Merge remote-tracking branch 'blessed/master' into frame_pointers_2

This commit is contained in:
Raúl Marín 2024-07-18 14:26:35 +02:00
commit a446ff5524
1433 changed files with 31423 additions and 10656 deletions

View File

@ -27,6 +27,8 @@ Checks: [
'-bugprone-not-null-terminated-result',
'-bugprone-reserved-identifier', # useful but too slow, TODO retry when https://reviews.llvm.org/rG1c282052624f9d0bd273bde0b47b30c96699c6c7 is merged
'-bugprone-unchecked-optional-access',
'-bugprone-crtp-constructor-accessibility',
'-bugprone-suspicious-stringview-data-usage',
'-cert-dcl16-c',
'-cert-dcl37-c',
@ -36,6 +38,7 @@ Checks: [
'-cert-msc51-cpp',
'-cert-oop54-cpp',
'-cert-oop57-cpp',
'-cert-err33-c', # Misreports on clang-19: it warns about all functions containing 'remove' in the name, not only about the standard library.
'-clang-analyzer-optin.performance.Padding',
@ -99,6 +102,7 @@ Checks: [
'-modernize-use-emplace',
'-modernize-use-nodiscard',
'-modernize-use-trailing-return-type',
'-modernize-use-designated-initializers',
'-performance-enum-size',
'-performance-inefficient-string-concatenation',

View File

@ -13,3 +13,6 @@
# dbms/ → src/
# (though it is unlikely that you will see it in blame)
06446b4f08a142d6f1bc30664c47ded88ab51782
# Applied Black formatter for Python code
e6f5a3f98b21ba99cf274a9833797889e020a2b3

View File

@ -7,3 +7,4 @@ self-hosted-runner:
- stress-tester
- style-checker
- style-checker-aarch64
- release-maker

View File

@ -62,7 +62,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckX86:

View File

@ -6,8 +6,8 @@ concurrency:
'on':
workflow_dispatch:
inputs:
sha:
description: 'The SHA hash of the commit from which to create the release'
ref:
description: 'Git reference (branch or commit sha) from which to create the release'
required: true
type: string
type:
@ -15,15 +15,152 @@ concurrency:
required: true
type: choice
options:
- new
- patch
- new
dry-run:
description: 'Dry run'
required: false
default: true
type: boolean
jobs:
Release:
runs-on: [self-hosted, style-checker-aarch64]
CreateRelease:
env:
GH_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
runs-on: [self-hosted, release-maker]
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Set envs
# https://docs.github.com/en/actions/learn-github-actions/workflow-commands-for-github-actions#multiline-strings
run: |
cat >> "$GITHUB_ENV" << 'EOF'
ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
RELEASE_INFO_FILE=${{ runner.temp }}/release_info.json
EOF
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Print greeting
with:
token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
fetch-depth: 0
- name: Prepare Release Info
run: |
python3 ./tests/ci/release.py --commit ${{ inputs.sha }} --type ${{ inputs.type }} --dry-run
python3 ./tests/ci/create_release.py --prepare-release-info \
--ref ${{ inputs.ref }} --release-type ${{ inputs.type }} \
--outfile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
echo "::group::Release Info"
python3 -m json.tool "$RELEASE_INFO_FILE"
echo "::endgroup::"
release_tag=$(jq -r '.release_tag' "$RELEASE_INFO_FILE")
commit_sha=$(jq -r '.commit_sha' "$RELEASE_INFO_FILE")
echo "Release Tag: $release_tag"
echo "RELEASE_TAG=$release_tag" >> "$GITHUB_ENV"
echo "COMMIT_SHA=$commit_sha" >> "$GITHUB_ENV"
- name: Download All Release Artifacts
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/create_release.py --infile "$RELEASE_INFO_FILE" --download-packages ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Push Git Tag for the Release
run: |
python3 ./tests/ci/create_release.py --push-release-tag --infile "$RELEASE_INFO_FILE" ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Push New Release Branch
if: ${{ inputs.type == 'new' }}
run: |
python3 ./tests/ci/create_release.py --push-new-release-branch --infile "$RELEASE_INFO_FILE" ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Bump CH Version and Update Contributors' List
run: |
python3 ./tests/ci/create_release.py --create-bump-version-pr --infile "$RELEASE_INFO_FILE" ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Checkout master
run: |
git checkout master
- name: Bump Docker versions, Changelog, Security
if: ${{ inputs.type == 'patch' }}
run: |
[ "$(git branch --show-current)" != "master" ] && echo "not on the master" && exit 1
echo "List versions"
./utils/list-versions/list-versions.sh > ./utils/list-versions/version_date.tsv
echo "Update docker version"
./utils/list-versions/update-docker-version.sh
echo "Generate ChangeLog"
export CI=1
docker run -u "${UID}:${GID}" -e PYTHONUNBUFFERED=1 -e CI=1 --network=host \
--volume=".:/ClickHouse" clickhouse/style-test \
/ClickHouse/tests/ci/changelog.py -v --debug-helpers \
--gh-user-or-token="$GH_TOKEN" --jobs=5 \
--output="/ClickHouse/docs/changelogs/${{ env.RELEASE_TAG }}.md" ${{ env.RELEASE_TAG }}
git add ./docs/changelogs/${{ env.RELEASE_TAG }}.md
echo "Generate Security"
python3 ./utils/security-generator/generate_security.py > SECURITY.md
git diff HEAD
- name: Create ChangeLog PR
if: ${{ inputs.type == 'patch' && ! inputs.dry-run }}
uses: peter-evans/create-pull-request@v6
with:
author: "robot-clickhouse <robot-clickhouse@users.noreply.github.com>"
token: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
committer: "robot-clickhouse <robot-clickhouse@users.noreply.github.com>"
commit-message: Update version_date.tsv and changelogs after ${{ env.RELEASE_TAG }}
branch: auto/${{ env.RELEASE_TAG }}
assignees: ${{ github.event.sender.login }} # assign the PR to the tag pusher
delete-branch: true
title: Update version_date.tsv and changelog after ${{ env.RELEASE_TAG }}
labels: do not test
body: |
Update version_date.tsv and changelogs after ${{ env.RELEASE_TAG }}
### Changelog category (leave one):
- Not for changelog (changelog entry is not required)
- name: Reset changes if Dry-run
if: ${{ inputs.dry-run }}
run: |
git reset --hard HEAD
- name: Checkout back to GITHUB_REF
run: |
git checkout "$GITHUB_REF_NAME"
- name: Create GH Release
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/create_release.py --create-gh-release \
--infile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Export TGZ Packages
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/artifactory.py --export-tgz --infile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Test TGZ Packages
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/artifactory.py --test-tgz --infile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Export RPM Packages
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/artifactory.py --export-rpm --infile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Test RPM Packages
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/artifactory.py --test-rpm --infile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Export Debian Packages
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/artifactory.py --export-debian --infile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Test Debian Packages
if: ${{ inputs.type == 'patch' }}
run: |
python3 ./tests/ci/artifactory.py --test-debian --infile ${{ env.RELEASE_INFO_FILE }} ${{ inputs.dry-run && '--dry-run' || '' }}
- name: Docker clickhouse/clickhouse-server building
if: ${{ inputs.type == 'patch' }}
run: |
cd "./tests/ci"
export CHECK_NAME="Docker server image"
python3 docker_server.py --release-type auto --version ${{ env.RELEASE_TAG }} --check-name "$CHECK_NAME" --sha ${{ env.COMMIT_SHA }} ${{ ! inputs.dry-run && '--push' || '' }}
- name: Docker clickhouse/clickhouse-keeper building
if: ${{ inputs.type == 'patch' }}
run: |
cd "./tests/ci"
export CHECK_NAME="Docker keeper image"
python3 docker_server.py --release-type auto --version ${{ env.RELEASE_TAG }} --check-name "$CHECK_NAME" --sha ${{ env.COMMIT_SHA }} ${{ ! inputs.dry-run && '--push' || '' }}
- name: Post Slack Message
if: always()
run: |
echo Slack Message

View File

@ -58,7 +58,7 @@ jobs:
# BuildDockers:
# needs: [RunConfig]
# if: ${{ !failure() && !cancelled() }}
# uses: ./.github/workflows/reusable_docker.yml
# uses: ./.github/workflows/docker_test_images.yml
# with:
# data: ${{ needs.RunConfig.outputs.data }}
# StyleCheck:

View File

@ -51,7 +51,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
StyleCheck:

View File

@ -40,7 +40,7 @@ jobs:
} >> "$GITHUB_OUTPUT"
BuildDockers:
needs: [RunConfig]
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: "${{ needs.RunConfig.outputs.data }}"
set_latest: true

View File

@ -72,7 +72,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
StyleCheck:
@ -172,7 +172,7 @@ jobs:
################################# Stage Final #################################
#
FinishCheck:
if: ${{ !cancelled() }}
if: ${{ !failure() && !cancelled() }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
runs-on: [self-hosted, style-checker-aarch64]
steps:

View File

@ -57,7 +57,7 @@ jobs:
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_docker.yml
uses: ./.github/workflows/docker_test_images.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
CompatibilityCheckX86:

View File

@ -102,6 +102,8 @@ jobs:
--job-name '${{inputs.test_name}}' \
--run \
--run-command '''${{inputs.run_command}}'''
# shellcheck disable=SC2319
echo "JOB_EXIT_CODE=$?" >> "$GITHUB_ENV"
- name: Post run
if: ${{ !cancelled() }}
run: |

View File

@ -34,7 +34,7 @@ curl https://clickhouse.com/ | sh
Every month we get together with the community (users, contributors, customers, those interested in learning more about ClickHouse) to discuss what is coming in the latest release. If you are interested in sharing what you've built on ClickHouse, let us know.
* [v24.6 Community Call](https://clickhouse.com/company/events/v24-6-community-release-call) - Jul 2
* [v24.7 Community Call](https://clickhouse.com/company/events/v24-7-community-release-call) - Jul 30
## Upcoming Events

