thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 00:30:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'ClickHouse:master' into master

Browse Source
This commit is contained in:
MyroTk 2024-02-01 17:05:36 -08:00 committed by GitHub
commit dffc539880
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1544 changed files with 38646 additions and 13499 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
.github/workflows/backport_branches.yml vendored
View File

@ -138,19 +138,26 @@ jobs:
############################################################################################
##################################### Docker images #######################################
############################################################################################
DockerServerImages:
DockerServerImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker server and keeper images
test_name: Docker server image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0 # It MUST BE THE SAME for all dependencies and the job itself
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-server --image-path docker/server --allow-build-reuse
DockerKeeperImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker keeper image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper --allow-build-reuse
############################################################################################

2
.github/workflows/jepsen.yml vendored
View File

@ -8,13 +8,13 @@ on: # yamllint disable-line rule:truthy
schedule:
- cron: '0 */6 * * *'
workflow_dispatch:
workflow_call:
jobs:
KeeperJepsenRelease:
uses: ./.github/workflows/reusable_simple_job.yml
with:
test_name: Jepsen keeper check
runner_type: style-checker
report_required: true
run_command: |
python3 jepsen_check.py keeper
# ServerJepsenRelease:

26
.github/workflows/master.yml vendored
View File

@ -15,6 +15,8 @@ jobs:
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@a701ed95a46e6f2fb0df25e1a558c16356fae35a
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
@ -33,11 +35,9 @@ jobs:
- name: PrepareRunConfig
id: runconfig
run: |
echo "::group::configure CI run"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --rebuild-all-binaries --outfile ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
echo "::group::CI run configure results"
echo "::group::CI configuration"
python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
@ -242,22 +242,28 @@ jobs:
############################################################################################
##################################### Docker images #######################################
############################################################################################
DockerServerImages:
DockerServerImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker server and keeper images
test_name: Docker server image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
# FIXME: avoid using 0 checkout
checkout_depth: 0 # It MUST BE THE SAME for all dependencies and the job itself
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_server.py --release-type head \
--image-repo clickhouse/clickhouse-server --image-path docker/server
--image-repo clickhouse/clickhouse-server --image-path docker/server --allow-build-reuse
DockerKeeperImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker keeper image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 docker_server.py --release-type head \
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper --allow-build-reuse
############################################################################################
##################################### BUILD REPORTER #######################################
############################################################################################

45
.github/workflows/pull_request.yml vendored
View File

@ -22,6 +22,8 @@ jobs:
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@a701ed95a46e6f2fb0df25e1a558c16356fae35a
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
@ -44,11 +46,9 @@ jobs:
- name: PrepareRunConfig
id: runconfig
run: |
echo "::group::configure CI run"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --outfile ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
echo "::group::CI run configure results"
echo "::group::CI configuration"
python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
@ -67,6 +67,7 @@ jobs:
DOCKER_TAG=$(echo '${{ toJson(fromJson(steps.runconfig.outputs.CI_DATA).docker_data.images) }}' | tr -d '\n')
export DOCKER_TAG=$DOCKER_TAG
python3 ./tests/ci/style_check.py --no-push
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ runner.temp }}/ci_run_data.json --post --job-name 'Style check'
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() }}
@ -103,7 +104,7 @@ jobs:
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Fast tests
test_name: Fast test
runner_type: builder
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
@ -272,19 +273,26 @@ jobs:
############################################################################################
##################################### Docker images #######################################
############################################################################################
DockerServerImages:
DockerServerImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker server and keeper images
test_name: Docker server image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0 # It MUST BE THE SAME for all dependencies and the job itself
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-server --image-path docker/server --allow-build-reuse
DockerKeeperImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker keeper image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper --allow-build-reuse
############################################################################################
@ -796,7 +804,7 @@ jobs:
test_name: Unit tests (asan)
runner_type: fuzzer-unit-tester
data: ${{ needs.RunConfig.outputs.data }}
UnitTestsReleaseClang:
UnitTestsRelease:
needs: [RunConfig, BuilderBinRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
@ -923,7 +931,7 @@ jobs:
- UnitTestsTsan
- UnitTestsMsan
- UnitTestsUBsan
- UnitTestsReleaseClang
- UnitTestsRelease
- CompatibilityCheckX86
- CompatibilityCheckAarch64
- SQLancerTestRelease
@ -966,13 +974,20 @@ jobs:
#############################################################################################
###################################### JEPSEN TESTS #########################################
#############################################################################################
# This is special test NOT INCLUDED in FinishCheck
# When it's skipped, all dependent tasks will be skipped too.
# DO NOT add it there
Jepsen:
# This is special test NOT INCLUDED in FinishCheck
# When it's skipped, all dependent tasks will be skipped too.
# DO NOT add it there
if: ${{ !failure() && !cancelled() && contains(github.event.pull_request.labels.*.name, 'jepsen-test') }}
# we need concurrency as the job uses dedicated instances in the cloud
concurrency:
group: jepsen
if: ${{ !failure() && !cancelled() }}
needs: [RunConfig, BuilderBinRelease]
uses: ./.github/workflows/jepsen.yml
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse Keeper Jepsen
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
#############################################################################################
####################################### libFuzzer ###########################################
#############################################################################################

18
.github/workflows/release_branches.yml vendored
View File

@ -153,19 +153,26 @@ jobs:
############################################################################################
##################################### Docker images #######################################
############################################################################################
DockerServerImages:
DockerServerImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker server and keeper images
test_name: Docker server image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0
run_command: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-server --image-path docker/server --allow-build-reuse
DockerKeeperImage:
needs: [RunConfig, BuilderDebRelease, BuilderDebAarch64]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Docker keeper image
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 docker_server.py --release-type head --no-push \
--image-repo clickhouse/clickhouse-keeper --image-path docker/keeper --allow-build-reuse
############################################################################################
@ -456,7 +463,8 @@ jobs:
FinishCheck:
if: ${{ !failure() && !cancelled() }}
needs:
- DockerServerImages
- DockerServerImage
- DockerKeeperImage
- BuilderReport
- BuilderSpecialReport
- MarkReleaseReady

10
.github/workflows/reusable_build.yml vendored
View File

@ -58,6 +58,7 @@ jobs:
- name: Apply sparse checkout for contrib # in order to check that it doesn't break build
# This step is done in GITHUB_WORKSPACE,
# because it's broken in REPO_COPY for some reason
# See also update-submodules.sh
if: ${{ env.BUILD_SPARSE_CHECKOUT == 'true' }}
run: |
rm -rf "$GITHUB_WORKSPACE/contrib" && echo 'removed'
@ -72,12 +73,15 @@ jobs:
- name: Pre
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --pre --job-name '${{inputs.build_name}}'
- name: Build
- name: Run
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/build_check.py" "$BUILD_NAME"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" \
--infile ${{ toJson(inputs.data) }} \
--job-name "$BUILD_NAME" \
--run
- name: Post
# it still be build report to upload for failed build job
if: always()
if: ${{ !cancelled() }}
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --post --job-name '${{inputs.build_name}}'
- name: Mark as done

18
.github/workflows/reusable_simple_job.yml vendored
View File

@ -34,12 +34,16 @@ name: Simple job
working-directory:
description: sets custom working directory
type: string
default: ""
default: "$GITHUB_WORKSPACE/tests/ci"
git_ref:
description: commit to use, merge commit for pr or head
required: false
type: string
default: ${{ github.event.after }} # no merge commit
report_required:
description: set to true if job report with the commit status required
type: boolean
default: false
secrets:
secret_envs:
description: if given, it's passed to the environments
@ -58,6 +62,8 @@ jobs:
env:
GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}
steps:
- name: DebugInfo
uses: hmarr/debug-action@a701ed95a46e6f2fb0df25e1a558c16356fae35a
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
@ -79,12 +85,12 @@ jobs:
job_type: test
- name: Run
run: |
if [ -n '${{ inputs.working-directory }}' ]; then
cd "${{ inputs.working-directory }}"
else
cd "$GITHUB_WORKSPACE/tests/ci"
fi
cd "${{ inputs.working-directory }}"
${{ inputs.run_command }}
- name: Post
if: ${{ inputs.report_required }}
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --post --job-name '${{inputs.test_name}}'
- name: Clean
if: always()
uses: ./.github/actions/clean

21
.github/workflows/reusable_test.yml vendored
View File

@ -38,7 +38,7 @@ name: Testing workflow
working-directory:
description: sets custom working directory
type: string
default: ""
default: "$GITHUB_WORKSPACE/tests/ci"
secrets:
secret_envs:
description: if given, it's passed to the environments
@ -96,19 +96,14 @@ jobs:
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --pre --job-name '${{inputs.test_name}}'
- name: Run
run: |
if [ -n "${{ inputs.working-directory }}" ]; then
cd "${{ inputs.working-directory }}"
else
cd "$GITHUB_WORKSPACE/tests/ci"
fi
if [ -n "$(echo '${{ inputs.run_command }}' | tr -d '\n')" ]; then
echo "Running command from workflow input"
${{ inputs.run_command }}
else
echo "Running command from job config"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --run --job-name '${{inputs.test_name}}'
fi
cd "${{ inputs.working-directory }}"
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" \
--infile ${{ toJson(inputs.data) }} \
--job-name '${{inputs.test_name}}' \
--run \
--run-command '''${{inputs.run_command}}'''
- name: Post run
if: ${{ !cancelled() }}
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ toJson(inputs.data) }} --post --job-name '${{inputs.test_name}}'
- name: Mark as done

15
.gitmessage
View File

@ -1,9 +1,18 @@
## To avoid merge commit in CI run (add a leading space to apply):
#no-merge-commit
### CI modificators (add a leading space to apply):
## Running specified job (add a leading space to apply):
## To avoid a merge commit in CI:
#no_merge_commit
## To discard CI cache:
#no_ci_cache
## To run specified set of tests in CI:
#ci_set_<SET_NAME>
#ci_set_reduced
## To run specified job in CI:
#job_<JOB NAME>
#job_stateless_tests_release
#job_package_debug

2
.gitmodules vendored
View File

@ -99,7 +99,7 @@
url = https://github.com/awslabs/aws-c-event-stream
[submodule "aws-c-common"]
path = contrib/aws-c-common
url = https://github.com/ClickHouse/aws-c-common
url = https://github.com/awslabs/aws-c-common.git
[submodule "aws-checksums"]
path = contrib/aws-checksums
url = https://github.com/awslabs/aws-checksums

2308
CHANGELOG.md
View File

File diff suppressed because it is too large Load Diff

3
SECURITY.md
View File

@ -13,9 +13,10 @@ The following versions of ClickHouse server are currently being supported with s
| Version | Supported |
|:-|:-|
| 24.1 | ✔️ |
| 23.12 | ✔️ |
| 23.11 | ✔️ |
| 23.10 | ✔️ |
| 23.10 | ❌ |
| 23.9 | ❌ |
| 23.8 | ✔️ |
| 23.7 | ❌ |

20
base/base/sort.h
View File

@ -64,19 +64,14 @@ using ComparatorWrapper = Comparator;
#include <miniselect/floyd_rivest_select.h>
template <typename RandomIt>
void nth_element(RandomIt first, RandomIt nth, RandomIt last)
template <typename RandomIt, typename Compare>
void nth_element(RandomIt first, RandomIt nth, RandomIt last, Compare compare)
{
using value_type = typename std::iterator_traits<RandomIt>::value_type;
using comparator = std::less<value_type>;
comparator compare;
ComparatorWrapper<comparator> compare_wrapper = compare;
#ifndef NDEBUG
::shuffle(first, last);
#endif
ComparatorWrapper<Compare> compare_wrapper = compare;
::miniselect::floyd_rivest_select(first, nth, last, compare_wrapper);
#ifndef NDEBUG
@ -87,6 +82,15 @@ void nth_element(RandomIt first, RandomIt nth, RandomIt last)
#endif
}
template <typename RandomIt>
void nth_element(RandomIt first, RandomIt nth, RandomIt last)
{
using value_type = typename std::iterator_traits<RandomIt>::value_type;
using comparator = std::less<value_type>;
::nth_element(first, nth, last, comparator());
}
template <typename RandomIt, typename Compare>
void partial_sort(RandomIt first, RandomIt middle, RandomIt last, Compare compare)
{

6
base/poco/Foundation/CMakeLists.txt
View File

@ -166,6 +166,12 @@ set (SRCS
)
add_library (_poco_foundation ${SRCS})
target_link_libraries (_poco_foundation
PUBLIC
boost::headers_only
boost::system
)
add_library (Poco::Foundation ALIAS _poco_foundation)
# TODO: remove these warning exclusions

7
base/poco/Foundation/include/Poco/BufferedStreamBuf.h
View File

@ -26,6 +26,11 @@
#include "Poco/StreamUtil.h"
namespace DB
{
class ReadBufferFromIStream;
}
namespace Poco
{
@ -120,6 +125,8 @@ protected:
openmode getMode() const { return _mode; }
private:
friend class DB::ReadBufferFromIStream;
virtual int readFromDevice(char_type * /*buffer*/, std::streamsize /*length*/) { return 0; }
virtual int writeToDevice(const char_type * /*buffer*/, std::streamsize /*length*/) { return 0; }

56
base/poco/Foundation/include/Poco/Logger.h
View File

@ -22,6 +22,9 @@
#include <cstddef>
#include <map>
#include <vector>
#include <boost/smart_ptr/intrusive_ptr.hpp>
#include "Poco/Channel.h"
#include "Poco/Format.h"
#include "Poco/Foundation.h"
@ -33,7 +36,8 @@ namespace Poco
class Exception;
class Logger;
using LoggerPtr = boost::intrusive_ptr<Logger>;
class Foundation_API Logger : public Channel
/// Logger is a special Channel that acts as the main
@ -870,21 +874,21 @@ public:
/// If the Logger does not yet exist, it is created, based
/// on its parent logger.
static Logger & unsafeGet(const std::string & name);
/// Returns a reference to the Logger with the given name.
static LoggerPtr getShared(const std::string & name, bool should_be_owned_by_shared_ptr_if_created = true);
/// Returns a shared pointer to the Logger with the given name.
/// If the Logger does not yet exist, it is created, based
/// on its parent logger.
///
/// WARNING: This method is not thread safe. You should
/// probably use get() instead.
/// The only time this method should be used is during
/// program initialization, when only one thread is running.
static Logger & create(const std::string & name, Channel * pChannel, int level = Message::PRIO_INFORMATION);
/// Creates and returns a reference to a Logger with the
/// given name. The Logger's Channel and log level as set as
/// specified.
static LoggerPtr createShared(const std::string & name, Channel * pChannel, int level = Message::PRIO_INFORMATION);
/// Creates and returns a shared pointer to a Logger with the
/// given name. The Logger's Channel and log level as set as
/// specified.
static Logger & root();
/// Returns a reference to the root logger, which is the ultimate
/// ancestor of all Loggers.
@ -893,13 +897,6 @@ public:
/// Returns a pointer to the Logger with the given name if it
/// exists, or a null pointer otherwise.
static void destroy(const std::string & name);
/// Destroys the logger with the specified name. Does nothing
/// if the logger is not found.
///
/// After a logger has been destroyed, all references to it
/// become invalid.
static void shutdown();
/// Shuts down the logging framework and releases all
/// Loggers.
@ -928,9 +925,17 @@ public:
static const std::string ROOT; /// The name of the root logger ("").
protected:
typedef std::map<std::string, Logger *> LoggerMap;
public:
struct LoggerEntry
{
Poco::Logger * logger;
bool owned_by_shared_ptr = false;
};
using LoggerMap = std::unordered_map<std::string, LoggerEntry>;
using LoggerMapIterator = LoggerMap::iterator;
protected:
Logger(const std::string & name, Channel * pChannel, int level);
~Logger();
@ -938,11 +943,19 @@ protected:
void log(const std::string & text, Message::Priority prio, const char * file, int line);
static std::string format(const std::string & fmt, int argc, std::string argv[]);
static Logger & parent(const std::string & name);
static void add(Logger * pLogger);
static Logger * find(const std::string & name);
private:
static std::pair<Logger::LoggerMapIterator, bool> unsafeGet(const std::string & name, bool get_shared);
static Logger * unsafeGetRawPtr(const std::string & name);
static std::pair<LoggerMapIterator, bool> unsafeCreate(const std::string & name, Channel * pChannel, int level = Message::PRIO_INFORMATION);
static Logger & parent(const std::string & name);
static std::pair<LoggerMapIterator, bool> add(Logger * pLogger);
static std::optional<LoggerMapIterator> find(const std::string & name);
static Logger * findRawPtr(const std::string & name);
friend void intrusive_ptr_add_ref(Logger * ptr);
friend void intrusive_ptr_release(Logger * ptr);
Logger();
Logger(const Logger &);
Logger & operator=(const Logger &);
@ -950,9 +963,6 @@ private:
std::string _name;
Channel * _pChannel;
std::atomic_int _level;
static LoggerMap * _pLoggerMap;
static Mutex _mapMtx;
};

29
base/poco/Foundation/include/Poco/RefCountedObject.h
View File

@ -38,55 +38,58 @@ public:
/// Creates the RefCountedObject.
/// The initial reference count is one.
void duplicate() const;
/// Increments the object's reference count.
size_t duplicate() const;
/// Increments the object's reference count, returns reference count before call.
void release() const throw();
size_t release() const throw();
/// Decrements the object's reference count
/// and deletes the object if the count
/// reaches zero.
/// reaches zero, returns reference count before call.
int referenceCount() const;
size_t referenceCount() const;
/// Returns the reference count.
protected:
virtual ~RefCountedObject();
/// Destroys the RefCountedObject.
mutable std::atomic<size_t> _counter;
private:
RefCountedObject(const RefCountedObject &);
RefCountedObject & operator=(const RefCountedObject &);
mutable AtomicCounter _counter;
};
//
// inlines
//
inline int RefCountedObject::referenceCount() const
inline size_t RefCountedObject::referenceCount() const
{
return _counter.value();
return _counter.load(std::memory_order_acquire);
}
inline void RefCountedObject::duplicate() const
inline size_t RefCountedObject::duplicate() const
{
++_counter;
return _counter.fetch_add(1, std::memory_order_acq_rel);
}
inline void RefCountedObject::release() const throw()
inline size_t RefCountedObject::release() const throw()
{
size_t reference_count_before = _counter.fetch_sub(1, std::memory_order_acq_rel);
try
{
if (--_counter == 0)
if (reference_count_before == 1)
delete this;
}
catch (...)
{
poco_unexpected();
}
return reference_count_before;
}

254
base/poco/Foundation/src/Logger.cpp
View File

@ -20,12 +20,31 @@
#include "Poco/NumberParser.h"
#include "Poco/String.h"
#include <cassert>
#include <mutex>
namespace
{
std::mutex & getLoggerMutex()
{
auto get_logger_mutex_placeholder_memory = []()
{
static char buffer[sizeof(std::mutex)]{};
return buffer;
};
static std::mutex * logger_mutex = new (get_logger_mutex_placeholder_memory()) std::mutex();
return *logger_mutex;
}
Poco::Logger::LoggerMap * _pLoggerMap = nullptr;
}
namespace Poco {
Logger::LoggerMap* Logger::_pLoggerMap = 0;
Mutex Logger::_mapMtx;
const std::string Logger::ROOT;
@ -112,17 +131,17 @@ void Logger::dump(const std::string& msg, const void* buffer, std::size_t length
void Logger::setLevel(const std::string& name, int level)
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
if (_pLoggerMap)
{
std::string::size_type len = name.length();
for (LoggerMap::iterator it = _pLoggerMap->begin(); it != _pLoggerMap->end(); ++it)
for (auto & it : *_pLoggerMap)
{
if (len == 0 ||
(it->first.compare(0, len, name) == 0 && (it->first.length() == len || it->first[len] == '.')))
(it.first.compare(0, len, name) == 0 && (it.first.length() == len || it.first[len] == '.')))
{
it->second->setLevel(level);
it.second.logger->setLevel(level);
}
}
}
@ -131,17 +150,17 @@ void Logger::setLevel(const std::string& name, int level)
void Logger::setChannel(const std::string& name, Channel* pChannel)
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
if (_pLoggerMap)
{
std::string::size_type len = name.length();
for (LoggerMap::iterator it = _pLoggerMap->begin(); it != _pLoggerMap->end(); ++it)
for (auto & it : *_pLoggerMap)
{
if (len == 0 ||
(it->first.compare(0, len, name) == 0 && (it->first.length() == len || it->first[len] == '.')))
(it.first.compare(0, len, name) == 0 && (it.first.length() == len || it.first[len] == '.')))
{
it->second->setChannel(pChannel);
it.second.logger->setChannel(pChannel);
}
}
}
@ -150,17 +169,17 @@ void Logger::setChannel(const std::string& name, Channel* pChannel)
void Logger::setProperty(const std::string& loggerName, const std::string& propertyName, const std::string& value)
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
if (_pLoggerMap)
{
std::string::size_type len = loggerName.length();
for (LoggerMap::iterator it = _pLoggerMap->begin(); it != _pLoggerMap->end(); ++it)
for (auto & it : *_pLoggerMap)
{
if (len == 0 ||
(it->first.compare(0, len, loggerName) == 0 && (it->first.length() == len || it->first[len] == '.')))
(it.first.compare(0, len, loggerName) == 0 && (it.first.length() == len || it.first[len] == '.')))
{
it->second->setProperty(propertyName, value);
it.second.logger->setProperty(propertyName, value);
}
}
}
@ -280,108 +299,226 @@ void Logger::formatDump(std::string& message, const void* buffer, std::size_t le
}
Logger& Logger::get(const std::string& name)
namespace
{
Mutex::ScopedLock lock(_mapMtx);
return unsafeGet(name);
inline LoggerPtr makeLoggerPtr(Logger & logger)
{
return LoggerPtr(&logger, false /*add_ref*/);
}
}
Logger& Logger::unsafeGet(const std::string& name)
Logger& Logger::get(const std::string& name)
{
Logger* pLogger = find(name);
if (!pLogger)
std::lock_guard<std::mutex> lock(getLoggerMutex());
auto [it, inserted] = unsafeGet(name, false /*get_shared*/);
return *it->second.logger;
}
LoggerPtr Logger::getShared(const std::string & name, bool should_be_owned_by_shared_ptr_if_created)
{
std::lock_guard<std::mutex> lock(getLoggerMutex());
auto [it, inserted] = unsafeGet(name, true /*get_shared*/);
/** If during `unsafeGet` logger was created, then this shared pointer owns it.
* If logger was already created, then this shared pointer does not own it.
*/
if (inserted)
{
if (should_be_owned_by_shared_ptr_if_created)
it->second.owned_by_shared_ptr = true;
else
it->second.logger->duplicate();
}
return makeLoggerPtr(*it->second.logger);
}
std::pair<Logger::LoggerMapIterator, bool> Logger::unsafeGet(const std::string& name, bool get_shared)
{
std::optional<Logger::LoggerMapIterator> optional_logger_it = find(name);
bool should_recreate_logger = false;
if (optional_logger_it)
{
auto & logger_it = *optional_logger_it;
std::optional<size_t> reference_count_before;
if (get_shared)
{
reference_count_before = logger_it->second.logger->duplicate();
}
else if (logger_it->second.owned_by_shared_ptr)
{
reference_count_before = logger_it->second.logger->duplicate();
logger_it->second.owned_by_shared_ptr = false;
}
/// Other thread already decided to delete this logger, but did not yet remove it from map
if (reference_count_before && reference_count_before == 0)
should_recreate_logger = true;
}
if (!optional_logger_it || should_recreate_logger)
{
Logger * logger = nullptr;
if (name == ROOT)
{
pLogger = new Logger(name, 0, Message::PRIO_INFORMATION);
logger = new Logger(name, nullptr, Message::PRIO_INFORMATION);
}
else
{
Logger& par = parent(name);
pLogger = new Logger(name, par.getChannel(), par.getLevel());
logger = new Logger(name, par.getChannel(), par.getLevel());
}
add(pLogger);
if (should_recreate_logger)
{
(*optional_logger_it)->second.logger = logger;
return std::make_pair(*optional_logger_it, true);
}
return add(logger);
}
return *pLogger;
return std::make_pair(*optional_logger_it, false);
}
Logger * Logger::unsafeGetRawPtr(const std::string & name)
{
return unsafeGet(name, false /*get_shared*/).first->second.logger;
}
Logger& Logger::create(const std::string& name, Channel* pChannel, int level)
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
if (find(name)) throw ExistsException();
Logger* pLogger = new Logger(name, pChannel, level);
add(pLogger);
return *pLogger;
return *unsafeCreate(name, pChannel, level).first->second.logger;
}
LoggerPtr Logger::createShared(const std::string & name, Channel * pChannel, int level)
{
std::lock_guard<std::mutex> lock(getLoggerMutex());
auto [it, inserted] = unsafeCreate(name, pChannel, level);
it->second.owned_by_shared_ptr = true;
return makeLoggerPtr(*it->second.logger);
}
Logger& Logger::root()
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
return unsafeGet(ROOT);
return *unsafeGetRawPtr(ROOT);
}
Logger* Logger::has(const std::string& name)
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
return find(name);
auto optional_it = find(name);
if (!optional_it)
return nullptr;
return (*optional_it)->second.logger;
}
void Logger::shutdown()
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
if (_pLoggerMap)
{
for (LoggerMap::iterator it = _pLoggerMap->begin(); it != _pLoggerMap->end(); ++it)
for (auto & it : *_pLoggerMap)
{
it->second->release();
if (it.second.owned_by_shared_ptr)
continue;
it.second.logger->release();
}
delete _pLoggerMap;
_pLoggerMap = 0;
_pLoggerMap = nullptr;
}
}
Logger* Logger::find(const std::string& name)
std::optional<Logger::LoggerMapIterator> Logger::find(const std::string& name)
{
if (_pLoggerMap)
{
LoggerMap::iterator it = _pLoggerMap->find(name);
if (it != _pLoggerMap->end())
return it->second;
return it;
return {};
}
return 0;
return {};
}
Logger * Logger::findRawPtr(const std::string & name)
{
auto optional_it = find(name);
if (!optional_it)
return nullptr;
return (*optional_it)->second.logger;
}
void Logger::destroy(const std::string& name)
void intrusive_ptr_add_ref(Logger * ptr)
{
Mutex::ScopedLock lock(_mapMtx);
ptr->duplicate();
}
void intrusive_ptr_release(Logger * ptr)
{
size_t reference_count_before = ptr->_counter.fetch_sub(1, std::memory_order_acq_rel);
if (reference_count_before != 1)
return;
if (_pLoggerMap)
{
LoggerMap::iterator it = _pLoggerMap->find(name);
if (it != _pLoggerMap->end())
std::lock_guard<std::mutex> lock(getLoggerMutex());
if (_pLoggerMap)
{
it->second->release();
_pLoggerMap->erase(it);
auto it = _pLoggerMap->find(ptr->name());
/** It is possible that during release other thread created logger and
* updated iterator in map.
*/
if (it != _pLoggerMap->end() && ptr == it->second.logger)
{
/** If reference count is 0, this means this intrusive pointer owns logger
* and need destroy it.
*/
assert(it->second.owned_by_shared_ptr);
_pLoggerMap->erase(it);
}
}
}
delete ptr;
}
void Logger::names(std::vector<std::string>& names)
{
Mutex::ScopedLock lock(_mapMtx);
std::lock_guard<std::mutex> lock(getLoggerMutex());
names.clear();
if (_pLoggerMap)
@ -394,19 +531,27 @@ void Logger::names(std::vector<std::string>& names)
}
std::pair<Logger::LoggerMapIterator, bool> Logger::unsafeCreate(const std::string & name, Channel * pChannel, int level)
{
if (find(name)) throw ExistsException();
Logger* pLogger = new Logger(name, pChannel, level);
return add(pLogger);
}
Logger& Logger::parent(const std::string& name)
{
std::string::size_type pos = name.rfind('.');
if (pos != std::string::npos)
{
std::string pname = name.substr(0, pos);
Logger* pParent = find(pname);
Logger* pParent = findRawPtr(pname);
if (pParent)
return *pParent;
else
return parent(pname);
}
else return unsafeGet(ROOT);
else return *unsafeGetRawPtr(ROOT);
}
@ -474,11 +619,14 @@ namespace
}
void Logger::add(Logger* pLogger)
std::pair<Logger::LoggerMapIterator, bool> Logger::add(Logger* pLogger)
{
if (!_pLoggerMap)
_pLoggerMap = new LoggerMap;
_pLoggerMap->insert(LoggerMap::value_type(pLogger->name(), pLogger));
_pLoggerMap = new Logger::LoggerMap;
auto result = _pLoggerMap->emplace(pLogger->name(), LoggerEntry{pLogger, false /*owned_by_shared_ptr*/});
assert(result.second);
return result;
}

10
cmake/autogenerated_versions.txt
View File

@ -2,11 +2,11 @@
# NOTE: has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
SET(VERSION_REVISION 54482)
SET(VERSION_REVISION 54483)
SET(VERSION_MAJOR 24)
SET(VERSION_MINOR 1)
SET(VERSION_MINOR 2)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH a2faa65b080a587026c86844f3a20c74d23a86f8)
SET(VERSION_DESCRIBE v24.1.1.1-testing)
SET(VERSION_STRING 24.1.1.1)
SET(VERSION_GITHASH 5a024dfc0936e062770d0cfaad0805b57c1fba17)
SET(VERSION_DESCRIBE v24.2.1.1-testing)
SET(VERSION_STRING 24.2.1.1)
# end of autochange

