Merge branch 'master' into add-retries-for-zk-create

This commit is contained in:
Antonio Andelic 2023-06-29 20:38:37 +02:00 committed by GitHub
commit 447a4e7b2a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
30 changed files with 320 additions and 56 deletions

View File

@ -27,6 +27,8 @@ using FromDoubleIntermediateType = long double;
using FromDoubleIntermediateType = boost::multiprecision::cpp_bin_float_double_extended;
#endif
namespace CityHash_v1_0_2 { struct uint128; }
namespace wide
{
@ -281,6 +283,17 @@ struct integer<Bits, Signed>::_impl
}
}
template <typename CityHashUInt128 = CityHash_v1_0_2::uint128>
constexpr static void wide_integer_from_cityhash_uint128(integer<Bits, Signed> & self, const CityHashUInt128 & value) noexcept
{
static_assert(sizeof(item_count) >= 2);
if constexpr (std::endian::native == std::endian::little)
wide_integer_from_tuple_like(self, std::make_pair(value.low64, value.high64));
else
wide_integer_from_tuple_like(self, std::make_pair(value.high64, value.low64));
}
/**
* N.B. t is constructed from double, so max(t) = max(double) ~ 2^310
* the recursive call happens when t / 2^64 > 2^64, so there won't be more than 5 of them.
@ -1036,6 +1049,8 @@ constexpr integer<Bits, Signed>::integer(T rhs) noexcept
_impl::wide_integer_from_wide_integer(*this, rhs);
else if constexpr (IsTupleLike<T>::value)
_impl::wide_integer_from_tuple_like(*this, rhs);
else if constexpr (std::is_same_v<std::remove_cvref_t<T>, CityHash_v1_0_2::uint128>)
_impl::wide_integer_from_cityhash_uint128(*this, rhs);
else
_impl::wide_integer_from_builtin(*this, rhs);
}
@ -1051,6 +1066,8 @@ constexpr integer<Bits, Signed>::integer(std::initializer_list<T> il) noexcept
_impl::wide_integer_from_wide_integer(*this, *il.begin());
else if constexpr (IsTupleLike<T>::value)
_impl::wide_integer_from_tuple_like(*this, *il.begin());
else if constexpr (std::is_same_v<std::remove_cvref_t<T>, CityHash_v1_0_2::uint128>)
_impl::wide_integer_from_cityhash_uint128(*this, *il.begin());
else
_impl::wide_integer_from_builtin(*this, *il.begin());
}
@ -1088,6 +1105,8 @@ constexpr integer<Bits, Signed> & integer<Bits, Signed>::operator=(T rhs) noexce
{
if constexpr (IsTupleLike<T>::value)
_impl::wide_integer_from_tuple_like(*this, rhs);
else if constexpr (std::is_same_v<std::remove_cvref_t<T>, CityHash_v1_0_2::uint128>)
_impl::wide_integer_from_cityhash_uint128(*this, rhs);
else
_impl::wide_integer_from_builtin(*this, rhs);
return *this;

View File

@ -61,11 +61,24 @@ namespace CityHash_v1_0_2
typedef uint8_t uint8;
typedef uint32_t uint32;
typedef uint64_t uint64;
typedef std::pair<uint64, uint64> uint128;
/// Represent an unsigned integer of 128 bits as it's used in CityHash.
/// Originally CityHash used `std::pair<uint64, uint64>` instead of this struct,
/// however the members `first` and `second` could be easily confused so they were renamed to `low64` and `high64`:
/// `first` -> `low64`, `second` -> `high64`.
struct uint128
{
uint64 low64 = 0;
uint64 high64 = 0;
inline uint64 Uint128Low64(const uint128& x) { return x.first; }
inline uint64 Uint128High64(const uint128& x) { return x.second; }
uint128() = default;
uint128(uint64 low64_, uint64 high64_) : low64(low64_), high64(high64_) {}
friend bool operator ==(const uint128 & x, const uint128 & y) { return (x.low64 == y.low64) && (x.high64 == y.high64); }
friend bool operator !=(const uint128 & x, const uint128 & y) { return !(x == y); }
};
inline uint64 Uint128Low64(const uint128 & x) { return x.low64; }
inline uint64 Uint128High64(const uint128 & x) { return x.high64; }
// Hash function for a byte array.
uint64 CityHash64(const char *buf, size_t len);

View File

@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
esac
ARG REPOSITORY="https://s3.amazonaws.com/clickhouse-builds/22.4/31c367d3cd3aefd316778601ff6565119fe36682/package_release"
ARG VERSION="23.5.3.24"
ARG VERSION="23.5.4.25"
ARG PACKAGES="clickhouse-keeper"
# user/group precreated explicitly with fixed uid/gid on purpose.