View File

@ -3,8 +3,9 @@
#include <base/defines.h>
#include <fstream>
#include <sstream>
#include <string>
namespace fs = std::filesystem;
bool cgroupsV2Enabled()
{
@ -13,11 +14,11 @@ bool cgroupsV2Enabled()
{
/// This file exists iff the host has cgroups v2 enabled.
auto controllers_file = default_cgroups_mount / "cgroup.controllers";
if (!std::filesystem::exists(controllers_file))
if (!fs::exists(controllers_file))
return false;
return true;
}
catch (const std::filesystem::filesystem_error &) /// all "underlying OS API errors", typically: permission denied
catch (const fs::filesystem_error &) /// all "underlying OS API errors", typically: permission denied
{
return false; /// not logging the exception as most callers fall back to cgroups v1
}
@ -33,8 +34,9 @@ bool cgroupsV2MemoryControllerEnabled()
/// According to https://docs.kernel.org/admin-guide/cgroup-v2.html, file "cgroup.controllers" defines which controllers are available
/// for the current + child cgroups. The set of available controllers can be restricted from level to level using file
/// "cgroups.subtree_control". It is therefore sufficient to check the bottom-most nested "cgroup.controllers" file.
std::string cgroup = cgroupV2OfProcess();
auto cgroup_dir = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
fs::path cgroup_dir = cgroupV2PathOfProcess();
if (cgroup_dir.empty())
return false;
std::ifstream controllers_file(cgroup_dir / "cgroup.controllers");
if (!controllers_file.is_open())
return false;
@ -46,7 +48,7 @@ bool cgroupsV2MemoryControllerEnabled()
#endif
}
std::string cgroupV2OfProcess()
fs::path cgroupV2PathOfProcess()
{
#if defined(OS_LINUX)
chassert(cgroupsV2Enabled());
@ -54,17 +56,18 @@ std::string cgroupV2OfProcess()
/// A simpler way to get the membership is:
std::ifstream cgroup_name_file("/proc/self/cgroup");
if (!cgroup_name_file.is_open())
return "";
return {};
/// With cgroups v2, there will be a *single* line with prefix "0::/"
/// (see https://docs.kernel.org/admin-guide/cgroup-v2.html)
std::string cgroup;
std::getline(cgroup_name_file, cgroup);
static const std::string v2_prefix = "0::/";
if (!cgroup.starts_with(v2_prefix))
return "";
return {};
cgroup = cgroup.substr(v2_prefix.length());
return cgroup;
/// Note: The 'root' cgroup can have an empty cgroup name, this is valid
return default_cgroups_mount / cgroup;
#else
return "";
return {};
#endif
}

View File

@ -1,7 +1,6 @@
#pragma once
#include <filesystem>
#include <string>
#if defined(OS_LINUX)
/// I think it is possible to mount the cgroups hierarchy somewhere else (e.g. when in containers).
@ -16,7 +15,7 @@ bool cgroupsV2Enabled();
/// Assumes that cgroupsV2Enabled() is enabled.
bool cgroupsV2MemoryControllerEnabled();
/// Which cgroup does the process belong to?
/// Returns an empty string if the cgroup cannot be determined.
/// Detects which cgroup v2 the process belongs to and returns the filesystem path to the cgroup.
/// Returns an empty path the cgroup cannot be determined.
/// Assumes that cgroupsV2Enabled() is enabled.
std::string cgroupV2OfProcess();
std::filesystem::path cgroupV2PathOfProcess();

View File

@ -1,5 +1,6 @@
#pragma once
#include <cstdlib>
#include <memory>
#include <string>

View File

@ -108,6 +108,14 @@ struct make_unsigned // NOLINT(readability-identifier-naming)
using type = std::make_unsigned_t<T>;
};
template <> struct make_unsigned<Int8> { using type = UInt8; };
template <> struct make_unsigned<UInt8> { using type = UInt8; };
template <> struct make_unsigned<Int16> { using type = UInt16; };
template <> struct make_unsigned<UInt16> { using type = UInt16; };
template <> struct make_unsigned<Int32> { using type = UInt32; };
template <> struct make_unsigned<UInt32> { using type = UInt32; };
template <> struct make_unsigned<Int64> { using type = UInt64; };
template <> struct make_unsigned<UInt64> { using type = UInt64; };
template <> struct make_unsigned<Int128> { using type = UInt128; };
template <> struct make_unsigned<UInt128> { using type = UInt128; };
template <> struct make_unsigned<Int256> { using type = UInt256; };
@ -121,6 +129,14 @@ struct make_signed // NOLINT(readability-identifier-naming)
using type = std::make_signed_t<T>;
};
template <> struct make_signed<Int8> { using type = Int8; };
template <> struct make_signed<UInt8> { using type = Int8; };
template <> struct make_signed<Int16> { using type = Int16; };
template <> struct make_signed<UInt16> { using type = Int16; };
template <> struct make_signed<Int32> { using type = Int32; };
template <> struct make_signed<UInt32> { using type = Int32; };
template <> struct make_signed<Int64> { using type = Int64; };
template <> struct make_signed<UInt64> { using type = Int64; };
template <> struct make_signed<Int128> { using type = Int128; };
template <> struct make_signed<UInt128> { using type = Int128; };
template <> struct make_signed<Int256> { using type = Int256; };

View File

@ -23,8 +23,9 @@ std::optional<uint64_t> getCgroupsV2MemoryLimit()
if (!cgroupsV2MemoryControllerEnabled())
return {};
std::string cgroup = cgroupV2OfProcess();
auto current_cgroup = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
std::filesystem::path current_cgroup = cgroupV2PathOfProcess();
if (current_cgroup.empty())
return {};
/// Open the bottom-most nested memory limit setting file. If there is no such file at the current
/// level, try again at the parent level as memory settings are inherited.

View File

@ -0,0 +1,9 @@
#pragma once
#include <memory>
template <typename T>
bool isSharedPtrUnique(const std::shared_ptr<T> & ptr)
{
return ptr.use_count() == 1;
}

View File

@ -232,7 +232,7 @@ void Foundation_API format(
const Any & value10);
void Foundation_API format(std::string & result, const std::string & fmt, const std::vector<Any> & values);
void Foundation_API formatVector(std::string & result, const std::string & fmt, const std::vector<Any> & values);
/// Supports a variable number of arguments and is used by
/// all other variants of format().

View File

@ -21,6 +21,8 @@
#include "Poco/AtomicCounter.h"
#include "Poco/Foundation.h"
#include <atomic>
namespace Poco
{

View File

@ -51,8 +51,8 @@ namespace
}
if (width != 0) str.width(width);
}
void parsePrec(std::ostream& str, std::string::const_iterator& itFmt, const std::string::const_iterator& endFmt)
{
if (itFmt != endFmt && *itFmt == '.')
@ -67,7 +67,7 @@ namespace
if (prec >= 0) str.precision(prec);
}
}
char parseMod(std::string::const_iterator& itFmt, const std::string::const_iterator& endFmt)
{
char mod = 0;
@ -77,13 +77,13 @@ namespace
{
case 'l':
case 'h':
case 'L':
case 'L':
case '?': mod = *itFmt++; break;
}
}
return mod;
}
std::size_t parseIndex(std::string::const_iterator& itFmt, const std::string::const_iterator& endFmt)
{
int index = 0;
@ -110,8 +110,8 @@ namespace
case 'f': str << std::fixed; break;
}
}
void writeAnyInt(std::ostream& str, const Any& any)
{
if (any.type() == typeid(char))
@ -201,7 +201,7 @@ namespace
str << RefAnyCast<std::string>(*itVal++);
break;
case 'z':
str << AnyCast<std::size_t>(*itVal++);
str << AnyCast<std::size_t>(*itVal++);
break;
case 'I':
case 'D':
@ -303,7 +303,7 @@ void format(std::string& result, const std::string& fmt, const Any& value)
{
std::vector<Any> args;
args.push_back(value);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -312,7 +312,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
std::vector<Any> args;
args.push_back(value1);
args.push_back(value2);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -322,7 +322,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value1);
args.push_back(value2);
args.push_back(value3);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -333,7 +333,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value2);
args.push_back(value3);
args.push_back(value4);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -345,7 +345,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value3);
args.push_back(value4);
args.push_back(value5);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -358,7 +358,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value4);
args.push_back(value5);
args.push_back(value6);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -372,7 +372,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value5);
args.push_back(value6);
args.push_back(value7);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -387,7 +387,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value6);
args.push_back(value7);
args.push_back(value8);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -403,7 +403,7 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value7);
args.push_back(value8);
args.push_back(value9);
format(result, fmt, args);
formatVector(result, fmt, args);
}
@ -420,16 +420,16 @@ void format(std::string& result, const std::string& fmt, const Any& value1, cons
args.push_back(value8);
args.push_back(value9);
args.push_back(value10);
format(result, fmt, args);
formatVector(result, fmt, args);
}
void format(std::string& result, const std::string& fmt, const std::vector<Any>& values)
void formatVector(std::string& result, const std::string& fmt, const std::vector<Any>& values)
{
std::string::const_iterator itFmt = fmt.begin();
std::string::const_iterator endFmt = fmt.end();
std::vector<Any>::const_iterator itVal = values.begin();
std::vector<Any>::const_iterator endVal = values.end();
std::vector<Any>::const_iterator endVal = values.end();
while (itFmt != endFmt)
{
switch (*itFmt)

View File

@ -57,7 +57,7 @@ std::string ObjectId::toString(const std::string& fmt) const
for (int i = 0; i < 12; ++i)
{
s += format(fmt, (unsigned int) _id[i]);
s += Poco::format(fmt, (unsigned int) _id[i]);
}
return s;
}

View File

@ -43,9 +43,9 @@ namespace Poco {
namespace MongoDB {
static const std::string keyCursor {"cursor"};
static const std::string keyFirstBatch {"firstBatch"};
static const std::string keyNextBatch {"nextBatch"};
[[ maybe_unused ]] static const std::string keyCursor {"cursor"};
[[ maybe_unused ]] static const std::string keyFirstBatch {"firstBatch"};
[[ maybe_unused ]] static const std::string keyNextBatch {"nextBatch"};
static Poco::Int64 cursorIdFromResponse(const MongoDB::Document& doc);
@ -131,7 +131,7 @@ OpMsgMessage& OpMsgCursor::next(Connection& connection)
connection.readResponse(_response);
}
else
#endif
#endif
{
_response.clear();
_query.setCursor(_cursorID, _batchSize);

View File

@ -79,7 +79,7 @@ namespace Net
/// Returns the value of the first name-value pair with the given name.
/// If no value with the given name has been found, the defaultValue is returned.
const std::vector<std::reference_wrapper<const std::string>> getAll(const std::string & name) const;
std::vector<std::string> getAll(const std::string & name) const;
/// Returns all values of all name-value pairs with the given name.
///
/// Returns an empty vector if there are no name-value pairs with the given name.