9
cmake/sanitize.cmake
View File

@ -79,7 +79,10 @@ if (SANITIZE_COVERAGE)
# But the actual coverage will be enabled on per-library basis: for ClickHouse code, but not for 3rd-party.
set (COVERAGE_FLAGS "-fsanitize-coverage=trace-pc-guard,pc-table")
endif()
set (WITHOUT_COVERAGE_FLAGS "-fno-profile-instr-generate -fno-coverage-mapping -fno-sanitize-coverage=trace-pc-guard,pc-table")
set (WITHOUT_COVERAGE_FLAGS_LIST -fno-profile-instr-generate -fno-coverage-mapping -fno-sanitize-coverage=trace-pc-guard,pc-table)
set (WITHOUT_COVERAGE_FLAGS "-fno-profile-instr-generate -fno-coverage-mapping -fno-sanitize-coverage=trace-pc-guard,pc-table")
set (WITHOUT_COVERAGE_FLAGS_LIST -fno-profile-instr-generate -fno-coverage-mapping -fno-sanitize-coverage=trace-pc-guard,pc-table)
else()
set (WITHOUT_COVERAGE_FLAGS "")
set (WITHOUT_COVERAGE_FLAGS_LIST "")
endif()

2
contrib/aws vendored

@ -1 +1 @@
Subproject commit ca02358dcc7ce3ab733dd4cbcc32734eecfa4ee3
Subproject commit 4ec215f3607c2111bf2cc91ba842046a6b5eb0c4

2
contrib/aws-c-auth vendored

@ -1 +1 @@
Subproject commit 97133a2b5dbca1ccdf88cd6f44f39d0531d27d12
Subproject commit baeffa791d9d1cf61460662a6d9ac2186aaf05df

2
contrib/aws-c-cal vendored

@ -1 +1 @@
Subproject commit 85dd7664b786a389c6fb1a6f031ab4bb2282133d
Subproject commit 9453687ff5493ba94eaccf8851200565c4364c77

2
contrib/aws-c-common vendored

@ -1 +1 @@
Subproject commit 45dcb2849c891dba2100b270b4676765c92949ff
Subproject commit 80f21b3cac5ac51c6b8a62c7d2a5ef58a75195ee

2
contrib/aws-c-compression vendored

@ -1 +1 @@
Subproject commit b517b7decd0dac30be2162f5186c250221c53aff
Subproject commit 99ec79ee2970f1a045d4ced1501b97ee521f2f85

2
contrib/aws-c-event-stream vendored

@ -1 +1 @@
Subproject commit 2f9b60c42f90840ec11822acda3d8cdfa97a773d
Subproject commit 08f24e384e5be20bcffa42b49213d24dad7881ae

2
contrib/aws-c-http vendored

@ -1 +1 @@
Subproject commit dd34461987947672444d0bc872c5a733dfdb9711
Subproject commit a082f8a2067e4a31db73f1d4ffd702a8dc0f7089

2
contrib/aws-c-io vendored

@ -1 +1 @@
Subproject commit d58ed4f272b1cb4f89ac9196526ceebe5f2b0d89
Subproject commit 11ce3c750a1dac7b04069fc5bff89e97e91bad4d

2
contrib/aws-c-mqtt vendored

@ -1 +1 @@
Subproject commit 33c3455cec82b16feb940e12006cefd7b3ef4194
Subproject commit 6d36cd3726233cb757468d0ea26f6cd8dad151ec

2
contrib/aws-c-s3 vendored

@ -1 +1 @@
Subproject commit d7bfe602d6925948f1fff95784e3613cca6a3900
Subproject commit de36fee8fe7ab02f10987877ae94a805bf440c1f

2
contrib/aws-c-sdkutils vendored

@ -1 +1 @@
Subproject commit 208a701fa01e99c7c8cc3dcebc8317da71362972
Subproject commit fd8c0ba2e233997eaaefe82fb818b8b444b956d3

2
contrib/aws-checksums vendored

@ -1 +1 @@
Subproject commit ad53be196a25bbefa3700a01187fdce573a7d2d0
Subproject commit 321b805559c8e911be5bddba13fcbd222a3e2d3a

17
contrib/aws-cmake/CMakeLists.txt
View File

@ -25,6 +25,7 @@ include("${ClickHouse_SOURCE_DIR}/contrib/aws-cmake/AwsFeatureTests.cmake")
include("${ClickHouse_SOURCE_DIR}/contrib/aws-cmake/AwsThreadAffinity.cmake")
include("${ClickHouse_SOURCE_DIR}/contrib/aws-cmake/AwsThreadName.cmake")
include("${ClickHouse_SOURCE_DIR}/contrib/aws-cmake/AwsSIMD.cmake")
include("${ClickHouse_SOURCE_DIR}/contrib/aws-crt-cpp/cmake/AwsGetVersion.cmake")
# Gather sources and options.
@ -35,6 +36,8 @@ set(AWS_PUBLIC_COMPILE_DEFS)
set(AWS_PRIVATE_COMPILE_DEFS)
set(AWS_PRIVATE_LIBS)
list(APPEND AWS_PRIVATE_COMPILE_DEFS "-DINTEL_NO_ITTNOTIFY_API")
if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG")
list(APPEND AWS_PRIVATE_COMPILE_DEFS "-DDEBUG_BUILD")
endif()
@ -85,14 +88,20 @@ file(GLOB AWS_SDK_CORE_SRC
"${AWS_SDK_CORE_DIR}/source/external/cjson/*.cpp"
"${AWS_SDK_CORE_DIR}/source/external/tinyxml2/*.cpp"
"${AWS_SDK_CORE_DIR}/source/http/*.cpp"
"${AWS_SDK_CORE_DIR}/source/http/crt/*.cpp"
"${AWS_SDK_CORE_DIR}/source/http/standard/*.cpp"
"${AWS_SDK_CORE_DIR}/source/internal/*.cpp"
"${AWS_SDK_CORE_DIR}/source/monitoring/*.cpp"
"${AWS_SDK_CORE_DIR}/source/net/*.cpp"
"${AWS_SDK_CORE_DIR}/source/net/linux-shared/*.cpp"
"${AWS_SDK_CORE_DIR}/source/platform/linux-shared/*.cpp"
"${AWS_SDK_CORE_DIR}/source/smithy/tracing/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/base64/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/component-registry/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/crypto/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/crypto/openssl/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/crypto/factory/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/crypto/openssl/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/event/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/json/*.cpp"
"${AWS_SDK_CORE_DIR}/source/utils/logging/*.cpp"
@ -115,9 +124,8 @@ OPTION(USE_AWS_MEMORY_MANAGEMENT "Aws memory management" OFF)
configure_file("${AWS_SDK_CORE_DIR}/include/aws/core/SDKConfig.h.in"
"${CMAKE_CURRENT_BINARY_DIR}/include/aws/core/SDKConfig.h" @ONLY)
list(APPEND AWS_PUBLIC_COMPILE_DEFS "-DAWS_SDK_VERSION_MAJOR=1")
list(APPEND AWS_PUBLIC_COMPILE_DEFS "-DAWS_SDK_VERSION_MINOR=10")
list(APPEND AWS_PUBLIC_COMPILE_DEFS "-DAWS_SDK_VERSION_PATCH=36")
aws_get_version(AWS_CRT_CPP_VERSION_MAJOR AWS_CRT_CPP_VERSION_MINOR AWS_CRT_CPP_VERSION_PATCH FULL_VERSION GIT_HASH)
configure_file("${AWS_CRT_DIR}/include/aws/crt/Config.h.in" "${AWS_CRT_DIR}/include/aws/crt/Config.h" @ONLY)
list(APPEND AWS_SOURCES ${AWS_SDK_CORE_SRC} ${AWS_SDK_CORE_NET_SRC} ${AWS_SDK_CORE_PLATFORM_SRC})
@ -176,6 +184,7 @@ file(GLOB AWS_COMMON_SRC
"${AWS_COMMON_DIR}/source/*.c"
"${AWS_COMMON_DIR}/source/external/*.c"
"${AWS_COMMON_DIR}/source/posix/*.c"
"${AWS_COMMON_DIR}/source/linux/*.c"
)
file(GLOB AWS_COMMON_ARCH_SRC

2
contrib/aws-crt-cpp vendored

@ -1 +1 @@
Subproject commit 8a301b7e842f1daed478090c869207300972379f
Subproject commit f532d6abc0d2b0d8b5d6fe9e7c51eaedbe4afbd0

2
contrib/aws-s2n-tls vendored

@ -1 +1 @@
Subproject commit 71f4794b7580cf780eb4aca77d69eded5d3c7bb4
Subproject commit 9a1e75454023e952b366ce1eab9c54007250119f

48
contrib/corrosion-cmake/CMakeLists.txt
View File

@ -1,8 +1,5 @@
if (NOT ENABLE_LIBRARIES)
set(DEFAULT_ENABLE_RUST FALSE)
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "darwin") AND (CMAKE_TOOLCHAIN_FILE MATCHES "aarch64"))
message(STATUS "Rust is not available on aarch64-apple-darwin")
set(DEFAULT_ENABLE_RUST FALSE)
else()
list (APPEND CMAKE_MODULE_PATH "${ClickHouse_SOURCE_DIR}/contrib/corrosion/cmake")
find_package(Rust)
@ -19,27 +16,30 @@ message(STATUS "Checking Rust toolchain for current target")
# See https://doc.rust-lang.org/nightly/rustc/platform-support.html
if((CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-x86_64") AND (CMAKE_TOOLCHAIN_FILE MATCHES "musl"))
set(Rust_CARGO_TARGET "x86_64-unknown-linux-musl")
elseif(CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-x86_64")
set(Rust_CARGO_TARGET "x86_64-unknown-linux-gnu")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-aarch64") AND (CMAKE_TOOLCHAIN_FILE MATCHES "musl"))
set(Rust_CARGO_TARGET "aarch64-unknown-linux-musl")
elseif(CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-aarch64")
set(Rust_CARGO_TARGET "aarch64-unknown-linux-gnu")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "darwin") AND (CMAKE_TOOLCHAIN_FILE MATCHES "x86_64"))
set(Rust_CARGO_TARGET "x86_64-apple-darwin")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "freebsd") AND (CMAKE_TOOLCHAIN_FILE MATCHES "x86_64"))
set(Rust_CARGO_TARGET "x86_64-unknown-freebsd")
elseif(CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-riscv64")
set(Rust_CARGO_TARGET "riscv64gc-unknown-linux-gnu")
endif()
if(CMAKE_TOOLCHAIN_FILE MATCHES "ppc64le")
set(Rust_CARGO_TARGET "powerpc64le-unknown-linux-gnu")
endif()
message(STATUS "Switched Rust target to ${Rust_CARGO_TARGET}")
if(DEFINED CMAKE_TOOLCHAIN_FILE)
if(CMAKE_TOOLCHAIN_FILE MATCHES "ppc64le")
set(Rust_CARGO_TARGET "powerpc64le-unknown-linux-gnu")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-x86_64") AND (CMAKE_TOOLCHAIN_FILE MATCHES "musl"))
set(Rust_CARGO_TARGET "x86_64-unknown-linux-musl")
elseif(CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-x86_64")
set(Rust_CARGO_TARGET "x86_64-unknown-linux-gnu")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-aarch64") AND (CMAKE_TOOLCHAIN_FILE MATCHES "musl"))
set(Rust_CARGO_TARGET "aarch64-unknown-linux-musl")
elseif(CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-aarch64")
set(Rust_CARGO_TARGET "aarch64-unknown-linux-gnu")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "darwin") AND (CMAKE_TOOLCHAIN_FILE MATCHES "x86_64"))
set(Rust_CARGO_TARGET "x86_64-apple-darwin")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "darwin") AND (CMAKE_TOOLCHAIN_FILE MATCHES "aarch64"))
set(Rust_CARGO_TARGET "aarch64-apple-darwin")
elseif((CMAKE_TOOLCHAIN_FILE MATCHES "freebsd") AND (CMAKE_TOOLCHAIN_FILE MATCHES "x86_64"))
set(Rust_CARGO_TARGET "x86_64-unknown-freebsd")
elseif(CMAKE_TOOLCHAIN_FILE MATCHES "linux/toolchain-riscv64")
set(Rust_CARGO_TARGET "riscv64gc-unknown-linux-gnu")
else()
message(FATAL_ERROR "Unsupported rust target")
endif()
message(STATUS "Switched Rust target to ${Rust_CARGO_TARGET}")
endif ()
# FindRust.cmake
list(APPEND CMAKE_MODULE_PATH "${ClickHouse_SOURCE_DIR}/contrib/corrosion/cmake")

2
contrib/curl vendored

@ -1 +1 @@
Subproject commit d755a5f7c009dd63a61b2c745180d8ba937cbfeb
Subproject commit 7161cb17c01dcff1dc5bf89a18437d9d729f1ecd

2
contrib/libssh-cmake/CMakeLists.txt
View File

@ -1,4 +1,4 @@
option (ENABLE_SSH "Enable support for SSH keys and protocol" ON)
option (ENABLE_SSH "Enable support for SSH keys and protocol" ${ENABLE_LIBRARIES})
if (NOT ENABLE_SSH)
message(STATUS "Not using SSH")

5
contrib/llvm-project-cmake/CMakeLists.txt
View File

@ -1,5 +1,6 @@
if (APPLE OR SANITIZE STREQUAL "undefined" OR SANITIZE STREQUAL "memory")
# llvm-tblgen, that is used during LLVM build, doesn't work with UBSan.
if (APPLE OR SANITIZE STREQUAL "memory")
# llvm-tblgen, that is used during LLVM build, will throw MSAN errors when running (breaking the build)
# TODO: Retest when upgrading LLVM or build only llvm-tblgen without sanitizers
set (ENABLE_EMBEDDED_COMPILER_DEFAULT OFF)
set (ENABLE_DWARF_PARSER_DEFAULT OFF)
else()

2
contrib/simdjson vendored

@ -1 +1 @@
Subproject commit 1075e8609c4afa253162d441437af929c29e31bb
Subproject commit 6060be2fdf62edf4a8f51a8b0883d57d09397b30

8
contrib/update-submodules.sh vendored
View File

@ -6,9 +6,15 @@ SCRIPT_DIR=$(dirname "${SCRIPT_PATH}")
GIT_DIR=$(git -C "$SCRIPT_DIR" rev-parse --show-toplevel)
cd $GIT_DIR
# Exclude from contribs some garbage subdirs that we don't need.
# It reduces the checked out files size about 3 times and therefore speeds up indexing in IDEs and searching.
# NOTE .git/ still contains everything that we don't check out (although, it's compressed)
# See also https://git-scm.com/docs/git-sparse-checkout
contrib/sparse-checkout/setup-sparse-checkout.sh
git submodule init
git submodule sync
# NOTE: do not use --remote for `git submodule update`[1] command, since the submodule references to the specific commit SHA1 in the subproject.
# It may cause unexpected behavior. Instead you need to commit a new SHA1 for a submodule.
#
@ -18,7 +24,7 @@ git config --file .gitmodules --get-regexp '.*path' | sed 's/[^ ]* //' | xargs -
# We don't want to depend on any third-party CMake files.
# To check it, find and delete them.
grep -o -P '"contrib/[^"]+"' .gitmodules |
grep -v -P 'contrib/(llvm-project|google-protobuf|grpc|abseil-cpp|corrosion)' |
grep -v -P 'contrib/(llvm-project|google-protobuf|grpc|abseil-cpp|corrosion|aws-crt-cpp)' |
xargs -I@ find @ \
-'(' -name 'CMakeLists.txt' -or -name '*.cmake' -')' -and -not -name '*.h.cmake' \
-delete

2
docker/keeper/Dockerfile
View File

@ -34,7 +34,7 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="23.12.2.59"
ARG VERSION="24.1.1.2048"
ARG PACKAGES="clickhouse-keeper"
ARG DIRECT_DOWNLOAD_URLS=""

2
docker/server/Dockerfile.alpine
View File

@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
# lts / testing / prestable / etc
ARG REPO_CHANNEL="stable"
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
ARG VERSION="23.12.2.59"
ARG VERSION="24.1.1.2048"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
ARG DIRECT_DOWNLOAD_URLS=""

2
docker/server/Dockerfile.ubuntu
View File

@ -30,7 +30,7 @@ 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="23.12.2.59"
ARG VERSION="24.1.1.2048"
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
# set non-empty deb_location_url url to create a docker image

30
docker/server/entrypoint.sh
View File

@ -49,17 +49,10 @@ CLICKHOUSE_PASSWORD="${CLICKHOUSE_PASSWORD:-}"
CLICKHOUSE_DB="${CLICKHOUSE_DB:-}"
CLICKHOUSE_ACCESS_MANAGEMENT="${CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT:-0}"
for dir in "$DATA_DIR" \
"$ERROR_LOG_DIR" \
"$LOG_DIR" \
"$TMP_DIR" \
"$USER_PATH" \
"$FORMAT_SCHEMA_PATH" \
"${DISKS_PATHS[@]}" \
"${DISKS_METADATA_PATHS[@]}"
do
function create_directory_and_do_chown() {
local dir=$1
# check if variable not empty
[ -z "$dir" ] && continue
[ -z "$dir" ] && return
# ensure directories exist
if [ "$DO_CHOWN" = "1" ]; then
mkdir="mkdir"
@ -81,6 +74,23 @@ do
chown -R "$USER:$GROUP" "$dir"
fi
fi
}
create_directory_and_do_chown "$DATA_DIR"
# Change working directory to $DATA_DIR in case there're paths relative to $DATA_DIR, also avoids running
# clickhouse-server at root directory.
cd "$DATA_DIR"
for dir in "$ERROR_LOG_DIR" \
"$LOG_DIR" \
"$TMP_DIR" \
"$USER_PATH" \
"$FORMAT_SCHEMA_PATH" \
"${DISKS_PATHS[@]}" \
"${DISKS_METADATA_PATHS[@]}"
do
create_directory_and_do_chown "$dir"
done
# if clickhouse user is defined - create it (user "default" already exists out of box)

2
docker/test/fasttest/Dockerfile
View File

@ -22,7 +22,7 @@ RUN apt-get update \
zstd \
--yes --no-install-recommends
RUN pip3 install numpy scipy pandas Jinja2
RUN pip3 install numpy==1.26.3 scipy==1.12.0 pandas==1.5.3 Jinja2==3.1.3
ARG odbc_driver_url="https://github.com/ClickHouse/clickhouse-odbc/releases/download/v1.1.4.20200302/clickhouse-odbc-1.1.4-Linux.tar.gz"

11
docker/test/fasttest/run.sh
View File

@ -211,6 +211,17 @@ function build
echo "build_clickhouse_fasttest_binary: [ OK ] $BUILD_SECONDS_ELAPSED sec." \
| ts '%Y-%m-%d %H:%M:%S' \
| tee "$FASTTEST_OUTPUT/test_result.txt"
(
# This query should fail, and print stacktrace with proper symbol names (even on a stripped binary)
clickhouse_output=$(programs/clickhouse-stripped --stacktrace -q 'select' 2>&1 || :)
if [[ $clickhouse_output =~ DB::LocalServer::main ]]; then
echo "stripped_clickhouse_shows_symbols_names: [ OK ] 0 sec."
else
echo -e "stripped_clickhouse_shows_symbols_names: [ FAIL ] 0 sec. - clickhouse output:\n\n$clickhouse_output\n"
fi
) | ts '%Y-%m-%d %H:%M:%S' | tee -a "$FASTTEST_OUTPUT/test_result.txt"
if [ "$COPY_CLICKHOUSE_BINARY_TO_OUTPUT" -eq "1" ]; then
mkdir -p "$FASTTEST_OUTPUT/binaries/"
cp programs/clickhouse "$FASTTEST_OUTPUT/binaries/clickhouse"

12
docker/test/integration/runner/dockerd-entrypoint.sh
View File

@ -23,13 +23,15 @@ if [ -f /sys/fs/cgroup/cgroup.controllers ]; then
> /sys/fs/cgroup/cgroup.subtree_control
fi
# In case of test hung it is convenient to use pytest --pdb to debug it,
# and on hung you can simply press Ctrl-C and it will spawn a python pdb,
# but on SIGINT dockerd will exit, so ignore it to preserve the daemon.
trap '' INT
# Binding to an IP address without --tlsverify is deprecated. Startup is intentionally being slowed
# unless --tls=false or --tlsverify=false is set
dockerd --host=unix:///var/run/docker.sock --tls=false --host=tcp://0.0.0.0:2375 --default-address-pool base=172.17.0.0/12,size=24 &>/ClickHouse/tests/integration/dockerd.log &
#
# In case of test hung it is convenient to use pytest --pdb to debug it,
# and on hung you can simply press Ctrl-C and it will spawn a python pdb,
# but on SIGINT dockerd will exit, so we spawn new session to ignore SIGINT by
# docker.
# Note, that if you will run it via runner, it will send SIGINT to docker anyway.
setsid dockerd --host=unix:///var/run/docker.sock --tls=false --host=tcp://0.0.0.0:2375 --default-address-pool base=172.17.0.0/12,size=24 &>/ClickHouse/tests/integration/dockerd.log &
set +e
reties=0

61
docker/test/stateless/run.sh
View File

@ -99,6 +99,16 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
> /etc/clickhouse-server2/config.d/filesystem_caches_path.xml.tmp
mv /etc/clickhouse-server2/config.d/filesystem_caches_path.xml.tmp /etc/clickhouse-server2/config.d/filesystem_caches_path.xml
sudo cat /etc/clickhouse-server1/config.d/filesystem_caches_path.xml \
| sed "s|<custom_cached_disks_base_directory replace=\"replace\">/var/lib/clickhouse/filesystem_caches/</custom_cached_disks_base_directory>|<custom_cached_disks_base_directory replace=\"replace\">/var/lib/clickhouse/filesystem_caches_1/</custom_cached_disks_base_directory>|" \
> /etc/clickhouse-server1/config.d/filesystem_caches_path.xml.tmp
mv /etc/clickhouse-server1/config.d/filesystem_caches_path.xml.tmp /etc/clickhouse-server1/config.d/filesystem_caches_path.xml
sudo cat /etc/clickhouse-server2/config.d/filesystem_caches_path.xml \
| sed "s|<custom_cached_disks_base_directory replace=\"replace\">/var/lib/clickhouse/filesystem_caches/</custom_cached_disks_base_directory>|<custom_cached_disks_base_directory replace=\"replace\">/var/lib/clickhouse/filesystem_caches_2/</custom_cached_disks_base_directory>|" \
> /etc/clickhouse-server2/config.d/filesystem_caches_path.xml.tmp
mv /etc/clickhouse-server2/config.d/filesystem_caches_path.xml.tmp /etc/clickhouse-server2/config.d/filesystem_caches_path.xml
mkdir -p /var/run/clickhouse-server1
sudo chown clickhouse:clickhouse /var/run/clickhouse-server1
sudo -E -u clickhouse /usr/bin/clickhouse server --config /etc/clickhouse-server1/config.xml --daemon \
@ -235,6 +245,23 @@ clickhouse-client -q "system flush logs" ||:
# stop logs replication to make it possible to dump logs tables via clickhouse-local
stop_logs_replication
# Try to get logs while server is running
failed_to_save_logs=0
for table in query_log zookeeper_log trace_log transactions_info_log metric_log
do
err=$( { clickhouse-client -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.tsv.zst; } 2>&1 )
echo "$err"
[[ "0" != "${#err}" ]] && failed_to_save_logs=1
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
err=$( { clickhouse-client -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst; } 2>&1 )
echo "$err"
[[ "0" != "${#err}" ]] && failed_to_save_logs=1
err=$( { clickhouse-client -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.2.tsv.zst; } 2>&1 )
echo "$err"
[[ "0" != "${#err}" ]] && failed_to_save_logs=1
fi
done
# Stop server so we can safely read data with clickhouse-local.
# Why do we read data with clickhouse-local?
# Because it's the simplest way to read it when server has crashed.
@ -254,21 +281,25 @@ if [[ -n "$USE_S3_STORAGE_FOR_MERGE_TREE" ]] && [[ "$USE_S3_STORAGE_FOR_MERGE_TR
data_path_config="--config-file=/etc/clickhouse-server/config.xml"
fi
# Compress tables.
#
# NOTE:
# - that due to tests with s3 storage we cannot use /var/lib/clickhouse/data
# directly
# - even though ci auto-compress some files (but not *.tsv) it does this only
# for files >64MB, we want this files to be compressed explicitly
for table in query_log zookeeper_log trace_log transactions_info_log
do
clickhouse-local "$data_path_config" --only-system-tables -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.tsv.zst ||:
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
clickhouse-local --path /var/lib/clickhouse1/ --only-system-tables -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst ||:
clickhouse-local --path /var/lib/clickhouse2/ --only-system-tables -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.2.tsv.zst ||:
fi
done
# If server crashed dump system logs with clickhouse-local
if [ $failed_to_save_logs -ne 0 ]; then
# Compress tables.
#
# NOTE:
# - that due to tests with s3 storage we cannot use /var/lib/clickhouse/data
# directly
# - even though ci auto-compress some files (but not *.tsv) it does this only
# for files >64MB, we want this files to be compressed explicitly
for table in query_log zookeeper_log trace_log transactions_info_log metric_log
do
clickhouse-local "$data_path_config" --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.tsv.zst ||:
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
clickhouse-local --path /var/lib/clickhouse1/ --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst ||:
clickhouse-local --path /var/lib/clickhouse2/ --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.2.tsv.zst ||:
fi
done
fi
# Also export trace log in flamegraph-friendly format.
for trace_type in CPU Memory Real

2
docker/test/stateless/stress_tests.lib
View File

@ -78,6 +78,8 @@ function configure()
randomize_config_boolean_value use_compression zookeeper
fi
randomize_config_boolean_value allow_experimental_block_number_column block_number
# for clickhouse-server (via service)
echo "ASAN_OPTIONS='malloc_context_size=10 verbosity=1 allocator_release_to_os_interval_ms=10000'" >> /etc/environment
# for clickhouse-client

63
docker/test/upgrade/run.sh
View File

@ -56,6 +56,9 @@ echo "ATTACH DATABASE system ENGINE=Ordinary" > /var/lib/clickhouse/metadata/sys
# Install previous release packages
install_packages previous_release_package_folder
# Save old settings from system table for settings changes check
clickhouse-local -q "select * from system.settings format Native" > old_settings.native
# Initial run without S3 to create system.*_log on local file system to make it
# available for dump via clickhouse-local
configure
@ -119,6 +122,7 @@ rm /etc/clickhouse-server/config.d/merge_tree.xml
rm /etc/clickhouse-server/config.d/enable_wait_for_shutdown_replicated_tables.xml
rm /etc/clickhouse-server/config.d/zero_copy_destructive_operations.xml
rm /etc/clickhouse-server/config.d/storage_conf_02963.xml
rm /etc/clickhouse-server/config.d/block_number.xml
rm /etc/clickhouse-server/users.d/nonconst_timezone.xml
rm /etc/clickhouse-server/users.d/s3_cache_new.xml
rm /etc/clickhouse-server/users.d/replicated_ddl_entry.xml
@ -152,6 +156,63 @@ install_packages package_folder
export ZOOKEEPER_FAULT_INJECTION=1
configure
# Check that all new/changed setting were added in settings changes history.
# Some settings can be different for builds with sanitizers, so we check
# settings changes only for non-sanitizer builds.
IS_SANITIZED=$(clickhouse-local --query "SELECT value LIKE '%-fsanitize=%' FROM system.build_options WHERE name = 'CXX_FLAGS'")
if [ "${IS_SANITIZED}" -eq "0" ]
then
clickhouse-local -q "select * from system.settings format Native" > new_settings.native
clickhouse-local -nmq "
CREATE TABLE old_settings AS file('old_settings.native');
CREATE TABLE new_settings AS file('new_settings.native');
SELECT
name,
new_settings.value AS new_value,
old_settings.value AS old_value
FROM new_settings
LEFT JOIN old_settings ON new_settings.name = old_settings.name
WHERE (new_settings.value != old_settings.value) AND (name NOT IN (
SELECT arrayJoin(tupleElement(changes, 'name'))
FROM system.settings_changes
WHERE version = extract(version(), '^(?:\\d+\\.\\d+)')
))
SETTINGS join_use_nulls = 1
INTO OUTFILE 'changed_settings.txt'
FORMAT PrettyCompactNoEscapes;
SELECT name
FROM new_settings
WHERE (name NOT IN (
SELECT name
FROM old_settings
)) AND (name NOT IN (
SELECT arrayJoin(tupleElement(changes, 'name'))
FROM system.settings_changes
WHERE version = extract(version(), '^(?:\\d+\\.\\d+)')
))
INTO OUTFILE 'new_settings.txt'
FORMAT PrettyCompactNoEscapes;
"
if [ -s changed_settings.txt ]
then
mv changed_settings.txt /test_output/
echo -e "Changed settings are not reflected in settings changes history (see changed_settings.txt)$FAIL$(head_escaped /test_output/changed_settings.txt)" >> /test_output/test_results.tsv
else
echo -e "There are no changed settings or they are reflected in settings changes history$OK" >> /test_output/test_results.tsv
fi
if [ -s new_settings.txt ]
then
mv new_settings.txt /test_output/
echo -e "New settings are not reflected in settings changes history (see new_settings.txt)$FAIL$(head_escaped /test_output/new_settings.txt)" >> /test_output/test_results.tsv
else
echo -e "There are no new settings or they are reflected in settings changes history$OK" >> /test_output/test_results.tsv
fi
fi
# Just in case previous version left some garbage in zk
sudo cat /etc/clickhouse-server/config.d/lost_forever_check.xml \
| sed "s|>1<|>0<|g" \
@ -257,6 +318,8 @@ clickhouse-local --structure "test String, res String, time Nullable(Float32), d
(test like '%Fatal message%') DESC,
(test like '%Error message%') DESC,
(test like '%previous release%') DESC,
(test like '%Changed settings%') DESC,
(test like '%New settings%') DESC,
rowNumberInAllBlocks()
LIMIT 1" < /test_output/test_results.tsv > /test_output/check_status.tsv || echo "failure\tCannot parse test_results.tsv" > /test_output/check_status.tsv
[ -s /test_output/check_status.tsv ] || echo -e "success\tNo errors found" > /test_output/check_status.tsv

1
docs/changelogs/v23.9.1.1854-stable.md
View File

@ -11,6 +11,7 @@ sidebar_label: 2023
* Remove the `status_info` configuration option and dictionaries status from the default Prometheus handler. [#54090](https://github.com/ClickHouse/ClickHouse/pull/54090) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The experimental parts metadata cache is removed from the codebase. [#54215](https://github.com/ClickHouse/ClickHouse/pull/54215) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Disable setting `input_format_json_try_infer_numbers_from_strings` by default, so we don't try to infer numbers from strings in JSON formats by default to avoid possible parsing errors when sample data contains strings that looks like a number. [#55099](https://github.com/ClickHouse/ClickHouse/pull/55099) ([Kruglov Pavel](https://github.com/Avogar)).
* IPv6 bloom filter indexes created prior to March 2023 are not compatible with current version and have to be rebuilt. [#54200](https://github.com/ClickHouse/ClickHouse/pull/54200) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
#### New Feature
* Added new type of authentication based on SSH keys. It works only for Native TCP protocol. [#41109](https://github.com/ClickHouse/ClickHouse/pull/41109) ([George Gamezardashvili](https://github.com/InfJoker)).