View File

@ -33,7 +33,7 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="23.5.3.24"
ARG VERSION="23.5.4.25"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# user/group precreated explicitly with fixed uid/gid on purpose.

View File

@ -23,7 +23,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
ARG VERSION="23.5.3.24"
ARG VERSION="23.5.4.25"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# set non-empty deb_location_url url to create a docker image

View File

@ -52,6 +52,8 @@ export CLICKHOUSE_TESTS_BASE_CONFIG_DIR=/clickhouse-config
export CLICKHOUSE_ODBC_BRIDGE_BINARY_PATH=/clickhouse-odbc-bridge
export CLICKHOUSE_LIBRARY_BRIDGE_BINARY_PATH=/clickhouse-library-bridge
export DOCKER_BASE_TAG=${DOCKER_BASE_TAG:=latest}
export DOCKER_HELPER_TAG=${DOCKER_HELPER_TAG:=latest}
export DOCKER_MYSQL_GOLANG_CLIENT_TAG=${DOCKER_MYSQL_GOLANG_CLIENT_TAG:=latest}
export DOCKER_DOTNET_CLIENT_TAG=${DOCKER_DOTNET_CLIENT_TAG:=latest}
export DOCKER_MYSQL_JAVA_CLIENT_TAG=${DOCKER_MYSQL_JAVA_CLIENT_TAG:=latest}

View File

@ -0,0 +1,31 @@
---
sidebar_position: 1
sidebar_label: 2023
---
# 2023 Changelog
### ClickHouse release v23.5.4.25-stable (190f962abcf) FIXME as compared to v23.5.3.24-stable (76f54616d3b)
#### Improvement
* Backported in [#51235](https://github.com/ClickHouse/ClickHouse/issues/51235): Improve the progress bar for file/s3/hdfs/url table functions by using chunk size from source data and using incremental total size counting in each thread. Fix the progress bar for *Cluster functions. This closes [#47250](https://github.com/ClickHouse/ClickHouse/issues/47250). [#51088](https://github.com/ClickHouse/ClickHouse/pull/51088) ([Kruglov Pavel](https://github.com/Avogar)).
* Backported in [#51255](https://github.com/ClickHouse/ClickHouse/issues/51255): Disable cache setting `do_not_evict_index_and_mark_files` (Was enabled in `23.5`). [#51222](https://github.com/ClickHouse/ClickHouse/pull/51222) ([Kseniia Sumarokova](https://github.com/kssenii)).
#### Build/Testing/Packaging Improvement
* Backported in [#51531](https://github.com/ClickHouse/ClickHouse/issues/51531): Split huge `RUN` in Dockerfile into smaller conditional. Install the necessary tools on demand in the same `RUN` layer, and remove them after that. Upgrade the OS only once at the beginning. Use a modern way to check the signed repository. Downgrade the base repo to ubuntu:20.04 to address the issues on older docker versions. Upgrade golang version to address golang vulnerabilities. [#51504](https://github.com/ClickHouse/ClickHouse/pull/51504) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Backported in [#51572](https://github.com/ClickHouse/ClickHouse/issues/51572): This a follow-up for [#51504](https://github.com/ClickHouse/ClickHouse/issues/51504), the cleanup was lost during refactoring. [#51564](https://github.com/ClickHouse/ClickHouse/pull/51564) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Query Cache: Try to fix bad cast from ColumnConst to ColumnVector<char8_t> [#50704](https://github.com/ClickHouse/ClickHouse/pull/50704) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix type of LDAP server params hash in cache entry [#50865](https://github.com/ClickHouse/ClickHouse/pull/50865) ([Julian Maicher](https://github.com/jmaicher)).
* Fallback to parsing big integer from String instead of exception in Parquet format [#50873](https://github.com/ClickHouse/ClickHouse/pull/50873) ([Kruglov Pavel](https://github.com/Avogar)).
* Do not apply projection if read-in-order was enabled. [#50923](https://github.com/ClickHouse/ClickHouse/pull/50923) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix race azure blob storage iterator [#50936](https://github.com/ClickHouse/ClickHouse/pull/50936) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix ineffective query cache for SELECTs with subqueries [#51132](https://github.com/ClickHouse/ClickHouse/pull/51132) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix fuzzer failure in ActionsDAG [#51301](https://github.com/ClickHouse/ClickHouse/pull/51301) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Fix ParallelReadBuffer seek [#50820](https://github.com/ClickHouse/ClickHouse/pull/50820) ([Michael Kolupaev](https://github.com/al13n321)).