View File

@ -17,9 +17,9 @@
#include "Poco/NumberFormatter.h"
#include "Poco/NumberParser.h"
#include "Poco/String.h"
#include <charconv>
#include <format>
using Poco::NumberFormatter;
using Poco::NumberParser;
using Poco::icompare;
@ -75,7 +75,7 @@ void HTTPMessage::setContentLength(std::streamsize length)
erase(CONTENT_LENGTH);
}
std::streamsize HTTPMessage::getContentLength() const
{
const std::string& contentLength = get(CONTENT_LENGTH, EMPTY);
@ -98,7 +98,7 @@ void HTTPMessage::setContentLength64(Poco::Int64 length)
erase(CONTENT_LENGTH);
}
Poco::Int64 HTTPMessage::getContentLength64() const
{
const std::string& contentLength = get(CONTENT_LENGTH, EMPTY);
@ -133,13 +133,13 @@ void HTTPMessage::setChunkedTransferEncoding(bool flag)
setTransferEncoding(IDENTITY_TRANSFER_ENCODING);
}
bool HTTPMessage::getChunkedTransferEncoding() const
{
return icompare(getTransferEncoding(), CHUNKED_TRANSFER_ENCODING) == 0;
}
void HTTPMessage::setContentType(const std::string& mediaType)
{
if (mediaType.empty())
@ -154,7 +154,7 @@ void HTTPMessage::setContentType(const MediaType& mediaType)
setContentType(mediaType.toString());
}
const std::string& HTTPMessage::getContentType() const
{
return get(CONTENT_TYPE, UNKNOWN_CONTENT_TYPE);

View File

@ -102,9 +102,9 @@ const std::string& NameValueCollection::get(const std::string& name, const std::
return defaultValue;
}
const std::vector<std::reference_wrapper<const std::string>> NameValueCollection::getAll(const std::string& name) const
std::vector<std::string> NameValueCollection::getAll(const std::string& name) const
{
std::vector<std::reference_wrapper<const std::string>> values;
std::vector<std::string> values;
for (ConstIterator it = _map.find(name); it != _map.end(); it++)
if (it->first == name)
values.push_back(it->second);

View File

@ -42,9 +42,19 @@ endif ()
# But use 2 parallel jobs, since:
# - this is what llvm does
# - and I've verfied that lld-11 does not use all available CPU time (in peak) while linking one binary
if (CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO" AND ENABLE_THINLTO AND PARALLEL_LINK_JOBS GREATER 2)
message(STATUS "ThinLTO provides its own parallel linking - limiting parallel link jobs to 2.")
set (PARALLEL_LINK_JOBS 2)
if (CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO" AND ENABLE_THINLTO)
if (ARCH_AARCH64)
# aarch64 builds start to often fail with OOMs (reason not yet clear), for now let's limit the concurrency
message(STATUS "ThinLTO provides its own parallel linking - limiting parallel link jobs to 1.")
set (PARALLEL_LINK_JOBS 1)
if (LINKER_NAME MATCHES "lld")
math(EXPR LTO_JOBS ${NUMBER_OF_LOGICAL_CORES}/4)
set (CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO "${CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO} -Wl,--thinlto-jobs=${LTO_JOBS}")
endif()
elseif (PARALLEL_LINK_JOBS GREATER 2)
message(STATUS "ThinLTO provides its own parallel linking - limiting parallel link jobs to 2.")
set (PARALLEL_LINK_JOBS 2)
endif ()
endif()
message(STATUS "Building sub-tree with ${PARALLEL_COMPILE_JOBS} compile jobs and ${PARALLEL_LINK_JOBS} linker jobs (system: ${NUMBER_OF_LOGICAL_CORES} cores, ${TOTAL_PHYSICAL_MEMORY} MB RAM, 'OFF' means the native core count).")

2
contrib/avro vendored

@ -1 +1 @@
Subproject commit d43acc84d3d455b016f847d6666fbc3cd27f16a9
Subproject commit 545e7002683cbc2198164d93088ac8e4955b4628

View File

@ -125,7 +125,7 @@ configure_file("${AWS_SDK_CORE_DIR}/include/aws/core/SDKConfig.h.in"
"${CMAKE_CURRENT_BINARY_DIR}/include/aws/core/SDKConfig.h" @ONLY)
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)
configure_file("${AWS_CRT_DIR}/include/aws/crt/Config.h.in" "${CMAKE_CURRENT_BINARY_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})

2
contrib/azure vendored

@ -1 +1 @@
Subproject commit 92c94d7f37a43cc8fc4d466884a95f610c0593bf
Subproject commit ea3e19a7be08519134c643177d56c7484dfec884

2
contrib/grpc vendored

@ -1 +1 @@
Subproject commit 77b2737a709d43d8c6895e3f03ca62b00bd9201c
Subproject commit 1716359d2e28d304a250f9df0e6c0ccad03de8db

View File

@ -34,11 +34,7 @@ if (OS_LINUX)
# avoid spurious latencies and additional work associated with
# MADV_DONTNEED. See
# https://github.com/ClickHouse/ClickHouse/issues/11121 for motivation.
if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG")
set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
else()
set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000,prof:true,prof_active:false,background_thread:true")
endif()
set (JEMALLOC_CONFIG_MALLOC_CONF "percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000,prof:true,prof_active:false,background_thread:true")
else()
set (JEMALLOC_CONFIG_MALLOC_CONF "oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
endif()
@ -179,12 +175,19 @@ endif ()
target_compile_definitions(_jemalloc PRIVATE -DJEMALLOC_PROF=1)
# jemalloc provides support for two different libunwind flavors: the original HP libunwind and the one coming with gcc / g++ / libstdc++.
# The latter is identified by `JEMALLOC_PROF_LIBGCC` and uses `_Unwind_Backtrace` method instead of `unw_backtrace`.
# At the time ClickHouse uses LLVM libunwind which follows libgcc's way of backtracking.
# jemalloc provides support two unwind flavors:
# - JEMALLOC_PROF_LIBUNWIND - unw_backtrace() - gnu libunwind (compatible with llvm libunwind)
# - JEMALLOC_PROF_LIBGCC - _Unwind_Backtrace() - the original HP libunwind and the one coming with gcc / g++ / libstdc++.
#
# ClickHouse has to provide `unw_backtrace` method by the means of [commit 8e2b31e](https://github.com/ClickHouse/libunwind/commit/8e2b31e766dd502f6df74909e04a7dbdf5182eb1).
target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBGCC=1)
# But for JEMALLOC_PROF_LIBGCC it also calls _Unwind_Backtrace() during
# bootstraping of jemalloc, which may lead to deadlock, if the dlsym will do
# allocations somewhere (like glibc does prio 2.34, see [1]).
#
# [1]: https://sourceware.org/git/?p=glibc.git;a=commit;h=fada9018199c21c469ff0e731ef75c6020074ac9
#
# And since ClickHouse unwind already supports unw_backtrace() we can safely
# switch to it to avoid this deadlock.
target_compile_definitions (_jemalloc PRIVATE -DJEMALLOC_PROF_LIBUNWIND=1)
target_link_libraries (_jemalloc PRIVATE unwind)
# for RTLD_NEXT

View File

@ -4,3 +4,14 @@ It allows to integrate JEMalloc into CMake project.
- Added JEMALLOC_CONFIG_MALLOC_CONF substitution
- Add musl support (USE_MUSL)
- Also note, that darwin build requires JEMALLOC_PREFIX, while others do not
- JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE should be disabled
CLOCK_MONOTONIC_COARSE can go backwards after clock_adjtime(ADJ_FREQUENCY)
Let's disable it for now, and this menas that CLOCK_MONOTONIC will be used,
and this, should not be a problem, since:
- jemalloc do not call clock_gettime() that frequently
- the difference is CLOCK_MONOTONIC 20ns and CLOCK_MONOTONIC_COARSE 4ns
This can be done with the following command:
gg JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE | cut -d: -f1 | xargs sed -i 's@#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE@/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */@'

View File

@ -96,7 +96,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

View File

@ -96,7 +96,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

View File

@ -98,7 +98,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

View File

@ -99,7 +99,7 @@
/*
* Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
*/
#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE
/* #undef JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE */
/*
* Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.

View File

@ -54,7 +54,6 @@ set(SRCS
"${LIBPQ_SOURCE_DIR}/port/pgstrcasecmp.c"
"${LIBPQ_SOURCE_DIR}/port/thread.c"
"${LIBPQ_SOURCE_DIR}/port/path.c"
"${LIBPQ_SOURCE_DIR}/port/explicit_bzero.c"
)
add_library(_libpq ${SRCS})

2
contrib/libunwind vendored

@ -1 +1 @@
Subproject commit d6a01c46327e56fd86beb8aaa31591fcd9a6b7df
Subproject commit 8f28e64d15819d2d096badd598c7d85bebddb1f2

View File

@ -4,9 +4,6 @@ set(LIBUNWIND_CXX_SOURCES
"${LIBUNWIND_SOURCE_DIR}/src/libunwind.cpp"
"${LIBUNWIND_SOURCE_DIR}/src/Unwind-EHABI.cpp"
"${LIBUNWIND_SOURCE_DIR}/src/Unwind-seh.cpp")
if (APPLE)
set(LIBUNWIND_CXX_SOURCES ${LIBUNWIND_CXX_SOURCES} "${LIBUNWIND_SOURCE_DIR}/src/Unwind_AppleExtras.cpp")
endif ()
set(LIBUNWIND_C_SOURCES
"${LIBUNWIND_SOURCE_DIR}/src/UnwindLevel1.c"
@ -32,6 +29,7 @@ set_target_properties(unwind PROPERTIES FOLDER "contrib/libunwind-cmake")
target_include_directories(unwind SYSTEM BEFORE PUBLIC $<BUILD_INTERFACE:${LIBUNWIND_SOURCE_DIR}/include>)
target_compile_definitions(unwind PRIVATE -D_LIBUNWIND_NO_HEAP=1)
target_compile_definitions(unwind PRIVATE -D_LIBUNWIND_REMEMBER_STACK_ALLOC=1)
# NOTE: from this macros sizeof(unw_context_t)/sizeof(unw_cursor_t) is depends, so it should be set always
target_compile_definitions(unwind PUBLIC -D_LIBUNWIND_IS_NATIVE_ONLY)

2
contrib/openssl vendored

@ -1 +1 @@
Subproject commit ee2bb8513b28bf86b35404dd17a0e29305ca9e08
Subproject commit 66deddc1e53cda8706604a019777259372d1bd62

2
contrib/pocketfft vendored

@ -1 +1 @@
Subproject commit 9efd4da52cf8d28d14531d14e43ad9d913807546
Subproject commit f4c1aa8aa9ce79ad39e80f2c9c41b92ead90fda3

2
contrib/rocksdb vendored

@ -1 +1 @@
Subproject commit 3a0b80ca9d6eebb38fad7ea3f41dfc9db4f6a984
Subproject commit be366233921293bd07a84dc4ea6991858665f202

