++counter; while (counter != capacity + 1) {} }; //-V776
 
     ThreadPool pool(capacity, 0, capacity);
     for (size_t i = 0; i < capacity; ++i)

src/Common/ya.make

@@ -33,6 +33,7 @@ SRCS(
     Config/AbstractConfigurationComparison.cpp
     Config/ConfigProcessor.cpp
     Config/ConfigReloader.cpp
+    Config/YAMLParser.cpp
     Config/configReadClient.cpp
     CurrentMemoryTracker.cpp
     CurrentMetrics.cpp

src/Interpreters/ActionsDAG.cpp

@@ -540,7 +540,7 @@ Block ActionsDAG::updateHeader(Block header) const
 
     struct Frame
     {
-        const Node * node;
+        const Node * node = nullptr;
         size_t next_child = 0;
     };
 
@@ -587,8 +587,7 @@ Block ActionsDAG::updateHeader(Block header) const
                 }
             }
 
-            auto & column = node_to_column[output];
-            if (column.column)
+            if (node_to_column[output].column)
                 result_columns.push_back(node_to_column[output]);
         }
     }

src/Interpreters/InterpreterCreateQuery.cpp

@@ -263,7 +263,7 @@ BlockIO InterpreterCreateQuery::createDatabase(ASTCreateQuery & create)
         }
 
         /// We use global context here, because storages lifetime is bigger than query context lifetime
-        database->loadStoredObjects(getContext()->getGlobalContext(), has_force_restore_data_flag, create.attach && force_attach);
+        database->loadStoredObjects(getContext()->getGlobalContext(), has_force_restore_data_flag, create.attach && force_attach); //-V560
     }
     catch (...)
     {

src/Parsers/New/ParserErrorListener.cpp

@@ -26,7 +26,7 @@ void ParserErrorListener::syntaxError(
     auto * parser = dynamic_cast<ClickHouseParser *>(recognizer);
     assert(parser);
 
-    LOG_ERROR(&Poco::Logger::get("ClickHouseParser"),
+    LOG_ERROR(&Poco::Logger::get("ClickHouseParser"), //-V522
               "Last element parsed so far:\n"
               "{}\n"
               "Parser error: (pos {}) {}", parser->getRuleContext()->toStringTree(parser, true), token->getStartIndex(), message);

src/Storages/MergeTree/MergeTreeDataSelectExecutor.cpp

@@ -578,6 +578,8 @@ QueryPlanPtr MergeTreeDataSelectExecutor::readFromParts(
     MergeTreeDataSelectSamplingData sampling = use_cache ? std::move(cache->sampling) : MergeTreeDataSelectSamplingData{};
     if (!use_cache)
     {
+        assert(key_condition.has_value());
+
         RelativeSize relative_sample_size = 0;
         RelativeSize relative_sample_offset = 0;
 
@@ -606,7 +608,7 @@ QueryPlanPtr MergeTreeDataSelectExecutor::readFromParts(
             /// read) into the relative `SAMPLE 0.1` (how much data to read).
             size_t approx_total_rows = 0;
             if (relative_sample_size > 1 || relative_sample_offset > 1)
-                approx_total_rows = getApproximateTotalRowsToRead(parts, metadata_snapshot, *key_condition, settings);
+                approx_total_rows = getApproximateTotalRowsToRead(parts, metadata_snapshot, *key_condition, settings); //-V1007
 
             if (relative_sample_size > 1)
             {
@@ -765,7 +767,7 @@ QueryPlanPtr MergeTreeDataSelectExecutor::readFromParts(
 
                 if (has_lower_limit)
                 {
-                    if (!key_condition->addCondition(sampling_key.column_names[0], Range::createLeftBounded(lower, true)))
+                    if (!key_condition->addCondition(sampling_key.column_names[0], Range::createLeftBounded(lower, true))) //-V1007
                         throw Exception("Sampling column not in primary key", ErrorCodes::ILLEGAL_COLUMN);
 