View File

@ -44,11 +44,12 @@ Create a table in ClickHouse which allows to read data from Redis:
``` sql
CREATE TABLE redis_table
(
`k` String,
`m` String,
`n` UInt32
`key` String,
`v1` UInt32,
`v2` String,
`v3` Float32
)
ENGINE = Redis('redis1:6379') PRIMARY KEY(k);
ENGINE = Redis('redis1:6379') PRIMARY KEY(key);
```
Insert:
@ -111,9 +112,16 @@ Flush Redis db asynchronously. Also `Truncate` support SYNC mode.
TRUNCATE TABLE redis_table SYNC;
```
Join:
Join with other tables.
```
SELECT * FROM redis_table JOIN merge_tree_table ON merge_tree_table.key=redis_table.key;
```
## Limitations {#limitations}
Redis engine also supports scanning queries, such as `where k > xx`, but it has some limitations:
1. Scanning query may produce some duplicated keys in a very rare case when it is rehashing. See details in [Redis Scan](https://github.com/redis/redis/blob/e4d183afd33e0b2e6e8d1c79a832f678a04a7886/src/dict.c#L1186-L1269)
1. Scanning query may produce some duplicated keys in a very rare case when it is rehashing. See details in [Redis Scan](https://github.com/redis/redis/blob/e4d183afd33e0b2e6e8d1c79a832f678a04a7886/src/dict.c#L1186-L1269).
2. During the scanning, keys could be created and deleted, so the resulting dataset can not represent a valid point in time.

View File

@ -756,6 +756,17 @@ If you perform the `SELECT` query between merges, you may get expired data. To a
- [ttl_only_drop_parts](/docs/en/operations/settings/settings.md/#ttl_only_drop_parts) setting
## Disk types
In addition to local block devices, ClickHouse supports these storage types:
- [`s3` for S3 and MinIO](#table_engine-mergetree-s3)
- [`gcs` for GCS](/docs/en/integrations/data-ingestion/gcs/index.md/#creating-a-disk)
- [`blob_storage_disk` for Azure Blob Storage](#table_engine-mergetree-azure-blob-storage)
- [`hdfs` for HDFS](#hdfs-storage)
- [`web` for read-only from web](#web-storage)
- [`cache` for local caching](/docs/en/operations/storing-data.md/#using-local-cache)
- [`s3_plain` for backups to S3](/docs/en/operations/backup#backuprestore-using-an-s3-disk)
## Using Multiple Block Devices for Data Storage {#table_engine-mergetree-multiple-volumes}
### Introduction {#introduction}
@ -936,6 +947,8 @@ configuration files; all the settings are in the CREATE/ATTACH query.
The example uses `type=web`, but any disk type can be configured as dynamic, even Local disk. Local disks require a path argument to be inside the server config parameter `custom_local_disks_base_directory`, which has no default, so set that also when using local disk.
:::
#### Example dynamic web storage
```sql
ATTACH TABLE uk_price_paid UUID 'cf712b4f-2ca8-435c-ac23-c4393efe52f7'
(
@ -1238,6 +1251,93 @@ Examples of working configurations can be found in integration tests directory (
Zero-copy replication is disabled by default in ClickHouse version 22.8 and higher. This feature is not recommended for production use.
:::
## HDFS storage {#hdfs-storage}
In this sample configuration:
- the disk is of type `hdfs`
- the data is hosted at `hdfs://hdfs1:9000/clickhouse/`
```xml
<clickhouse>
<storage_configuration>
<disks>
<hdfs>
<type>hdfs</type>
<endpoint>hdfs://hdfs1:9000/clickhouse/</endpoint>
<skip_access_check>true</skip_access_check>
</hdfs>
<hdd>
<type>local</type>
<path>/</path>
</hdd>
</disks>
<policies>
<hdfs>
<volumes>
<main>
<disk>hdfs</disk>
</main>
<external>
<disk>hdd</disk>
</external>
</volumes>
</hdfs>
</policies>
</storage_configuration>
</clickhouse>
```
## Web storage (read-only) {#web-storage}
Web storage can be used for read-only purposes. An example use is for hosting sample
data, or for migrating data.
:::tip
Storage can also be configured temporarily within a query, if a web dataset is not expected
to be used routinely, see [dynamic storage](#dynamic-storage) and skip editing the
configuration file.
:::
In this sample configuration:
- the disk is of type `web`
- the data is hosted at `http://nginx:80/test1/`
- a cache on local storage is used
```xml
<clickhouse>
<storage_configuration>
<disks>
<web>
<type>web</type>
<endpoint>http://nginx:80/test1/</endpoint>
</web>
<cached_web>
<type>cache</type>
<disk>web</disk>
<path>cached_web_cache/</path>
<max_size>100000000</max_size>
</cached_web>
</disks>
<policies>
<web>
<volumes>
<main>
<disk>web</disk>
</main>
</volumes>
</web>
<cached_web>
<volumes>
<main>
<disk>cached_web</disk>
</main>
</volumes>
</cached_web>
</policies>
</storage_configuration>
</clickhouse>
```
## Virtual Columns {#virtual-columns}
- `_part` — Name of a part.