View File

@ -1,24 +1,17 @@
option (ENABLE_ROCKSDB "Enable rocksdb library" ${ENABLE_LIBRARIES})
option (ENABLE_ROCKSDB "Enable RocksDB" ${ENABLE_LIBRARIES})
if (NOT ENABLE_ROCKSDB)
message (STATUS "Not using rocksdb")
message (STATUS "Not using RocksDB")
return()
endif()
## this file is extracted from `contrib/rocksdb/CMakeLists.txt`
set(ROCKSDB_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/rocksdb")
list(APPEND CMAKE_MODULE_PATH "${ROCKSDB_SOURCE_DIR}/cmake/modules/")
set(PORTABLE ON)
## always disable jemalloc for rocksdb by default
## because it introduces non-standard jemalloc APIs
# Always disable jemalloc for rocksdb by default because it introduces non-standard jemalloc APIs
option(WITH_JEMALLOC "build with JeMalloc" OFF)
set(USE_SNAPPY OFF)
if (TARGET ch_contrib::snappy)
set(USE_SNAPPY ON)
endif()
option(WITH_SNAPPY "build with SNAPPY" ${USE_SNAPPY})
## lz4, zlib, zstd is enabled in ClickHouse by default
option(WITH_LIBURING "build with liburing" OFF) # TODO could try to enable this conditionally, depending on ClickHouse's ENABLE_LIBURING
# ClickHouse cannot be compiled without snappy, lz4, zlib, zstd
option(WITH_SNAPPY "build with SNAPPY" ON)
option(WITH_LZ4 "build with lz4" ON)
option(WITH_ZLIB "build with zlib" ON)
option(WITH_ZSTD "build with zstd" ON)
@ -26,78 +19,46 @@ option(WITH_ZSTD "build with zstd" ON)
# third-party/folly is only validated to work on Linux and Windows for now.
# So only turn it on there by default.
if(CMAKE_SYSTEM_NAME MATCHES "Linux|Windows")
if(MSVC AND MSVC_VERSION LESS 1910)
# Folly does not compile with MSVC older than VS2017
option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
else()
option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
endif()
option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
else()
option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
endif()
if( NOT DEFINED CMAKE_CXX_STANDARD )
set(CMAKE_CXX_STANDARD 11)
if(WITH_SNAPPY)
add_definitions(-DSNAPPY)
list(APPEND THIRDPARTY_LIBS ch_contrib::snappy)
endif()
if(MSVC)
option(WITH_XPRESS "build with windows built in compression" OFF)
include("${ROCKSDB_SOURCE_DIR}/thirdparty.inc")
else()
if(CMAKE_SYSTEM_NAME MATCHES "FreeBSD" AND NOT CMAKE_SYSTEM_NAME MATCHES "kFreeBSD")
# FreeBSD has jemalloc as default malloc
# but it does not have all the jemalloc files in include/...
set(WITH_JEMALLOC ON)
else()
if(WITH_JEMALLOC AND TARGET ch_contrib::jemalloc)
add_definitions(-DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE)
list(APPEND THIRDPARTY_LIBS ch_contrib::jemalloc)
endif()
endif()
if(WITH_SNAPPY)
add_definitions(-DSNAPPY)
list(APPEND THIRDPARTY_LIBS ch_contrib::snappy)
endif()
if(WITH_ZLIB)
add_definitions(-DZLIB)
list(APPEND THIRDPARTY_LIBS ch_contrib::zlib)
endif()
if(WITH_LZ4)
add_definitions(-DLZ4)
list(APPEND THIRDPARTY_LIBS ch_contrib::lz4)
endif()
if(WITH_ZSTD)
add_definitions(-DZSTD)
list(APPEND THIRDPARTY_LIBS ch_contrib::zstd)
endif()
if(WITH_ZLIB)
add_definitions(-DZLIB)
list(APPEND THIRDPARTY_LIBS ch_contrib::zlib)
endif()
if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
if(POWER9)
set(HAS_POWER9 1)
set(HAS_ALTIVEC 1)
else()
set(HAS_POWER8 1)
set(HAS_ALTIVEC 1)
endif(POWER9)
endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
if(WITH_LZ4)
add_definitions(-DLZ4)
list(APPEND THIRDPARTY_LIBS ch_contrib::lz4)
endif()
if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64|arm64|ARM64")
set(HAS_ARMV8_CRC 1)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
endif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64|arm64|ARM64")
if(WITH_ZSTD)
add_definitions(-DZSTD)
list(APPEND THIRDPARTY_LIBS ch_contrib::zstd)
endif()
option(PORTABLE "build a portable binary" ON)
if(ENABLE_AVX2 AND ENABLE_PCLMULQDQ)
if(ENABLE_SSE42 AND ENABLE_PCLMULQDQ)
add_definitions(-DHAVE_SSE42)
add_definitions(-DHAVE_PCLMUL)
endif()
if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64|AARCH64")
set (HAS_ARMV8_CRC 1)
# the original build descriptions set specific flags for ARM. These flags are already subsumed by ClickHouse's general
# ARM flags, see cmake/cpu_features.cmake
# set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
# set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
endif()
set (HAVE_THREAD_LOCAL 1)
if(HAVE_THREAD_LOCAL)
add_definitions(-DROCKSDB_SUPPORT_THREAD_LOCAL)
@ -107,8 +68,6 @@ if(CMAKE_SYSTEM_NAME MATCHES "Darwin")
add_definitions(-DOS_MACOSX)
elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
add_definitions(-DOS_LINUX)
elseif(CMAKE_SYSTEM_NAME MATCHES "SunOS")
add_definitions(-DOS_SOLARIS)
elseif(CMAKE_SYSTEM_NAME MATCHES "FreeBSD")
add_definitions(-DOS_FREEBSD)
elseif(CMAKE_SYSTEM_NAME MATCHES "Android")
@ -123,12 +82,10 @@ endif()
if (OS_LINUX)
add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
add_definitions(-DROCKSDB_AUXV_SYSAUXV_PRESENT)
add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
elseif (OS_FREEBSD)
add_definitions(-DROCKSDB_AUXV_SYSAUXV_PRESENT)
endif()
set(ROCKSDB_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/rocksdb")
include_directories(${ROCKSDB_SOURCE_DIR})
include_directories("${ROCKSDB_SOURCE_DIR}/include")
@ -136,11 +93,11 @@ if(WITH_FOLLY_DISTRIBUTED_MUTEX)
include_directories("${ROCKSDB_SOURCE_DIR}/third-party/folly")
endif()
# Main library source code
set(SOURCES
${ROCKSDB_SOURCE_DIR}/cache/cache.cc
${ROCKSDB_SOURCE_DIR}/cache/cache_entry_roles.cc
${ROCKSDB_SOURCE_DIR}/cache/cache_key.cc
${ROCKSDB_SOURCE_DIR}/cache/cache_reservation_manager.cc
${ROCKSDB_SOURCE_DIR}/cache/clock_cache.cc
${ROCKSDB_SOURCE_DIR}/cache/lru_cache.cc
${ROCKSDB_SOURCE_DIR}/cache/sharded_cache.cc
@ -156,6 +113,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_format.cc
${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_sequential_reader.cc
${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_writer.cc
${ROCKSDB_SOURCE_DIR}/db/blob/prefetch_buffer_collection.cc
${ROCKSDB_SOURCE_DIR}/db/builder.cc
${ROCKSDB_SOURCE_DIR}/db/c.cc
${ROCKSDB_SOURCE_DIR}/db/column_family.cc
@ -229,6 +187,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/env/file_system_tracer.cc
${ROCKSDB_SOURCE_DIR}/env/fs_remap.cc
${ROCKSDB_SOURCE_DIR}/env/mock_env.cc
${ROCKSDB_SOURCE_DIR}/env/unique_id_gen.cc
${ROCKSDB_SOURCE_DIR}/file/delete_scheduler.cc
${ROCKSDB_SOURCE_DIR}/file/file_prefetch_buffer.cc
${ROCKSDB_SOURCE_DIR}/file/file_util.cc
@ -247,6 +206,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/memory/concurrent_arena.cc
${ROCKSDB_SOURCE_DIR}/memory/jemalloc_nodump_allocator.cc
${ROCKSDB_SOURCE_DIR}/memory/memkind_kmem_allocator.cc
${ROCKSDB_SOURCE_DIR}/memory/memory_allocator.cc
${ROCKSDB_SOURCE_DIR}/memtable/alloc_tracker.cc
${ROCKSDB_SOURCE_DIR}/memtable/hash_linklist_rep.cc
${ROCKSDB_SOURCE_DIR}/memtable/hash_skiplist_rep.cc
@ -322,6 +282,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/table/table_factory.cc
${ROCKSDB_SOURCE_DIR}/table/table_properties.cc
${ROCKSDB_SOURCE_DIR}/table/two_level_iterator.cc
${ROCKSDB_SOURCE_DIR}/table/unique_id.cc
${ROCKSDB_SOURCE_DIR}/test_util/sync_point.cc
${ROCKSDB_SOURCE_DIR}/test_util/sync_point_impl.cc
${ROCKSDB_SOURCE_DIR}/test_util/testutil.cc
@ -333,9 +294,12 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/tools/ldb_tool.cc
${ROCKSDB_SOURCE_DIR}/tools/sst_dump_tool.cc
${ROCKSDB_SOURCE_DIR}/tools/trace_analyzer_tool.cc
${ROCKSDB_SOURCE_DIR}/trace_replay/trace_replay.cc
${ROCKSDB_SOURCE_DIR}/trace_replay/block_cache_tracer.cc
${ROCKSDB_SOURCE_DIR}/trace_replay/io_tracer.cc
${ROCKSDB_SOURCE_DIR}/trace_replay/trace_record_handler.cc
${ROCKSDB_SOURCE_DIR}/trace_replay/trace_record_result.cc
${ROCKSDB_SOURCE_DIR}/trace_replay/trace_record.cc
${ROCKSDB_SOURCE_DIR}/trace_replay/trace_replay.cc
${ROCKSDB_SOURCE_DIR}/util/coding.cc
${ROCKSDB_SOURCE_DIR}/util/compaction_job_stats_impl.cc
${ROCKSDB_SOURCE_DIR}/util/comparator.cc
@ -347,6 +311,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/util/murmurhash.cc
${ROCKSDB_SOURCE_DIR}/util/random.cc
${ROCKSDB_SOURCE_DIR}/util/rate_limiter.cc
${ROCKSDB_SOURCE_DIR}/util/regex.cc
${ROCKSDB_SOURCE_DIR}/util/ribbon_config.cc
${ROCKSDB_SOURCE_DIR}/util/slice.cc
${ROCKSDB_SOURCE_DIR}/util/file_checksum_helper.cc
@ -362,18 +327,23 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db_impl_filesnapshot.cc
${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_dump_tool.cc
${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_file.cc
${ROCKSDB_SOURCE_DIR}/utilities/cache_dump_load.cc
${ROCKSDB_SOURCE_DIR}/utilities/cache_dump_load_impl.cc
${ROCKSDB_SOURCE_DIR}/utilities/cassandra/cassandra_compaction_filter.cc
${ROCKSDB_SOURCE_DIR}/utilities/cassandra/format.cc
${ROCKSDB_SOURCE_DIR}/utilities/cassandra/merge_operator.cc
${ROCKSDB_SOURCE_DIR}/utilities/checkpoint/checkpoint_impl.cc
${ROCKSDB_SOURCE_DIR}/utilities/compaction_filters.cc
${ROCKSDB_SOURCE_DIR}/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
${ROCKSDB_SOURCE_DIR}/utilities/debug.cc
${ROCKSDB_SOURCE_DIR}/utilities/env_mirror.cc
${ROCKSDB_SOURCE_DIR}/utilities/env_timed.cc
${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_env.cc
${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_fs.cc
${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_secondary_cache.cc
${ROCKSDB_SOURCE_DIR}/utilities/leveldb_options/leveldb_options.cc
${ROCKSDB_SOURCE_DIR}/utilities/memory/memory_util.cc
${ROCKSDB_SOURCE_DIR}/utilities/merge_operators.cc
${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/bytesxor.cc
${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/max.cc
${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/put.cc
@ -393,6 +363,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/utilities/simulator_cache/sim_cache.cc
${ROCKSDB_SOURCE_DIR}/utilities/table_properties_collectors/compact_on_deletion_collector.cc
${ROCKSDB_SOURCE_DIR}/utilities/trace/file_trace_reader_writer.cc
${ROCKSDB_SOURCE_DIR}/utilities/trace/replayer_impl.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/lock_manager.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_tracker.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_manager.cc
@ -411,6 +382,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn_db.cc
${ROCKSDB_SOURCE_DIR}/utilities/ttl/db_ttl_impl.cc
${ROCKSDB_SOURCE_DIR}/utilities/wal_filter.cc
${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index.cc
${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index_internal.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/concurrent_tree.cc
@ -425,7 +397,7 @@ set(SOURCES
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/standalone_port.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/util/dbt.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/util/memarena.cc
rocksdb_build_version.cc)
build_version.cc) # generated by hand
if(ENABLE_SSE42 AND ENABLE_PCLMULQDQ)
set_source_files_properties(
@ -462,5 +434,6 @@ endif()
add_library(_rocksdb ${SOURCES})
add_library(ch_contrib::rocksdb ALIAS _rocksdb)
target_link_libraries(_rocksdb PRIVATE ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
# SYSTEM is required to overcome some issues
target_include_directories(_rocksdb SYSTEM BEFORE INTERFACE "${ROCKSDB_SOURCE_DIR}/include")