                     ASTPtr args = std::make_shared<ASTExpressionList>();
@@ -782,7 +784,7 @@ QueryPlanPtr MergeTreeDataSelectExecutor::readFromParts(
 
                 if (has_upper_limit)
                 {
-                    if (!key_condition->addCondition(sampling_key.column_names[0], Range::createRightBounded(upper, false)))
+                    if (!key_condition->addCondition(sampling_key.column_names[0], Range::createRightBounded(upper, false))) //-V1007
                         throw Exception("Sampling column not in primary key", ErrorCodes::ILLEGAL_COLUMN);
 
                     ASTPtr args = std::make_shared<ASTExpressionList>();

src/Storages/MergeTree/MergeTreeDataSelectExecutor.h

@@ -15,7 +15,7 @@ class KeyCondition;
 
 struct MergeTreeDataSelectSamplingData
 {
-    bool use_sampling;
+    bool use_sampling = false;
     std::shared_ptr<ASTFunction> filter_function;
     ActionsDAGPtr filter_expression;
 };

src/Storages/MergeTree/MergeTreeReaderWide.cpp

@@ -173,7 +173,7 @@ void MergeTreeReaderWide::readData(
 {
     auto get_stream_getter = [&](bool stream_for_prefix) -> ISerialization::InputStreamGetter
     {
-        return [&, stream_for_prefix](const ISerialization::SubstreamPath & substream_path) -> ReadBuffer *
+        return [&, stream_for_prefix](const ISerialization::SubstreamPath & substream_path) -> ReadBuffer * //-V1047
         {
             /// If substream have already been read.
             if (cache.count(ISerialization::getSubcolumnNameForStream(substream_path)))

src/Storages/SelectQueryInfo.h

@@ -122,7 +122,7 @@ struct MergeTreeDataSelectCache;
 // The projection selected to execute current query
 struct ProjectionCandidate
 {
-    const ProjectionDescription * desc;
+    const ProjectionDescription * desc{};
     PrewhereInfoPtr prewhere_info;
     ActionsDAGPtr before_where;
     String where_column_name;

src/Storages/StorageLog.cpp

@@ -172,7 +172,7 @@ void LogSource::readData(const NameAndTypePair & name_and_type, ColumnPtr & colu
 
     auto create_stream_getter = [&](bool stream_for_prefix)
     {
-        return [&, stream_for_prefix] (const ISerialization::SubstreamPath & path) -> ReadBuffer *
+        return [&, stream_for_prefix] (const ISerialization::SubstreamPath & path) -> ReadBuffer * //-V1047
         {
             if (cache.count(ISerialization::getSubcolumnNameForStream(path)))
                 return nullptr;

tests/performance/agg_functions_min_max_any.xml

@@ -1,4 +1,4 @@
-<test>
+<test max_ignored_relative_change="0.3">
     <preconditions>
         <table_exists>hits_100m_single</table_exists>
     </preconditions>

tests/performance/arithmetic.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test max_ignored_relative_change="0.7">
     <settings>
         <max_memory_usage>30000000000</max_memory_usage>
     </settings>

tests/performance/array_join.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
 
 
 

tests/performance/avg_weighted.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.4">
+<test>
     <settings>
         <allow_experimental_bigint_types>1</allow_experimental_bigint_types>
         <max_threads>1</max_threads>

tests/performance/bounding_ratio.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <query>SELECT boundingRatio(number, number) FROM numbers(100000000)</query>
     <query>SELECT (argMax(number, number) - argMin(number, number)) / (max(number) - min(number)) FROM numbers(100000000)</query>
 </test>

tests/performance/codecs_float_insert.xml

@@ -1,5 +1,4 @@
-<!-- FIXME this instability is abysmal, investigate the unstable queries -->
-<test max_ignored_relative_change="0.2">
+<test>
     <settings>
         <allow_suspicious_codecs>1</allow_suspicious_codecs>
     </settings>

tests/performance/codecs_int_insert.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <settings>
         <allow_suspicious_codecs>1</allow_suspicious_codecs>
     </settings>

tests/performance/collations.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
 