View File

@ -49,8 +49,8 @@ static void validateChecksum(char * data, size_t size, const Checksum expected_c
/// TODO mess up of endianness in error message.
message << "Checksum doesn't match: corrupted data."
" Reference: " + getHexUIntLowercase(expected_checksum.first) + getHexUIntLowercase(expected_checksum.second)
+ ". Actual: " + getHexUIntLowercase(calculated_checksum.first) + getHexUIntLowercase(calculated_checksum.second)
" Reference: " + getHexUIntLowercase(expected_checksum.high64) + getHexUIntLowercase(expected_checksum.low64)
+ ". Actual: " + getHexUIntLowercase(calculated_checksum.high64) + getHexUIntLowercase(calculated_checksum.low64)
+ ". Size of compressed block: " + toString(size);
const char * message_hardware_failure = "This is most likely due to hardware failure. "
@ -95,8 +95,8 @@ static void validateChecksum(char * data, size_t size, const Checksum expected_c
}
/// Check if the difference caused by single bit flip in stored checksum.
size_t difference = std::popcount(expected_checksum.first ^ calculated_checksum.first)
+ std::popcount(expected_checksum.second ^ calculated_checksum.second);
size_t difference = std::popcount(expected_checksum.low64 ^ calculated_checksum.low64)
+ std::popcount(expected_checksum.high64 ^ calculated_checksum.high64);
if (difference == 1)
{
@ -194,8 +194,8 @@ size_t CompressedReadBufferBase::readCompressedData(size_t & size_decompressed,
{
Checksum checksum;
ReadBufferFromMemory checksum_in(own_compressed_buffer.data(), sizeof(checksum));
readBinaryLittleEndian(checksum.first, checksum_in);
readBinaryLittleEndian(checksum.second, checksum_in);
readBinaryLittleEndian(checksum.low64, checksum_in);
readBinaryLittleEndian(checksum.high64, checksum_in);
validateChecksum(compressed_buffer, size_compressed_without_checksum, checksum);
}
@ -238,8 +238,8 @@ size_t CompressedReadBufferBase::readCompressedDataBlockForAsynchronous(size_t &
{
Checksum checksum;
ReadBufferFromMemory checksum_in(own_compressed_buffer.data(), sizeof(checksum));
readBinaryLittleEndian(checksum.first, checksum_in);
readBinaryLittleEndian(checksum.second, checksum_in);
readBinaryLittleEndian(checksum.low64, checksum_in);
readBinaryLittleEndian(checksum.high64, checksum_in);
validateChecksum(compressed_buffer, size_compressed_without_checksum, checksum);
}