438
docs/changelogs/v24.1.1.2048-stable.md Normal file
View File

@ -0,0 +1,438 @@
---
sidebar_position: 1
sidebar_label: 2024
---
# 2024 Changelog
### ClickHouse release v24.1.1.2048-stable (5a024dfc093) FIXME as compared to v23.12.1.1368-stable (a2faa65b080)
#### Backward Incompatible Change
* The setting `print_pretty_type_names` is turned on by default. You can turn it off to keep the old behavior or `SET compatibility = '23.12'`. [#57726](https://github.com/ClickHouse/ClickHouse/pull/57726) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The MergeTree setting `clean_deleted_rows` is deprecated, it has no effect anymore. The `CLEANUP` keyword for `OPTIMIZE` is not allowed by default (unless `allow_experimental_replacing_merge_with_cleanup` is enabled). [#58316](https://github.com/ClickHouse/ClickHouse/pull/58316) ([Alexander Tokmakov](https://github.com/tavplubix)).
* The function `reverseDNSQuery` is no longer available. This closes [#58368](https://github.com/ClickHouse/ClickHouse/issues/58368). [#58369](https://github.com/ClickHouse/ClickHouse/pull/58369) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Enable various changes to improve the access control in the configuration file. These changes affect the behavior, and you check the `config.xml` in the `access_control_improvements` section. In case you are not confident, keep the values in the configuration file as they were in the previous version. [#58584](https://github.com/ClickHouse/ClickHouse/pull/58584) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Allow queries without aliases for subqueries for `PASTE JOIN`. [#58654](https://github.com/ClickHouse/ClickHouse/pull/58654) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Fix sumMapFiltered with NaN values. NaN values are now placed at the end (instead of randomly) and considered different from any values. `-0` is now also treated as equal to `0`; since 0 values are discarded, `-0` values are discarded too. [#58959](https://github.com/ClickHouse/ClickHouse/pull/58959) ([Raúl Marín](https://github.com/Algunenano)).
* The function `visibleWidth` will behave according to the docs. In previous versions, it simply counted code points after string serialization, like the `lengthUTF8` function, but didn't consider zero-width and combining characters, full-width characters, tabs, and deletes. Now the behavior is changed accordingly. If you want to keep the old behavior, set `function_visible_width_behavior` to `0`, or set `compatibility` to `23.12` or lower. [#59022](https://github.com/ClickHouse/ClickHouse/pull/59022) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Kusto dialect is disabled until these two bugs will be fixed: [#59037](https://github.com/ClickHouse/ClickHouse/issues/59037) and [#59036](https://github.com/ClickHouse/ClickHouse/issues/59036). [#59305](https://github.com/ClickHouse/ClickHouse/pull/59305) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
#### New Feature
* Allow partitions from tables with different partition expressions to be attached when the destination table partition expression doesn't re-partition/ split the part. [#39507](https://github.com/ClickHouse/ClickHouse/pull/39507) ([Arthur Passos](https://github.com/arthurpassos)).
* Added statement `SYSTEM RELOAD ASYNCHRONOUS METRICS` which updates the asynchronous metrics. Mostly useful for testing and development. [#53710](https://github.com/ClickHouse/ClickHouse/pull/53710) ([Robert Schulze](https://github.com/rschu1ze)).
* Certain settings (currently `min_compress_block_size` and `max_compress_block_size`) can now be specified at column-level where they take precedence over the corresponding table-level setting. Example: `CREATE TABLE tab (col String SETTINGS (min_compress_block_size = 81920, max_compress_block_size = 163840)) ENGINE = MergeTree ORDER BY tuple();`. [#55201](https://github.com/ClickHouse/ClickHouse/pull/55201) ([Duc Canh Le](https://github.com/canhld94)).
* Add `quantileDDSketch` aggregate function as well as the corresponding `quantilesDDSketch` and `medianDDSketch`. It is based on the DDSketch https://www.vldb.org/pvldb/vol12/p2195-masson.pdf. ### Documentation entry for user-facing changes. [#56342](https://github.com/ClickHouse/ClickHouse/pull/56342) ([Srikanth Chekuri](https://github.com/srikanthccv)).
* Added function `seriesDecomposeSTL()` which decomposes a time series into a season, a trend and a residual component. [#57078](https://github.com/ClickHouse/ClickHouse/pull/57078) ([Bhavna Jindal](https://github.com/bhavnajindal)).
* Introduced MySQL Binlog Client for MaterializedMySQL: One binlog connection for many databases. [#57323](https://github.com/ClickHouse/ClickHouse/pull/57323) ([Val Doroshchuk](https://github.com/valbok)).
* Intel QuickAssist Technology (QAT) provides hardware-accelerated compression and cryptograpy. ClickHouse got a new compression codec `ZSTD_QAT` which utilizes QAT for zstd compression. The codec uses [Intel's QATlib](https://github.com/intel/qatlib) and [Inte's QAT ZSTD Plugin](https://github.com/intel/QAT-ZSTD-Plugin). Right now, only compression can be accelerated in hardware (a software fallback kicks in in case QAT could not be initialized), decompression always runs in software. [#57509](https://github.com/ClickHouse/ClickHouse/pull/57509) ([jasperzhu](https://github.com/jinjunzh)).
* Implementing the new way how object storage keys are generated for s3 disks. Now the format could be defined in terms of `re2` regex syntax with `key_template` option in disc description. [#57663](https://github.com/ClickHouse/ClickHouse/pull/57663) ([Sema Checherinda](https://github.com/CheSema)).
* Table system.dropped_tables_parts contains parts of system.dropped_tables tables (dropped but not yet removed tables). [#58038](https://github.com/ClickHouse/ClickHouse/pull/58038) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Implement Variant data type that represents a union of other data types. Type `Variant(T1, T2, ..., TN)` means that each row of this type has a value of either type `T1` or `T2` or ... or `TN` or none of them (`NULL` value). Variant type is available under a setting `allow_experimental_variant_type`. Reference: [#54864](https://github.com/ClickHouse/ClickHouse/issues/54864). [#58047](https://github.com/ClickHouse/ClickHouse/pull/58047) ([Kruglov Pavel](https://github.com/Avogar)).
* Add settings `max_materialized_views_size_for_table` to limit the number of materialized views attached to a table. [#58068](https://github.com/ClickHouse/ClickHouse/pull/58068) ([zhongyuankai](https://github.com/zhongyuankai)).
* `clickhouse-format` improvements: * support INSERT queries with `VALUES` * support comments (use `--comments` to output them) * support `--max_line_length` option to format only long queries in multiline. [#58246](https://github.com/ClickHouse/ClickHouse/pull/58246) ([vdimir](https://github.com/vdimir)).
* Added `null_status_on_timeout_only_active` and `throw_only_active` modes for `distributed_ddl_output_mode` that allow to avoid waiting for inactive replicas. [#58350](https://github.com/ClickHouse/ClickHouse/pull/58350) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Add table `system.database_engines`. [#58390](https://github.com/ClickHouse/ClickHouse/pull/58390) ([Bharat Nallan](https://github.com/bharatnc)).
* Added FROM <Replicas> modifier for SYSTEM SYNC REPLICA LIGHTWEIGHT query. The FROM modifier ensures we wait for for fetches and drop-ranges only for the specified source replicas, as well as any replica not in zookeeper or with an empty source_replica. [#58393](https://github.com/ClickHouse/ClickHouse/pull/58393) ([Jayme Bird](https://github.com/jaymebrd)).
* Add function `arrayShingles()` to compute subarrays, e.g. `arrayShingles([1, 2, 3, 4, 5], 3)` returns `[[1,2,3],[2,3,4],[3,4,5]]`. [#58396](https://github.com/ClickHouse/ClickHouse/pull/58396) ([Zheng Miao](https://github.com/zenmiao7)).
* Added functions `punycodeEncode()`, `punycodeDecode()`, `idnaEncode()` and `idnaDecode()` which are useful for translating international domain names to an ASCII representation according to the IDNA standard. [#58454](https://github.com/ClickHouse/ClickHouse/pull/58454) ([Robert Schulze](https://github.com/rschu1ze)).
* Added string similarity functions `dramerauLevenshteinDistance()`, `jaroSimilarity()` and `jaroWinklerSimilarity()`. [#58531](https://github.com/ClickHouse/ClickHouse/pull/58531) ([Robert Schulze](https://github.com/rschu1ze)).
* Add two settings `output_format_compression_level` to change output compression level and `output_format_compression_zstd_window_log` to explicitly set compression window size and enable long-range mode for zstd compression if output compression method is `zstd`. Applied for `INTO OUTFILE` and when writing to table functions `file`, `url`, `hdfs`, `s3`, and `azureBlobStorage`. [#58539](https://github.com/ClickHouse/ClickHouse/pull/58539) ([Duc Canh Le](https://github.com/canhld94)).
* Automatically disable ANSI escape sequences in Pretty formats if the output is not a terminal. Add new `auto` mode to setting `output_format_pretty_color`. [#58614](https://github.com/ClickHouse/ClickHouse/pull/58614) ([Shaun Struwig](https://github.com/Blargian)).
* Added setting `update_insert_deduplication_token_in_dependent_materialized_views`. This setting allows to update insert deduplication token with table identifier during insert in dependent materialized views. Closes [#59165](https://github.com/ClickHouse/ClickHouse/issues/59165). [#59238](https://github.com/ClickHouse/ClickHouse/pull/59238) ([Maksim Kita](https://github.com/kitaisreal)).
#### Performance Improvement
* More cache-friendly final implementation. Note on the behaviour change: previously queries with `FINAL` modifier that read with a single stream (e.g. `max_threads=1`) produced sorted output without explicitly provided `ORDER BY` clause. This behaviour no longer exists when `enable_vertical_final = true` (and it is so by default). [#54366](https://github.com/ClickHouse/ClickHouse/pull/54366) ([Duc Canh Le](https://github.com/canhld94)).
* Optimize array element function when input is array(map)/array(array(num)/array(array(string))/array(bigint)/array(decimal). Current implementation causes too many reallocs. The optimization speed up by ~6x especially when input type is array(map). [#56403](https://github.com/ClickHouse/ClickHouse/pull/56403) ([李扬](https://github.com/taiyang-li)).
* Bypass `Poco::BasicBufferedStreamBuf` abstraction when reading from S3 (namely `ReadBufferFromIStream`) to avoid extra copying of data. [#56961](https://github.com/ClickHouse/ClickHouse/pull/56961) ([Nikita Taranov](https://github.com/nickitat)).
* Read column once while reading more that one subcolumn from it in Compact parts. [#57631](https://github.com/ClickHouse/ClickHouse/pull/57631) ([Kruglov Pavel](https://github.com/Avogar)).
* Rewrite the AST of sum(column + literal) function. [#57853](https://github.com/ClickHouse/ClickHouse/pull/57853) ([Jiebin Sun](https://github.com/jiebinn)).
* The evaluation of function `match()` now utilizes skipping indices `ngrambf_v1` and `tokenbf_v1`. [#57882](https://github.com/ClickHouse/ClickHouse/pull/57882) ([凌涛](https://github.com/lingtaolf)).
* Default coordinator for parallel replicas is rewritten for better cache locality (same mark ranges are almost always assigned to the same replicas). Consistent hashing is used also during work stealing, so better tail latency is expected. It has been tested for linear scalability on a hundred of replicas. [#57968](https://github.com/ClickHouse/ClickHouse/pull/57968) ([Nikita Taranov](https://github.com/nickitat)).
* MergeTree FINAL to not compare rows from same non-L0 part. [#58142](https://github.com/ClickHouse/ClickHouse/pull/58142) ([Duc Canh Le](https://github.com/canhld94)).
* Speed up iota calls (filling array with consecutive numbers). [#58271](https://github.com/ClickHouse/ClickHouse/pull/58271) ([Raúl Marín](https://github.com/Algunenano)).
* The evaluation of function `match()` now utilizes inverted indices. [#58284](https://github.com/ClickHouse/ClickHouse/pull/58284) ([凌涛](https://github.com/lingtaolf)).
* Speedup MIN/MAX for non numeric types. [#58334](https://github.com/ClickHouse/ClickHouse/pull/58334) ([Raúl Marín](https://github.com/Algunenano)).
* Enable JIT compilation for aggregation without a key. Closes [#41461](https://github.com/ClickHouse/ClickHouse/issues/41461). Originally [#53757](https://github.com/ClickHouse/ClickHouse/issues/53757). [#58440](https://github.com/ClickHouse/ClickHouse/pull/58440) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The performance experiments of **OnTime** on the Intel server with up to AVX2 (and BMI2) support show that this change could effectively improve the QPS of **Q2** and **Q3** by **5.0%** and **3.7%** through reducing the cycle ratio of the hotspot, **_DB::MergeTreeRangeReader::ReadResult::optimize_**, **from 11.48% to 1.09%** and **from 8.09% to 0.67%** respectively while having no impact on others. [#58800](https://github.com/ClickHouse/ClickHouse/pull/58800) ([Zhiguo Zhou](https://github.com/ZhiguoZh)).
* Use one thread less in `clickhouse-local`. [#58968](https://github.com/ClickHouse/ClickHouse/pull/58968) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Large aggregation states of `uniqExact` will be merged in parallel in distrubuted queries. [#59009](https://github.com/ClickHouse/ClickHouse/pull/59009) ([Nikita Taranov](https://github.com/nickitat)).
* Lower memory usage after reading from `MergeTree` tables. [#59290](https://github.com/ClickHouse/ClickHouse/pull/59290) ([Anton Popov](https://github.com/CurtizJ)).
* Lower memory usage in vertical merges. [#59340](https://github.com/ClickHouse/ClickHouse/pull/59340) ([Anton Popov](https://github.com/CurtizJ)).
#### Improvement
* Enable MySQL/MariaDB on macOS. This closes [#21191](https://github.com/ClickHouse/ClickHouse/issues/21191). [#46316](https://github.com/ClickHouse/ClickHouse/pull/46316) ([Robert Schulze](https://github.com/rschu1ze)).
* Do not interpret numbers with leading zeroes as octals. [#55575](https://github.com/ClickHouse/ClickHouse/pull/55575) ([Joanna Hulboj](https://github.com/jh0x)).
* Replace HTTP outgoing buffering based on std ostream with CH Buffer. Add bytes counting metrics for interfaces. [#56064](https://github.com/ClickHouse/ClickHouse/pull/56064) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Disable `max_rows_in_set_to_optimize_join` by default. [#56396](https://github.com/ClickHouse/ClickHouse/pull/56396) ([vdimir](https://github.com/vdimir)).
* Add `<host_name>` config parameter that allows avoiding resolving hostnames in DDLWorker. This mitigates the possibility of the queue being stuck in case of a change in cluster definition. Closes [#57573](https://github.com/ClickHouse/ClickHouse/issues/57573). [#57603](https://github.com/ClickHouse/ClickHouse/pull/57603) ([Nikolay Degterinsky](https://github.com/evillique)).
* Increase `load_metadata_threads` to 16 for the filesystem cache. It will make the server start up faster. [#57732](https://github.com/ClickHouse/ClickHouse/pull/57732) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Improve the `multiIf` function performance when the type is Nullable. [#57745](https://github.com/ClickHouse/ClickHouse/pull/57745) ([KevinyhZou](https://github.com/KevinyhZou)).
* Add ability to throttle merges/mutations (`max_mutations_bandwidth_for_server`/`max_merges_bandwidth_for_server`). [#57877](https://github.com/ClickHouse/ClickHouse/pull/57877) ([Azat Khuzhin](https://github.com/azat)).
* Replaced undocumented (boolean) column `is_hot_reloadable` in system table `system.server_settings` by (Enum8) column `changeable_without_restart` with possible values `No`, `Yes`, `IncreaseOnly` and `DecreaseOnly`. Also documented the column. [#58029](https://github.com/ClickHouse/ClickHouse/pull/58029) ([skyoct](https://github.com/skyoct)).
* ClusterDiscovery supports setting username and password, close [#58063](https://github.com/ClickHouse/ClickHouse/issues/58063). [#58123](https://github.com/ClickHouse/ClickHouse/pull/58123) ([vdimir](https://github.com/vdimir)).
* Support query parameters in ALTER TABLE ... PART. [#58297](https://github.com/ClickHouse/ClickHouse/pull/58297) ([Azat Khuzhin](https://github.com/azat)).
* Create consumers for Kafka tables on fly (but keep them for some period - `kafka_consumers_pool_ttl_ms`, since last used), this should fix problem with statistics for `system.kafka_consumers` (that does not consumed when nobody reads from Kafka table, which leads to live memory leak and slow table detach) and also this PR enables stats for `system.kafka_consumers` by default again. [#58310](https://github.com/ClickHouse/ClickHouse/pull/58310) ([Azat Khuzhin](https://github.com/azat)).
* Sparkbar as an alias to sparkbar. [#58335](https://github.com/ClickHouse/ClickHouse/pull/58335) ([凌涛](https://github.com/lingtaolf)).
* Avoid sending ComposeObject requests after upload to GCS. [#58343](https://github.com/ClickHouse/ClickHouse/pull/58343) ([Azat Khuzhin](https://github.com/azat)).
* Correctly handle keys with dot in the name in configurations XMLs. [#58354](https://github.com/ClickHouse/ClickHouse/pull/58354) ([Azat Khuzhin](https://github.com/azat)).
* Added comments (brief descriptions) to all columns of system tables. The are several reasons fro this: - We use system tables a lot and sometimes is could be very difficult for developer to understand the purpose and the meaning of a particular column. - We change (add new ones or modify existing) system tables a lot and the documentation for them is always outdated. For example take a look at the documentation page for [`system.parts`](https://clickhouse.com/docs/en/operations/system-tables/parts). It misses a lot of columns - We would like to eventually generate documentation directly from ClickHouse. [#58356](https://github.com/ClickHouse/ClickHouse/pull/58356) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Allow to configure any kind of object storage with any kind of metadata type. [#58357](https://github.com/ClickHouse/ClickHouse/pull/58357) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Make function `format` return constant on constant arguments. This closes [#58355](https://github.com/ClickHouse/ClickHouse/issues/58355). [#58358](https://github.com/ClickHouse/ClickHouse/pull/58358) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Attach all system tables in `clickhouse-local`, including `system.parts`. This closes [#58312](https://github.com/ClickHouse/ClickHouse/issues/58312). [#58359](https://github.com/ClickHouse/ClickHouse/pull/58359) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Support for `Enum` data types in function `transform`. This closes [#58241](https://github.com/ClickHouse/ClickHouse/issues/58241). [#58360](https://github.com/ClickHouse/ClickHouse/pull/58360) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Allow registering database engines independently. [#58365](https://github.com/ClickHouse/ClickHouse/pull/58365) ([Bharat Nallan](https://github.com/bharatnc)).
* Adding a setting `max_estimated_execution_time` to separate `max_execution_time` and `max_estimated_execution_time`. [#58402](https://github.com/ClickHouse/ClickHouse/pull/58402) ([Zhang Yifan](https://github.com/zhangyifan27)).
* Allow registering interpreters independently. [#58443](https://github.com/ClickHouse/ClickHouse/pull/58443) ([Bharat Nallan](https://github.com/bharatnc)).
* Provide hint when an invalid database engine name is used. [#58444](https://github.com/ClickHouse/ClickHouse/pull/58444) ([Bharat Nallan](https://github.com/bharatnc)).
* Avoid huge memory consumption during Keeper startup for more cases. [#58455](https://github.com/ClickHouse/ClickHouse/pull/58455) ([Antonio Andelic](https://github.com/antonio2368)).
* Add settings for better control of indexes type in Arrow dictionary. Use signed integer type for indexes by default as Arrow recommends. Closes [#57401](https://github.com/ClickHouse/ClickHouse/issues/57401). [#58519](https://github.com/ClickHouse/ClickHouse/pull/58519) ([Kruglov Pavel](https://github.com/Avogar)).
* Added function `sqidDecode()` which decodes [Sqids](https://sqids.org/). [#58544](https://github.com/ClickHouse/ClickHouse/pull/58544) ([Robert Schulze](https://github.com/rschu1ze)).
* Allow to read Bool values into String in JSON input formats. It's done under a setting `input_format_json_read_bools_as_strings` that is enabled by default. [#58561](https://github.com/ClickHouse/ClickHouse/pull/58561) ([Kruglov Pavel](https://github.com/Avogar)).
* Implement [#58575](https://github.com/ClickHouse/ClickHouse/issues/58575) Support `CLICKHOUSE_PASSWORD_FILE ` environment variable when running the docker image. [#58583](https://github.com/ClickHouse/ClickHouse/pull/58583) ([Eyal Halpern Shalev](https://github.com/Eyal-Shalev)).
* When executing some queries, which require a lot of streams for reading data, the error `"Paste JOIN requires sorted tables only"` was previously thrown. Now the numbers of streams resize to 1 in that case. [#58608](https://github.com/ClickHouse/ClickHouse/pull/58608) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Add `SYSTEM JEMALLOC PURGE` for purging unused jemalloc pages, `SYSTEM JEMALLOC [ ENABLE | DISABLE | FLUSH ] PROFILE` for controlling jemalloc profile if the profiler is enabled. Add jemalloc-related 4LW command in Keeper: `jmst` for dumping jemalloc stats, `jmfp`, `jmep`, `jmdp` for controlling jemalloc profile if the profiler is enabled. [#58665](https://github.com/ClickHouse/ClickHouse/pull/58665) ([Antonio Andelic](https://github.com/antonio2368)).
* Better message for INVALID_IDENTIFIER error. [#58703](https://github.com/ClickHouse/ClickHouse/pull/58703) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Improved handling of signed numeric literals in normalizeQuery. [#58710](https://github.com/ClickHouse/ClickHouse/pull/58710) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
* Support Point data type for MySQL. [#58721](https://github.com/ClickHouse/ClickHouse/pull/58721) ([Kseniia Sumarokova](https://github.com/kssenii)).
* When comparing a Float32 column and a const string, read the string as Float32 (instead of Float64). [#58724](https://github.com/ClickHouse/ClickHouse/pull/58724) ([Raúl Marín](https://github.com/Algunenano)).
* Improve S3 compatible, add Ecloud EOS storage support. [#58786](https://github.com/ClickHouse/ClickHouse/pull/58786) ([xleoken](https://github.com/xleoken)).
* Allow `KILL QUERY` to cancel backups / restores. This PR also makes running backups and restores visible in `system.processes`. Also there is a new setting in the server configuration now - `shutdown_wait_backups_and_restores` (default=true) which makes the server either wait on shutdown for all running backups and restores to finish or just cancel them. [#58804](https://github.com/ClickHouse/ClickHouse/pull/58804) ([Vitaly Baranov](https://github.com/vitlibar)).
* Avro format support Zstd codec. Closes [#58735](https://github.com/ClickHouse/ClickHouse/issues/58735). [#58805](https://github.com/ClickHouse/ClickHouse/pull/58805) ([flynn](https://github.com/ucasfl)).
* MySQL interface gained support for `net_write_timeout` and `net_read_timeout` settings. `net_write_timeout` is translated into the native `send_timeout` ClickHouse setting and, similarly, `net_read_timeout` into `receive_timeout`. Fixed an issue where it was possible to set MySQL `sql_select_limit` setting only if the entire statement was in upper case. [#58835](https://github.com/ClickHouse/ClickHouse/pull/58835) ([Serge Klochkov](https://github.com/slvrtrn)).
* Fixing a problem described in [#58719](https://github.com/ClickHouse/ClickHouse/issues/58719). [#58841](https://github.com/ClickHouse/ClickHouse/pull/58841) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Make sure that for custom (created from SQL) disks ether `filesystem_caches_path` (a common directory prefix for all filesystem caches) or `custom_cached_disks_base_directory` (a common directory prefix for only filesystem caches created from custom disks) is specified in server config. `custom_cached_disks_base_directory` has higher priority for custom disks over `filesystem_caches_path`, which is used if the former one is absent. Filesystem cache setting `path` must lie inside that directory, otherwise exception will be thrown preventing disk to be created. This will not affect disks created on an older version and server was upgraded - then the exception will not be thrown to allow the server to successfully start). `custom_cached_disks_base_directory` is added to default server config as `/var/lib/clickhouse/caches/`. Closes [#57825](https://github.com/ClickHouse/ClickHouse/issues/57825). [#58869](https://github.com/ClickHouse/ClickHouse/pull/58869) ([Kseniia Sumarokova](https://github.com/kssenii)).
* MySQL interface gained compatibility with `SHOW WARNINGS`/`SHOW COUNT(*) WARNINGS` queries, though the returned result is always an empty set. [#58929](https://github.com/ClickHouse/ClickHouse/pull/58929) ([Serge Klochkov](https://github.com/slvrtrn)).
* Skip unavailable replicas when executing parallel distributed `INSERT SELECT`. [#58931](https://github.com/ClickHouse/ClickHouse/pull/58931) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Display word-descriptive log level while enabling structured log formatting in json. [#58936](https://github.com/ClickHouse/ClickHouse/pull/58936) ([Tim Liou](https://github.com/wheatdog)).
* MySQL interface gained support for `CAST(x AS SIGNED)` and `CAST(x AS UNSIGNED)` statements via data type aliases: `SIGNED` for Int64, and `UNSIGNED` for UInt64. This improves compatibility with BI tools such as Looker Studio. [#58954](https://github.com/ClickHouse/ClickHouse/pull/58954) ([Serge Klochkov](https://github.com/slvrtrn)).
* Function `seriesDecomposeSTL()` now returns a baseline component as season + trend components. [#58961](https://github.com/ClickHouse/ClickHouse/pull/58961) ([Bhavna Jindal](https://github.com/bhavnajindal)).
* Fix memory management in copyDataToS3File. [#58962](https://github.com/ClickHouse/ClickHouse/pull/58962) ([Vitaly Baranov](https://github.com/vitlibar)).
* Change working directory to data path in docker container. [#58975](https://github.com/ClickHouse/ClickHouse/pull/58975) ([cangyin](https://github.com/cangyin)).
* Added setting for Azure Blob Storage `azure_max_unexpected_write_error_retries` , can also be set from config under azure section. [#59001](https://github.com/ClickHouse/ClickHouse/pull/59001) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Keeper improvement: reduce Keeper's memory usage for stored nodes. [#59002](https://github.com/ClickHouse/ClickHouse/pull/59002) ([Antonio Andelic](https://github.com/antonio2368)).
* Allow server to start with broken data lake table. Closes [#58625](https://github.com/ClickHouse/ClickHouse/issues/58625). [#59080](https://github.com/ClickHouse/ClickHouse/pull/59080) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fixes https://github.com/ClickHouse/ClickHouse/pull/59120#issuecomment-1906177350. [#59122](https://github.com/ClickHouse/ClickHouse/pull/59122) ([Arthur Passos](https://github.com/arthurpassos)).
* The state of URL's #hash in the dashboard is now compressed using [lz-string](https://github.com/pieroxy/lz-string). The default size of the state string is compressed from 6856B to 2823B. [#59124](https://github.com/ClickHouse/ClickHouse/pull/59124) ([Amos Bird](https://github.com/amosbird)).
* Allow to ignore schema evolution in Iceberg table engine and read all data using schema specified by the user on table creation or latest schema parsed from metadata on table creation. This is done under a setting `iceberg_engine_ignore_schema_evolution` that is disabled by default. Note that enabling this setting can lead to incorrect result as in case of evolved schema all data files will be read using the same schema. [#59133](https://github.com/ClickHouse/ClickHouse/pull/59133) ([Kruglov Pavel](https://github.com/Avogar)).
* Prohibit mutable operations (`INSERT`/`ALTER`/`OPTIMIZE`/...) on read-only/write-once storages with a proper `TABLE_IS_READ_ONLY` error (to avoid leftovers). Avoid leaving left-overs on write-once disks (`format_version.txt`) on `CREATE`/`ATTACH`. Ignore `DROP` for `ReplicatedMergeTree` (so as for `MergeTree`). Fix iterating over `s3_plain` (`MetadataStorageFromPlainObjectStorage::iterateDirectory`). Note read-only is `web` disk, and write-once is `s3_plain`. [#59170](https://github.com/ClickHouse/ClickHouse/pull/59170) ([Azat Khuzhin](https://github.com/azat)).
* MySQL interface gained support for `net_write_timeout` and `net_read_timeout` settings. `net_write_timeout` is translated into the native `send_timeout` ClickHouse setting and, similarly, `net_read_timeout` into `receive_timeout`. Fixed an issue where it was possible to set MySQL `sql_select_limit` setting only if the entire statement was in upper case. [#59293](https://github.com/ClickHouse/ClickHouse/pull/59293) ([Serge Klochkov](https://github.com/slvrtrn)).
* Fix bug in experimental `_block_number` column which could lead to logical error during complex combination of `ALTER`s and `merge`s. Fixes [#56202](https://github.com/ClickHouse/ClickHouse/issues/56202). Replaces [#58601](https://github.com/ClickHouse/ClickHouse/issues/58601). CC @SmitaRKulkarni. [#59295](https://github.com/ClickHouse/ClickHouse/pull/59295) ([alesapin](https://github.com/alesapin)).
* Play UI understands when an exception is returned inside JSON. Adjustment for [#52853](https://github.com/ClickHouse/ClickHouse/issues/52853). [#59303](https://github.com/ClickHouse/ClickHouse/pull/59303) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* `/binary` HTTP handler allows to specify user, host, and optionally, password in the query string. [#59311](https://github.com/ClickHouse/ClickHouse/pull/59311) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Support backups for compressed in-memory tables. This closes [#57893](https://github.com/ClickHouse/ClickHouse/issues/57893). [#59315](https://github.com/ClickHouse/ClickHouse/pull/59315) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Improve exception message of function regexp_extract, close [#56393](https://github.com/ClickHouse/ClickHouse/issues/56393). [#59319](https://github.com/ClickHouse/ClickHouse/pull/59319) ([李扬](https://github.com/taiyang-li)).
* Support the FORMAT clause in BACKUP and RESTORE queries. [#59338](https://github.com/ClickHouse/ClickHouse/pull/59338) ([Vitaly Baranov](https://github.com/vitlibar)).
* Function `concatWithSeparator()` now supports arbitrary argument types (instead of only `String` and `FixedString` arguments). For example, `SELECT concatWithSeparator('.', 'number', 1)` now returns `number.1`. [#59341](https://github.com/ClickHouse/ClickHouse/pull/59341) ([Robert Schulze](https://github.com/rschu1ze)).
#### Build/Testing/Packaging Improvement
* Improve aliases for clickhouse binary (now `ch`/`clickhouse` is `clickhouse-local` or `clickhouse` depends on the arguments) and add bash completion for new aliases. [#58344](https://github.com/ClickHouse/ClickHouse/pull/58344) ([Azat Khuzhin](https://github.com/azat)).
* Add settings changes check to CI to check that all settings changes are reflected in settings changes history. [#58555](https://github.com/ClickHouse/ClickHouse/pull/58555) ([Kruglov Pavel](https://github.com/Avogar)).
* Use tables directly attached from S3 in stateful tests. [#58791](https://github.com/ClickHouse/ClickHouse/pull/58791) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Save the whole `fuzzer.log` as an archive instead of the last 100k lines. `tail -n 100000` often removes lines with table definitions. Example:. [#58821](https://github.com/ClickHouse/ClickHouse/pull/58821) ([Dmitry Novik](https://github.com/novikd)).
* Enable Rust on OSX ARM64 (this will add fuzzy search in client with skim and prql language, though I don't think that are people who hosts ClickHouse on darwin, so it is mostly for fuzzy search in client I would say). [#59272](https://github.com/ClickHouse/ClickHouse/pull/59272) ([Azat Khuzhin](https://github.com/azat)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Add join keys conversion for nested lowcardinality [#51550](https://github.com/ClickHouse/ClickHouse/pull/51550) ([vdimir](https://github.com/vdimir)).
* Flatten only true Nested type if flatten_nested=1, not all Array(Tuple) [#56132](https://github.com/ClickHouse/ClickHouse/pull/56132) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix a bug with projections and the aggregate_functions_null_for_empty setting during insertion. [#56944](https://github.com/ClickHouse/ClickHouse/pull/56944) ([Amos Bird](https://github.com/amosbird)).
* Fixed potential exception due to stale profile UUID [#57263](https://github.com/ClickHouse/ClickHouse/pull/57263) ([Vasily Nemkov](https://github.com/Enmk)).
* Fix working with read buffers in StreamingFormatExecutor [#57438](https://github.com/ClickHouse/ClickHouse/pull/57438) ([Kruglov Pavel](https://github.com/Avogar)).
* Ignore MVs with dropped target table during pushing to views [#57520](https://github.com/ClickHouse/ClickHouse/pull/57520) ([Kruglov Pavel](https://github.com/Avogar)).
* [RFC] Eliminate possible race between ALTER_METADATA and MERGE_PARTS [#57755](https://github.com/ClickHouse/ClickHouse/pull/57755) ([Azat Khuzhin](https://github.com/azat)).
* Fix the exprs order bug in group by with rollup [#57786](https://github.com/ClickHouse/ClickHouse/pull/57786) ([Chen768959](https://github.com/Chen768959)).
* Fix lost blobs after dropping a replica with broken detached parts [#58333](https://github.com/ClickHouse/ClickHouse/pull/58333) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Allow users to work with symlinks in user_files_path (again) [#58447](https://github.com/ClickHouse/ClickHouse/pull/58447) ([Duc Canh Le](https://github.com/canhld94)).
* Fix segfault when graphite table does not have agg function [#58453](https://github.com/ClickHouse/ClickHouse/pull/58453) ([Duc Canh Le](https://github.com/canhld94)).
* Delay reading from StorageKafka to allow multiple reads in materialized views [#58477](https://github.com/ClickHouse/ClickHouse/pull/58477) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Fix a stupid case of intersecting parts [#58482](https://github.com/ClickHouse/ClickHouse/pull/58482) ([Alexander Tokmakov](https://github.com/tavplubix)).
* MergeTreePrefetchedReadPool disable for LIMIT only queries [#58505](https://github.com/ClickHouse/ClickHouse/pull/58505) ([Maksim Kita](https://github.com/kitaisreal)).
* Enable ordinary databases while restoration [#58520](https://github.com/ClickHouse/ClickHouse/pull/58520) ([Jihyuk Bok](https://github.com/tomahawk28)).
* Fix hive threadpool read ORC/Parquet/... Failed [#58537](https://github.com/ClickHouse/ClickHouse/pull/58537) ([sunny](https://github.com/sunny19930321)).
* Hide credentials in system.backup_log base_backup_name column [#58550](https://github.com/ClickHouse/ClickHouse/pull/58550) ([Daniel Pozo Escalona](https://github.com/danipozo)).
* toStartOfInterval for milli- microsencods values rounding [#58557](https://github.com/ClickHouse/ClickHouse/pull/58557) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Disable max_joined_block_rows in ConcurrentHashJoin [#58595](https://github.com/ClickHouse/ClickHouse/pull/58595) ([vdimir](https://github.com/vdimir)).
* Fix join using nullable in old analyzer [#58596](https://github.com/ClickHouse/ClickHouse/pull/58596) ([vdimir](https://github.com/vdimir)).
* `makeDateTime64()`: Allow non-const fraction argument [#58597](https://github.com/ClickHouse/ClickHouse/pull/58597) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix possible NULL dereference during symbolizing inline frames [#58607](https://github.com/ClickHouse/ClickHouse/pull/58607) ([Azat Khuzhin](https://github.com/azat)).
* Improve isolation of query cache entries under re-created users or role switches [#58611](https://github.com/ClickHouse/ClickHouse/pull/58611) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix broken partition key analysis when doing projection optimization [#58638](https://github.com/ClickHouse/ClickHouse/pull/58638) ([Amos Bird](https://github.com/amosbird)).
* Query cache: Fix per-user quota [#58731](https://github.com/ClickHouse/ClickHouse/pull/58731) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix stream partitioning in parallel window functions [#58739](https://github.com/ClickHouse/ClickHouse/pull/58739) ([Dmitry Novik](https://github.com/novikd)).
* Fix double destroy call on exception throw in addBatchLookupTable8 [#58745](https://github.com/ClickHouse/ClickHouse/pull/58745) ([Raúl Marín](https://github.com/Algunenano)).
* Don't process requests in Keeper during shutdown [#58765](https://github.com/ClickHouse/ClickHouse/pull/58765) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix Segfault in `SlabsPolygonIndex::find` [#58771](https://github.com/ClickHouse/ClickHouse/pull/58771) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Fix JSONExtract function for LowCardinality(Nullable) columns [#58808](https://github.com/ClickHouse/ClickHouse/pull/58808) ([vdimir](https://github.com/vdimir)).
* Table CREATE DROP Poco::Logger memory leak fix [#58831](https://github.com/ClickHouse/ClickHouse/pull/58831) ([Maksim Kita](https://github.com/kitaisreal)).
* Fix HTTP compressors finalization [#58846](https://github.com/ClickHouse/ClickHouse/pull/58846) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Multiple read file log storage in mv [#58877](https://github.com/ClickHouse/ClickHouse/pull/58877) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Restriction for the access key id for s3. [#58900](https://github.com/ClickHouse/ClickHouse/pull/58900) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* Fix possible crash in clickhouse-local during loading suggestions [#58907](https://github.com/ClickHouse/ClickHouse/pull/58907) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix crash when indexHint() is used [#58911](https://github.com/ClickHouse/ClickHouse/pull/58911) ([Dmitry Novik](https://github.com/novikd)).
* Fix StorageURL forgetting headers on server restart [#58933](https://github.com/ClickHouse/ClickHouse/pull/58933) ([Michael Kolupaev](https://github.com/al13n321)).
* Analyzer: fix storage replacement with insertion block [#58958](https://github.com/ClickHouse/ClickHouse/pull/58958) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* Fix seek in ReadBufferFromZipArchive [#58966](https://github.com/ClickHouse/ClickHouse/pull/58966) ([Michael Kolupaev](https://github.com/al13n321)).
* `DROP INDEX` of inverted index now removes all relevant files from persistence [#59040](https://github.com/ClickHouse/ClickHouse/pull/59040) ([mochi](https://github.com/MochiXu)).
* Fix data race on query_factories_info [#59049](https://github.com/ClickHouse/ClickHouse/pull/59049) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Disable "Too many redirects" error retry [#59099](https://github.com/ClickHouse/ClickHouse/pull/59099) ([skyoct](https://github.com/skyoct)).
* Fix aggregation issue in mixed x86_64 and ARM clusters [#59132](https://github.com/ClickHouse/ClickHouse/pull/59132) ([Harry Lee](https://github.com/HarryLeeIBM)).
* Fix not started database shutdown deadlock [#59137](https://github.com/ClickHouse/ClickHouse/pull/59137) ([Sergei Trifonov](https://github.com/serxa)).
* Fix: LIMIT BY and LIMIT in distributed query [#59153](https://github.com/ClickHouse/ClickHouse/pull/59153) ([Igor Nikonov](https://github.com/devcrafter)).
* Fix crash with nullable timezone for `toString` [#59190](https://github.com/ClickHouse/ClickHouse/pull/59190) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* Fix abort in iceberg metadata on bad file paths [#59275](https://github.com/ClickHouse/ClickHouse/pull/59275) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix architecture name in select of Rust target [#59307](https://github.com/ClickHouse/ClickHouse/pull/59307) ([p1rattttt](https://github.com/p1rattttt)).