View File

@ -26,7 +26,10 @@ RUN apt-get update \
zstd \
--yes --no-install-recommends \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
&& rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/* \
&& groupadd --system --gid 1000 clickhouse \
&& useradd --system --gid 1000 --uid 1000 -m clickhouse
# ^ For some reason, groupadd and useradd are needed for tests with 'expect', but I don't know, why.
COPY requirements.txt /
RUN pip3 install --no-cache-dir -r /requirements.txt

View File

@ -9,7 +9,7 @@ trap 'kill $(jobs -pr) ||:' EXIT
stage=${stage:-}
# Compiler version, normally set by Dockerfile
export LLVM_VERSION=${LLVM_VERSION:-17}
export LLVM_VERSION=${LLVM_VERSION:-18}
# A variable to pass additional flags to CMake.
# Here we explicitly default it to nothing so that bash doesn't complain about
@ -284,6 +284,11 @@ function run_tests
NPROC=1
fi
export CLICKHOUSE_CONFIG_DIR=$FASTTEST_DATA
export CLICKHOUSE_CONFIG="$FASTTEST_DATA/config.xml"
export CLICKHOUSE_USER_FILES="$FASTTEST_DATA/user_files"
export CLICKHOUSE_SCHEMA_FILES="$FASTTEST_DATA/format_schemas"
local test_opts=(
--hung-check
--fast-tests-only

View File

@ -33,13 +33,9 @@ RUN apt-get update \
COPY requirements.txt /
RUN pip3 install --no-cache-dir -r /requirements.txt
COPY * /
ENV FUZZER_ARGS="-max_total_time=60"
SHELL ["/bin/bash", "-c"]
CMD set -o pipefail \
&& timeout -s 9 1h /run_libfuzzer.py 2>&1 | ts "$(printf '%%Y-%%m-%%d %%H:%%M:%%S\t')" | tee main.log
# docker run --network=host --volume <workspace>:/workspace -e PR_TO_TEST=<> -e SHA_TO_TEST=<> clickhouse/libfuzzer

View File

@ -16,11 +16,17 @@ dpkg -i package_folder/clickhouse-client_*.deb
ln -s /usr/share/clickhouse-test/clickhouse-test /usr/bin/clickhouse-test
# shellcheck disable=SC1091
source /utils.lib
# install test configs
/usr/share/clickhouse-test/config/install.sh
azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --silent --inMemoryPersistence &
./setup_minio.sh stateful
./mc admin trace clickminio > /test_output/minio.log &
MC_ADMIN_PID=$!
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
@ -251,6 +257,8 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
sudo clickhouse stop --pid-path /var/run/clickhouse-server2 ||:
fi
# Kill minio admin client to stop collecting logs
kill $MC_ADMIN_PID
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server.log ||:
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.zst ||:
@ -272,3 +280,5 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
mv /var/log/clickhouse-server/stderr1.log /test_output/ ||:
mv /var/log/clickhouse-server/stderr2.log /test_output/ ||:
fi
collect_core_dumps

View File

@ -86,6 +86,7 @@ RUN curl -L --no-verbose -O 'https://archive.apache.org/dist/hadoop/common/hadoo
ENV MINIO_ROOT_USER="clickhouse"
ENV MINIO_ROOT_PASSWORD="clickhouse"
ENV EXPORT_S3_STORAGE_POLICIES=1
ENV CLICKHOUSE_GRPC_CLIENT="/usr/share/clickhouse-utils/grpc-client/clickhouse-grpc-client.py"
RUN npm install -g azurite@3.30.0 \
&& npm install -g tslib && npm install -g node

View File

@ -8,6 +8,7 @@ cryptography==3.4.8
dbus-python==1.2.18
distro==1.7.0
docutils==0.17.1
grpcio==1.47.0
gyp==0.1
httplib2==0.20.2
idna==3.3
@ -28,6 +29,7 @@ packaging==24.1
pandas==1.5.3
pip==24.1.1
pipdeptree==2.23.0
protobuf==4.25.3
pyarrow==15.0.0
pyasn1==0.4.8
PyJWT==2.3.0