View File

@ -38,8 +38,8 @@ void CompressedWriteBuffer::nextImpl()
CityHash_v1_0_2::uint128 checksum = CityHash_v1_0_2::CityHash128(out_compressed_ptr, compressed_size);
writeBinaryLittleEndian(checksum.first, out);
writeBinaryLittleEndian(checksum.second, out);
writeBinaryLittleEndian(checksum.low64, out);
writeBinaryLittleEndian(checksum.high64, out);
out.position() += compressed_size;
}
@ -50,8 +50,8 @@ void CompressedWriteBuffer::nextImpl()
CityHash_v1_0_2::uint128 checksum = CityHash_v1_0_2::CityHash128(compressed_buffer.data(), compressed_size);
writeBinaryLittleEndian(checksum.first, out);
writeBinaryLittleEndian(checksum.second, out);
writeBinaryLittleEndian(checksum.low64, out);
writeBinaryLittleEndian(checksum.high64, out);
out.write(compressed_buffer.data(), compressed_size);
}

View File

@ -507,9 +507,6 @@ bool CachedOnDiskReadBufferFromFile::completeFileSegmentAndGetNext()
current_file_segment->use();
implementation_buffer = getImplementationBuffer(*current_file_segment);
if (read_type == ReadType::CACHED)
current_file_segment->incrementHitsCount();
LOG_TEST(
log, "New segment range: {}, old range: {}",
current_file_segment->range().toString(), completed_range.toString());
@ -852,9 +849,7 @@ bool CachedOnDiskReadBufferFromFile::nextImplStep()
else
{
implementation_buffer = getImplementationBuffer(file_segments->front());
if (read_type == ReadType::CACHED)
file_segments->front().incrementHitsCount();
file_segments->front().use();
}
chassert(!internal_buffer.empty());

View File

@ -154,6 +154,8 @@ private:
using ColVecType = ColumnVectorOrDecimal<Type>;
const auto col_vec = checkAndGetColumn<ColVecType>(col.column.get());
if (col_vec == nullptr)
return false;
return (res = execute<Type, ReturnType>(col_vec)) != nullptr;
};

View File

@ -898,7 +898,7 @@ void FileSegment::use()
if (it)
{
auto cache_lock = cache->lockCache();
it->use(cache_lock);
hits_count = it->use(cache_lock);
}
}

View File

@ -175,8 +175,6 @@ public:
size_t getRefCount() const { return ref_count; }
void incrementHitsCount() { ++hits_count; }
size_t getCurrentWriteOffset(bool sync) const;
size_t getFirstNonDownloadedOffset(bool sync) const;