* Fix not-ready set for system.tables [#59351](https://github.com/ClickHouse/ClickHouse/pull/59351) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix lazy initialization in RabbitMQ [#59352](https://github.com/ClickHouse/ClickHouse/pull/59352) ([Kruglov Pavel](https://github.com/Avogar)).
#### NO CL ENTRY
* NO CL ENTRY: 'Revert "Refreshable materialized views (takeover)"'. [#58296](https://github.com/ClickHouse/ClickHouse/pull/58296) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Fix an error in the release script - it didn't allow to make 23.12."'. [#58381](https://github.com/ClickHouse/ClickHouse/pull/58381) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* NO CL ENTRY: 'Revert "Use CH Buffer for HTTP out stream, add metrics for interfaces"'. [#58450](https://github.com/ClickHouse/ClickHouse/pull/58450) ([Raúl Marín](https://github.com/Algunenano)).
* NO CL ENTRY: 'Second attempt: Use CH Buffer for HTTP out stream, add metrics for interfaces'. [#58475](https://github.com/ClickHouse/ClickHouse/pull/58475) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
* NO CL ENTRY: 'Revert "Merging [#53757](https://github.com/ClickHouse/ClickHouse/issues/53757)"'. [#58542](https://github.com/ClickHouse/ClickHouse/pull/58542) ([Raúl Marín](https://github.com/Algunenano)).
* NO CL ENTRY: 'Revert "Add support for MySQL `net_write_timeout` and `net_read_timeout` settings"'. [#58872](https://github.com/ClickHouse/ClickHouse/pull/58872) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Extend performance test norm_dist.xml"'. [#58989](https://github.com/ClickHouse/ClickHouse/pull/58989) ([Raúl Marín](https://github.com/Algunenano)).
* NO CL ENTRY: 'Revert "Add a test for [#47892](https://github.com/ClickHouse/ClickHouse/issues/47892)"'. [#58990](https://github.com/ClickHouse/ClickHouse/pull/58990) ([Raúl Marín](https://github.com/Algunenano)).
* NO CL ENTRY: 'Revert "Allow parallel replicas for JOIN with analyzer [part 1]."'. [#59059](https://github.com/ClickHouse/ClickHouse/pull/59059) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Consume leading zeroes when parsing a number in ConstantExpressionTemplate"'. [#59070](https://github.com/ClickHouse/ClickHouse/pull/59070) ([Alexander Tokmakov](https://github.com/tavplubix)).
* NO CL ENTRY: 'Revert "Revert "Allow parallel replicas for JOIN with analyzer [part 1].""'. [#59076](https://github.com/ClickHouse/ClickHouse/pull/59076) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* NO CL ENTRY: 'Revert "Allow to attach partition from table with different partition expression when destination partition expression doesn't re-partition"'. [#59120](https://github.com/ClickHouse/ClickHouse/pull/59120) ([Robert Schulze](https://github.com/rschu1ze)).
* NO CL ENTRY: 'DisksApp.cpp: fix typo (specifiged → specified)'. [#59140](https://github.com/ClickHouse/ClickHouse/pull/59140) ([Nikolay Edigaryev](https://github.com/edigaryev)).
#### NOT FOR CHANGELOG / INSIGNIFICANT
* Analyzer: Fix resolving subcolumns in JOIN [#49703](https://github.com/ClickHouse/ClickHouse/pull/49703) ([vdimir](https://github.com/vdimir)).
* Analyzer: always qualify execution names [#53705](https://github.com/ClickHouse/ClickHouse/pull/53705) ([Dmitry Novik](https://github.com/novikd)).
* Insert quorum: check host node version in addition [#55528](https://github.com/ClickHouse/ClickHouse/pull/55528) ([Igor Nikonov](https://github.com/devcrafter)).
* Remove more old code of projection analysis [#55579](https://github.com/ClickHouse/ClickHouse/pull/55579) ([Anton Popov](https://github.com/CurtizJ)).
* Better exception messages in input formats [#57053](https://github.com/ClickHouse/ClickHouse/pull/57053) ([Kruglov Pavel](https://github.com/Avogar)).
* Parallel replicas custom key: skip unavailable replicas [#57235](https://github.com/ClickHouse/ClickHouse/pull/57235) ([Igor Nikonov](https://github.com/devcrafter)).
* Small change in log message in MergeTreeDataMergerMutator [#57550](https://github.com/ClickHouse/ClickHouse/pull/57550) ([Nikita Taranov](https://github.com/nickitat)).
* fs cache: small optimization [#57615](https://github.com/ClickHouse/ClickHouse/pull/57615) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Customizable dependency failure handling for AsyncLoader [#57697](https://github.com/ClickHouse/ClickHouse/pull/57697) ([Sergei Trifonov](https://github.com/serxa)).
* Bring test back [#57700](https://github.com/ClickHouse/ClickHouse/pull/57700) ([Nikita Taranov](https://github.com/nickitat)).
* Change default database name in clickhouse-local to 'default' [#57774](https://github.com/ClickHouse/ClickHouse/pull/57774) ([Kruglov Pavel](https://github.com/Avogar)).
* Add option `--show-whitespaces-in-diff` to clickhouse-test [#57870](https://github.com/ClickHouse/ClickHouse/pull/57870) ([vdimir](https://github.com/vdimir)).
* Update `query_masking_rules` when reloading the config, attempt 2 [#57993](https://github.com/ClickHouse/ClickHouse/pull/57993) ([Mikhail Koviazin](https://github.com/mkmkme)).
* Remove unneeded parameter `use_external_buffer` from `AsynchronousReadBuffer*` [#58077](https://github.com/ClickHouse/ClickHouse/pull/58077) ([Nikita Taranov](https://github.com/nickitat)).
* Print another message in Bugfix check if internal check had been failed [#58091](https://github.com/ClickHouse/ClickHouse/pull/58091) ([vdimir](https://github.com/vdimir)).
* Refactor StorageMerge virtual columns filtering. [#58255](https://github.com/ClickHouse/ClickHouse/pull/58255) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Analyzer: fix tuple comparison when result is always null [#58266](https://github.com/ClickHouse/ClickHouse/pull/58266) ([vdimir](https://github.com/vdimir)).
* Fix an error in the release script - it didn't allow to make 23.12. [#58288](https://github.com/ClickHouse/ClickHouse/pull/58288) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Update version_date.tsv and changelogs after v23.12.1.1368-stable [#58290](https://github.com/ClickHouse/ClickHouse/pull/58290) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Fix test_storage_s3_queue/test.py::test_drop_table [#58293](https://github.com/ClickHouse/ClickHouse/pull/58293) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix timeout in 01732_race_condition_storage_join_long [#58298](https://github.com/ClickHouse/ClickHouse/pull/58298) ([vdimir](https://github.com/vdimir)).
* Handle another case for preprocessing in Keeper [#58308](https://github.com/ClickHouse/ClickHouse/pull/58308) ([Antonio Andelic](https://github.com/antonio2368)).
* Disable max_bytes_before_external* in 00172_hits_joins [#58309](https://github.com/ClickHouse/ClickHouse/pull/58309) ([vdimir](https://github.com/vdimir)).
* Analyzer: support functional arguments in USING clause [#58317](https://github.com/ClickHouse/ClickHouse/pull/58317) ([Dmitry Novik](https://github.com/novikd)).
* Fixed logical error in CheckSortedTransform [#58318](https://github.com/ClickHouse/ClickHouse/pull/58318) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Refreshable materialized views again [#58320](https://github.com/ClickHouse/ClickHouse/pull/58320) ([Michael Kolupaev](https://github.com/al13n321)).
* Organize symbols from src/* into DB namespace [#58336](https://github.com/ClickHouse/ClickHouse/pull/58336) ([Amos Bird](https://github.com/amosbird)).
* Add a style check against DOS and Windows [#58345](https://github.com/ClickHouse/ClickHouse/pull/58345) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Check what happen if remove array joined columns from KeyCondition [#58346](https://github.com/ClickHouse/ClickHouse/pull/58346) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Upload time of the perf tests into artifacts as test_duration_ms [#58348](https://github.com/ClickHouse/ClickHouse/pull/58348) ([Azat Khuzhin](https://github.com/azat)).
* Keep exception format string in retries ctl [#58351](https://github.com/ClickHouse/ClickHouse/pull/58351) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix replication.lib helper (system.mutations has database not current_database) [#58352](https://github.com/ClickHouse/ClickHouse/pull/58352) ([Azat Khuzhin](https://github.com/azat)).
* Refactor StorageHDFS and StorageFile virtual columns filtering [#58353](https://github.com/ClickHouse/ClickHouse/pull/58353) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix suspended workers for AsyncLoader [#58362](https://github.com/ClickHouse/ClickHouse/pull/58362) ([Sergei Trifonov](https://github.com/serxa)).
* Remove stale events from README [#58364](https://github.com/ClickHouse/ClickHouse/pull/58364) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Do not fail the CI on an expired token [#58384](https://github.com/ClickHouse/ClickHouse/pull/58384) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add a test for [#38534](https://github.com/ClickHouse/ClickHouse/issues/38534) [#58391](https://github.com/ClickHouse/ClickHouse/pull/58391) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* fix database engine validation inside database factory [#58395](https://github.com/ClickHouse/ClickHouse/pull/58395) ([Bharat Nallan](https://github.com/bharatnc)).
* Fix bad formatting of the `timeDiff` compatibility alias [#58398](https://github.com/ClickHouse/ClickHouse/pull/58398) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix a comment; remove unused method; stop using pointers [#58399](https://github.com/ClickHouse/ClickHouse/pull/58399) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix test_user_valid_until [#58409](https://github.com/ClickHouse/ClickHouse/pull/58409) ([Nikolay Degterinsky](https://github.com/evillique)).
* Make a test not depend on the lack of floating point associativity [#58439](https://github.com/ClickHouse/ClickHouse/pull/58439) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix `02944_dynamically_change_filesystem_cache_size` [#58445](https://github.com/ClickHouse/ClickHouse/pull/58445) ([Nikolay Degterinsky](https://github.com/evillique)).
* Analyzer: Fix LOGICAL_ERROR with LowCardinality [#58457](https://github.com/ClickHouse/ClickHouse/pull/58457) ([Dmitry Novik](https://github.com/novikd)).
* Replace `std::regex` by re2 [#58458](https://github.com/ClickHouse/ClickHouse/pull/58458) ([Robert Schulze](https://github.com/rschu1ze)).
* Improve perf tests [#58478](https://github.com/ClickHouse/ClickHouse/pull/58478) ([Raúl Marín](https://github.com/Algunenano)).
* Check if I can remove KeyCondition analysis on AST. [#58480](https://github.com/ClickHouse/ClickHouse/pull/58480) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix some thread pool settings not updating at runtime [#58485](https://github.com/ClickHouse/ClickHouse/pull/58485) ([Michael Kolupaev](https://github.com/al13n321)).
* Lower log levels for some Raft logs to new test level [#58487](https://github.com/ClickHouse/ClickHouse/pull/58487) ([Antonio Andelic](https://github.com/antonio2368)).
* PartsSplitter small refactoring [#58506](https://github.com/ClickHouse/ClickHouse/pull/58506) ([Maksim Kita](https://github.com/kitaisreal)).
* Sync content of the docker test images [#58507](https://github.com/ClickHouse/ClickHouse/pull/58507) ([Max K.](https://github.com/maxknv)).
* CI: move ci-specifics from job scripts to ci.py [#58516](https://github.com/ClickHouse/ClickHouse/pull/58516) ([Max K.](https://github.com/maxknv)).
* Minor fixups for `sqid()` [#58517](https://github.com/ClickHouse/ClickHouse/pull/58517) ([Robert Schulze](https://github.com/rschu1ze)).
* Update version_date.tsv and changelogs after v23.12.2.59-stable [#58545](https://github.com/ClickHouse/ClickHouse/pull/58545) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.11.4.24-stable [#58546](https://github.com/ClickHouse/ClickHouse/pull/58546) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.8.9.54-lts [#58547](https://github.com/ClickHouse/ClickHouse/pull/58547) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.10.6.60-stable [#58548](https://github.com/ClickHouse/ClickHouse/pull/58548) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update version_date.tsv and changelogs after v23.3.19.32-lts [#58549](https://github.com/ClickHouse/ClickHouse/pull/58549) ([robot-clickhouse](https://github.com/robot-clickhouse)).
* Update CHANGELOG.md [#58559](https://github.com/ClickHouse/ClickHouse/pull/58559) ([Konstantin Bogdanov](https://github.com/thevar1able)).
* Fix test 02932_kill_query_sleep [#58560](https://github.com/ClickHouse/ClickHouse/pull/58560) ([Vitaly Baranov](https://github.com/vitlibar)).
* CI fix. Add packager script to build digest [#58571](https://github.com/ClickHouse/ClickHouse/pull/58571) ([Max K.](https://github.com/maxknv)).
* fix and test that S3Clients are reused [#58573](https://github.com/ClickHouse/ClickHouse/pull/58573) ([Sema Checherinda](https://github.com/CheSema)).
* Follow-up to [#58482](https://github.com/ClickHouse/ClickHouse/issues/58482) [#58574](https://github.com/ClickHouse/ClickHouse/pull/58574) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Do not load database engines in suggest [#58586](https://github.com/ClickHouse/ClickHouse/pull/58586) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix wrong message in Keeper [#58588](https://github.com/ClickHouse/ClickHouse/pull/58588) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add some missing LLVM includes [#58594](https://github.com/ClickHouse/ClickHouse/pull/58594) ([Raúl Marín](https://github.com/Algunenano)).
* Small fix in Keeper [#58598](https://github.com/ClickHouse/ClickHouse/pull/58598) ([Antonio Andelic](https://github.com/antonio2368)).
* Update analyzer_tech_debt.txt [#58599](https://github.com/ClickHouse/ClickHouse/pull/58599) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Simplify release.py script [#58600](https://github.com/ClickHouse/ClickHouse/pull/58600) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Update analyzer_tech_debt.txt [#58602](https://github.com/ClickHouse/ClickHouse/pull/58602) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Refactor stacktrace symbolizer to avoid copy-paste [#58610](https://github.com/ClickHouse/ClickHouse/pull/58610) ([Azat Khuzhin](https://github.com/azat)).
* Add intel AMX checking [#58617](https://github.com/ClickHouse/ClickHouse/pull/58617) ([Roman Glinskikh](https://github.com/omgronny)).
* Optional `client` argument for `S3Helper` [#58619](https://github.com/ClickHouse/ClickHouse/pull/58619) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Add sorting to 02366_kql_summarize.sql [#58621](https://github.com/ClickHouse/ClickHouse/pull/58621) ([Raúl Marín](https://github.com/Algunenano)).
* Fix possible race in ManyAggregatedData dtor. [#58624](https://github.com/ClickHouse/ClickHouse/pull/58624) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Remove more projections code [#58628](https://github.com/ClickHouse/ClickHouse/pull/58628) ([Anton Popov](https://github.com/CurtizJ)).
* Remove finalize() from ~WriteBufferFromEncryptedFile [#58629](https://github.com/ClickHouse/ClickHouse/pull/58629) ([Vitaly Baranov](https://github.com/vitlibar)).
* Update test_replicated_database/test.py [#58647](https://github.com/ClickHouse/ClickHouse/pull/58647) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Try disabling `muzzy_decay_ms` in jemalloc [#58648](https://github.com/ClickHouse/ClickHouse/pull/58648) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix test_replicated_database::test_startup_without_zk flakiness [#58649](https://github.com/ClickHouse/ClickHouse/pull/58649) ([Azat Khuzhin](https://github.com/azat)).
* Fix 01600_remerge_sort_lowered_memory_bytes_ratio flakiness (due to settings randomization) [#58650](https://github.com/ClickHouse/ClickHouse/pull/58650) ([Azat Khuzhin](https://github.com/azat)).
* Analyzer: Fix assertion in HashJoin with duplicate columns [#58652](https://github.com/ClickHouse/ClickHouse/pull/58652) ([vdimir](https://github.com/vdimir)).
* Document that `match()` can use `ngrambf_v1` and `tokenbf_v1` indexes [#58655](https://github.com/ClickHouse/ClickHouse/pull/58655) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix perf tests duration (checks.test_duration_ms) [#58656](https://github.com/ClickHouse/ClickHouse/pull/58656) ([Azat Khuzhin](https://github.com/azat)).
* Analyzer: Correctly handle constant set in index [#58657](https://github.com/ClickHouse/ClickHouse/pull/58657) ([Dmitry Novik](https://github.com/novikd)).
* fix a typo in stress randomization setting [#58658](https://github.com/ClickHouse/ClickHouse/pull/58658) ([Sema Checherinda](https://github.com/CheSema)).
* Small follow-up to `std::regex` --> `re2` conversion ([#58458](https://github.com/ClickHouse/ClickHouse/issues/58458)) [#58678](https://github.com/ClickHouse/ClickHouse/pull/58678) ([Robert Schulze](https://github.com/rschu1ze)).
* Remove `<regex>` from libcxx [#58681](https://github.com/ClickHouse/ClickHouse/pull/58681) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix bad log message [#58698](https://github.com/ClickHouse/ClickHouse/pull/58698) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Some small improvements to version_helper from [#57203](https://github.com/ClickHouse/ClickHouse/issues/57203) [#58712](https://github.com/ClickHouse/ClickHouse/pull/58712) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Small fixes in different helpers [#58717](https://github.com/ClickHouse/ClickHouse/pull/58717) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fix bug in new (not released yet) parallel replicas coordinator [#58722](https://github.com/ClickHouse/ClickHouse/pull/58722) ([Nikita Taranov](https://github.com/nickitat)).
* Analyzer: Fix LOGICAL_ERROR in CountDistinctPass [#58723](https://github.com/ClickHouse/ClickHouse/pull/58723) ([Dmitry Novik](https://github.com/novikd)).
* Fix reading of offsets subcolumn (`size0`) from `Nested` [#58729](https://github.com/ClickHouse/ClickHouse/pull/58729) ([Anton Popov](https://github.com/CurtizJ)).
* Fix Mac OS X [#58733](https://github.com/ClickHouse/ClickHouse/pull/58733) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* fix stress with generate-template-key [#58740](https://github.com/ClickHouse/ClickHouse/pull/58740) ([Sema Checherinda](https://github.com/CheSema)).
* more relaxed check [#58751](https://github.com/ClickHouse/ClickHouse/pull/58751) ([Sema Checherinda](https://github.com/CheSema)).
* Fix usage of small buffers for remote reading [#58768](https://github.com/ClickHouse/ClickHouse/pull/58768) ([Nikita Taranov](https://github.com/nickitat)).
* Add missing includes when _LIBCPP_REMOVE_TRANSITIVE_INCLUDES enabled [#58770](https://github.com/ClickHouse/ClickHouse/pull/58770) ([Artem Alperin](https://github.com/hdnpth)).
* Remove some code [#58772](https://github.com/ClickHouse/ClickHouse/pull/58772) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Remove some code [#58790](https://github.com/ClickHouse/ClickHouse/pull/58790) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix trash in performance tests [#58794](https://github.com/ClickHouse/ClickHouse/pull/58794) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix data race in Keeper [#58806](https://github.com/ClickHouse/ClickHouse/pull/58806) ([Antonio Andelic](https://github.com/antonio2368)).
* Increase log level to trace to help debug `00993_system_parts_race_condition_drop_zookeeper` [#58809](https://github.com/ClickHouse/ClickHouse/pull/58809) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* DatabaseCatalog background tasks add log names [#58832](https://github.com/ClickHouse/ClickHouse/pull/58832) ([Maksim Kita](https://github.com/kitaisreal)).
* Analyzer: Resolve GROUPING function on shards [#58833](https://github.com/ClickHouse/ClickHouse/pull/58833) ([Dmitry Novik](https://github.com/novikd)).
* Allow parallel replicas for JOIN with analyzer [part 1]. [#58838](https://github.com/ClickHouse/ClickHouse/pull/58838) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix `isRetry` method [#58839](https://github.com/ClickHouse/ClickHouse/pull/58839) ([alesapin](https://github.com/alesapin)).
* fs cache: fix data race in slru [#58842](https://github.com/ClickHouse/ClickHouse/pull/58842) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix reading from an invisible part in new (not released yet) parallel replicas coordinator [#58844](https://github.com/ClickHouse/ClickHouse/pull/58844) ([Nikita Taranov](https://github.com/nickitat)).
* Fix bad log message [#58849](https://github.com/ClickHouse/ClickHouse/pull/58849) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Set max_bytes_before_external_group_by in 01961_roaring_memory_tracking [#58863](https://github.com/ClickHouse/ClickHouse/pull/58863) ([vdimir](https://github.com/vdimir)).
* Fix `00089_group_by_arrays_of_fixed` with external aggregation [#58873](https://github.com/ClickHouse/ClickHouse/pull/58873) ([Antonio Andelic](https://github.com/antonio2368)).
* DiskWeb minor improvement in loading [#58874](https://github.com/ClickHouse/ClickHouse/pull/58874) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix RPN construction for indexHint [#58875](https://github.com/ClickHouse/ClickHouse/pull/58875) ([Dmitry Novik](https://github.com/novikd)).
* Analyzer: add test with GROUP BY on shards [#58876](https://github.com/ClickHouse/ClickHouse/pull/58876) ([Dmitry Novik](https://github.com/novikd)).
* Jepsen job to reuse builds [#58881](https://github.com/ClickHouse/ClickHouse/pull/58881) ([Max K.](https://github.com/maxknv)).
* Fix ambiguity in the setting description [#58883](https://github.com/ClickHouse/ClickHouse/pull/58883) ([Denny Crane](https://github.com/den-crane)).
* Less error prone interface of read buffers [#58886](https://github.com/ClickHouse/ClickHouse/pull/58886) ([Anton Popov](https://github.com/CurtizJ)).
* Add metric for keeper memory soft limit [#58890](https://github.com/ClickHouse/ClickHouse/pull/58890) ([Pradeep Chhetri](https://github.com/chhetripradeep)).
* Add a test for [#47988](https://github.com/ClickHouse/ClickHouse/issues/47988) [#58893](https://github.com/ClickHouse/ClickHouse/pull/58893) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Whitespaces [#58894](https://github.com/ClickHouse/ClickHouse/pull/58894) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix data race in `AggregatingTransform` [#58896](https://github.com/ClickHouse/ClickHouse/pull/58896) ([Antonio Andelic](https://github.com/antonio2368)).
* Update SLRUFileCachePriority.cpp [#58898](https://github.com/ClickHouse/ClickHouse/pull/58898) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add tests for [#57193](https://github.com/ClickHouse/ClickHouse/issues/57193) [#58899](https://github.com/ClickHouse/ClickHouse/pull/58899) ([Raúl Marín](https://github.com/Algunenano)).
* Add log for already download binary in Jepsen [#58901](https://github.com/ClickHouse/ClickHouse/pull/58901) ([Antonio Andelic](https://github.com/antonio2368)).
* fs cache: minor refactoring [#58902](https://github.com/ClickHouse/ClickHouse/pull/58902) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Checking on flaky test_parallel_replicas_custom_key_failover [#58909](https://github.com/ClickHouse/ClickHouse/pull/58909) ([Igor Nikonov](https://github.com/devcrafter)).
* Style fix [#58913](https://github.com/ClickHouse/ClickHouse/pull/58913) ([Dmitry Novik](https://github.com/novikd)).
* Opentelemetry spans to analyze CPU and S3 bottlenecks on inserts [#58914](https://github.com/ClickHouse/ClickHouse/pull/58914) ([Alexander Gololobov](https://github.com/davenger)).
* Fix fault handler in case of thread (for fault handler) cannot be spawned [#58917](https://github.com/ClickHouse/ClickHouse/pull/58917) ([Azat Khuzhin](https://github.com/azat)).
* Analyzer: Support GROUP BY injective function elimination [#58919](https://github.com/ClickHouse/ClickHouse/pull/58919) ([Dmitry Novik](https://github.com/novikd)).
* Cancel MasterCI in PRs [#58920](https://github.com/ClickHouse/ClickHouse/pull/58920) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Fix and test for azure [#58697](https://github.com/ClickHouse/ClickHouse/issues/58697) [#58921](https://github.com/ClickHouse/ClickHouse/pull/58921) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Extend performance test norm_dist.xml [#58922](https://github.com/ClickHouse/ClickHouse/pull/58922) ([Robert Schulze](https://github.com/rschu1ze)).
* Add regression test for parallel replicas (follow up [#58722](https://github.com/ClickHouse/ClickHouse/issues/58722), [#58844](https://github.com/ClickHouse/ClickHouse/issues/58844)) [#58923](https://github.com/ClickHouse/ClickHouse/pull/58923) ([Nikita Taranov](https://github.com/nickitat)).
* Add a test for [#47892](https://github.com/ClickHouse/ClickHouse/issues/47892) [#58927](https://github.com/ClickHouse/ClickHouse/pull/58927) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix `FunctionToSubcolumnsPass` in debug build [#58930](https://github.com/ClickHouse/ClickHouse/pull/58930) ([Anton Popov](https://github.com/CurtizJ)).
* Call `getMaxFileDescriptorCount` once in Keeper [#58938](https://github.com/ClickHouse/ClickHouse/pull/58938) ([Antonio Andelic](https://github.com/antonio2368)).
* Add missing files to digests [#58942](https://github.com/ClickHouse/ClickHouse/pull/58942) ([Raúl Marín](https://github.com/Algunenano)).
* Analyzer: fix join column not found with compound identifiers [#58943](https://github.com/ClickHouse/ClickHouse/pull/58943) ([vdimir](https://github.com/vdimir)).
* CI: pr_info to provide event_type for job scripts [#58947](https://github.com/ClickHouse/ClickHouse/pull/58947) ([Max K.](https://github.com/maxknv)).
* Using the destination object for paths generation in S3copy. [#58949](https://github.com/ClickHouse/ClickHouse/pull/58949) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
* Fix data race in slru (2) [#58950](https://github.com/ClickHouse/ClickHouse/pull/58950) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix flaky test_postgresql_replica_database_engine_2/test.py::test_dependent_loading [#58951](https://github.com/ClickHouse/ClickHouse/pull/58951) ([Kseniia Sumarokova](https://github.com/kssenii)).
* More safe way to dump system logs in tests [#58955](https://github.com/ClickHouse/ClickHouse/pull/58955) ([alesapin](https://github.com/alesapin)).
* Add a comment about sparse checkout [#58960](https://github.com/ClickHouse/ClickHouse/pull/58960) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Follow up to [#58357](https://github.com/ClickHouse/ClickHouse/issues/58357) [#58963](https://github.com/ClickHouse/ClickHouse/pull/58963) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Better error message about tuples [#58971](https://github.com/ClickHouse/ClickHouse/pull/58971) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix timeout for prometheus exporter for HTTP/1.1 (due to keep-alive) [#58981](https://github.com/ClickHouse/ClickHouse/pull/58981) ([Azat Khuzhin](https://github.com/azat)).
* Fix 02891_array_shingles with analyzer [#58982](https://github.com/ClickHouse/ClickHouse/pull/58982) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix script name in SQL example in executable.md [#58984](https://github.com/ClickHouse/ClickHouse/pull/58984) ([Lino Uruñuela](https://github.com/Wachynaky)).
* Fix typo [#58986](https://github.com/ClickHouse/ClickHouse/pull/58986) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Revert flaky [#58992](https://github.com/ClickHouse/ClickHouse/pull/58992) ([Raúl Marín](https://github.com/Algunenano)).
* Revive: Parallel replicas custom key: skip unavailable replicas [#58993](https://github.com/ClickHouse/ClickHouse/pull/58993) ([Igor Nikonov](https://github.com/devcrafter)).
* Make performance test `test norm_dist.xml` more realistic [#58995](https://github.com/ClickHouse/ClickHouse/pull/58995) ([Robert Schulze](https://github.com/rschu1ze)).
* Fix 02404_memory_bound_merging with analyzer (follow up [#56419](https://github.com/ClickHouse/ClickHouse/issues/56419)) [#58996](https://github.com/ClickHouse/ClickHouse/pull/58996) ([Nikita Taranov](https://github.com/nickitat)).
* Add test for [#58930](https://github.com/ClickHouse/ClickHouse/issues/58930) [#58999](https://github.com/ClickHouse/ClickHouse/pull/58999) ([Anton Popov](https://github.com/CurtizJ)).
* initialization ConnectionTimeouts [#59000](https://github.com/ClickHouse/ClickHouse/pull/59000) ([Sema Checherinda](https://github.com/CheSema)).
* DiskWeb fix loading [#59006](https://github.com/ClickHouse/ClickHouse/pull/59006) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Update log level for http buffer [#59008](https://github.com/ClickHouse/ClickHouse/pull/59008) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Change log level for super imporant message in Keeper [#59010](https://github.com/ClickHouse/ClickHouse/pull/59010) ([alesapin](https://github.com/alesapin)).
* Fix async loader stress test [#59011](https://github.com/ClickHouse/ClickHouse/pull/59011) ([Sergei Trifonov](https://github.com/serxa)).
* Remove `StaticResourceManager` [#59013](https://github.com/ClickHouse/ClickHouse/pull/59013) ([Sergei Trifonov](https://github.com/serxa)).
* preserve 'amz-sdk-invocation-id' and 'amz-sdk-request' headers with gcp [#59015](https://github.com/ClickHouse/ClickHouse/pull/59015) ([Sema Checherinda](https://github.com/CheSema)).
* Update rename.md [#59017](https://github.com/ClickHouse/ClickHouse/pull/59017) ([filimonov](https://github.com/filimonov)).
* очепятка [#59024](https://github.com/ClickHouse/ClickHouse/pull/59024) ([edpyt](https://github.com/edpyt)).
* Split resource scheduler off `IO/` into `Common/Scheduler/` [#59025](https://github.com/ClickHouse/ClickHouse/pull/59025) ([Sergei Trifonov](https://github.com/serxa)).
* Add a parameter for testing purposes [#59027](https://github.com/ClickHouse/ClickHouse/pull/59027) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix test 02932_kill_query_sleep when running with query cache [#59041](https://github.com/ClickHouse/ClickHouse/pull/59041) ([Vitaly Baranov](https://github.com/vitlibar)).
* CI: Jepsen: fix sanity check in ci.py [#59043](https://github.com/ClickHouse/ClickHouse/pull/59043) ([Max K.](https://github.com/maxknv)).
* CI: add ci_config classes for job and build names [#59046](https://github.com/ClickHouse/ClickHouse/pull/59046) ([Max K.](https://github.com/maxknv)).
* remove flaky test [#59066](https://github.com/ClickHouse/ClickHouse/pull/59066) ([Sema Checherinda](https://github.com/CheSema)).
* Followup to 57853 [#59068](https://github.com/ClickHouse/ClickHouse/pull/59068) ([Dmitry Novik](https://github.com/novikd)).
* Follow-up to [#59027](https://github.com/ClickHouse/ClickHouse/issues/59027) [#59075](https://github.com/ClickHouse/ClickHouse/pull/59075) ([Alexander Tokmakov](https://github.com/tavplubix)).
* Fix `test_parallel_replicas_invisible_parts` [#59077](https://github.com/ClickHouse/ClickHouse/pull/59077) ([Nikita Taranov](https://github.com/nickitat)).
* Increase max_bytes_before_external_group_by for 00165_jit_aggregate_functions [#59078](https://github.com/ClickHouse/ClickHouse/pull/59078) ([Raúl Marín](https://github.com/Algunenano)).
* Fix stateless/run.sh [#59079](https://github.com/ClickHouse/ClickHouse/pull/59079) ([Kseniia Sumarokova](https://github.com/kssenii)).
* CI: hot fix for reuse [#59081](https://github.com/ClickHouse/ClickHouse/pull/59081) ([Max K.](https://github.com/maxknv)).
* Fix server shutdown due to exception while loading metadata [#59083](https://github.com/ClickHouse/ClickHouse/pull/59083) ([Sergei Trifonov](https://github.com/serxa)).
* Coordinator returns ranges for reading in sorted order [#59089](https://github.com/ClickHouse/ClickHouse/pull/59089) ([Nikita Taranov](https://github.com/nickitat)).
* Raise timeout in 02294_decimal_second_errors [#59090](https://github.com/ClickHouse/ClickHouse/pull/59090) ([Raúl Marín](https://github.com/Algunenano)).
* Add `[[nodiscard]]` to a couple of methods [#59093](https://github.com/ClickHouse/ClickHouse/pull/59093) ([Nikita Taranov](https://github.com/nickitat)).
* Docs: Update integer and float aliases [#59100](https://github.com/ClickHouse/ClickHouse/pull/59100) ([Robert Schulze](https://github.com/rschu1ze)).
* Avoid election timeouts during startup in Keeper [#59102](https://github.com/ClickHouse/ClickHouse/pull/59102) ([Antonio Andelic](https://github.com/antonio2368)).
* Add missing setting max_estimated_execution_time in SettingsChangesHistory [#59104](https://github.com/ClickHouse/ClickHouse/pull/59104) ([Kruglov Pavel](https://github.com/Avogar)).
* Rename some inverted index test files [#59106](https://github.com/ClickHouse/ClickHouse/pull/59106) ([Robert Schulze](https://github.com/rschu1ze)).
* Further reduce runtime of `norm_distance.xml` [#59108](https://github.com/ClickHouse/ClickHouse/pull/59108) ([Robert Schulze](https://github.com/rschu1ze)).
* Minor follow-up to [#53710](https://github.com/ClickHouse/ClickHouse/issues/53710) [#59109](https://github.com/ClickHouse/ClickHouse/pull/59109) ([Robert Schulze](https://github.com/rschu1ze)).
* Update stateless/run.sh [#59116](https://github.com/ClickHouse/ClickHouse/pull/59116) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Followup 57875 [#59117](https://github.com/ClickHouse/ClickHouse/pull/59117) ([Dmitry Novik](https://github.com/novikd)).
* Fixing build [#59130](https://github.com/ClickHouse/ClickHouse/pull/59130) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Capability check for `s3_plain` [#59145](https://github.com/ClickHouse/ClickHouse/pull/59145) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix `02015_async_inserts_stress_long` [#59146](https://github.com/ClickHouse/ClickHouse/pull/59146) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix AggregateFunctionNothing result type issues introducing it with different names [#59147](https://github.com/ClickHouse/ClickHouse/pull/59147) ([vdimir](https://github.com/vdimir)).
* Fix url encoding issue [#59162](https://github.com/ClickHouse/ClickHouse/pull/59162) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Upgrade simdjson to v3.6.3 [#59166](https://github.com/ClickHouse/ClickHouse/pull/59166) ([Robert Schulze](https://github.com/rschu1ze)).
* Decrease log level for one log message [#59168](https://github.com/ClickHouse/ClickHouse/pull/59168) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix broken cache for non-existing temp_path [#59172](https://github.com/ClickHouse/ClickHouse/pull/59172) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Move some headers [#59175](https://github.com/ClickHouse/ClickHouse/pull/59175) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Analyzer: Fix CTE name clash resolution [#59177](https://github.com/ClickHouse/ClickHouse/pull/59177) ([Dmitry Novik](https://github.com/novikd)).
* Fix another place with special symbols in the URL [#59184](https://github.com/ClickHouse/ClickHouse/pull/59184) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
* Actions dag build filter actions refactoring [#59228](https://github.com/ClickHouse/ClickHouse/pull/59228) ([Maksim Kita](https://github.com/kitaisreal)).
* Minor cleanup of msan usage [#59229](https://github.com/ClickHouse/ClickHouse/pull/59229) ([Robert Schulze](https://github.com/rschu1ze)).
* Load server configs in clickhouse local [#59231](https://github.com/ClickHouse/ClickHouse/pull/59231) ([pufit](https://github.com/pufit)).
* Make libssh build dependent on `-DENABLE_LIBRARIES` [#59242](https://github.com/ClickHouse/ClickHouse/pull/59242) ([Robert Schulze](https://github.com/rschu1ze)).
* Disable copy constructor for MultiVersion [#59244](https://github.com/ClickHouse/ClickHouse/pull/59244) ([Vitaly Baranov](https://github.com/vitlibar)).
* CI: fix ci configuration for nightly job [#59252](https://github.com/ClickHouse/ClickHouse/pull/59252) ([Max K.](https://github.com/maxknv)).
* Fix 02475_bson_each_row_format flakiness (due to small parsing block) [#59253](https://github.com/ClickHouse/ClickHouse/pull/59253) ([Azat Khuzhin](https://github.com/azat)).
* Improve pytest --pdb experience by preserving dockerd on SIGINT (v2) [#59255](https://github.com/ClickHouse/ClickHouse/pull/59255) ([Azat Khuzhin](https://github.com/azat)).
* Fix fasttest by pinning pip dependencies [#59256](https://github.com/ClickHouse/ClickHouse/pull/59256) ([Azat Khuzhin](https://github.com/azat)).
* Added AtomicLogger [#59273](https://github.com/ClickHouse/ClickHouse/pull/59273) ([Maksim Kita](https://github.com/kitaisreal)).
* Update test_reload_after_fail_in_cache_dictionary for analyzer [#59274](https://github.com/ClickHouse/ClickHouse/pull/59274) ([vdimir](https://github.com/vdimir)).
* Update run.sh [#59280](https://github.com/ClickHouse/ClickHouse/pull/59280) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add missing setting optimize_injective_functions_in_group_by to SettingsChangesHistory [#59283](https://github.com/ClickHouse/ClickHouse/pull/59283) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix perf tests (after sumMap starts to filter out -0.) [#59287](https://github.com/ClickHouse/ClickHouse/pull/59287) ([Azat Khuzhin](https://github.com/azat)).
* Use fresh ZooKeeper client on DROP (to have higher chances on success) [#59288](https://github.com/ClickHouse/ClickHouse/pull/59288) ([Azat Khuzhin](https://github.com/azat)).
* Additional check [#59292](https://github.com/ClickHouse/ClickHouse/pull/59292) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* No debug symbols in Rust [#59306](https://github.com/ClickHouse/ClickHouse/pull/59306) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Fix deadlock in `AsyncLoader::stop()` [#59308](https://github.com/ClickHouse/ClickHouse/pull/59308) ([Sergei Trifonov](https://github.com/serxa)).
* Speed up `00165_jit_aggregate_functions` [#59312](https://github.com/ClickHouse/ClickHouse/pull/59312) ([Nikita Taranov](https://github.com/nickitat)).
* CI: WA for issue with perf test with artifact reuse [#59325](https://github.com/ClickHouse/ClickHouse/pull/59325) ([Max K.](https://github.com/maxknv)).
* Fix typo [#59329](https://github.com/ClickHouse/ClickHouse/pull/59329) ([Raúl Marín](https://github.com/Algunenano)).
* Simplify query_run_metric_arrays in perf tests [#59333](https://github.com/ClickHouse/ClickHouse/pull/59333) ([Raúl Marín](https://github.com/Algunenano)).
* IVolume constructor improve exception message [#59335](https://github.com/ClickHouse/ClickHouse/pull/59335) ([Maksim Kita](https://github.com/kitaisreal)).
* Fix upgrade check for new setting [#59343](https://github.com/ClickHouse/ClickHouse/pull/59343) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix sccache when building without coverage [#59345](https://github.com/ClickHouse/ClickHouse/pull/59345) ([Raúl Marín](https://github.com/Algunenano)).
* Loggers initialization fix [#59347](https://github.com/ClickHouse/ClickHouse/pull/59347) ([Maksim Kita](https://github.com/kitaisreal)).
* Add setting update_insert_deduplication_token_in_dependent_materialized_views to settings changes history [#59349](https://github.com/ClickHouse/ClickHouse/pull/59349) ([Maksim Kita](https://github.com/kitaisreal)).
* Slightly better memory usage in `AsynchronousBoundedReadBuffer` [#59354](https://github.com/ClickHouse/ClickHouse/pull/59354) ([Anton Popov](https://github.com/CurtizJ)).
* Try to make variant tests a bit faster [#59355](https://github.com/ClickHouse/ClickHouse/pull/59355) ([Kruglov Pavel](https://github.com/Avogar)).
* Minor typos in Settings.h [#59371](https://github.com/ClickHouse/ClickHouse/pull/59371) ([Jordi Villar](https://github.com/jrdi)).
* Rename `quantileDDSketch` to `quantileDD` [#59372](https://github.com/ClickHouse/ClickHouse/pull/59372) ([Alexey Milovidov](https://github.com/alexey-milovidov)).