View File

@ -6,22 +6,30 @@ source /setup_export_logs.sh
# fail on errors, verbose and export all env variables
set -e -x -a
MAX_RUN_TIME=${MAX_RUN_TIME:-10800}
MAX_RUN_TIME=$((MAX_RUN_TIME == 0 ? 10800 : MAX_RUN_TIME))
MAX_RUN_TIME=${MAX_RUN_TIME:-7200}
MAX_RUN_TIME=$((MAX_RUN_TIME == 0 ? 7200 : MAX_RUN_TIME))
USE_DATABASE_REPLICATED=${USE_DATABASE_REPLICATED:=0}
USE_SHARED_CATALOG=${USE_SHARED_CATALOG:=0}
RUN_SEQUENTIAL_TESTS_IN_PARALLEL=0
if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]] || [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
RUN_SEQUENTIAL_TESTS_IN_PARALLEL=0
fi
# Choose random timezone for this test run.
#
# NOTE: that clickhouse-test will randomize session_timezone by itself as well
# (it will choose between default server timezone and something specific).
TZ="$(rg -v '#' /usr/share/zoneinfo/zone.tab | awk '{print $3}' | shuf | head -n1)"
echo "Choosen random timezone $TZ"
echo "Chosen random timezone $TZ"
ln -snf "/usr/share/zoneinfo/$TZ" /etc/localtime && echo "$TZ" > /etc/timezone
dpkg -i package_folder/clickhouse-common-static_*.deb
dpkg -i package_folder/clickhouse-common-static-dbg_*.deb
# Accept failure in the next two commands until 24.4 is released (for compatibility and Bugfix validation run)
dpkg -i package_folder/clickhouse-odbc-bridge_*.deb || true
dpkg -i package_folder/clickhouse-library-bridge_*.deb || true
dpkg -i package_folder/clickhouse-odbc-bridge_*.deb
dpkg -i package_folder/clickhouse-library-bridge_*.deb
dpkg -i package_folder/clickhouse-server_*.deb
dpkg -i package_folder/clickhouse-client_*.deb
@ -46,6 +54,9 @@ source /utils.lib
/usr/share/clickhouse-test/config/install.sh
./setup_minio.sh stateless
./mc admin trace clickminio > /test_output/minio.log &
MC_ADMIN_PID=$!
./setup_hdfs_minicluster.sh
config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
@ -58,12 +69,6 @@ if [[ -n "$BUGFIX_VALIDATE_CHECK" ]] && [[ "$BUGFIX_VALIDATE_CHECK" -eq 1 ]]; th
rm /etc/clickhouse-server/users.d/s3_cache_new.xml
rm /etc/clickhouse-server/config.d/zero_copy_destructive_operations.xml
#todo: remove these after 24.3 released.
sudo sed -i "s|<object_storage_type>azure<|<object_storage_type>azure_blob_storage<|" /etc/clickhouse-server/config.d/azure_storage_conf.xml
#todo: remove these after 24.3 released.
sudo sed -i "s|<object_storage_type>local<|<object_storage_type>local_blob_storage<|" /etc/clickhouse-server/config.d/storage_conf.xml
function remove_keeper_config()
{
sudo sed -i "/<$1>$2<\/$1>/d" /etc/clickhouse-server/config.d/keeper_port.xml
@ -96,10 +101,57 @@ if [ "$NUM_TRIES" -gt "1" ]; then
mkdir -p /var/run/clickhouse-server
fi
# Run a CH instance to execute sequential tests on it in parallel with all other tests.
if [[ "$RUN_SEQUENTIAL_TESTS_IN_PARALLEL" -eq 1 ]]; then
mkdir -p /var/run/clickhouse-server3 /etc/clickhouse-server3 /var/lib/clickhouse3
cp -r -L /etc/clickhouse-server/* /etc/clickhouse-server3/
sudo chown clickhouse:clickhouse /var/run/clickhouse-server3 /var/lib/clickhouse3 /etc/clickhouse-server3/
sudo chown -R clickhouse:clickhouse /etc/clickhouse-server3/*
function replace(){
sudo find /etc/clickhouse-server3/ -type f -name '*.xml' -exec sed -i "$1" {} \;
}
replace "s|<port>9000</port>|<port>19000</port>|g"
replace "s|<port>9440</port>|<port>19440</port>|g"
replace "s|<port>9988</port>|<port>19988</port>|g"
replace "s|<port>9234</port>|<port>19234</port>|g"
replace "s|<port>9181</port>|<port>19181</port>|g"
replace "s|<https_port>8443</https_port>|<https_port>18443</https_port>|g"
replace "s|<tcp_port>9000</tcp_port>|<tcp_port>19000</tcp_port>|g"
replace "s|<tcp_port>9181</tcp_port>|<tcp_port>19181</tcp_port>|g"
replace "s|<tcp_port_secure>9440</tcp_port_secure>|<tcp_port_secure>19440</tcp_port_secure>|g"
replace "s|<tcp_with_proxy_port>9010</tcp_with_proxy_port>|<tcp_with_proxy_port>19010</tcp_with_proxy_port>|g"
replace "s|<mysql_port>9004</mysql_port>|<mysql_port>19004</mysql_port>|g"
replace "s|<postgresql_port>9005</postgresql_port>|<postgresql_port>19005</postgresql_port>|g"
replace "s|<interserver_http_port>9009</interserver_http_port>|<interserver_http_port>19009</interserver_http_port>|g"
replace "s|8123|18123|g"
replace "s|/var/lib/clickhouse/|/var/lib/clickhouse3/|g"
replace "s|/etc/clickhouse-server/|/etc/clickhouse-server3/|g"
# distributed cache
replace "s|<tcp_port>10001</tcp_port>|<tcp_port>10003</tcp_port>|g"
replace "s|<tcp_port>10002</tcp_port>|<tcp_port>10004</tcp_port>|g"
sudo -E -u clickhouse /usr/bin/clickhouse server --daemon --config /etc/clickhouse-server3/config.xml \
--pid-file /var/run/clickhouse-server3/clickhouse-server.pid \
-- --path /var/lib/clickhouse3/ --logger.stderr /var/log/clickhouse-server/stderr3.log \
--logger.log /var/log/clickhouse-server/clickhouse-server3.log --logger.errorlog /var/log/clickhouse-server/clickhouse-server3.err.log \
--tcp_port 19000 --tcp_port_secure 19440 --http_port 18123 --https_port 18443 --interserver_http_port 19009 --tcp_with_proxy_port 19010 \
--prometheus.port 19988 --keeper_server.raft_configuration.server.port 19234 --keeper_server.tcp_port 19181 \
--mysql_port 19004 --postgresql_port 19005
for _ in {1..100}
do
clickhouse-client --port 19000 --query "SELECT 1" && break
sleep 1
done
fi
# simplest way to forward env variables to server
sudo -E -u clickhouse /usr/bin/clickhouse-server --config /etc/clickhouse-server/config.xml --daemon --pid-file /var/run/clickhouse-server/clickhouse-server.pid
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
sudo sed -i "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_1/</filesystem_caches_path>|" /etc/clickhouse-server1/config.d/filesystem_caches_path.xml
sudo sed -i "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_2/</filesystem_caches_path>|" /etc/clickhouse-server2/config.d/filesystem_caches_path.xml
@ -136,7 +188,7 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
MAX_RUN_TIME=$((MAX_RUN_TIME != 0 ? MAX_RUN_TIME : 9000)) # set to 2.5 hours if 0 (unlimited)
fi
if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
sudo cat /etc/clickhouse-server1/config.d/filesystem_caches_path.xml \
| sed "s|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches/</filesystem_caches_path>|<filesystem_caches_path>/var/lib/clickhouse/filesystem_caches_1/</filesystem_caches_path>|" \
> /etc/clickhouse-server1/config.d/filesystem_caches_path.xml.tmp
@ -216,15 +268,15 @@ function run_tests()
ADDITIONAL_OPTIONS+=('--no-random-merge-tree-settings')
fi
if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
ADDITIONAL_OPTIONS+=('--shared-catalog')
fi
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
ADDITIONAL_OPTIONS+=('--replicated-database')
# Too many tests fail for DatabaseReplicated in parallel.
ADDITIONAL_OPTIONS+=('--jobs')
ADDITIONAL_OPTIONS+=('2')
ADDITIONAL_OPTIONS+=('3')
elif [[ 1 == $(clickhouse-client --query "SELECT value LIKE '%SANITIZE_COVERAGE%' FROM system.build_options WHERE name = 'CXX_FLAGS'") ]]; then
# Coverage on a per-test basis could only be collected sequentially.
# Do not set the --jobs parameter.
@ -232,7 +284,11 @@ function run_tests()
else
# All other configurations are OK.
ADDITIONAL_OPTIONS+=('--jobs')
ADDITIONAL_OPTIONS+=('8')
ADDITIONAL_OPTIONS+=('5')
fi
if [[ "$RUN_SEQUENTIAL_TESTS_IN_PARALLEL" -eq 1 ]]; then
ADDITIONAL_OPTIONS+=('--run-sequential-tests-in-parallel')
fi
if [[ -n "$RUN_BY_HASH_NUM" ]] && [[ -n "$RUN_BY_HASH_TOTAL" ]]; then
@ -256,7 +312,7 @@ function run_tests()
try_run_with_retry 10 clickhouse-client -q "insert into system.zookeeper (name, path, value) values ('auxiliary_zookeeper2', '/test/chroot/', '')"
set +e
timeout -s TERM --preserve-status 120m clickhouse-test --testname --shard --zookeeper --check-zookeeper-session --hung-check --print-time \
timeout -k 60m -s TERM --preserve-status 140m clickhouse-test --testname --shard --zookeeper --check-zookeeper-session --hung-check --print-time \
--no-drop-if-fail --test-runs "$NUM_TRIES" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
| ts '%Y-%m-%d %H:%M:%S' \
| tee -a test_output/test_result.txt
@ -267,7 +323,7 @@ export -f run_tests
# This should be enough to setup job and collect artifacts
TIMEOUT=$((MAX_RUN_TIME - 300))
TIMEOUT=$((MAX_RUN_TIME - 700))
if [ "$NUM_TRIES" -gt "1" ]; then
# We don't run tests with Ordinary database in PRs, only in master.
# So run new/changed tests with Ordinary at least once in flaky check.
@ -296,7 +352,7 @@ do
err=$(clickhouse-client -q "select * from system.$table into outfile '/test_output/$table.tsv.gz' format TSVWithNamesAndTypes")
echo "$err"
[[ "0" != "${#err}" ]] && failed_to_save_logs=1
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
err=$( { clickhouse-client --port 19000 -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
@ -305,7 +361,7 @@ do
[[ "0" != "${#err}" ]] && failed_to_save_logs=1
fi
if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
err=$( { clickhouse-client --port 19000 -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst; } 2>&1 )
echo "$err"
[[ "0" != "${#err}" ]] && failed_to_save_logs=1
@ -316,19 +372,33 @@ done
# Why do we read data with clickhouse-local?
# Because it's the simplest way to read it when server has crashed.
sudo clickhouse stop ||:
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
if [[ "$RUN_SEQUENTIAL_TESTS_IN_PARALLEL" -eq 1 ]]; then
sudo clickhouse stop --pid-path /var/run/clickhouse-server3 ||:
fi
if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
sudo clickhouse stop --pid-path /var/run/clickhouse-server1 ||:
sudo clickhouse stop --pid-path /var/run/clickhouse-server2 ||:
fi
if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
sudo clickhouse stop --pid-path /var/run/clickhouse-server1 ||:
fi
# Kill minio admin client to stop collecting logs
kill $MC_ADMIN_PID
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server.log ||:
rg -A50 -Fa "============" /var/log/clickhouse-server/stderr.log ||:
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.zst &
if [[ "$RUN_SEQUENTIAL_TESTS_IN_PARALLEL" -eq 1 ]]; then
rg -Fa "<Fatal>" /var/log/clickhouse-server3/clickhouse-server.log ||:
rg -A50 -Fa "============" /var/log/clickhouse-server3/stderr.log ||:
zstd --threads=0 < /var/log/clickhouse-server3/clickhouse-server.log > /test_output/clickhouse-server3.log.zst &
fi
data_path_config="--path=/var/lib/clickhouse/"
if [[ -n "$USE_S3_STORAGE_FOR_MERGE_TREE" ]] && [[ "$USE_S3_STORAGE_FOR_MERGE_TREE" -eq 1 ]]; then
# We need s3 storage configuration (but it's more likely that clickhouse-local will fail for some reason)
@ -348,12 +418,17 @@ if [ $failed_to_save_logs -ne 0 ]; then
for table in query_log zookeeper_log trace_log transactions_info_log metric_log blob_storage_log error_log
do
clickhouse-local "$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
if [[ "$RUN_SEQUENTIAL_TESTS_IN_PARALLEL" -eq 1 ]]; then
clickhouse-local --path /var/lib/clickhouse3/ --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.3.tsv.zst ||:
fi
if [[ "$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
if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
clickhouse-local --path /var/lib/clickhouse1/ --only-system-tables --stacktrace -q "select * from system.$table format TSVWithNamesAndTypes" | zstd --threads=0 > /test_output/$table.1.tsv.zst ||:
fi
done
@ -389,7 +464,14 @@ rm -rf /var/lib/clickhouse/data/system/*/
tar -chf /test_output/store.tar /var/lib/clickhouse/store ||:
tar -chf /test_output/metadata.tar /var/lib/clickhouse/metadata/*.sql ||:
if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
if [[ "$RUN_SEQUENTIAL_TESTS_IN_PARALLEL" -eq 1 ]]; then
rm -rf /var/lib/clickhouse3/data/system/*/
tar -chf /test_output/store.tar /var/lib/clickhouse3/store ||:
tar -chf /test_output/metadata.tar /var/lib/clickhouse3/metadata/*.sql ||:
fi
if [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server1.log ||:
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server2.log ||:
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server1.log > /test_output/clickhouse-server1.log.zst ||:
@ -400,9 +482,11 @@ if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]
tar -chf /test_output/coordination2.tar /var/lib/clickhouse2/coordination ||:
fi
if [[ -n "$USE_SHARED_CATALOG" ]] && [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
if [[ "$USE_SHARED_CATALOG" -eq 1 ]]; then
rg -Fa "<Fatal>" /var/log/clickhouse-server/clickhouse-server1.log ||:
zstd --threads=0 < /var/log/clickhouse-server/clickhouse-server1.log > /test_output/clickhouse-server1.log.zst ||:
mv /var/log/clickhouse-server/stderr1.log /test_output/ ||:
tar -chf /test_output/coordination1.tar /var/lib/clickhouse1/coordination ||:
fi
collect_core_dumps

View File

@ -10,7 +10,7 @@ cd hadoop-3.3.1
export JAVA_HOME=/usr
mkdir -p target/test/data
chown clickhouse ./target/test/data
sudo -E -u clickhouse bin/mapred minicluster -format -nomr -nnport 12222 >> /test_output/garbage.log 2>&1 &
sudo -E -u clickhouse bin/mapred minicluster -format -nomr -nnport 12222 >> /test_output/hdfs_minicluster.log 2>&1 &
while ! nc -z localhost 12222; do
sleep 1

View File

@ -1,8 +1,5 @@
#!/bin/bash
# core.COMM.PID-TID
sysctl kernel.core_pattern='core.%e.%p-%P'
OK="\tOK\t\\N\t"
FAIL="\tFAIL\t\\N\t"
@ -315,12 +312,4 @@ function collect_query_and_trace_logs()
done
}
function collect_core_dumps()
{
find . -type f -maxdepth 1 -name 'core.*' | while read -r core; do
zstd --threads=0 "$core"
mv "$core.zst" /test_output/
done
}
# vi: ft=bash

View File

@ -1,5 +1,10 @@
#!/bin/bash
# core.COMM.PID-TID
sysctl kernel.core_pattern='core.%e.%p-%P'
# ASAN doesn't work with suid_dumpable=2
sysctl fs.suid_dumpable=1
function run_with_retry()
{
if [[ $- =~ e ]]; then
@ -48,4 +53,12 @@ function timeout_with_logging() {
return $exit_code
}
function collect_core_dumps()
{
find . -type f -maxdepth 1 -name 'core.*' | while read -r core; do
zstd --threads=0 "$core"
mv "$core.zst" /test_output/
done
}
# vi: ft=bash

View File

@ -21,6 +21,9 @@ source /attach_gdb.lib
# shellcheck source=../stateless/stress_tests.lib
source /stress_tests.lib
# shellcheck disable=SC1091
source /utils.lib
install_packages package_folder
# Thread Fuzzer allows to check more permutations of possible thread scheduling

View File

@ -3,7 +3,7 @@ aiosignal==1.3.1
astroid==3.1.0
async-timeout==4.0.3
attrs==23.2.0
black==23.12.0
black==24.4.2
boto3==1.34.131
botocore==1.34.131
certifi==2024.6.2

View File

@ -17,6 +17,7 @@ ENV DEBIAN_FRONTEND=noninteractive LLVM_VERSION=18
RUN apt-get update \
&& apt-get install \
sudo \
apt-transport-https \
apt-utils \
ca-certificates \