View File

@ -22,6 +22,8 @@
#include <Poco/ConsoleChannel.h>
#include <Disks/IO/CachedOnDiskWriteBufferFromFile.h>
#include <Disks/IO/CachedOnDiskReadBufferFromFile.h>
#include <Disks/IO/createReadBufferFromFileBase.h>
#include <Interpreters/Cache/WriteBufferToFileSegment.h>
namespace fs = std::filesystem;
@ -862,3 +864,78 @@ TEST_F(FileCacheTest, temporaryData)
ASSERT_LE(file_cache.getUsedCacheSize(), size_used_before_temporary_data);
ASSERT_LE(file_cache.getFileSegmentsNum(), segments_used_before_temporary_data);
}
TEST_F(FileCacheTest, CachedReadBuffer)
{
DB::ThreadStatus thread_status;
/// To work with cache need query_id and query context.
std::string query_id = "query_id";
Poco::XML::DOMParser dom_parser;
std::string xml(R"CONFIG(<clickhouse>
</clickhouse>)CONFIG");
Poco::AutoPtr<Poco::XML::Document> document = dom_parser.parseString(xml);
Poco::AutoPtr<Poco::Util::XMLConfiguration> config = new Poco::Util::XMLConfiguration(document);
getMutableContext().context->setConfig(config);
auto query_context = DB::Context::createCopy(getContext().context);
query_context->makeQueryContext();
query_context->setCurrentQueryId(query_id);
chassert(&DB::CurrentThread::get() == &thread_status);
DB::CurrentThread::QueryScope query_scope_holder(query_context);
DB::FileCacheSettings settings;
settings.base_path = cache_base_path;
settings.max_file_segment_size = 5;
settings.max_size = 30;
settings.max_elements = 10;
settings.boundary_alignment = 1;
ReadSettings read_settings;
read_settings.enable_filesystem_cache = true;
read_settings.local_fs_method = LocalFSReadMethod::pread;
std::string file_path = fs::current_path() / "test";
auto read_buffer_creator = [&]()
{
return createReadBufferFromFileBase(file_path, read_settings, std::nullopt, std::nullopt);
};
auto wb = std::make_unique<WriteBufferFromFile>(file_path, DBMS_DEFAULT_BUFFER_SIZE);
std::string s(30, '*');
wb->write(s.data(), s.size());
wb->next();
wb->finalize();
auto cache = std::make_shared<DB::FileCache>(settings);
cache->initialize();
auto key = cache->createKeyForPath(file_path);
{
auto cached_buffer = std::make_shared<CachedOnDiskReadBufferFromFile>(
file_path, key, cache, read_buffer_creator, read_settings, "test", s.size(), false, false, std::nullopt, nullptr);
WriteBufferFromOwnString result;
copyData(*cached_buffer, result);
ASSERT_EQ(result.str(), s);
assertEqual(cache->dumpQueue(), { Range(0, 4), Range(5, 9), Range(10, 14), Range(15, 19), Range(20, 24), Range(25, 29) });
}
{
ReadSettings modified_settings{read_settings};
modified_settings.local_fs_buffer_size = 10;
modified_settings.remote_fs_buffer_size = 10;
auto cached_buffer = std::make_shared<CachedOnDiskReadBufferFromFile>(
file_path, key, cache, read_buffer_creator, modified_settings, "test", s.size(), false, false, std::nullopt, nullptr);
cached_buffer->next();
assertEqual(cache->dumpQueue(), { Range(5, 9), Range(10, 14), Range(15, 19), Range(20, 24), Range(25, 29), Range(0, 4) });
cached_buffer->position() = cached_buffer->buffer().end();
cached_buffer->next();
assertEqual(cache->dumpQueue(), {Range(10, 14), Range(15, 19), Range(20, 24), Range(25, 29), Range(0, 4), Range(5, 9) });
}
}

View File

@ -40,8 +40,8 @@ DistributedAsyncInsertHeader DistributedAsyncInsertHeader::read(ReadBufferFromFi
{
throw Exception(ErrorCodes::CHECKSUM_DOESNT_MATCH,
"Checksum of extra info doesn't match: corrupted data. Reference: {}{}. Actual: {}{}.",
getHexUIntLowercase(expected_checksum.first), getHexUIntLowercase(expected_checksum.second),
getHexUIntLowercase(calculated_checksum.first), getHexUIntLowercase(calculated_checksum.second));
getHexUIntLowercase(expected_checksum.high64), getHexUIntLowercase(expected_checksum.low64),
getHexUIntLowercase(calculated_checksum.high64), getHexUIntLowercase(calculated_checksum.low64));
}
/// Read the parts of the header.

View File

@ -400,7 +400,7 @@ void DataPartStorageOnDiskBase::backup(
if (it != checksums.files.end())
{
file_size = it->second.file_size;
file_hash = {it->second.file_hash.first, it->second.file_hash.second};
file_hash = it->second.file_hash;
}
BackupEntryPtr backup_entry = std::make_unique<BackupEntryFromImmutableFile>(disk, filepath_on_disk, copy_encrypted, file_size, file_hash);

View File

@ -154,9 +154,9 @@ bool MergeTreeDataPartChecksums::readV2(ReadBuffer & in)
assertString("\n\tsize: ", in);
readText(sum.file_size, in);
assertString("\n\thash: ", in);
readText(sum.file_hash.first, in);
readText(sum.file_hash.low64, in);
assertString(" ", in);
readText(sum.file_hash.second, in);
readText(sum.file_hash.high64, in);
assertString("\n\tcompressed: ", in);
readText(sum.is_compressed, in);
if (sum.is_compressed)
@ -164,9 +164,9 @@ bool MergeTreeDataPartChecksums::readV2(ReadBuffer & in)
assertString("\n\tuncompressed size: ", in);
readText(sum.uncompressed_size, in);
assertString("\n\tuncompressed hash: ", in);
readText(sum.uncompressed_hash.first, in);
readText(sum.uncompressed_hash.low64, in);
assertString(" ", in);
readText(sum.uncompressed_hash.second, in);
readText(sum.uncompressed_hash.high64, in);
}
assertChar('\n', in);