3
docs/en/development/tests.md
View File

@ -109,6 +109,9 @@ Do not check for a particular wording of error message, it may change in the fut
If you want to use distributed queries in functional tests, you can leverage `remote` table function with `127.0.0.{1..2}` addresses for the server to query itself; or you can use predefined test clusters in server configuration file like `test_shard_localhost`. Remember to add the words `shard` or `distributed` to the test name, so that it is run in CI in correct configurations, where the server is configured to support distributed queries.
### Working with Temporary Files
Sometimes in a shell test you may need to create a file on the fly to work with. Keep in mind that some CI checks run tests in parallel, so if you are creating or removing a temporary file in your script without a unique name this can cause some of the CI checks, such as Flaky, to fail. To get around this you should use environment variable `$CLICKHOUSE_TEST_UNIQUE_NAME` to give temporary files a name unique to the test that is running. That way you can be sure that the file you are creating during setup or removing during cleanup is the file only in use by that test and not some other test which is running in parallel.
## Known Bugs {#known-bugs}

35
docs/en/engines/table-engines/integrations/mysql.md
View File

@ -16,7 +16,7 @@ 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],
...
) ENGINE = MySQL('host:port', 'database', 'table', 'user', 'password'[, replace_query, 'on_duplicate_clause'])
) ENGINE = MySQL({host:port, database, table, user, password[, replace_query, on_duplicate_clause] | named_collection[, option=value [,..]]})
SETTINGS
[ connection_pool_size=16, ]
[ connection_max_tries=3, ]
@ -42,23 +42,17 @@ The MySQL Table Engine is currently not available on the ClickHouse builds for M
**Engine Parameters**
- `host:port` — MySQL server address.
- `database` — Remote database name.
- `table` — Remote table name.
- `user` — MySQL user.
- `password` — User password.
- `replace_query` — Flag that converts `INSERT INTO` queries to `REPLACE INTO`. If `replace_query=1`, the query is substituted.
- `on_duplicate_clause` — The `ON DUPLICATE KEY on_duplicate_clause` expression that is added to the `INSERT` query.
Example: `INSERT INTO t (c1,c2) VALUES ('a', 2) ON DUPLICATE KEY UPDATE c2 = c2 + 1`, where `on_duplicate_clause` is `UPDATE c2 = c2 + 1`. See the [MySQL documentation](https://dev.mysql.com/doc/refman/8.0/en/insert-on-duplicate.html) to find which `on_duplicate_clause` you can use with the `ON DUPLICATE KEY` clause.
To specify `on_duplicate_clause` you need to pass `0` to the `replace_query` parameter. If you simultaneously pass `replace_query = 1` and `on_duplicate_clause`, ClickHouse generates an exception.
Arguments also can be passed using [named collections](/docs/en/operations/named-collections.md). In this case `host` and `port` should be specified separately. This approach is recommended for production environment.
Simple `WHERE` clauses such as `=, !=, >, >=, <, <=` are executed on the MySQL server.
The rest of the conditions and the `LIMIT` sampling constraint are executed in ClickHouse only after the query to MySQL finishes.
@ -71,7 +65,7 @@ CREATE TABLE test_replicas (id UInt32, name String, age UInt32, money UInt32) EN
## Usage Example {#usage-example}
Table in MySQL:
Create table in MySQL:
``` text
mysql> CREATE TABLE `test`.`test` (
@ -94,7 +88,7 @@ mysql> select * from test;
1 row in set (0,00 sec)
```
Table in ClickHouse, retrieving data from the MySQL table created above:
Create table in ClickHouse using plain arguments:
``` sql
CREATE TABLE mysql_table
@ -105,6 +99,25 @@ CREATE TABLE mysql_table
ENGINE = MySQL('localhost:3306', 'test', 'test', 'bayonet', '123')
```
Or using [named collections](/docs/en/operations/named-collections.md):
```sql
CREATE NAMED COLLECTION creds AS
host = 'localhost',
port = 3306,
database = 'test',
user = 'bayonet',
password = '123';
CREATE TABLE mysql_table
(
`float_nullable` Nullable(Float32),
`int_id` Int32
)
ENGINE = MySQL(creds, table='test')
```
Retrieving data from MySQL table:
``` sql
SELECT * FROM mysql_table
```