 
 

tests/performance/date_time_64.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <preconditions>
         <table_exists>hits_100m_single</table_exists>
     </preconditions>

tests/performance/date_time_long.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test>
     <substitutions>
        <substitution>
            <name>datetime_transform</name>

tests/performance/decimal_aggregates.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.5">
+<test max_ignored_relative_change="0.2">
     <settings>
         <max_memory_usage>35G</max_memory_usage>
     </settings>

tests/performance/decimal_casts.xml

@@ -1,4 +1,4 @@
-<test>
+<test max_ignored_relative_change="0.2">
     <settings>
         <max_memory_usage>15G</max_memory_usage>
     </settings>

tests/performance/direct_dictionary.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test max_ignored_relative_change="0.4">
     <create_query>
         CREATE TABLE simple_key_direct_dictionary_source_table
         (

tests/performance/encodeXMLComponent.xml

@@ -1,7 +1,7 @@
 <test>
     <preconditions>
-        <table_exists>test.hits</table_exists>
+        <table_exists>hits_100m_single</table_exists>
     </preconditions>
 
-    <query>SELECT count() FROM test.hits WHERE NOT ignore(encodeXMLComponent(URL))</query>
+    <query>SELECT count() FROM hits_100m_single WHERE NOT ignore(encodeXMLComponent(URL))</query>
 </test>

tests/performance/flat_dictionary.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test>
     <create_query>
         CREATE TABLE simple_key_flat_dictionary_source_table
         (

tests/performance/float_parsing.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <substitutions>
        <substitution>
            <name>expr</name>

tests/performance/fuzz_bits.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test>
 
 
 

tests/performance/general_purpose_hashes.xml

@@ -1,4 +1,4 @@
-<test>
+<test max_ignored_relative_change="0.2">
     <substitutions>
         <substitution>
            <name>gp_hash_func</name>

tests/performance/general_purpose_hashes_on_UUID.xml

@@ -1,4 +1,4 @@
-<test>
+<test max_ignored_relative_change="0.6">
     <substitutions>
         <substitution>
            <name>hash_func</name>

tests/performance/generate_table_function.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <query>SELECT sum(NOT ignore(*)) FROM (SELECT * FROM generateRandom('ui64 UInt64, i64 Int64, ui32 UInt32, i32 Int32, ui16 UInt16, i16 Int16, ui8 UInt8, i8 Int8') LIMIT 1000000000);</query>
     <query>SELECT sum(NOT ignore(*)) FROM (SELECT * FROM generateRandom('ui64 UInt64, i64 Int64, ui32 UInt32, i32 Int32, ui16 UInt16, i16 Int16, ui8 UInt8, i8 Int8', 0, 10, 10) LIMIT 1000000000);</query>
     <query>SELECT sum(NOT ignore(*)) FROM (SELECT * FROM generateRandom('i Enum8(\'hello\' = 1, \'world\' = 5)', 0, 10, 10) LIMIT 1000000000);</query>

tests/performance/hashed_dictionary.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test max_ignored_relative_change="0.2">
     <create_query>
         CREATE TABLE simple_key_hashed_dictionary_source_table
         (

tests/performance/int_parsing.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <preconditions>
         <table_exists>hits_100m_single</table_exists>
         <table_exists>hits_10m_single</table_exists>

tests/performance/jit_small_requests.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <query>
         WITH
             bitXor(number, 0x4CF2D2BAAE6DA887) AS x0,

tests/performance/json_extract_rapidjson.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
 
 
 

tests/performance/json_extract_simdjson.xml

@@ -1,4 +1,4 @@
-<test>
+<test max_ignored_relative_change="0.2">
     <substitutions>
         <substitution>
            <name>json</name>

tests/performance/math.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test max_ignored_relative_change="0.6">
     <substitutions>
         <substitution>
            <name>func_slow</name>

tests/performance/merge_tree_many_partitions_2.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
 