View File

@ -250,8 +250,8 @@ std::unordered_map<String, IPartMetadataManager::uint128> PartMetadataManagerWit
ErrorCodes::CORRUPTED_DATA,
"Checksums doesn't match in part {} for {}. Expected: {}. Found {}.",
part->name, file_path,
getHexUIntUppercase(disk_checksum.first) + getHexUIntUppercase(disk_checksum.second),
getHexUIntUppercase(cache_checksums[i].first) + getHexUIntUppercase(cache_checksums[i].second));
getHexUIntUppercase(disk_checksum.high64) + getHexUIntUppercase(disk_checksum.low64),
getHexUIntUppercase(cache_checksums[i].high64) + getHexUIntUppercase(cache_checksums[i].low64));
disk_checksums.push_back(disk_checksum);
continue;
@ -287,8 +287,8 @@ std::unordered_map<String, IPartMetadataManager::uint128> PartMetadataManagerWit
ErrorCodes::CORRUPTED_DATA,
"Checksums doesn't match in projection part {} {}. Expected: {}. Found {}.",
part->name, proj_name,
getHexUIntUppercase(disk_checksum.first) + getHexUIntUppercase(disk_checksum.second),
getHexUIntUppercase(cache_checksums[i].first) + getHexUIntUppercase(cache_checksums[i].second));
getHexUIntUppercase(disk_checksum.high64) + getHexUIntUppercase(disk_checksum.low64),
getHexUIntUppercase(cache_checksums[i].high64) + getHexUIntUppercase(cache_checksums[i].low64));
disk_checksums.push_back(disk_checksum);
}
return results;

View File

@ -252,17 +252,17 @@ void StorageSystemParts::processNextStorage(
if (columns_mask[src_index++])
{
auto checksum = helper.hash_of_all_files;
columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
}
if (columns_mask[src_index++])
{
auto checksum = helper.hash_of_uncompressed_files;
columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
}
if (columns_mask[src_index++])
{
auto checksum = helper.uncompressed_hash_of_compressed_files;
columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
}
}

View File

@ -221,17 +221,17 @@ void StorageSystemProjectionParts::processNextStorage(
if (columns_mask[src_index++])
{
auto checksum = helper.hash_of_all_files;
columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
}
if (columns_mask[src_index++])
{
auto checksum = helper.hash_of_uncompressed_files;
columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
}
if (columns_mask[src_index++])
{
auto checksum = helper.uncompressed_hash_of_compressed_files;
columns[res_index++]->insert(getHexUIntLowercase(checksum.first) + getHexUIntLowercase(checksum.second));
columns[res_index++]->insert(getHexUIntLowercase(checksum.high64) + getHexUIntLowercase(checksum.low64));
}
}

View File

@ -1,5 +1,5 @@
from pathlib import Path
from typing import Dict, List
from typing import Dict, List, Optional
import os
import logging
@ -58,14 +58,19 @@ def upload_results(
test_results: TestResults,
additional_files: List[str],
check_name: str,
additional_urls: Optional[List[str]] = None,
) -> str:
normalized_check_name = check_name.lower()
for r in ((" ", "_"), ("(", "_"), (")", "_"), (",", "_"), ("/", "_")):
normalized_check_name = normalized_check_name.replace(*r)
# Preserve additional_urls to not modify the original one
original_additional_urls = additional_urls or []
s3_path_prefix = f"{pr_number}/{commit_sha}/{normalized_check_name}"
additional_urls = process_logs(
s3_client, additional_files, s3_path_prefix, test_results
)
additional_urls.extend(original_additional_urls)
branch_url = f"{GITHUB_SERVER_URL}/{GITHUB_REPOSITORY}/commits/master"
branch_name = "master"