28
docs/en/engines/table-engines/integrations/postgresql.md
View File

@ -16,7 +16,7 @@ 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],
...
) ENGINE = PostgreSQL('host:port', 'database', 'table', 'user', 'password'[, `schema`]);
) ENGINE = PostgreSQL({host:port, database, table, user, password[, schema, [, on_conflict]] | named_collection[, option=value [,..]]})
```
See a detailed description of the [CREATE TABLE](../../../sql-reference/statements/create/table.md#create-table-query) query.
@ -35,31 +35,25 @@ The table structure can differ from the original PostgreSQL table structure:
- `user` — PostgreSQL user.
- `password` — User password.
- `schema` — Non-default table schema. Optional.
- `on conflict ...` — example: `ON CONFLICT DO NOTHING`. Optional. Note: adding this option will make insertion less efficient.
- `on_conflict` — Conflict resolution strategy. Example: `ON CONFLICT DO NOTHING`. Optional. Note: adding this option will make insertion less efficient.
or via config (since version 21.11):
[Named collections](/docs/en/operations/named-collections.md) (available since version 21.11) are recommended for production environment. Here is an example:
```
<named_collections>
<postgres1>
<host></host>
<port></port>
<user></user>
<password></password>
<table></table>
</postgres1>
<postgres2>
<host></host>
<port></port>
<user></user>
<password></password>
</postgres2>
<postgres_creds>
<host>localhost</host>
<port>5432</port>
<user>postgres</user>
<password>****</password>
<schema>schema1</schema>
</postgres_creds>
</named_collections>
```
Some parameters can be overridden by key value arguments:
``` sql
SELECT * FROM postgresql(postgres1, schema='schema1', table='table1');
SELECT * FROM postgresql(postgres_creds, table='table1');
```
## Implementation Details {#implementation-details}

45
docs/en/engines/table-engines/integrations/redis.md
View File

@ -16,30 +16,32 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name
name1 [type1],
name2 [type2],
...
) ENGINE = Redis(host:port[, db_index[, password[, pool_size]]]) PRIMARY KEY(primary_key_name);
) ENGINE = Redis({host:port[, db_index[, password[, pool_size]]] | named_collection[, option=value [,..]] })
PRIMARY KEY(primary_key_name);
```
**Engine Parameters**
- `host:port` — Redis server address, you can ignore port and default Redis port 6379 will be used.
- `db_index` — Redis db index range from 0 to 15, default is 0.
- `password` — User password, default is blank string.
- `pool_size` — Redis max connection pool size, default is 16.
- `primary_key_name` - any column name in the column list.
- `primary` must be specified, it supports only one column in the primary key. The primary key will be serialized in binary as a Redis key.
:::note Serialization
`PRIMARY KEY` supports only one column. The primary key will be serialized in binary as a Redis key.
Columns other than the primary key will be serialized in binary as Redis value in corresponding order.
:::
- columns other than the primary key will be serialized in binary as Redis value in corresponding order.
Arguments also can be passed using [named collections](/docs/en/operations/named-collections.md). In this case `host` and `port` should be specified separately. This approach is recommended for production environment. At this moment, all parameters passed using named collections to redis are required.
- queries with key equals or in filtering will be optimized to multi keys lookup from Redis. If queries without filtering key full table scan will happen which is a heavy operation.
:::note Filtering
Queries with `key equals` or `in filtering` will be optimized to multi keys lookup from Redis. If queries without filtering key full table scan will happen which is a heavy operation.
:::
## Usage Example {#usage-example}
Create a table in ClickHouse which allows to read data from Redis:
Create a table in ClickHouse using `Redis` engine with plain arguments:
``` sql
CREATE TABLE redis_table
@ -52,6 +54,31 @@ CREATE TABLE redis_table
ENGINE = Redis('redis1:6379') PRIMARY KEY(key);
```
Or using [named collections](/docs/en/operations/named-collections.md):
```
<named_collections>
<redis_creds>
<host>localhost</host>
<port>6379</port>
<password>****</password>
<pool_size>16</pool_size>
<db_index>s0</db_index>
</redis_creds>
</named_collections>
```
```sql
CREATE TABLE redis_table
(
`key` String,
`v1` UInt32,
`v2` String,
`v3` Float32
)
ENGINE = Redis(redis_creds) PRIMARY KEY(key);
```
Insert:
```sql

61
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -39,8 +39,8 @@ If you need to update rows frequently, we recommend using the [`ReplacingMergeTr
``` sql
CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
(
name1 [type1] [[NOT] NULL] [DEFAULT|MATERIALIZED|ALIAS|EPHEMERAL expr1] [COMMENT ...] [CODEC(codec1)] [STATISTIC(stat1)] [TTL expr1] [PRIMARY KEY],
name2 [type2] [[NOT] NULL] [DEFAULT|MATERIALIZED|ALIAS|EPHEMERAL expr2] [COMMENT ...] [CODEC(codec2)] [STATISTIC(stat2)] [TTL expr2] [PRIMARY KEY],
name1 [type1] [[NOT] NULL] [DEFAULT|MATERIALIZED|ALIAS|EPHEMERAL expr1] [COMMENT ...] [CODEC(codec1)] [STATISTIC(stat1)] [TTL expr1] [PRIMARY KEY] [SETTINGS (name = value, ...)],
name2 [type2] [[NOT] NULL] [DEFAULT|MATERIALIZED|ALIAS|EPHEMERAL expr2] [COMMENT ...] [CODEC(codec2)] [STATISTIC(stat2)] [TTL expr2] [PRIMARY KEY] [SETTINGS (name = value, ...)],
...
INDEX index_name1 expr1 TYPE type1(...) [GRANULARITY value1],
INDEX index_name2 expr2 TYPE type2(...) [GRANULARITY value2],
@ -56,7 +56,7 @@ ORDER BY expr
[DELETE|TO DISK 'xxx'|TO VOLUME 'xxx' [, ...] ]
[WHERE conditions]
[GROUP BY key_expr [SET v1 = aggr_func(v1) [, v2 = aggr_func(v2) ...]] ] ]
[SETTINGS name=value, ...]
[SETTINGS name = value, ...]
```
For a description of parameters, see the [CREATE query description](/docs/en/sql-reference/statements/create/table.md).
@ -620,7 +620,7 @@ The `TTL` clause can’t be used for key columns.
#### Creating a table with `TTL`:
``` sql
CREATE TABLE example_table
CREATE TABLE tab
(
d DateTime,
a Int TTL d + INTERVAL 1 MONTH,
@ -635,7 +635,7 @@ ORDER BY d;
#### Adding TTL to a column of an existing table
``` sql
ALTER TABLE example_table
ALTER TABLE tab
MODIFY COLUMN
c String TTL d + INTERVAL 1 DAY;
```
@ -643,7 +643,7 @@ ALTER TABLE example_table
#### Altering TTL of the column
``` sql
ALTER TABLE example_table
ALTER TABLE tab
MODIFY COLUMN
c String TTL d + INTERVAL 1 MONTH;
```
@ -681,7 +681,7 @@ If a column is not part of the `GROUP BY` expression and is not set explicitly i
#### Creating a table with `TTL`:
``` sql
CREATE TABLE example_table
CREATE TABLE tab
(
d DateTime,
a Int
@ -697,7 +697,7 @@ TTL d + INTERVAL 1 MONTH DELETE,
#### Altering `TTL` of the table:
``` sql
ALTER TABLE example_table
ALTER TABLE tab
MODIFY TTL d + INTERVAL 1 DAY;
```
@ -1366,7 +1366,7 @@ In this sample configuration:
The statistic declaration is in the columns section of the `CREATE` query for tables from the `*MergeTree*` Family when we enable `set allow_experimental_statistic = 1`.
``` sql
CREATE TABLE example_table
CREATE TABLE tab
(
a Int64 STATISTIC(tdigest),
b Float64
@ -1378,8 +1378,8 @@ ORDER BY a
We can also manipulate statistics with `ALTER` statements.
```sql
ALTER TABLE example_table ADD STATISTIC b TYPE tdigest;
ALTER TABLE example_table DROP STATISTIC a TYPE tdigest;
ALTER TABLE tab ADD STATISTIC b TYPE tdigest;
ALTER TABLE tab DROP STATISTIC a TYPE tdigest;
```
These lightweight statistics aggregate information about distribution of values in columns.
@ -1390,3 +1390,42 @@ They can be used for query optimization when we enable `set allow_statistic_opti
- `tdigest`
Stores distribution of values from numeric columns in [TDigest](https://github.com/tdunning/t-digest) sketch.
## Column-level Settings {#column-level-settings}
Certain MergeTree settings can be override at column level:
- `max_compress_block_size` — Maximum size of blocks of uncompressed data before compressing for writing to a table.
- `min_compress_block_size` — Minimum size of blocks of uncompressed data required for compression when writing the next mark.
Example:
```sql
CREATE TABLE tab
(
id Int64,
document String SETTINGS (min_compress_block_size = 16777216, max_compress_block_size = 16777216)
)
ENGINE = MergeTree
ORDER BY id
```
Column-level settings can be modified or removed using [ALTER MODIFY COLUMN](/docs/en/sql-reference/statements/alter/column.md), for example:
- Remove `SETTINGS` from column declaration:
```sql
ALTER TABLE tab MODIFY COLUMN document REMOVE SETTINGS;
```
- Modify a setting:
```sql
ALTER TABLE tab MODIFY COLUMN document MODIFY SETTING min_compress_block_size = 8192;
```
- Reset one or more settings, also removes the setting declaration in the column expression of the table's CREATE query.
```sql
ALTER TABLE tab MODIFY COLUMN document RESET SETTING min_compress_block_size;
```

342
docs/en/getting-started/example-datasets/noaa.md Normal file
View File

@ -0,0 +1,342 @@
---
slug: /en/getting-started/example-datasets/noaa
sidebar_label: NOAA Global Historical Climatology Network
sidebar_position: 1
description: 2.5 billion rows of climate data for the last 120 yrs
---
# NOAA Global Historical Climatology Network
This dataset contains weather measurements for the last 120 years. Each row is a measurement for a point in time and station.
More precisely and according to the [origin of this data](https://github.com/awslabs/open-data-docs/tree/main/docs/noaa/noaa-ghcn):
> GHCN-Daily is a dataset that contains daily observations over global land areas. It contains station-based measurements from land-based stations worldwide, about two-thirds of which are for precipitation measurements only (Menne et al., 2012). GHCN-Daily is a composite of climate records from numerous sources that were merged together and subjected to a common suite of quality assurance reviews (Durre et al., 2010). The archive includes the following meteorological elements:
- Daily maximum temperature
- Daily minimum temperature
- Temperature at the time of observation
- Precipitation (i.e., rain, melted snow)
- Snowfall
- Snow depth
- Other elements where available
## Downloading the data
- A [pre-prepared version](#pre-prepared-data) of the data for ClickHouse, which has been cleansed, re-structured, and enriched. This data covers the years 1900 to 2022.
- [Download the original data](#original-data) and convert to the format required by ClickHouse. Users wanting to add their own columns may wish to explore this approach.
### Pre-prepared data
More specifically, rows have been removed that did not fail any quality assurance checks by Noaa. The data has also been restructured from a measurement per line to a row per station id and date, i.e.
```csv
"station_id","date","tempAvg","tempMax","tempMin","precipitation","snowfall","snowDepth","percentDailySun","averageWindSpeed","maxWindSpeed","weatherType"
"AEM00041194","2022-07-30",347,0,308,0,0,0,0,0,0,0
"AEM00041194","2022-07-31",371,413,329,0,0,0,0,0,0,0
"AEM00041194","2022-08-01",384,427,357,0,0,0,0,0,0,0
"AEM00041194","2022-08-02",381,424,352,0,0,0,0,0,0,0
```
This is simpler to query and ensures the resulting table is less sparse. Finally, the data has also been enriched with latitude and longitude.
This data is available in the following S3 location. Either download the data to your local filesystem (and insert using the ClickHouse client) or insert directly into ClickHouse (see [Inserting from S3](#inserting-from-s3)).
To download:
```bash
wget https://datasets-documentation.s3.eu-west-3.amazonaws.com/noaa/noaa_enriched.parquet
```
### Original data
The following details the steps to download and transform the original data in preparation for loading into ClickHouse.
#### Download
To download the original data:
```bash
for i in {1900..2023}; do wget https://noaa-ghcn-pds.s3.amazonaws.com/csv.gz/${i}.csv.gz; done
```
#### Sampling the data
```bash
$ clickhouse-local --query "SELECT * FROM '2021.csv.gz' LIMIT 10" --format PrettyCompact
┌─c1──────────┬───────c2─┬─c3───┬──c4─┬─c5───┬─c6───┬─c7─┬───c8─┐
│ AE000041196 │ 20210101 │ TMAX │ 278 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AE000041196 │ 20210101 │ PRCP │ 0 │ D │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AE000041196 │ 20210101 │ TAVG │ 214 │ H │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AEM00041194 │ 20210101 │ TMAX │ 266 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AEM00041194 │ 20210101 │ TMIN │ 178 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AEM00041194 │ 20210101 │ PRCP │ 0 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AEM00041194 │ 20210101 │ TAVG │ 217 │ H │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AEM00041217 │ 20210101 │ TMAX │ 262 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AEM00041217 │ 20210101 │ TMIN │ 155 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
│ AEM00041217 │ 20210101 │ TAVG │ 202 │ H │ ᴺᵁᴸᴸ │ S │ ᴺᵁᴸᴸ │
└─────────────┴──────────┴──────┴─────┴──────┴──────┴────┴──────┘
```
Summarizing the [format documentation](https://github.com/awslabs/open-data-docs/tree/main/docs/noaa/noaa-ghcn):
Summarizing the format documentation and the columns in order:
- An 11 character station identification code. This itself encodes some useful information
- YEAR/MONTH/DAY = 8 character date in YYYYMMDD format (e.g. 19860529 = May 29, 1986)
- ELEMENT = 4 character indicator of element type. Effectively the measurement type. While there are many measurements available, we select the following:
- PRCP - Precipitation (tenths of mm)
- SNOW - Snowfall (mm)
- SNWD - Snow depth (mm)
- TMAX - Maximum temperature (tenths of degrees C)
- TAVG - Average temperature (tenths of a degree C)
- TMIN - Minimum temperature (tenths of degrees C)
- PSUN - Daily percent of possible sunshine (percent)
- AWND - Average daily wind speed (tenths of meters per second)
- WSFG - Peak gust wind speed (tenths of meters per second)
- WT** = Weather Type where ** defines the weather type. Full list of weather types here.
- DATA VALUE = 5 character data value for ELEMENT i.e. the value of the measurement.
- M-FLAG = 1 character Measurement Flag. This has 10 possible values. Some of these values indicate questionable data accuracy. We accept data where this is set to “P” - identified as missing presumed zero, as this is only relevant to the PRCP, SNOW and SNWD measurements.
- Q-FLAG is the measurement quality flag with 14 possible values. We are only interested in data with an empty value i.e. it did not fail any quality assurance checks.
- S-FLAG is the source flag for the observation. Not useful for our analysis and ignored.
- OBS-TIME = 4-character time of observation in hour-minute format (i.e. 0700 =7:00 am). Typically not present in older data. We ignore this for our purposes.
A measurement per line would result in a sparse table structure in ClickHouse. We should transform to a row per time and station, with measurements as columns. First, we limit the dataset to those rows without issues i.e. where `qFlag` is equal to an empty string.
#### Clean the data
Using [ClickHouse local](https://clickhouse.com/blog/extracting-converting-querying-local-files-with-sql-clickhouse-local) we can filter rows that represent measurements of interest and pass our quality requirements:
```bash
clickhouse local --query "SELECT count()
FROM file('*.csv.gz', CSV, 'station_id String, date String, measurement String, value Int64, mFlag String, qFlag String, sFlag String, obsTime String') WHERE qFlag = '' AND (measurement IN ('PRCP', 'SNOW', 'SNWD', 'TMAX', 'TAVG', 'TMIN', 'PSUN', 'AWND', 'WSFG') OR startsWith(measurement, 'WT'))"
2679264563
```
With over 2.6 billion rows, this isn’t a fast query since it involves parsing all the files. On our 8 core machine, this takes around 160 seconds.
### Pivot data
While the measurement per line structure can be used with ClickHouse, it will unnecessarily complicate future queries. Ideally, we need a row per station id and date, where each measurement type and associated value are a column i.e.
```csv
"station_id","date","tempAvg","tempMax","tempMin","precipitation","snowfall","snowDepth","percentDailySun","averageWindSpeed","maxWindSpeed","weatherType"
"AEM00041194","2022-07-30",347,0,308,0,0,0,0,0,0,0
"AEM00041194","2022-07-31",371,413,329,0,0,0,0,0,0,0
"AEM00041194","2022-08-01",384,427,357,0,0,0,0,0,0,0
"AEM00041194","2022-08-02",381,424,352,0,0,0,0,0,0,0
```
Using ClickHouse local and a simple `GROUP BY`, we can repivot our data to this structure. To limit memory overhead, we do this one file at a time.
```bash
for i in {1900..2022}
do
clickhouse-local --query "SELECT station_id,
toDate32(date) as date,
anyIf(value, measurement = 'TAVG') as tempAvg,
anyIf(value, measurement = 'TMAX') as tempMax,
anyIf(value, measurement = 'TMIN') as tempMin,
anyIf(value, measurement = 'PRCP') as precipitation,
anyIf(value, measurement = 'SNOW') as snowfall,
anyIf(value, measurement = 'SNWD') as snowDepth,
anyIf(value, measurement = 'PSUN') as percentDailySun,
anyIf(value, measurement = 'AWND') as averageWindSpeed,
anyIf(value, measurement = 'WSFG') as maxWindSpeed,
toUInt8OrZero(replaceOne(anyIf(measurement, startsWith(measurement, 'WT') AND value = 1), 'WT', '')) as weatherType
FROM file('$i.csv.gz', CSV, 'station_id String, date String, measurement String, value Int64, mFlag String, qFlag String, sFlag String, obsTime String')
WHERE qFlag = '' AND (measurement IN ('PRCP', 'SNOW', 'SNWD', 'TMAX', 'TAVG', 'TMIN', 'PSUN', 'AWND', 'WSFG') OR startsWith(measurement, 'WT'))
GROUP BY station_id, date
ORDER BY station_id, date FORMAT CSV" >> "noaa.csv";
done
```
This query produces a single 50GB file `noaa.csv`.
### Enriching the data
The data has no indication of location aside from a station id, which includes a prefix country code. Ideally, each station would have a latitude and longitude associated with it. To achieve this, NOAA conveniently provides the details of each station as a separate [ghcnd-stations.txt](https://github.com/awslabs/open-data-docs/tree/main/docs/noaa/noaa-ghcn#format-of-ghcnd-stationstxt-file). This file has [several columns](https://github.com/awslabs/open-data-docs/tree/main/docs/noaa/noaa-ghcn#format-of-ghcnd-stationstxt-file), of which five are useful to our future analysis: id, latitude, longitude, elevation, and name.
```bash
wget http://noaa-ghcn-pds.s3.amazonaws.com/ghcnd-stations.txt
```
```bash
clickhouse local --query "WITH stations AS (SELECT id, lat, lon, elevation, splitByString(' GSN ',name)[1] as name FROM file('ghcnd-stations.txt', Regexp, 'id String, lat Float64, lon Float64, elevation Float32, name String'))
SELECT station_id,
date,
tempAvg,
tempMax,
tempMin,
precipitation,
snowfall,
snowDepth,
percentDailySun,
averageWindSpeed,
maxWindSpeed,
weatherType,
tuple(lon, lat) as location,
elevation,
name
FROM file('noaa.csv', CSV,
'station_id String, date Date32, tempAvg Int32, tempMax Int32, tempMin Int32, precipitation Int32, snowfall Int32, snowDepth Int32, percentDailySun Int8, averageWindSpeed Int32, maxWindSpeed Int32, weatherType UInt8') as noaa LEFT OUTER
JOIN stations ON noaa.station_id = stations.id INTO OUTFILE 'noaa_enriched.parquet' FORMAT Parquet SETTINGS format_regexp='^(.{11})\s+(\-?\d{1,2}\.\d{4})\s+(\-?\d{1,3}\.\d{1,4})\s+(\-?\d*\.\d*)\s+(.*)\s+(?:[\d]*)'"
```
This query takes a few minutes to run and produces a 6.4 GB file, `noaa_enriched.parquet`.
## Create table
Create a MergeTree table in ClickHouse (from the ClickHouse client).
```sql
CREATE TABLE noaa
(
`station_id` LowCardinality(String),
`date` Date32,
`tempAvg` Int32 COMMENT 'Average temperature (tenths of a degrees C)',
`tempMax` Int32 COMMENT 'Maximum temperature (tenths of degrees C)',
`tempMin` Int32 COMMENT 'Minimum temperature (tenths of degrees C)',
`precipitation` UInt32 COMMENT 'Precipitation (tenths of mm)',
`snowfall` UInt32 COMMENT 'Snowfall (mm)',
`snowDepth` UInt32 COMMENT 'Snow depth (mm)',
`percentDailySun` UInt8 COMMENT 'Daily percent of possible sunshine (percent)',
`averageWindSpeed` UInt32 COMMENT 'Average daily wind speed (tenths of meters per second)',
`maxWindSpeed` UInt32 COMMENT 'Peak gust wind speed (tenths of meters per second)',
`weatherType` Enum8('Normal' = 0, 'Fog' = 1, 'Heavy Fog' = 2, 'Thunder' = 3, 'Small Hail' = 4, 'Hail' = 5, 'Glaze' = 6, 'Dust/Ash' = 7, 'Smoke/Haze' = 8, 'Blowing/Drifting Snow' = 9, 'Tornado' = 10, 'High Winds' = 11, 'Blowing Spray' = 12, 'Mist' = 13, 'Drizzle' = 14, 'Freezing Drizzle' = 15, 'Rain' = 16, 'Freezing Rain' = 17, 'Snow' = 18, 'Unknown Precipitation' = 19, 'Ground Fog' = 21, 'Freezing Fog' = 22),
`location` Point,
`elevation` Float32,
`name` LowCardinality(String)
) ENGINE = MergeTree() ORDER BY (station_id, date);
```
## Inserting into ClickHouse
### Inserting from local file
Data can be inserted from a local file as follows (from the ClickHouse client):
```sql
INSERT INTO noaa FROM INFILE '<path>/noaa_enriched.parquet'
```
where `<path>` represents the full path to the local file on disk.
See [here](https://clickhouse.com/blog/real-world-data-noaa-climate-data#load-the-data) for how to speed this load up.
### Inserting from S3
```sql
INSERT INTO noaa SELECT *
FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/noaa/noaa_enriched.parquet')
```
For how to speed this up, see our blog post on [tuning large data loads](https://clickhouse.com/blog/supercharge-your-clickhouse-data-loads-part2).
## Sample queries
### Highest temperature ever
```sql
SELECT
tempMax / 10 AS maxTemp,
location,
name,
date
FROM blogs.noaa
WHERE tempMax > 500
ORDER BY
tempMax DESC,
date ASC
LIMIT 5
┌─maxTemp─┬─location──────────┬─name───────────────────────────────────────────┬───────date─┐
│ 56.7 │ (-116.8667,36.45) │ CA GREENLAND RCH │ 1913-07-10 │
│ 56.7 │ (-115.4667,32.55) │ MEXICALI (SMN) │ 1949-08-20 │
│ 56.7 │ (-115.4667,32.55) │ MEXICALI (SMN) │ 1949-09-18 │
│ 56.7 │ (-115.4667,32.55) │ MEXICALI (SMN) │ 1952-07-17 │
│ 56.7 │ (-115.4667,32.55) │ MEXICALI (SMN) │ 1952-09-04 │
└─────────┴───────────────────┴────────────────────────────────────────────────┴────────────┘
5 rows in set. Elapsed: 0.514 sec. Processed 1.06 billion rows, 4.27 GB (2.06 billion rows/s., 8.29 GB/s.)
```
Reassuringly consistent with the [documented record](https://en.wikipedia.org/wiki/List_of_weather_records#Highest_temperatures_ever_recorded) at [Furnace Creek](https://www.google.com/maps/place/36%C2%B027'00.0%22N+116%C2%B052'00.1%22W/@36.1329666,-116.1104099,8.95z/data=!4m5!3m4!1s0x0:0xf2ed901b860f4446!8m2!3d36.45!4d-116.8667) as of 2023.
### Best ski resorts
Using a [list of ski resorts](https://gist.githubusercontent.com/gingerwizard/dd022f754fd128fdaf270e58fa052e35/raw/622e03c37460f17ef72907afe554cb1c07f91f23/ski_resort_stats.csv) in the united states and their respective locations, we join these against the top 1000 weather stations with the most in any month in the last 5 yrs. Sorting this join by [geoDistance](https://clickhouse.com/docs/en/sql-reference/functions/geo/coordinates/#geodistance) and restricting the results to those where the distance is less than 20km, we select the top result per resort and sort this by total snow. Note we also restrict resorts to those above 1800m, as a broad indicator of good skiing conditions.
```sql
SELECT
resort_name,
total_snow / 1000 AS total_snow_m,
resort_location,
month_year
FROM
(
WITH resorts AS
(
SELECT
resort_name,
state,
(lon, lat) AS resort_location,
'US' AS code
FROM url('https://gist.githubusercontent.com/gingerwizard/dd022f754fd128fdaf270e58fa052e35/raw/622e03c37460f17ef72907afe554cb1c07f91f23/ski_resort_stats.csv', CSVWithNames)
)
SELECT
resort_name,
highest_snow.station_id,
geoDistance(resort_location.1, resort_location.2, station_location.1, station_location.2) / 1000 AS distance_km,
highest_snow.total_snow,
resort_location,
station_location,
month_year
FROM
(
SELECT
sum(snowfall) AS total_snow,
station_id,
any(location) AS station_location,
month_year,
substring(station_id, 1, 2) AS code
FROM noaa
WHERE (date > '2017-01-01') AND (code = 'US') AND (elevation > 1800)
GROUP BY
station_id,
toYYYYMM(date) AS month_year
ORDER BY total_snow DESC
LIMIT 1000
) AS highest_snow
INNER JOIN resorts ON highest_snow.code = resorts.code
WHERE distance_km < 20
ORDER BY
resort_name ASC,
total_snow DESC
LIMIT 1 BY
resort_name,
station_id
)
ORDER BY total_snow DESC
LIMIT 5
┌─resort_name──────────┬─total_snow_m─┬─resort_location─┬─month_year─┐
│ Sugar Bowl, CA │ 7.799 │ (-120.3,39.27) │ 201902 │
│ Donner Ski Ranch, CA │ 7.799 │ (-120.34,39.31) │ 201902 │
│ Boreal, CA │ 7.799 │ (-120.35,39.33) │ 201902 │
│ Homewood, CA │ 4.926 │ (-120.17,39.08) │ 201902 │
│ Alpine Meadows, CA │ 4.926 │ (-120.22,39.17) │ 201902 │
└──────────────────────┴──────────────┴─────────────────┴────────────┘
5 rows in set. Elapsed: 0.750 sec. Processed 689.10 million rows, 3.20 GB (918.20 million rows/s., 4.26 GB/s.)
Peak memory usage: 67.66 MiB.
```
## Credits
We would like to acknowledge the efforts of the Global Historical Climatology Network for preparing, cleansing, and distributing this data. We appreciate your efforts.
Menne, M.J., I. Durre, B. Korzeniewski, S. McNeal, K. Thomas, X. Yin, S. Anthony, R. Ray, R.S. Vose, B.E.Gleason, and T.G. Houston, 2012: Global Historical Climatology Network - Daily (GHCN-Daily), Version 3. [indicate subset used following decimal, e.g. Version 3.25]. NOAA National Centers for Environmental Information. http://doi.org/10.7289/V5D21VHZ [17/08/2020]

23
docs/en/interfaces/cli.md
View File

@ -197,6 +197,29 @@ You can pass parameters to `clickhouse-client` (all parameters have a default va
Instead of `--host`, `--port`, `--user` and `--password` options, ClickHouse client also supports connection strings (see next section).
## Aliases {#cli_aliases}
- `\l` - SHOW DATABASES
- `\d` - SHOW TABLES
- `\c <DATABASE>` - USE DATABASE
- `.` - repeat the last query
## Shortkeys {#shortkeys_aliases}
- `Alt (Option) + Shift + e` - open editor with current query. It is possible to set up an environment variable - `EDITOR`, by default vim is used.
- `Alt (Option) + #` - comment line.
- `Ctrl + r` - fuzzy history search.
:::tip
To configure the correct work of meta key (Option) on MacOS:
iTerm2: Go to Preferences -> Profile -> Keys -> Left Option key and click Esc+
:::
The full list with all available shortkeys - [replxx](https://github.com/AmokHuginnsson/replxx/blob/1f149bf/src/replxx_impl.cxx#L262).
## Connection string {#connection_string}
clickhouse-client alternatively supports connecting to clickhouse server using a connection string similar to [MongoDB](https://www.mongodb.com/docs/manual/reference/connection-string/), [PostgreSQL](https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNSTRING), [MySQL](https://dev.mysql.com/doc/refman/8.0/en/connecting-using-uri-or-key-value-pairs.html#connecting-using-uri). It has the following syntax:

2
docs/en/operations/configuration-files.md
View File

@ -163,7 +163,7 @@ key: value
Corresponding XML:
``` xml
<key>value</value>
<key>value</key>
```
A nested XML node is represented by a YAML map:

3
docs/en/operations/named-collections.md
View File

@ -296,7 +296,6 @@ host = '127.0.0.1',
port = 5432,
database = 'test',
schema = 'test_schema',
connection_pool_size = 8
```
Example of configuration:
@ -310,7 +309,6 @@ Example of configuration:
<port>5432</port>
<database>test</database>
<schema>test_schema</schema>
<connection_pool_size>8</connection_pool_size>
</mypg>
</named_collections>
</clickhouse>
@ -445,4 +443,3 @@ SELECT dictGet('dict', 'b', 1);
│ a │
└─────────────────────────┘
```

7
docs/en/operations/server-configuration-parameters/settings.md
View File

@ -2866,3 +2866,10 @@ This also allows a mix of resolver types can be used.
### disable_tunneling_for_https_requests_over_http_proxy {#disable_tunneling_for_https_requests_over_http_proxy}
By default, tunneling (i.e, `HTTP CONNECT`) is used to make `HTTPS` requests over `HTTP` proxy. This setting can be used to disable it.
## max_materialized_views_count_for_table {#max_materialized_views_count_for_table}
A limit on the number of materialized views attached to a table.
Note that only directly dependent views are considered here, and the creation of one view on top of another view is not considered.
Default value: `0`.

6
docs/en/operations/settings/query-complexity.md
View File

@ -172,7 +172,7 @@ If you set `timeout_before_checking_execution_speed `to 0, ClickHouse will use c
## timeout_overflow_mode {#timeout-overflow-mode}
What to do if the query is run longer than `max_execution_time`: `throw` or `break`. By default, `throw`.
What to do if the query is run longer than `max_execution_time` or the estimated running time is longer than `max_estimated_execution_time`: `throw` or `break`. By default, `throw`.
# max_execution_time_leaf
@ -214,6 +214,10 @@ A maximum number of execution bytes per second. Checked on every data block when
Checks that execution speed is not too slow (no less than ‘min_execution_speed’), after the specified time in seconds has expired.
## max_estimated_execution_time {#max_estimated_execution_time}
Maximum query estimate execution time in seconds. Checked on every data block when ‘timeout_before_checking_execution_speed’ expires.
## max_columns_to_read {#max-columns-to-read}
A maximum number of columns that can be read from a table in a single query. If a query requires reading a greater number of columns, it throws an exception.