     <create_query>CREATE TABLE bad_partitions (a UInt64, b UInt64, c UInt64, d UInt64, e UInt64, f UInt64, g UInt64, h UInt64, i UInt64, j UInt64, k UInt64, l UInt64, m UInt64, n UInt64, o UInt64, p UInt64, q UInt64, r UInt64, s UInt64, t UInt64, u UInt64, v UInt64, w UInt64, x UInt64, y UInt64, z UInt64) ENGINE = MergeTree PARTITION BY x ORDER BY x</create_query>
     <fill_query>INSERT INTO bad_partitions (x) SELECT * FROM numbers_mt(3000)</fill_query>

tests/performance/number_formatting_formats.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test max_ignored_relative_change="0.3">
     <substitutions>
         <substitution>
             <name>format</name>

tests/performance/optimized_select_final.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test>
     <settings>
         <do_not_merge_across_partitions_select_final>1</do_not_merge_across_partitions_select_final>
     </settings>

tests/performance/parallel_mv.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <settings>
         <parallel_view_processing>1</parallel_view_processing>
     </settings>

tests/performance/point_in_polygon.xml

@@ -1,4 +1,4 @@
-<test>
+<test max_ignored_relative_change="0.2">
     <settings>
         <!--
             Not sure why it's needed. Maybe it has something to do with the

tests/performance/polymorphic_parts_l.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <create_query>
         CREATE TABLE hits_wide AS hits_10m_single ENGINE = MergeTree()
         PARTITION BY toYYYYMM(EventDate)

tests/performance/polymorphic_parts_m.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <create_query>
         CREATE TABLE hits_wide AS hits_10m_single ENGINE = MergeTree()
         PARTITION BY toYYYYMM(EventDate)

tests/performance/polymorphic_parts_s.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <create_query>
         CREATE TABLE hits_wide AS hits_10m_single ENGINE = MergeTree()
         PARTITION BY toYYYYMM(EventDate)

tests/performance/questdb_sum_int32.xml

@@ -1,4 +1,4 @@
-<test>
+<test max_ignored_relative_change="0.2">
     <settings>
         <max_threads>4</max_threads>
         <max_memory_usage>20G</max_memory_usage>

tests/performance/random_string.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <query>SELECT count() FROM zeros(100000000) WHERE NOT ignore(randomString(10))</query>
     <query>SELECT count() FROM zeros(100000000) WHERE NOT ignore(randomString(100))</query>
     <query>SELECT count() FROM zeros(1000000) WHERE NOT ignore(randomString(1000))</query>

tests/performance/redundant_functions_in_order_by.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test>
     <preconditions>
         <table_exists>hits_100m_single</table_exists>
     </preconditions>

tests/performance/rewrite_sumIf.xml

@@ -1,4 +1,5 @@
 <test>
-    <query>SELECT sumIf(1, 0) FROM numbers(100000000)</query>
-    <query>SELECT sumIf(1, 1) FROM numbers(100000000)</query>
+    <!-- Shouldn't have been a perf test, but an EXPLAIN one. -->
+    <query>SELECT sumIf(1, 0) FROM numbers(1000000000)</query>
+    <query>SELECT sumIf(1, 1) FROM numbers(1000000000)</query>
 </test>

tests/performance/sum_map.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test max_ignored_relative_change="0.2">
     <settings>
         <max_threads>1</max_threads>
     </settings>

tests/performance/synthetic_hardware_benchmark.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test max_ignored_relative_change="0.2">
     <settings>
         <max_memory_usage>30000000000</max_memory_usage>
     </settings>

tests/performance/url_hits.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.2">
+<test>
     <preconditions>
         <table_exists>hits_100m_single</table_exists>
         <table_exists>hits_10m_single</table_exists>

tests/performance/visit_param_extract_raw.xml

@@ -1,4 +1,4 @@
-<test max_ignored_relative_change="0.3">
+<test max_ignored_relative_change="0.2">
     <substitutions>
         <substitution>
            <name>param</name>