View File

@ -231,6 +231,9 @@ class _NetworkManager:
def _ensure_container(self):
if self._container is None or self._container_expire_time <= time.time():
image_name = "clickhouse/integration-helper:" + os.getenv(
"DOCKER_HELPER_TAG", "latest"
)
for i in range(5):
if self._container is not None:
try:
@ -247,7 +250,7 @@ class _NetworkManager:
time.sleep(i)
image = subprocess.check_output(
"docker images -q clickhouse/integration-helper 2>/dev/null", shell=True
f"docker images -q {image_name} 2>/dev/null", shell=True
)
if not image.strip():
print("No network image helper, will try download")
@ -256,16 +259,16 @@ class _NetworkManager:
for i in range(5):
try:
subprocess.check_call( # STYLE_CHECK_ALLOW_SUBPROCESS_CHECK_CALL
"docker pull clickhouse/integration-helper", shell=True
f"docker pull {image_name}", shell=True
)
break
except:
time.sleep(i)
else:
raise Exception("Cannot pull clickhouse/integration-helper image")
raise Exception(f"Cannot pull {image_name} image")
self._container = self._docker_client.containers.run(
"clickhouse/integration-helper",
image_name,
auto_remove=True,
command=("sleep %s" % self.container_exit_timeout),
# /run/xtables.lock passed inside for correct iptables --wait

View File

@ -336,6 +336,8 @@ if __name__ == "__main__":
env_tags += "-e {}={} ".format("DOCKER_MYSQL_PHP_CLIENT_TAG", tag)
elif image == "clickhouse/postgresql-java-client":
env_tags += "-e {}={} ".format("DOCKER_POSTGRESQL_JAVA_CLIENT_TAG", tag)
elif image == "clickhouse/integration-helper":
env_tags += "-e {}={} ".format("DOCKER_HELPER_TAG", tag)
elif image == "clickhouse/integration-test":
env_tags += "-e {}={} ".format("DOCKER_BASE_TAG", tag)
elif image == "clickhouse/kerberized-hadoop":

View File

@ -1 +1 @@
20000101_1_1_0 test_00961 b5fce9c4ef1ca42ce4ed027389c208d2 fc3b062b646cd23d4c23d7f5920f89ae da96ff1e527a8a1f908ddf2b1d0af239
20000101_1_1_0 test_00961 e4ed027389c208d2b5fce9c4ef1ca42c 4c23d7f5920f89aefc3b062b646cd23d 908ddf2b1d0af239da96ff1e527a8a1f

View File

@ -0,0 +1,2 @@
1
1

View File

@ -0,0 +1,6 @@
DROP TABLE IF EXISTS t10;
CREATE TABLE t10 (`c0` Int32) ENGINE = MergeTree ORDER BY tuple();
INSERT INTO t10 (c0) FORMAT Values (-1);
SELECT 1 FROM t10 GROUP BY erf(-sign(t10.c0));
SELECT 1 FROM t10 GROUP BY -sign(t10.c0);
DROP TABLE t10;

View File

@ -45,7 +45,7 @@ int main(int, char **)
{
auto flipped = flipBit(str, pos);
auto checksum = CityHash_v1_0_2::CityHash128(flipped.data(), flipped.size());
std::cout << getHexUIntLowercase(checksum.first) << getHexUIntLowercase(checksum.second) << "\t" << pos / 8 << ", " << pos % 8 << "\n";
std::cout << getHexUIntLowercase(checksum.high64) << getHexUIntLowercase(checksum.low64) << "\t" << pos / 8 << ", " << pos % 8 << "\n";
}
return 0;

View File

@ -1,3 +1,4 @@
v23.5.4.25-stable 2023-06-29
v23.5.3.24-stable 2023-06-17
v23.5.2.7-stable 2023-06-10
v23.5.1.3174-stable 2023-06-09

1 v23.5.3.24-stable v23.5.4.25-stable 2023-06-17 2023-06-29
1 v23.5.4.25-stable 2023-06-29
2 v23.5.3.24-stable v23.5.3.24-stable 2023-06-17 2023-06-17
3 v23.5.2.7-stable v23.5.2.7-stable 2023-06-10 2023-06-10
4 v23.5.1.3174-stable v23.5.1.3174-stable 2023-06-09 2023-06-09