View File

@ -11,6 +11,7 @@ TIMEOUT_SIGN = "[ Timeout! "
UNKNOWN_SIGN = "[ UNKNOWN "
SKIPPED_SIGN = "[ SKIPPED "
HUNG_SIGN = "Found hung queries in processlist"
SERVER_DIED_SIGN = "Server died, terminating all processes"
DATABASE_SIGN = "Database: "
SUCCESS_FINISH_SIGNS = ["All tests have finished", "No tests were run"]
@ -25,6 +26,7 @@ def process_test_log(log_path, broken_tests):
failed = 0
success = 0
hung = False
server_died = False
retries = False
success_finish = False
test_results = []
@ -41,6 +43,8 @@ def process_test_log(log_path, broken_tests):
if HUNG_SIGN in line:
hung = True
break
if SERVER_DIED_SIGN in line:
server_died = True
if RETRIES_SIGN in line:
retries = True
if any(
@ -123,6 +127,7 @@ def process_test_log(log_path, broken_tests):
failed,
success,
hung,
server_died,
success_finish,
retries,
test_results,
@ -150,6 +155,7 @@ def process_result(result_path, broken_tests):
failed,
success,
hung,
server_died,
success_finish,
retries,
test_results,
@ -165,6 +171,10 @@ def process_result(result_path, broken_tests):
description = "Some queries hung, "
state = "failure"
test_results.append(("Some queries hung", "FAIL", "0", ""))
elif server_died:
description = "Server died, "
state = "failure"
test_results.append(("Server died", "FAIL", "0", ""))
elif not success_finish:
description = "Tests are not finished, "
state = "failure"
@ -218,5 +228,20 @@ if __name__ == "__main__":
state, description, test_results = process_result(args.in_results_dir, broken_tests)
logging.info("Result parsed")
status = (state, description)
def test_result_comparator(item):
# sort by status then by check name
order = {
"FAIL": 0,
"Timeout": 1,
"NOT_FAILED": 2,
"BROKEN": 3,
"OK": 4,
"SKIPPED": 5,
}
return order.get(item[1], 10), str(item[0]), item[1]
test_results.sort(key=test_result_comparator)
write_results(args.out_results_file, args.out_status_file, test_results, status)
logging.info("Result written")