125
docs/en/operations/settings/settings.md
View File

@ -2040,6 +2040,32 @@ SELECT * FROM test_table
└───┘
```
## update_insert_deduplication_token_in_dependent_materialized_views {#update-insert-deduplication-token-in-dependent-materialized-views}
Allows to update `insert_deduplication_token` with table identifier during insert in dependent materialized views, if setting `deduplicate_blocks_in_dependent_materialized_views` is enabled and `insert_deduplication_token` is set.
Possible values:
0 — Disabled.
1 — Enabled.
Default value: 0.
Usage:
If setting `deduplicate_blocks_in_dependent_materialized_views` is enabled, `insert_deduplication_token` is passed to dependent materialized views. But in complex INSERT flows it is possible that we want to avoid deduplication for dependent materialized views.
Example:
```
landing -┬--> mv_1_1 ---> ds_1_1 ---> mv_2_1 --┬-> ds_2_1 ---> mv_3_1 ---> ds_3_1
| |
└--> mv_1_2 ---> ds_1_2 ---> mv_2_2 --┘
```
In this example we want to avoid deduplication for two different blocks generated from `mv_2_1` and `mv_2_2` that will be inserted into `ds_2_1`. Without `update_insert_deduplication_token_in_dependent_materialized_views` setting enabled, those two different blocks will be deduplicated, because different blocks from `mv_2_1` and `mv_2_2` will have the same `insert_deduplication_token`.
If setting `update_insert_deduplication_token_in_dependent_materialized_views` is enabled, during each insert into dependent materialized views `insert_deduplication_token` is updated with table identifier, so block from `mv_2_1` and block from `mv_2_2` will have different `insert_deduplication_token` and will not be deduplicated.
## insert_keeper_max_retries
The setting sets the maximum number of retries for ClickHouse Keeper (or ZooKeeper) requests during insert into replicated MergeTree. Only Keeper requests which failed due to network error, Keeper session timeout, or request timeout are considered for retries.
@ -5176,6 +5202,95 @@ When set to `false` than all attempts are made with identical timeouts.
Default value: `true`.
## allow_experimental_variant_type {#allow_experimental_variant_type}
Allows creation of experimental [Variant](../../sql-reference/data-types/variant.md).
Default value: `false`.
## use_variant_as_common_type {#use_variant_as_common_type}
Allows to use `Variant` type as a result type for [if](../../sql-reference/functions/conditional-functions.md/#if)/[multiIf](../../sql-reference/functions/conditional-functions.md/#multiif)/[array](../../sql-reference/functions/array-functions.md)/[map](../../sql-reference/functions/tuple-map-functions.md) functions when there is no common type for argument types.
Example:
```sql
SET use_variant_as_common_type = 1;
SELECT toTypeName(if(number % 2, number, range(number))) as variant_type FROM numbers(1);
SELECT if(number % 2, number, range(number)) as variant FROM numbers(5);
```
```text
┌─variant_type───────────────────┐
│ Variant(Array(UInt64), UInt64) │
└────────────────────────────────┘
┌─variant───┐
│ [] │
│ 1 │
│ [0,1] │
│ 3 │
│ [0,1,2,3] │
└───────────┘
```
```sql
SET use_variant_as_common_type = 1;
SELECT toTypeName(multiIf((number % 4) = 0, 42, (number % 4) = 1, [1, 2, 3], (number % 4) = 2, 'Hello, World!', NULL)) AS variant_type FROM numbers(1);
SELECT multiIf((number % 4) = 0, 42, (number % 4) = 1, [1, 2, 3], (number % 4) = 2, 'Hello, World!', NULL) AS variant FROM numbers(4);
```
```text
─variant_type─────────────────────────┐
│ Variant(Array(UInt8), String, UInt8) │
└──────────────────────────────────────┘
┌─variant───────┐
│ 42 │
│ [1,2,3] │
│ Hello, World! │
│ ᴺᵁᴸᴸ │
└───────────────┘
```
```sql
SET use_variant_as_common_type = 1;
SELECT toTypeName(array(range(number), number, 'str_' || toString(number))) as array_of_variants_type from numbers(1);
SELECT array(range(number), number, 'str_' || toString(number)) as array_of_variants FROM numbers(3);
```
```text
┌─array_of_variants_type────────────────────────┐
│ Array(Variant(Array(UInt64), String, UInt64)) │
└───────────────────────────────────────────────┘
┌─array_of_variants─┐
│ [[],0,'str_0'] │
│ [[0],1,'str_1'] │
│ [[0,1],2,'str_2'] │
└───────────────────┘
```
```sql
SET use_variant_as_common_type = 1;
SELECT toTypeName(map('a', range(number), 'b', number, 'c', 'str_' || toString(number))) as map_of_variants_type from numbers(1);
SELECT map('a', range(number), 'b', number, 'c', 'str_' || toString(number)) as map_of_variants FROM numbers(3);
```
```text
┌─map_of_variants_type────────────────────────────────┐
│ Map(String, Variant(Array(UInt64), String, UInt64)) │
└─────────────────────────────────────────────────────┘
┌─map_of_variants───────────────┐
│ {'a':[],'b':0,'c':'str_0'} │
│ {'a':[0],'b':1,'c':'str_1'} │
│ {'a':[0,1],'b':2,'c':'str_2'} │
└───────────────────────────────┘
```
Default value: `false`.
## max_partition_size_to_drop
Restriction on dropping partitions in query time.
@ -5197,3 +5312,13 @@ The value 0 means that you can delete all tables without any restrictions.
:::note
This query setting overwrites its server setting equivalent, see [max_table_size_to_drop](/docs/en/operations/server-configuration-parameters/settings.md/#max-table-size-to-drop)
:::
## iceberg_engine_ignore_schema_evolution {#iceberg_engine_ignore_schema_evolution}
Allow to ignore schema evolution in Iceberg table engine and read all data using schema specified by the user on table creation or latest schema parsed from metadata on table creation.
:::note
Enabling this setting can lead to incorrect result as in case of evolved schema all data files will be read using the same schema.
:::
Default value: 'false'.

2
docs/en/operations/system-tables/asynchronous_metric_log.md
View File

@ -10,7 +10,7 @@ Columns:
- `hostname` ([LowCardinality(String)](../../sql-reference/data-types/string.md)) — Hostname of the server executing the query.
- `event_date` ([Date](../../sql-reference/data-types/date.md)) — Event date.
- `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Event time.
- `name` ([String](../../sql-reference/data-types/string.md)) — Metric name.
- `metric` ([String](../../sql-reference/data-types/string.md)) — Metric name.
- `value` ([Float64](../../sql-reference/data-types/float.md)) — Metric value.
**Example**

2
docs/en/operations/system-tables/metrics.md
View File

@ -287,7 +287,7 @@ Number of threads in the HashedDictionary thread pool running a task.
### IOPrefetchThreads
Number of threads in the IO prefertch thread pool.
Number of threads in the IO prefetch thread pool.
### IOPrefetchThreadsActive

2
docs/en/operations/system-tables/quota_usage.md
View File

@ -25,6 +25,8 @@ Columns:
- `max_read_rows` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of rows read from all tables and table functions participated in queries.
- `read_bytes` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — The total number of bytes read from all tables and table functions participated in queries.
- `max_read_bytes` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum of bytes read from all tables and table functions.
- `failed_sequential_authentications` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/float.md))) — The total count of sequential authentication failures. If the user entered the correct password before exceed `failed_sequential_authentications` threshold then the counter will be reset.
- `max_failed_sequential_authentications` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/float.md))) — Maximum count of sequential authentication failures.
- `execution_time` ([Nullable](../../sql-reference/data-types/nullable.md)([Float64](../../sql-reference/data-types/float.md))) — The total query execution time, in seconds (wall time).
- `max_execution_time` ([Nullable](../../sql-reference/data-types/nullable.md)([Float64](../../sql-reference/data-types/float.md))) — Maximum of query execution time.

6
docs/en/operations/system-tables/quotas_usage.md
View File

@ -28,8 +28,10 @@ Columns:
- `max_read_rows` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of rows read from all tables and table functions participated in queries.
- `read_bytes` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — The total number of bytes read from all tables and table functions participated in queries.
- `max_read_bytes` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum of bytes read from all tables and table functions.
- `execution_time` ([Nullable](../../sql-reference/data-types/nullable.md)([Float64](../../sql-reference/data-types/float.md))) — The total query execution time, in seconds (wall time).
- `max_execution_time` ([Nullable](../../sql-reference/data-types/nullable.md)([Float64](../../sql-reference/data-types/float.md))) — Maximum of query execution time.
- `failed_sequential_authentications` ([Nullable](../../sql-reference/data-types/nullable.md)([Float64](../../sql-reference/data-types/float.md))) — The total count of sequential authentication failures. If the user entered the correct password before exceed `failed_sequential_authentications` threshold then the counter will be reset.
- `max_failed_sequential_authentications` ([Nullable](../../sql-reference/data-types/nullable.md)([Float64](../../sql-reference/data-types/float.md))) — Maximum count of sequential authentication failures.
- `execution_time` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/float.md))) — The total query execution time, in seconds (wall time).
- `max_execution_time` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/float.md))) — Maximum of query execution time.
## See Also {#see-also}

2
docs/en/operations/system-tables/replication_queue.md
View File

@ -49,7 +49,7 @@ Columns:
- `last_attempt_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Date and time when the task was last attempted.
- `num_postponed` ([UInt32](../../sql-reference/data-types/int-uint.md)) — The number of postponed tasks.
- `num_postponed` ([UInt32](../../sql-reference/data-types/int-uint.md)) — The number of times the action was postponed.
- `postpone_reason` ([String](../../sql-reference/data-types/string.md)) — The reason why the task was postponed.

2
docs/en/operations/utilities/clickhouse-benchmark.md
View File

@ -45,11 +45,11 @@ clickhouse-benchmark [keys] < queries_file;
- `-c N`, `--concurrency=N` — Number of queries that `clickhouse-benchmark` sends simultaneously. Default value: 1.
- `-d N`, `--delay=N` — Interval in seconds between intermediate reports (to disable reports set 0). Default value: 1.
- `-h HOST`, `--host=HOST` — Server host. Default value: `localhost`. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `-h` keys.
- `-p N`, `--port=N` — Server port. Default value: 9000. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `-p` keys.
- `-i N`, `--iterations=N` — Total number of queries. Default value: 0 (repeat forever).
- `-r`, `--randomize` — Random order of queries execution if there is more than one input query.
- `-s`, `--secure` — Using `TLS` connection.
- `-t N`, `--timelimit=N` — Time limit in seconds. `clickhouse-benchmark` stops sending queries when the specified time limit is reached. Default value: 0 (time limit disabled).
- `--port=N` — Server port. Default value: 9000. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `--port` keys.
- `--confidence=N` — Level of confidence for T-test. Possible values: 0 (80%), 1 (90%), 2 (95%), 3 (98%), 4 (99%), 5 (99.5%). Default value: 5. In the [comparison mode](#clickhouse-benchmark-comparison-mode) `clickhouse-benchmark` performs the [Independent two-sample Student’s t-test](https://en.wikipedia.org/wiki/Student%27s_t-test#Independent_two-sample_t-test) to determine whether the two distributions aren’t different with the selected level of confidence.
- `--cumulative` — Printing cumulative data instead of data per interval.
- `--database=DATABASE_NAME` — ClickHouse database name. Default value: `default`.

48
docs/en/sql-reference/aggregate-functions/reference/grouparraysorted.md Normal file
View File

@ -0,0 +1,48 @@
---
toc_priority: 112
---
# groupArraySorted {#groupArraySorted}
Returns an array with the first N items in ascending order.
``` sql
groupArraySorted(N)(column)
```
**Arguments**
- `N` – The number of elements to return.
If the parameter is omitted, default value is the size of input.
- `column` – The value (Integer, String, Float and other Generic types).
**Example**
Gets the first 10 numbers:
``` sql
SELECT groupArraySorted(10)(number) FROM numbers(100)
```
``` text
┌─groupArraySorted(10)(number)─┐
│ [0,1,2,3,4,5,6,7,8,9] │
└──────────────────────────────┘
```
Gets all the String implementations of all numbers in column:
``` sql
SELECT groupArraySorted(str) FROM (SELECT toString(number) as str FROM numbers(5));
```
``` text
┌─groupArraySorted(str)────────┐
│ ['0','1','2','3','4'] │
└──────────────────────────────┘
```

3
docs/en/sql-reference/aggregate-functions/reference/index.md
View File

@ -54,6 +54,7 @@ ClickHouse-specific aggregate functions:
- [groupArrayMovingAvg](/docs/en/sql-reference/aggregate-functions/reference/grouparraymovingavg.md)
- [groupArrayMovingSum](/docs/en/sql-reference/aggregate-functions/reference/grouparraymovingsum.md)
- [groupArraySample](./grouparraysample.md)
- [groupArraySorted](/docs/en/sql-reference/aggregate-functions/reference/grouparraysorted.md)
- [groupBitAnd](/docs/en/sql-reference/aggregate-functions/reference/groupbitand.md)
- [groupBitOr](/docs/en/sql-reference/aggregate-functions/reference/groupbitor.md)
- [groupBitXor](/docs/en/sql-reference/aggregate-functions/reference/groupbitxor.md)
@ -88,6 +89,7 @@ ClickHouse-specific aggregate functions:
- [quantileTDigestWeighted](/docs/en/sql-reference/aggregate-functions/reference/quantiletdigestweighted.md)
- [quantileBFloat16](/docs/en/sql-reference/aggregate-functions/reference/quantilebfloat16.md#quantilebfloat16)
- [quantileBFloat16Weighted](/docs/en/sql-reference/aggregate-functions/reference/quantilebfloat16.md#quantilebfloat16weighted)
- [quantileDD](/docs/en/sql-reference/aggregate-functions/reference/quantileddsketch.md#quantileddsketch)
- [simpleLinearRegression](/docs/en/sql-reference/aggregate-functions/reference/simplelinearregression.md)
- [stochasticLinearRegression](/docs/en/sql-reference/aggregate-functions/reference/stochasticlinearregression.md)
- [stochasticLogisticRegression](/docs/en/sql-reference/aggregate-functions/reference/stochasticlogisticregression.md)
@ -104,4 +106,3 @@ ClickHouse-specific aggregate functions:
- [sparkBar](./sparkbar.md)
- [sumCount](./sumcount.md)
- [largestTriangleThreeBuckets](./largestTriangleThreeBuckets.md)

1
docs/en/sql-reference/aggregate-functions/reference/median.md
View File

@ -18,6 +18,7 @@ Functions:
- `medianTDigest` — Alias for [quantileTDigest](../../../sql-reference/aggregate-functions/reference/quantiletdigest.md#quantiletdigest).
- `medianTDigestWeighted` — Alias for [quantileTDigestWeighted](../../../sql-reference/aggregate-functions/reference/quantiletdigestweighted.md#quantiletdigestweighted).
- `medianBFloat16` — Alias for [quantileBFloat16](../../../sql-reference/aggregate-functions/reference/quantilebfloat16.md#quantilebfloat16).
- `medianDD` — Alias for [quantileDD](../../../sql-reference/aggregate-functions/reference/quantileddsketch.md#quantileddsketch).
**Example**

61
docs/en/sql-reference/aggregate-functions/reference/quantileddsketch.md Normal file
View File

@ -0,0 +1,61 @@
---
slug: /en/sql-reference/aggregate-functions/reference/quantileddsketch
sidebar_position: 211
title: quantileDD
---
Computes an approximate [quantile](https://en.wikipedia.org/wiki/Quantile) of a sample with relative-error guarantees. It works by building a [DD](https://www.vldb.org/pvldb/vol12/p2195-masson.pdf).
**Syntax**
``` sql
quantileDDsketch[relative_accuracy, (level)](expr)
```
**Arguments**
- `expr` — Column with numeric data. [Integer](../../../sql-reference/data-types/int-uint.md), [Float](../../../sql-reference/data-types/float.md).
**Parameters**
- `relative_accuracy` — Relative accuracy of the quantile. Possible values are in the range from 0 to 1. [Float](../../../sql-reference/data-types/float.md). The size of the sketch depends on the range of the data and the relative accuracy. The larger the range and the smaller the relative accuracy, the larger the sketch. The rough memory size of the of the sketch is `log(max_value/min_value)/relative_accuracy`. The recommended value is 0.001 or higher.
- `level` — Level of quantile. Optional. Possible values are in the range from 0 to 1. Default value: 0.5. [Float](../../../sql-reference/data-types/float.md).
**Returned value**
- Approximate quantile of the specified level.
Type: [Float64](../../../sql-reference/data-types/float.md#float32-float64).
**Example**
Input table has an integer and a float columns:
``` text
┌─a─┬─────b─┐
│ 1 │ 1.001 │
│ 2 │ 1.002 │
│ 3 │ 1.003 │
│ 4 │ 1.004 │
└───┴───────┘
```
Query to calculate 0.75-quantile (third quartile):
``` sql
SELECT quantileDD(0.01, 0.75)(a), quantileDD(0.01, 0.75)(b) FROM example_table;
```
Result:
``` text
┌─quantileDD(0.01, 0.75)(a)─┬─quantileDD(0.01, 0.75)(b)─┐
│ 2.974233423476717 │ 1.01 │
└─────────────────────────────────┴─────────────────────────────────┘
```
**See Also**
- [median](../../../sql-reference/aggregate-functions/reference/median.md#median)
- [quantiles](../../../sql-reference/aggregate-functions/reference/quantiles.md#quantiles)

2
docs/en/sql-reference/aggregate-functions/reference/quantiles.md
View File

@ -9,7 +9,7 @@ sidebar_position: 201
Syntax: `quantiles(level1, level2, …)(x)`
All the quantile functions also have corresponding quantiles functions: `quantiles`, `quantilesDeterministic`, `quantilesTiming`, `quantilesTimingWeighted`, `quantilesExact`, `quantilesExactWeighted`, `quantileInterpolatedWeighted`, `quantilesTDigest`, `quantilesBFloat16`. These functions calculate all the quantiles of the listed levels in one pass, and return an array of the resulting values.
All the quantile functions also have corresponding quantiles functions: `quantiles`, `quantilesDeterministic`, `quantilesTiming`, `quantilesTimingWeighted`, `quantilesExact`, `quantilesExactWeighted`, `quantileInterpolatedWeighted`, `quantilesTDigest`, `quantilesBFloat16`, `quantilesDD`. These functions calculate all the quantiles of the listed levels in one pass, and return an array of the resulting values.
## quantilesExactExclusive

4
docs/en/sql-reference/data-types/float.md
View File

@ -35,8 +35,8 @@ Types are equivalent to types of C:
Aliases:
- `Float32` — `FLOAT`.
- `Float64` — `DOUBLE`.
- `Float32` — `FLOAT`, `REAL`, `SINGLE`.
- `Float64` — `DOUBLE`, `DOUBLE PRECISION`.
When creating tables, numeric parameters for floating point numbers can be set (e.g. `FLOAT(12)`, `FLOAT(15, 22)`, `DOUBLE(12)`, `DOUBLE(4, 18)`), but ClickHouse ignores them.

16
docs/en/sql-reference/data-types/int-uint.md
View File

@ -21,10 +21,10 @@ When creating tables, numeric parameters for integer numbers can be set (e.g. `T
Aliases:
- `Int8` — `TINYINT`, `BOOL`, `BOOLEAN`, `INT1`.
- `Int16` — `SMALLINT`, `INT2`.
- `Int32` — `INT`, `INT4`, `INTEGER`.
- `Int64` — `BIGINT`.
- `Int8` — `TINYINT`, `INT1`, `BYTE`, `TINYINT SIGNED`, `INT1 SIGNED`.
- `Int16` — `SMALLINT`, `SMALLINT SIGNED`.
- `Int32` — `INT`, `INTEGER`, `MEDIUMINT`, `MEDIUMINT SIGNED`, `INT SIGNED`, `INTEGER SIGNED`.
- `Int64` — `BIGINT`, `SIGNED`, `BIGINT SIGNED`, `TIME`.
## UInt Ranges
@ -34,3 +34,11 @@ Aliases:
- `UInt64` — \[0 : 18446744073709551615\]
- `UInt128` — \[0 : 340282366920938463463374607431768211455\]
- `UInt256` — \[0 : 115792089237316195423570985008687907853269984665640564039457584007913129639935\]
Aliases:
- `UInt8` — `TINYINT UNSIGNED`, `INT1 UNSIGNED`.
- `UInt16` — `SMALLINT UNSIGNED`.
- `UInt32` — `MEDIUMINT UNSIGNED`, `INT UNSIGNED`, `INTEGER UNSIGNED`
- `UInt64` — `UNSIGNED`, `BIGINT UNSIGNED`, `BIT`, `SET`

5
docs/en/sql-reference/data-types/json.md
View File

@ -7,7 +7,7 @@ sidebar_label: JSON
# JSON
:::note
This feature is experimental and is not production ready. If you need to work with JSON documents, consider using [this guide](/docs/en/integrations/data-ingestion/data-formats/json.md) instead.
This feature is experimental and is not production-ready. If you need to work with JSON documents, consider using [this guide](/docs/en/integrations/data-ingestion/data-formats/json.md) instead.
:::
Stores JavaScript Object Notation (JSON) documents in a single column.
@ -15,7 +15,8 @@ Stores JavaScript Object Notation (JSON) documents in a single column.
`JSON` is an alias for `Object('json')`.
:::note
The JSON data type is an experimental feature. To use it, set `allow_experimental_object_type = 1`.
The JSON data type is an obsolete feature. Do not use it.
If you want to use it, set `allow_experimental_object_type = 1`.
:::
## Example

6
docs/en/sql-reference/data-types/nullable.md
View File

@ -4,11 +4,11 @@ sidebar_position: 55
sidebar_label: Nullable
---
# Nullable(typename)
# Nullable(T)
Allows to store special marker ([NULL](../../sql-reference/syntax.md)) that denotes “missing value” alongside normal values allowed by `TypeName`. For example, a `Nullable(Int8)` type column can store `Int8` type values, and the rows that do not have a value will store `NULL`.
Allows to store special marker ([NULL](../../sql-reference/syntax.md)) that denotes “missing value” alongside normal values allowed by `T`. For example, a `Nullable(Int8)` type column can store `Int8` type values, and the rows that do not have a value will store `NULL`.
For a `TypeName`, you can’t use composite data types [Array](../../sql-reference/data-types/array.md), [Map](../../sql-reference/data-types/map.md) and [Tuple](../../sql-reference/data-types/tuple.md). Composite data types can contain `Nullable` type values, such as `Array(Nullable(Int8))`.
`T` can’t be any of the composite data types [Array](../../sql-reference/data-types/array.md), [Map](../../sql-reference/data-types/map.md) and [Tuple](../../sql-reference/data-types/tuple.md) but composite data types can contain `Nullable` type values, e.g. `Array(Nullable(Int8))`.
A `Nullable` type field can’t be included in table indexes.

274
docs/en/sql-reference/data-types/variant.md Normal file
View File

@ -0,0 +1,274 @@
---
slug: /en/sql-reference/data-types/json
sidebar_position: 55
sidebar_label: Variant
---
# Variant(T1, T2, T3, ...)
This type represents a union of other data types. Type `Variant(T1, T2, ..., TN)` means that each row of this type
has a value of either type `T1` or `T2` or ... or `TN` or none of them (`NULL` value).
The order of nested types doesn't matter: Variant(T1, T2) = Variant(T2, T1).
Nested types can be arbitrary types except Nullable(...), LowCardinality(Nullable(...)) and Variant(...) types.
:::note
The Variant data type is an experimental feature. To use it, set `allow_experimental_variant_type = 1`.
:::
## Creating Variant
Using `Variant` type in table column definition:
```sql
CREATE TABLE test (v Variant(UInt64, String, Array(UInt64))) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), ('Hello, World!'), ([1, 2, 3]);
SELECT v FROM test;
```
```text
┌─v─────────────┐
│ ᴺᵁᴸᴸ │
│ 42 │
│ Hello, World! │
│ [1,2,3] │
└───────────────┘
```
Using CAST from ordinary columns:
```sql
SELECT toTypeName(variant) as type_name, 'Hello, World!'::Variant(UInt64, String, Array(UInt64)) as variant;
```
```text
┌─type_name──────────────────────────────┬─variant───────┐
│ Variant(Array(UInt64), String, UInt64) │ Hello, World! │
└────────────────────────────────────────┴───────────────┘
```
Using functions `if/multiIf` when arguments don't have common type (setting `use_variant_as_common_type` should be enabled for it):
```sql
SET use_variant_as_common_type = 1;
SELECT if(number % 2, number, range(number)) as variant FROM numbers(5);
```
```text
┌─variant───┐
│ [] │
│ 1 │
│ [0,1] │
│ 3 │
│ [0,1,2,3] │
└───────────┘
```
```sql
SET use_variant_as_common_type = 1;
SELECT multiIf((number % 4) = 0, 42, (number % 4) = 1, [1, 2, 3], (number % 4) = 2, 'Hello, World!', NULL) AS variant FROM numbers(4);
```
```text
┌─variant───────┐
│ 42 │
│ [1,2,3] │
│ Hello, World! │
│ ᴺᵁᴸᴸ │
└───────────────┘
```
Using functions 'array/map' if array elements/map values don't have common type (setting `use_variant_as_common_type` should be enabled for it):
```sql
SET use_variant_as_common_type = 1;
SELECT array(range(number), number, 'str_' || toString(number)) as array_of_variants FROM numbers(3);
```
```text
┌─array_of_variants─┐
│ [[],0,'str_0'] │
│ [[0],1,'str_1'] │
│ [[0,1],2,'str_2'] │
└───────────────────┘
```
```sql
SET use_variant_as_common_type = 1;
SELECT map('a', range(number), 'b', number, 'c', 'str_' || toString(number)) as map_of_variants FROM numbers(3);
```
```text
┌─map_of_variants───────────────┐
│ {'a':[],'b':0,'c':'str_0'} │
│ {'a':[0],'b':1,'c':'str_1'} │
│ {'a':[0,1],'b':2,'c':'str_2'} │
└───────────────────────────────┘
```
## Reading Variant nested types as subcolumns
Variant type supports reading a single nested type from a Variant column using the type name as a subcolumn.
So, if you have column `variant Variant(T1, T2, T3)` you can read a subcolumn of type `T2` using syntax `variant.T2`,
this subcolumn will have type `Nullable(T2)` if `T2` can be inside `Nullable` and `T2` otherwise. This subcolumn will
be the same size as original `Variant` column and will contain `NULL` values (or empty values if `T2` cannot be inside `Nullable`)
in all rows in which original `Variant` column doesn't have type `T2`.
Variant subcolumns can be also read using function `variantElement(variant_column, type_name)`.
Examples:
```sql
CREATE TABLE test (v Variant(UInt64, String, Array(UInt64))) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), ('Hello, World!'), ([1, 2, 3]);
SELECT v, v.String, v.UInt64, v.`Array(UInt64)` FROM test;
```
```text
┌─v─────────────┬─v.String──────┬─v.UInt64─┬─v.Array(UInt64)─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [] │
│ 42 │ ᴺᵁᴸᴸ │ 42 │ [] │
│ Hello, World! │ Hello, World! │ ᴺᵁᴸᴸ │ [] │
│ [1,2,3] │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [1,2,3] │
└───────────────┴───────────────┴──────────┴─────────────────┘
```
```sql
SELECT toTypeName(v.String), toTypeName(v.UInt64), toTypeName(v.`Array(UInt64)`) FROM test LIMIT 1;
```
```text
┌─toTypeName(v.String)─┬─toTypeName(v.UInt64)─┬─toTypeName(v.Array(UInt64))─┐
│ Nullable(String) │ Nullable(UInt64) │ Array(UInt64) │
└──────────────────────┴──────────────────────┴─────────────────────────────┘
```
```sql
SELECT v, variantElement(v, 'String'), variantElement(v, 'UInt64'), variantElement(v, 'Array(UInt64)') FROM test;
```
```text
┌─v─────────────┬─variantElement(v, 'String')─┬─variantElement(v, 'UInt64')─┬─variantElement(v, 'Array(UInt64)')─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [] │
│ 42 │ ᴺᵁᴸᴸ │ 42 │ [] │
│ Hello, World! │ Hello, World! │ ᴺᵁᴸᴸ │ [] │
│ [1,2,3] │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [1,2,3] │
└───────────────┴─────────────────────────────┴─────────────────────────────┴────────────────────────────────────┘
```
To know what variant is stored in each row function `variantType(variant_column)` can be used. It returns `Enum` with variant type name for each row (or `'None'` if row is `NULL`).
Example:
```sql
CREATE TABLE test (v Variant(UInt64, String, Array(UInt64))) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), ('Hello, World!'), ([1, 2, 3]);
SELECT variantType(v) from test;
```
```text
┌─variantType(v)─┐
│ None │
│ UInt64 │
│ String │
│ Array(UInt64) │
└────────────────┘
```
```sql
SELECT toTypeName(variantType(v)) FROM test LIMIT 1;
```
```text
┌─toTypeName(variantType(v))──────────────────────────────────────────┐
│ Enum8('None' = -1, 'Array(UInt64)' = 0, 'String' = 1, 'UInt64' = 2) │
└─────────────────────────────────────────────────────────────────────┘
```
## Conversion between Variant column and other columns
There are 3 possible conversions that can be performed with Variant column.
### Converting an ordinary column to a Variant column
It is possible to convert ordinary column with type `T` to a `Variant` column containing this type:
```sql
SELECT toTypeName(variant) as type_name, 'Hello, World!'::Variant(UInt64, String, Array(UInt64)) as variant;
```
```text
┌─type_name──────────────────────────────┬─variant───────┐
│ Variant(Array(UInt64), String, UInt64) │ Hello, World! │
└────────────────────────────────────────┴───────────────┘
```
### Converting a Variant column to an ordinary column
It is possible to convert a `Variant` column to an ordinary column. In this case all nested variants will be converted to a destination type:
```sql
CREATE TABLE test (v Variant(UInt64, String)) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), ('42.42');
SELECT v::Nullable(Float64) FROM test;
```
```text
┌─CAST(v, 'Nullable(Float64)')─┐
│ ᴺᵁᴸᴸ │
│ 42 │
│ 42.42 │
└──────────────────────────────┘
```
### Converting a Variant to another Variant
It is possible to convert a `Variant` column to another `Variant` column, but only if the destination `Variant` column contains all nested types from the original `Variant`:
```sql
CREATE TABLE test (v Variant(UInt64, String)) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), ('String');
SELECT v::Variant(UInt64, String, Array(UInt64)) FROM test;
```
```text
┌─CAST(v, 'Variant(UInt64, String, Array(UInt64))')─┐
│ ᴺᵁᴸᴸ │
│ 42 │
│ String │
└───────────────────────────────────────────────────┘
```
## Reading Variant type from the data
All text formats (TSV, CSV, CustomSeparated, Values, JSONEachRow, etc) supports reading `Variant` type. During data parsing ClickHouse tries to insert value into most appropriate variant type.
Example:
```sql
SELECT
v,
variantElement(v, 'String') AS str,
variantElement(v, 'UInt64') AS num,
variantElement(v, 'Float64') AS float,
variantElement(v, 'DateTime') AS date,
variantElement(v, 'Array(UInt64)') AS arr
FROM format(JSONEachRow, 'v Variant(String, UInt64, Float64, DateTime, Array(UInt64))', $$
{"v" : "Hello, World!"},
{"v" : 42},
{"v" : 42.42},
{"v" : "2020-01-01 00:00:00"},
{"v" : [1, 2, 3]}
$$)
```
```text
┌─v───────────────────┬─str───────────┬──num─┬─float─┬────────────────date─┬─arr─────┐
│ Hello, World! │ Hello, World! │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [] │
│ 42 │ ᴺᵁᴸᴸ │ 42 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [] │
│ 42.42 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ 42.42 │ ᴺᵁᴸᴸ │ [] │
│ 2020-01-01 00:00:00 │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ 2020-01-01 00:00:00 │ [] │
│ [1,2,3] │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [1,2,3] │
└─────────────────────┴───────────────┴──────┴───────┴─────────────────────┴─────────┘
```

1
docs/en/sql-reference/dictionaries/index.md
View File

@ -1805,6 +1805,7 @@ Example of settings:
``` xml
<source>
<postgresql>
<host>postgresql-hostname</hoat>
<port>5432</port>
<user>clickhouse</user>
<password>qwerty</password>

37
docs/en/sql-reference/functions/array-functions.md
View File

@ -657,6 +657,43 @@ SELECT arraySlice([1, 2, NULL, 4, 5], 2, 3) AS res;
Array elements set to `NULL` are handled as normal values.
## arrayShingles
Generates an array of "shingles", i.e. consecutive sub-arrays with specified length of the input array.
**Syntax**
``` sql
arrayShingles(array, length)
```
**Arguments**
- `array` — Input array [Array](../../sql-reference/data-types/array.md).
- `length` — The length of each shingle.
**Returned value**
- An array of generated shingles.
Type: [Array](../../sql-reference/data-types/array.md).
**Examples**
Query:
``` sql
SELECT arrayShingles([1,2,3,4], 3) as res;
```
Result:
``` text
┌─res───────────────┐
│ [[1,2,3],[2,3,4]] │
└───────────────────┘
```
## arraySort(\[func,\] arr, …) {#sort}
Sorts the elements of the `arr` array in ascending order. If the `func` function is specified, sorting order is determined by the result of the `func` function applied to the elements of the array. If `func` accepts multiple arguments, the `arraySort` function is passed several arrays that the arguments of `func` will correspond to. Detailed examples are shown at the end of `arraySort` description.

82
docs/en/sql-reference/functions/other-functions.md
View File

@ -2832,6 +2832,88 @@ Result:
└─────────────────────────────────────────────────────────────────────────┘
```
## variantElement
Extracts a column with specified type from a `Variant` column.
**Syntax**
```sql
variantElement(variant, type_name, [, default_value])
```
**Arguments**
- `variant` — Variant column. [Variant](../../sql-reference/data-types/variant.md).
- `type_name` — The name of the variant type to extract. [String](../../sql-reference/data-types/string.md).
- `default_value` - The default value that will be used if variant doesn't have variant with specified type. Can be any type. Optional.
**Returned value**
- Subcolumn of a `Variant` column with specified type.
**Example**
```sql
CREATE TABLE test (v Variant(UInt64, String, Array(UInt64))) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), ('Hello, World!'), ([1, 2, 3]);
SELECT v, variantElement(v, 'String'), variantElement(v, 'UInt64'), variantElement(v, 'Array(UInt64)') FROM test;
```
```text
┌─v─────────────┬─variantElement(v, 'String')─┬─variantElement(v, 'UInt64')─┬─variantElement(v, 'Array(UInt64)')─┐
│ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [] │
│ 42 │ ᴺᵁᴸᴸ │ 42 │ [] │
│ Hello, World! │ Hello, World! │ ᴺᵁᴸᴸ │ [] │
│ [1,2,3] │ ᴺᵁᴸᴸ │ ᴺᵁᴸᴸ │ [1,2,3] │
└───────────────┴─────────────────────────────┴─────────────────────────────┴────────────────────────────────────┘
```
## variantType
Returns the variant type name for each row of `Variant` column. If row contains NULL, it returns `'None'` for it.
**Syntax**
```sql
variantType(variant)
```
**Arguments**
- `variant` — Variant column. [Variant](../../sql-reference/data-types/variant.md).
**Returned value**
- Enum8 column with variant type name for each row.
**Example**
```sql
CREATE TABLE test (v Variant(UInt64, String, Array(UInt64))) ENGINE = Memory;
INSERT INTO test VALUES (NULL), (42), ('Hello, World!'), ([1, 2, 3]);
SELECT variantType(v) FROM test;
```
```text
┌─variantType(v)─┐
│ None │
│ UInt64 │
│ String │
│ Array(UInt64) │
└────────────────┘
```
```sql
SELECT toTypeName(variantType(v)) FROM test LIMIT 1;
```
```text
┌─toTypeName(variantType(v))──────────────────────────────────────────┐
│ Enum8('None' = -1, 'Array(UInt64)' = 0, 'String' = 1, 'UInt64' = 2) │
└─────────────────────────────────────────────────────────────────────┘
```
## minSampleSizeConversion
Calculates minimum required sample size for an A/B test comparing conversions (proportions) in two samples.

2
docs/en/sql-reference/functions/string-functions.md
View File

@ -515,7 +515,7 @@ Alias: `concat_ws`
**Arguments**
- sep — separator. Const [String](../../sql-reference/data-types/string.md) or [FixedString](../../sql-reference/data-types/fixedstring.md).
- exprN — expression to be concatenated. [String](../../sql-reference/data-types/string.md) or [FixedString](../../sql-reference/data-types/fixedstring.md).
- exprN — expression to be concatenated. Arguments which are not of types [String](../../sql-reference/data-types/string.md) or [FixedString](../../sql-reference/data-types/fixedstring.md) are converted to strings using their default serialization. As this decreases performance, it is not recommended to use non-String/FixedString arguments.
**Returned values**

8
docs/en/sql-reference/functions/time-series-functions.md
View File

@ -77,8 +77,8 @@ The number of data points in `series` should be at least twice the value of `per
**Returned value**
- An array of three arrays where the first array include seasonal components, the second array - trend,
and the third array - residue component.
- An array of four arrays where the first array include seasonal components, the second array - trend,
the third array - residue component, and the fourth array - baseline(seasonal + trend) component.
Type: [Array](../../sql-reference/data-types/array.md).
@ -107,6 +107,10 @@ Result:
[
0, 0.0000019073486, -0.0000019073486, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -0.0000019073486, 0,
0
],
[
10.1, 20.449999, 40.340004, 10.100001, 20.45, 40.34, 10.100001, 20.45, 40.34, 10.1, 20.45, 40.34,
10.1, 20.45, 40.34, 10.1, 20.45, 40.34, 10.1, 20.45, 40.34, 10.100002, 20.45, 40.34
]] │
└────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
```

44
docs/en/sql-reference/statements/alter/column.md
View File

@ -23,10 +23,11 @@ The following actions are supported:
- [RENAME COLUMN](#rename-column) — Renames an existing column.
- [CLEAR COLUMN](#clear-column) — Resets column values.
- [COMMENT COLUMN](#comment-column) — Adds a text comment to the column.
- [MODIFY COLUMN](#modify-column) — Changes column’s type, default expression and TTL.
- [MODIFY COLUMN](#modify-column) — Changes column’s type, default expression, TTL, and column settings.
- [MODIFY COLUMN REMOVE](#modify-column-remove) — Removes one of the column properties.
- [MODIFY COLUMN MODIFY SETTING](#modify-column-modify-setting) - Changes column settings.
- [MODIFY COLUMN RESET SETTING](#modify-column-reset-setting) - Reset column settings.
- [MATERIALIZE COLUMN](#materialize-column) — Materializes the column in the parts where the column is missing.
These actions are described in detail below.
## ADD COLUMN
@ -208,7 +209,7 @@ The `ALTER` query for changing columns is replicated. The instructions are saved
## MODIFY COLUMN REMOVE
Removes one of the column properties: `DEFAULT`, `ALIAS`, `MATERIALIZED`, `CODEC`, `COMMENT`, `TTL`.
Removes one of the column properties: `DEFAULT`, `ALIAS`, `MATERIALIZED`, `CODEC`, `COMMENT`, `TTL`, `SETTING`.
Syntax:
@ -228,6 +229,43 @@ ALTER TABLE table_with_ttl MODIFY COLUMN column_ttl REMOVE TTL;
- [REMOVE TTL](ttl.md).
## MODIFY COLUMN MODIFY SETTING
Modify a column setting.
Syntax:
```sql
ALTER TABLE table_name MODIFY COLUMN MODIFY SETTING name=value,...;
```
**Example**
Modify column's `max_compress_block_size` to `1MB`:
```sql
ALTER TABLE table_name MODIFY COLUMN MODIFY SETTING max_compress_block_size = 1048576;
```
## MODIFY COLUMN RESET SETTING
Reset a column setting, also removes the setting declaration in the column expression of the table's CREATE query.
Syntax:
```sql
ALTER TABLE table_name MODIFY COLUMN RESET SETTING name,...;
```
**Example**
Remove column setting `max_compress_block_size` to `1MB`:
```sql
ALTER TABLE table_name MODIFY COLUMN REMOVE SETTING max_compress_block_size;
```
## MATERIALIZE COLUMN
Materializes or updates a column with an expression for a default value (`DEFAULT` or `MATERIALIZED`).

2
docs/en/sql-reference/statements/alter/partition.md
View File

@ -112,7 +112,7 @@ Note that:
For the query to run successfully, the following conditions must be met:
- Both tables must have the same structure.
- Both tables must have the same partition key, the same order by key and the same primary key.
- Both tables must have the same order by key and the same primary key.
- Both tables must have the same indices and projections.
- Both tables must have the same storage policy.

2
docs/en/sql-reference/statements/alter/view.md
View File

@ -8,8 +8,6 @@ sidebar_label: VIEW
You can modify `SELECT` query that was specified when a [materialized view](../create/view.md#materialized) was created with the `ALTER TABLE … MODIFY QUERY` statement without interrupting ingestion process.
The `allow_experimental_alter_materialized_view_structure` setting must be enabled.
This command is created to change materialized view created with `TO [db.]name` clause. It does not change the structure of the underling storage table and it does not change the columns' definition of the materialized view, because of this the application of this command is very limited for materialized views are created without `TO [db.]name` clause.
**Example with TO table**

2
docs/en/sql-reference/statements/create/quota.md
View File

@ -21,7 +21,7 @@ CREATE QUOTA [IF NOT EXISTS | OR REPLACE] name [ON CLUSTER cluster_name]
Keys `user_name`, `ip_address`, `client_key`, `client_key, user_name` and `client_key, ip_address` correspond to the fields in the [system.quotas](../../../operations/system-tables/quotas.md) table.
Parameters `queries`, `query_selects`, `query_inserts`, `errors`, `result_rows`, `result_bytes`, `read_rows`, `read_bytes`, `execution_time` correspond to the fields in the [system.quotas_usage](../../../operations/system-tables/quotas_usage.md) table.
Parameters `queries`, `query_selects`, `query_inserts`, `errors`, `result_rows`, `result_bytes`, `read_rows`, `read_bytes`, `execution_time`, `failed_sequential_authentications` correspond to the fields in the [system.quotas_usage](../../../operations/system-tables/quotas_usage.md) table.
`ON CLUSTER` clause allows creating quotas on a cluster, see [Distributed DDL](../../../sql-reference/distributed-ddl.md).

5
docs/en/sql-reference/statements/create/view.md
View File

@ -97,7 +97,7 @@ This feature is deprecated and will be removed in the future.
For your convenience, the old documentation is located [here](https://pastila.nl/?00f32652/fdf07272a7b54bda7e13b919264e449f.md)
## Refreshable Materialized View {#refreshable-materialized-view}
## Refreshable Materialized View [Experimental] {#refreshable-materialized-view}
```sql
CREATE MATERIALIZED VIEW [IF NOT EXISTS] [db.]table_name
@ -120,7 +120,8 @@ Differences from regular non-refreshable materialized views:
:::note
Refreshable materialized views are a work in progress. Setting `allow_experimental_refreshable_materialized_view = 1` is required for creating one. Current limitations:
* not compatible with Replicated database or table engines,
* not compatible with Replicated database or table engines
* It is not supported in ClickHouse Cloud
* require [Atomic database engine](../../../engines/database-engines/atomic.md),
* no retries for failed refresh - we just skip to the next scheduled refresh time,
* no limit on number of concurrent refreshes.

4
docs/en/sql-reference/statements/rename.md
View File

@ -9,10 +9,6 @@ sidebar_label: RENAME
Renames databases, tables, or dictionaries. Several entities can be renamed in a single query.
Note that the `RENAME` query with several entities is non-atomic operation. To swap entities names atomically, use the [EXCHANGE](./exchange.md) statement.
:::note
The `RENAME` query is supported by the [Atomic](../../engines/database-engines/atomic.md) database engine only.
:::
**Syntax**
```sql

4
docs/en/sql-reference/table-functions/executable.md
View File

@ -7,7 +7,7 @@ keywords: [udf, user defined function, clickhouse, executable, table, function]
# executable Table Function for UDFs
The `executable` table function creates a table based on the output of a user-defined function (UDF) that you define in a script that outputs rows to **stdout**. The executable script is stored in the `users_scripts` directory and can read data from any source.
The `executable` table function creates a table based on the output of a user-defined function (UDF) that you define in a script that outputs rows to **stdout**. The executable script is stored in the `users_scripts` directory and can read data from any source. Make sure your ClickHouse server has all the required packages to run the executable script. For example, if it is a Python script, ensure that the server has the necessary Python packages installed.
You can optionally include one or more input queries that stream their results to **stdin** for the script to read.
@ -63,7 +63,7 @@ if __name__ == "__main__":
Let's invoke the script and have it generate 10 random strings:
```sql
SELECT * FROM executable('my_script.py', TabSeparated, 'id UInt32, random String', (SELECT 10))
SELECT * FROM executable('generate_random.py', TabSeparated, 'id UInt32, random String', (SELECT 10))
```
The response looks like:

2
docs/en/sql-reference/table-functions/fuzzJSON.md
View File

@ -9,7 +9,7 @@ sidebar_label: fuzzJSON
Perturbs a JSON string with random variations.
``` sql
fuzzJSON({ named_collection [option=value [,..]] | json_str[, random_seed] })
fuzzJSON({ named_collection [, option=value [,..]] | json_str[, random_seed] })
```
**Arguments**

37
docs/en/sql-reference/table-functions/gcs.md
View File

@ -16,7 +16,8 @@ If you have multiple replicas in your cluster, you can use the [s3Cluster functi
**Syntax**
``` sql
gcs(path [,hmac_key, hmac_secret] [,format] [,structure] [,compression])
gcs(url [, NOSIGN | hmac_key, hmac_secret] [,format] [,structure] [,compression_method])
gcs(named_collection[, option=value [,..]])
```
:::tip GCS
@ -24,10 +25,9 @@ The GCS Table Function integrates with Google Cloud Storage by using the GCS XML
:::
**Arguments**
- `path` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings.
**Parameters**
- `url` — Bucket path to file. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings.
:::note GCS
The GCS path is in this format as the endpoint for the Google XML API is different than the JSON API:
```
@ -35,10 +35,21 @@ The GCS Table Function integrates with Google Cloud Storage by using the GCS XML
```
and not ~~https://storage.cloud.google.com~~.
:::
- `NOSIGN` — If this keyword is provided in place of credentials, all the requests will not be signed.
- `hmac_key` and `hmac_secret` — Keys that specify credentials to use with given endpoint. Optional.
- `format` — The [format](../../interfaces/formats.md#formats) of the file.
- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
- `compression_method` — Parameter is optional. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. By default, it will autodetect compression method by file extension.
Arguments can also be passed using [named collections](/docs/en/operations/named-collections.md). In this case `url`, `format`, `structure`, `compression_method` work in the same way, and some extra parameters are supported:
- `access_key_id` — `hmac_key`, optional.
- `secret_access_key` — `hmac_secret`, optional.
- `filename` — appended to the url if specified.
- `use_environment_credentials` — enabled by default, allows passing extra parameters using environment variables `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI`, `AWS_CONTAINER_CREDENTIALS_FULL_URI`, `AWS_CONTAINER_AUTHORIZATION_TOKEN`, `AWS_EC2_METADATA_DISABLED`.
- `no_sign_request` — disabled by default.
- `expiration_window_seconds` — default value is 120.
- `format` — The [format](../../interfaces/formats.md#formats) of the file.
- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
- `compression` — Parameter is optional. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. By default, it will autodetect compression by file extension.
**Returned value**
@ -61,7 +72,7 @@ LIMIT 2;
└─────────┴─────────┴─────────┘
```
The similar but from file with `gzip` compression:
The similar but from file with `gzip` compression method:
``` sql
SELECT *
@ -158,6 +169,16 @@ The below get data from all `test-data.csv.gz` files from any folder inside `my-
SELECT * FROM gcs('https://storage.googleapis.com/my-test-bucket-768/**/test-data.csv.gz', 'CSV', 'name String, value UInt32', 'gzip');
```
For production use cases it is recommended to use [named collections](/docs/en/operations/named-collections.md). Here is the example:
``` sql
CREATE NAMED COLLECTION creds AS
access_key_id = '***',
secret_access_key = '***';
SELECT count(*)
FROM gcs(creds, url='https://s3-object-url.csv')
```
## Partitioned Write
If you specify `PARTITION BY` expression when inserting data into `GCS` table, a separate file is created for each partition value. Splitting the data into separate files helps to improve reading operations efficiency.

26
docs/en/sql-reference/table-functions/mysql.md
View File

@ -11,31 +11,25 @@ Allows `SELECT` and `INSERT` queries to be performed on data that is stored on a
**Syntax**
``` sql
mysql('host:port', 'database', 'table', 'user', 'password'[, replace_query, 'on_duplicate_clause'])
mysql({host:port, database, table, user, password[, replace_query, on_duplicate_clause] | named_collection[, option=value [,..]]})
```
**Arguments**
**Parameters**
- `host:port` — MySQL server address.
- `database` — Remote database name.
- `table` — Remote table name.
- `user` — MySQL user.
- `password` — User password.
- `replace_query` — Flag that converts `INSERT INTO` queries to `REPLACE INTO`. Possible values:
- `0` - The query is executed as `INSERT INTO`.
- `1` - The query is executed as `REPLACE INTO`.
- `on_duplicate_clause` — The `ON DUPLICATE KEY on_duplicate_clause` expression that is added to the `INSERT` query. Can be specified only with `replace_query = 0` (if you simultaneously pass `replace_query = 1` and `on_duplicate_clause`, ClickHouse generates an exception).
Example: `INSERT INTO t (c1,c2) VALUES ('a', 2) ON DUPLICATE KEY UPDATE c2 = c2 + 1;`
`on_duplicate_clause` here is `UPDATE c2 = c2 + 1`. See the MySQL documentation to find which `on_duplicate_clause` you can use with the `ON DUPLICATE KEY` clause.
Arguments also can be passed using [named collections](/docs/en/operations/named-collections.md). In this case `host` and `port` should be specified separately. This approach is recommended for production environment.
Simple `WHERE` clauses such as `=, !=, >, >=, <, <=` are currently executed on the MySQL server.
The rest of the conditions and the `LIMIT` sampling constraint are executed in ClickHouse only after the query to MySQL finishes.
@ -86,6 +80,18 @@ Selecting data from ClickHouse:
SELECT * FROM mysql('localhost:3306', 'test', 'test', 'bayonet', '123');
```
Or using [named collections](/docs/en/operations/named-collections.md):
```sql
CREATE NAMED COLLECTION creds AS
host = 'localhost',
port = 3306,
database = 'test',
user = 'bayonet',
password = '123';
SELECT * FROM mysql(creds, table='test');
```
``` text
┌─int_id─┬─float─┐
│ 1 │ 2 │

21
docs/en/sql-reference/table-functions/postgresql.md
View File

@ -11,10 +11,10 @@ Allows `SELECT` and `INSERT` queries to be performed on data that is stored on a
**Syntax**
``` sql
postgresql('host:port', 'database', 'table', 'user', 'password'[, `schema`])
postgresql({host:port, database, table, user, password[, schema, [, on_conflict]] | named_collection[, option=value [,..]]})
```
**Arguments**
**Parameters**
- `host:port` — PostgreSQL server address.
- `database` — Remote database name.
@ -22,6 +22,9 @@ postgresql('host:port', 'database', 'table', 'user', 'password'[, `schema`])
- `user` — PostgreSQL user.
- `password` — User password.
- `schema` — Non-default table schema. Optional.
- `on_conflict` — Conflict resolution strategy. Example: `ON CONFLICT DO NOTHING`. Optional.
Arguments also can be passed using [named collections](/docs/en/operations/named-collections.md). In this case `host` and `port` should be specified separately. This approach is recommended for production environment.
**Returned Value**
@ -86,12 +89,24 @@ postgresql> SELECT * FROM test;
(1 row)
```
Selecting data from ClickHouse:
Selecting data from ClickHouse using plain arguments:
```sql
SELECT * FROM postgresql('localhost:5432', 'test', 'test', 'postgresql_user', 'password') WHERE str IN ('test');
```
Or using [named collections](/docs/en/operations/named-collections.md):
```sql
CREATE NAMED COLLECTION mypg AS
host = 'localhost',
port = 5432,
database = 'test',
user = 'postgresql_user',
password = 'password';
SELECT * FROM postgresql(mypg, table='test') WHERE str IN ('test');
```
``` text
┌─int_id─┬─int_nullable─┬─float─┬─str──┬─float_nullable─┐
│ 1 │ ᴺᵁᴸᴸ │ 2 │ test │ ᴺᵁᴸᴸ │

22
docs/en/sql-reference/table-functions/redis.md
View File

@ -34,6 +34,7 @@ redis(host:port, key, structure[, db_index[, password[, pool_size]]])
- queries with key equals or in filtering will be optimized to multi keys lookup from Redis. If queries without filtering key full table scan will happen which is a heavy operation.
[Named collections](/docs/en/operations/named-collections.md) are not supported for `redis` table function at the moment.
**Returned Value**
@ -41,17 +42,7 @@ A table object with key as Redis key, other columns packaged together as Redis v
## Usage Example {#usage-example}
Create a table in ClickHouse which allows to read data from Redis:
``` sql
CREATE TABLE redis_table
(
`k` String,
`m` String,
`n` UInt32
)
ENGINE = Redis('redis1:6379') PRIMARY KEY(k);
```
Read from Redis:
```sql
SELECT * FROM redis(
@ -61,6 +52,15 @@ SELECT * FROM redis(
)
```
Insert into Redis:
```sql
INSERT INTO TABLE FUNCTION redis(
'redis1:6379',
'key',
'key String, v1 String, v2 UInt32') values ('1', '1', 1);
```
**See Also**
- [The `Redis` table engine](/docs/en/engines/table-engines/integrations/redis.md)

23
docs/en/sql-reference/table-functions/remote.md
View File

@ -13,10 +13,12 @@ Both functions can be used in `SELECT` and `INSERT` queries.
## Syntax
``` sql
remote('addresses_expr', [db, table, 'user'[, 'password'], sharding_key])
remote('addresses_expr', [db.table, 'user'[, 'password'], sharding_key])
remoteSecure('addresses_expr', [db, table, 'user'[, 'password'], sharding_key])
remoteSecure('addresses_expr', [db.table, 'user'[, 'password'], sharding_key])
remote(addresses_expr, [db, table, user [, password], sharding_key])
remote(addresses_expr, [db.table, user [, password], sharding_key])
remote(named_collection[, option=value [,..]])
remoteSecure(addresses_expr, [db, table, user [, password], sharding_key])
remoteSecure(addresses_expr, [db.table, user [, password], sharding_key])
remoteSecure(named_collection[, option=value [,..]])
```
## Parameters
@ -39,6 +41,8 @@ remoteSecure('addresses_expr', [db.table, 'user'[, 'password'], sharding_key])
- `password` — User password. If not specified, an empty password is used. Type: [String](../../sql-reference/data-types/string.md).
- `sharding_key` — Sharding key to support distributing data across nodes. For example: `insert into remote('127.0.0.1:9000,127.0.0.2', db, table, 'default', rand())`. Type: [UInt32](../../sql-reference/data-types/int-uint.md).
Arguments also can be passed using [named collections](/docs/en/operations/named-collections.md).
## Returned value
A table located on a remote server.
@ -82,7 +86,16 @@ example01-01-1,example01-02-1
SELECT * FROM remote('127.0.0.1', db.remote_engine_table) LIMIT 3;
```
### Inserting data from a remote server into a table:
Or using [named collections](/docs/en/operations/named-collections.md):
```sql
CREATE NAMED COLLECTION creds AS
host = '127.0.0.1',
database = 'db';
SELECT * FROM remote(creds, table='remote_engine_table') LIMIT 3;
```
### Inserting data into a table on a remote server:
``` sql
CREATE TABLE remote_table (name String, value UInt32) ENGINE=Memory;

38
docs/en/sql-reference/table-functions/s3.md
View File

@ -16,33 +16,41 @@ When using the `s3 table function` with [`INSERT INTO...SELECT`](../../sql-refer
**Syntax**
``` sql
s3(path [, NOSIGN | aws_access_key_id, aws_secret_access_key [,session_token]] [,format] [,structure] [,compression])
s3(url [, NOSIGN | access_key_id, secret_access_key, [session_token]] [,format] [,structure] [,compression_method])
s3(named_collection[, option=value [,..]])
```
:::tip GCS
The S3 Table Function integrates with Google Cloud Storage by using the GCS XML API and HMAC keys. See the [Google interoperability docs]( https://cloud.google.com/storage/docs/interoperability) for more details about the endpoint and HMAC.
For GCS, substitute your HMAC key and HMAC secret where you see `aws_access_key_id` and `aws_secret_access_key`.
For GCS, substitute your HMAC key and HMAC secret where you see `access_key_id` and `secret_access_key`.
:::
**Arguments**
**Parameters**
- `path` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings. For more information see [here](../../engines/table-engines/integrations/s3.md#wildcards-in-path).
`s3` table function supports the following plain parameters:
- `url` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings. For more information see [here](../../engines/table-engines/integrations/s3.md#wildcards-in-path).
:::note GCS
The GCS path is in this format as the endpoint for the Google XML API is different than the JSON API:
The GCS url is in this format as the endpoint for the Google XML API is different than the JSON API:
```
https://storage.googleapis.com/<bucket>/<folder>/<filename(s)>
```
and not ~~https://storage.cloud.google.com~~.
:::
- `NOSIGN` - If this keyword is provided in place of credentials, all the requests will not be signed.
- `access_key_id`, `secret_access_key` — Keys that specify credentials to use with given endpoint. Optional.
- `NOSIGN` — If this keyword is provided in place of credentials, all the requests will not be signed.
- `access_key_id` and `secret_access_key` — Keys that specify credentials to use with given endpoint. Optional.
- `session_token` - Session token to use with the given keys. Optional when passing keys.
- `format` — The [format](../../interfaces/formats.md#formats) of the file.
- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
- `compression` — Parameter is optional. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. By default, it will autodetect compression by file extension.
- `compression_method` — Parameter is optional. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. By default, it will autodetect compression method by file extension.
Arguments can also be passed using [named collections](/docs/en/operations/named-collections.md). In this case `url`, `access_key_id`, `secret_access_key`, `format`, `structure`, `compression_method` work in the same way, and some extra parameters are supported:
- `filename` — appended to the url if specified.
- `use_environment_credentials` — enabled by default, allows passing extra parameters using environment variables `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI`, `AWS_CONTAINER_CREDENTIALS_FULL_URI`, `AWS_CONTAINER_AUTHORIZATION_TOKEN`, `AWS_EC2_METADATA_DISABLED`.
- `no_sign_request` — disabled by default.
- `expiration_window_seconds` — default value is 120.
**Returned value**
@ -82,7 +90,7 @@ FROM s3(
LIMIT 5;
```
ClickHouse also can determine the compression of the file. For example, if the file was zipped up with a `.csv.gz` extension, ClickHouse would decompress the file automatically.
ClickHouse also can determine the compression method of the file. For example, if the file was zipped up with a `.csv.gz` extension, ClickHouse would decompress the file automatically.
:::
@ -190,6 +198,16 @@ Custom mapper can be added into `config.xml`:
</url_scheme_mappers>
```
For production use cases it is recommended to use [named collections](/docs/en/operations/named-collections.md). Here is the example:
``` sql
CREATE NAMED COLLECTION creds AS
access_key_id = '***',
secret_access_key = '***';
SELECT count(*)
FROM s3(creds, url='https://s3-object-url.csv')
```
## Partitioned Write
If you specify `PARTITION BY` expression when inserting data into `S3` table, a separate file is created for each partition value. Splitting the data into separate files helps to improve reading operations efficiency.

Some files were not shown because too many files have changed in this diff Show More