View File

@ -11,7 +11,7 @@ This is for the case when you have Linux machine and want to use it to build `cl
The cross-build for RISC-V 64 is based on the [Build instructions](../development/build.md), follow them first.
## Install Clang-16
## Install Clang-18
Follow the instructions from https://apt.llvm.org/ for your Ubuntu or Debian setup or do
```

View File

@ -226,15 +226,59 @@ Other IDEs you can use are [Sublime Text](https://www.sublimetext.com/), [Visual
## Writing Code {#writing-code}
The description of ClickHouse architecture can be found here: https://clickhouse.com/docs/en/development/architecture/
Below you can find some quick links which may be useful when writing code for ClickHouse:
The Code Style Guide: https://clickhouse.com/docs/en/development/style/
- [ClickHouse architecture description](https://clickhouse.com/docs/en/development/architecture/).
- [The code style guide](https://clickhouse.com/docs/en/development/style/).
- [Adding third-party libraries](https://clickhouse.com/docs/en/development/contrib/#adding-third-party-libraries)
- [Writing tests](https://clickhouse.com/docs/en/development/tests/)
- [List of open issues](https://github.com/ClickHouse/ClickHouse/issues?q=is%3Aopen+is%3Aissue+label%3Ahacktoberfest)
Adding third-party libraries: https://clickhouse.com/docs/en/development/contrib/#adding-third-party-libraries
## Writing Documentation {#writing-documentation}
Writing tests: https://clickhouse.com/docs/en/development/tests/
As part of every pull request which adds a new feature, it is necessary to write documentation for it. If you'd like to preview your documentation changes the instructions for how to build the documentation page locally are available in the README.md file [here](https://github.com/ClickHouse/clickhouse-docs). When adding a new function to ClickHouse you can use the template below as a guide:
List of tasks: https://github.com/ClickHouse/ClickHouse/issues?q=is%3Aopen+is%3Aissue+label%3Ahacktoberfest
```markdown
# newFunctionName
A short description of the function goes here. It should describe briefly what it does and a typical usage case.
**Syntax**
\```sql
newFunctionName(arg1, arg2[, arg3])
\```
**Arguments**
- `arg1` — Description of the argument. [DataType](../data-types/float.md)
- `arg2` — Description of the argument. [DataType](../data-types/float.md)
- `arg3` — Description of optional argument (optional). [DataType](../data-types/float.md)
**Implementation Details**
A description of implementation details if relevant.
**Returned value**
- Returns {insert what the function returns here}. [DataType](../data-types/float.md)
**Example**
Query:
\```sql
SELECT 'write your example query here';
\```
Response:
\```response
┌───────────────────────────────────┐
│ the result of the query │
└───────────────────────────────────┘
\```
```
## Test Data {#test-data}

View File

@ -75,7 +75,7 @@ SETTINGS
Possible values:
- unordered — With unordered mode, the set of all already processed files is tracked with persistent nodes in ZooKeeper.
- ordered — With ordered mode, only the max name of the successfully consumed file, and the names of files that will be retried after unsuccessful loading attempt are being stored in ZooKeeper.
- ordered — With ordered mode, the files are processed in lexicographic order. It means that if file named 'BBB' was processed at some point and later on a file named 'AA' is added to the bucket, it will be ignored. Only the max name (in lexicographic sense) of the successfully consumed file, and the names of files that will be retried after unsuccessful loading attempt are being stored in ZooKeeper.
Default value: `ordered` in versions before 24.6. Starting with 24.6 there is no default value, the setting becomes required to be specified manually. For tables created on earlier versions the default value will remain `Ordered` for compatibility.

View File

@ -15,7 +15,7 @@ You have four options for getting up and running with ClickHouse:
- **[ClickHouse Cloud](https://clickhouse.com/cloud/):** The official ClickHouse as a service, - built by, maintained and supported by the creators of ClickHouse
- **[Quick Install](#quick-install):** an easy-to-download binary for testing and developing with ClickHouse
- **[Production Deployments](#available-installation-options):** ClickHouse can run on any Linux, FreeBSD, or macOS with x86-64, ARM, or PowerPC64LE CPU architecture
- **[Production Deployments](#available-installation-options):** ClickHouse can run on any Linux, FreeBSD, or macOS with x86-64, modern ARM (ARMv8.2-A up), or PowerPC64LE CPU architecture
- **[Docker Image](https://hub.docker.com/r/clickhouse/clickhouse-server/):** use the official Docker image in Docker Hub
## ClickHouse Cloud

View File

@ -185,6 +185,7 @@ You can pass parameters to `clickhouse-client` (all parameters have a default va
- `--format, -f` Use the specified default format to output the result.
- `--vertical, -E` If specified, use the [Vertical format](../interfaces/formats.md#vertical) by default to output the result. This is the same as `format=Vertical`. In this format, each value is printed on a separate line, which is helpful when displaying wide tables.
- `--time, -t` If specified, print the query execution time to stderr in non-interactive mode.
- `--memory-usage` If specified, print memory usage to stderr in non-interactive mode]. Possible values: 'none' - do not print memory usage, 'default' - print number of bytes, 'readable' - print memory usage in human-readable format.
- `--stacktrace` If specified, also print the stack trace if an exception occurs.
- `--config-file` The name of the configuration file.
- `--secure` If specified, will connect to server over secure connection (TLS). You might need to configure your CA certificates in the [configuration file](#configuration_files). The available configuration settings are the same as for [server-side TLS configuration](../operations/server-configuration-parameters/settings.md#server_configuration_parameters-openssl).
@ -339,7 +340,7 @@ clickhouse-client clickhouse://some_user%40some_mail.com@localhost:9000
Connect to one of provides hosts: `192.168.1.15`, `192.168.1.25`.
``` bash
clickhouse-client clickhouse://192.168.1.15,192.168.1.25
clickhouse-client clickhouse://192.168.1.15,192.168.1.25
```
### Configuration Files {#configuration_files}
@ -367,7 +368,7 @@ Example of a config file:
```
Or the same config in a YAML format:
```yaml
user: username
password: 'password'

View File

@ -67,6 +67,7 @@ The supported formats are:
| [Prometheus](#prometheus) | ✗ | ✔ |
| [Protobuf](#protobuf) | ✔ | ✔ |
| [ProtobufSingle](#protobufsingle) | ✔ | ✔ |
| [ProtobufList](#protobuflist) | ✔ | ✔ |
| [Avro](#data-format-avro) | ✔ | ✔ |
| [AvroConfluent](#data-format-avro-confluent) | ✔ | ✗ |
| [Parquet](#data-format-parquet) | ✔ | ✔ |
@ -1535,6 +1536,10 @@ the columns from input data will be mapped to the columns from the table by thei
Otherwise, the first row will be skipped.
If setting [input_format_with_types_use_header](/docs/en/operations/settings/settings-formats.md/#input_format_with_types_use_header) is set to 1,
the types from input data will be compared with the types of the corresponding columns from the table. Otherwise, the second row will be skipped.
If setting [output_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#output_format_binary_encode_types_in_binary_format) is set to 1,
the types in header will be written using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes output format.
If setting [input_format_binary_encode_types_in_binary_format](/docs/en/operations/settings/settings-formats.md/#input_format_binary_encode_types_in_binary_format) is set to 1,
the types in header will be read using [binary encoding](/docs/en/sql-reference/data-types/data-types-binary-encoding.md) instead of strings with type names in RowBinaryWithNamesAndTypes input format.
:::
## RowBinaryWithDefaults {#rowbinarywithdefaults}
@ -1948,6 +1953,35 @@ SYSTEM DROP FORMAT SCHEMA CACHE FOR Protobuf
Same as [Protobuf](#protobuf) but for storing/parsing single Protobuf message without length delimiters.
## ProtobufList {#protobuflist}
Similar to Protobuf but rows are represented as a sequence of sub-messages contained in a message with fixed name "Envelope".
Usage example:
``` sql
SELECT * FROM test.table FORMAT ProtobufList SETTINGS format_schema = 'schemafile:MessageType'
```
``` bash
cat protobuflist_messages.bin | clickhouse-client --query "INSERT INTO test.table FORMAT ProtobufList SETTINGS format_schema='schemafile:MessageType'"
```
where the file `schemafile.proto` looks like this:
``` capnp
syntax = "proto3";
message Envelope {
message MessageType {
string name = 1;
string surname = 2;
uint32 birthDate = 3;
repeated string phoneNumbers = 4;
};
MessageType row = 1;
};
```
## Avro {#data-format-avro}
[Apache Avro](https://avro.apache.org/) is a row-oriented data serialization framework developed within Apaches Hadoop project.

View File

@ -6,7 +6,20 @@ sidebar_label: MySQL Interface
# MySQL Interface
ClickHouse supports the MySQL wire protocol. This allow tools that are MySQL-compatible to interact with ClickHouse seamlessly (e.g. [Looker Studio](../integrations/data-visualization/looker-studio-and-clickhouse.md)).
ClickHouse supports the MySQL wire protocol. This allows certain clients that do not have native ClickHouse connectors leverage the MySQL protocol instead, and it has been validated with the following BI tools:
- [Looker Studio](../integrations/data-visualization/looker-studio-and-clickhouse.md)
- [Tableau Online](../integrations/tableau-online)
- [QuickSight](../integrations/quicksight)
If you are trying other untested clients or integrations, keep in mind that there could be the following limitations:
- SSL implementation might not be fully compatible; there could be potential [TLS SNI](https://www.cloudflare.com/learning/ssl/what-is-sni/) issues.
- A particular tool might require dialect features (e.g., MySQL-specific functions or settings) that are not implemented yet.
If there is a native driver available (e.g., [DBeaver](../integrations/dbeaver)), it is always preferred to use it instead of the MySQL interface. Additionally, while most of the MySQL language clients should work fine, MySQL interface is not guaranteed to be a drop-in replacement for a codebase with existing MySQL queries.
If your use case involves a particular tool that does not have a native ClickHouse driver, and you would like to use it via the MySQL interface and you found certain incompatibilities - please [create an issue](https://github.com/ClickHouse/ClickHouse/issues) in the ClickHouse repository.
## Enabling the MySQL Interface On ClickHouse Cloud

View File

@ -2,15 +2,11 @@
slug: /en/operations/opentelemetry
sidebar_position: 62
sidebar_label: Tracing ClickHouse with OpenTelemetry
title: "[experimental] Tracing ClickHouse with OpenTelemetry"
title: "Tracing ClickHouse with OpenTelemetry"
---
[OpenTelemetry](https://opentelemetry.io/) is an open standard for collecting traces and metrics from the distributed application. ClickHouse has some support for OpenTelemetry.
:::note
This is an experimental feature that will change in backwards-incompatible ways in future releases.
:::
## Supplying Trace Context to ClickHouse
ClickHouse accepts trace context HTTP headers, as described by the [W3C recommendation](https://www.w3.org/TR/trace-context/). It also accepts trace context over a native protocol that is used for communication between ClickHouse servers or between the client and server. For manual testing, trace context headers conforming to the Trace Context recommendation can be supplied to `clickhouse-client` using `--opentelemetry-traceparent` and `--opentelemetry-tracestate` flags.

View File

@ -1030,7 +1030,7 @@ A table with no primary key represents the extreme case of a single equivalence
The fewer and the larger the equivalence classes are, the higher the degree of freedom when re-shuffling rows.
The heuristics applied to find the best row order within each equivalence class is suggested by D. Lemir, O. Kaser in [Reordering columns for smaller indexes](https://doi.org/10.1016/j.ins.2011.02.002) and based on sorting the rows within each equivalence class by ascending cardinality of the non-primary key columns.
The heuristics applied to find the best row order within each equivalence class is suggested by D. Lemire, O. Kaser in [Reordering columns for smaller indexes](https://doi.org/10.1016/j.ins.2011.02.002) and based on sorting the rows within each equivalence class by ascending cardinality of the non-primary key columns.
It performs three steps:
1. Find all equivalence classes based on the row values in primary key columns.
2. For each equivalence class, calculate (usually estimate) the cardinalities of the non-primary-key columns.

View File

@ -1951,6 +1951,18 @@ The maximum allowed size for String in RowBinary format. It prevents allocating
Default value: `1GiB`.
### output_format_binary_encode_types_in_binary_format {#output_format_binary_encode_types_in_binary_format}
Write data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in RowBinaryWithNamesAndTypes output format.
Disabled by default.
### input_format_binary_decode_types_in_binary_format {#input_format_binary_decode_types_in_binary_format}
Read data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in RowBinaryWithNamesAndTypes input format.
Disabled by default.
## Native format settings {#native-format-settings}
### input_format_native_allow_types_conversion {#input_format_native_allow_types_conversion}
@ -1958,3 +1970,15 @@ Default value: `1GiB`.
Allow types conversion in Native input format between columns from input data and requested columns.
Enabled by default.
### output_format_native_encode_types_in_binary_format {#output_format_native_encode_types_in_binary_format}
Write data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in Native output format.
Disabled by default.
### input_format_native_decode_types_in_binary_format {#input_format_native_decode_types_in_binary_format}
Read data types in [binary format](../../sql-reference/data-types/data-types-binary-encoding.md) instead of type names in Native input format.
Disabled by default.

View File

@ -1170,6 +1170,10 @@ Data in the VALUES clause of INSERT queries is processed by a separate stream pa
Default value: 262144 (= 256 KiB).
:::note
`max_query_size` cannot be set within an SQL query (e.g., `SELECT now() SETTINGS max_query_size=10000`) because ClickHouse needs to allocate a buffer to parse the query, and this buffer size is determined by the `max_query_size` setting, which must be configured before the query is executed.
:::
## max_parser_depth {#max_parser_depth}
Limits maximum recursion depth in the recursive descent parser. Allows controlling the stack size.
@ -1354,12 +1358,25 @@ Connection pool size for PostgreSQL table engine and database engine.
Default value: 16
## postgresql_connection_attempt_timeout {#postgresql-connection-attempt-timeout}
Connection timeout in seconds of a single attempt to connect PostgreSQL end-point.
The value is passed as a `connect_timeout` parameter of the connection URL.
Default value: `2`.
## postgresql_connection_pool_wait_timeout {#postgresql-connection-pool-wait-timeout}
Connection pool push/pop timeout on empty pool for PostgreSQL table engine and database engine. By default it will block on empty pool.
Default value: 5000
## postgresql_connection_pool_retries {#postgresql-connection-pool-retries}
The maximum number of retries to establish a connection with the PostgreSQL end-point.
Default value: `2`.
## postgresql_connection_pool_auto_close_connection {#postgresql-connection-pool-auto-close-connection}
Close connection before returning connection to the pool.

View File

@ -0,0 +1,35 @@
---
slug: /en/operations/system-tables/detached_tables
---
# detached_tables
Contains information of each detached table.
Columns:
- `database` ([String](../../sql-reference/data-types/string.md)) — The name of the database the table is in.
- `table` ([String](../../sql-reference/data-types/string.md)) — Table name.
- `uuid` ([UUID](../../sql-reference/data-types/uuid.md)) — Table uuid (Atomic database).
- `metadata_path` ([String](../../sql-reference/data-types/string.md)) - Path to the table metadata in the file system.
- `is_permanently` ([UInt8](../../sql-reference/data-types/int-uint.md)) - Flag indicates that the table was detached PERMANENTLY.
**Example**
```sql
SELECT * FROM system.detached_tables FORMAT Vertical;
```
```text
Row 1:
──────
database: base
table: t1
uuid: 81b1c20a-b7c6-4116-a2ce-7583fb6b6736
metadata_path: /var/lib/clickhouse/store/461/461cf698-fd0b-406d-8c01-5d8fd5748a91/t1.sql
is_permanently: 1
```

View File

@ -357,7 +357,7 @@ Number of currently running inserts to Kafka
Number of alive connections
### KeeperOutstandingRequets
### KeeperOutstandingRequests
Number of outstanding requests

View File

@ -16,7 +16,7 @@ sidebar_label: clickhouse-local
While `clickhouse-local` is a great tool for development and testing purposes, and for processing files, it is not suitable for serving end users or applications. In these scenarios, it is recommended to use the open-source [ClickHouse](https://clickhouse.com/docs/en/install). ClickHouse is a powerful OLAP database that is designed to handle large-scale analytical workloads. It provides fast and efficient processing of complex queries on large datasets, making it ideal for use in production environments where high-performance is critical. Additionally, ClickHouse offers a wide range of features such as replication, sharding, and high availability, which are essential for scaling up to handle large datasets and serving applications. If you need to handle larger datasets or serve end users or applications, we recommend using open-source ClickHouse instead of `clickhouse-local`.
Please read the docs below that show example use cases for `clickhouse-local`, such as [querying local CSVs](#query-data-in-a-csv-file-using-sql) or [reading a parquet file in S3](#query-data-in-a-parquet-file-in-aws-s3).
Please read the docs below that show example use cases for `clickhouse-local`, such as [querying local file](#query_data_in_file) or [reading a parquet file in S3](#query-data-in-a-parquet-file-in-aws-s3).
## Download clickhouse-local

View File

@ -18,7 +18,7 @@ ClickHouse also supports:
During aggregation, all `NULL` arguments are skipped. If the aggregation has several arguments it will ignore any row in which one or more of them are NULL.
There is an exception to this rule, which are the functions [`first_value`](../../sql-reference/aggregate-functions/reference/first_value.md), [`last_value`](../../sql-reference/aggregate-functions/reference/last_value.md) and their aliases when followed by the modifier `RESPECT NULLS`: `FIRST_VALUE(b) RESPECT NULLS`.
There is an exception to this rule, which are the functions [`first_value`](../../sql-reference/aggregate-functions/reference/first_value.md), [`last_value`](../../sql-reference/aggregate-functions/reference/last_value.md) and their aliases (`any` and `anyLast` respectively) when followed by the modifier `RESPECT NULLS`. For example, `FIRST_VALUE(b) RESPECT NULLS`.
**Examples:**

View File

@ -5,12 +5,12 @@ sidebar_position: 102
# any
Selects the first encountered value of a column.
Selects the first encountered value of a column, ignoring any `NULL` values.
**Syntax**
```sql
any(column)
any(column) [RESPECT NULLS]
```
Aliases: `any_value`, [`first_value`](../reference/first_value.md).
@ -20,7 +20,9 @@ Aliases: `any_value`, [`first_value`](../reference/first_value.md).
**Returned value**
By default, it ignores NULL values and returns the first NOT NULL value found in the column. Like [`first_value`](../../../sql-reference/aggregate-functions/reference/first_value.md) it supports `RESPECT NULLS`, in which case it will select the first value passed, independently on whether it's NULL or not.
:::note
Supports the `RESPECT NULLS` modifier after the function name. Using this modifier will ensure the function selects the first value passed, regardless of whether it is `NULL` or not.
:::
:::note
The return type of the function is the same as the input, except for LowCardinality which is discarded. This means that given no rows as input it will return the default value of that type (0 for integers, or Null for a Nullable() column). You might use the `-OrNull` [combinator](../../../sql-reference/aggregate-functions/combinators.md) ) to modify this behaviour.

View File

@ -1,44 +0,0 @@
---
slug: /en/sql-reference/aggregate-functions/reference/any_respect_nulls
sidebar_position: 103
---
# any_respect_nulls
Selects the first encountered value of a column, irregardless of whether it is a `NULL` value or not.
Alias: `any_value_respect_nulls`, `first_value_repect_nulls`.
**Syntax**
```sql
any_respect_nulls(column)
```
**Parameters**
- `column`: The column name.
**Returned value**
- The last value encountered, irregardless of whether it is a `NULL` value or not.
**Example**
Query:
```sql
CREATE TABLE any_nulls (city Nullable(String)) ENGINE=Log;
INSERT INTO any_nulls (city) VALUES (NULL), ('Amsterdam'), ('New York'), ('Tokyo'), ('Valencia'), (NULL);
SELECT any(city), any_respect_nulls(city) FROM any_nulls;
```
```response
┌─any(city)─┬─any_respect_nulls(city)─┐
│ Amsterdam │ ᴺᵁᴸᴸ │
└───────────┴─────────────────────────┘
```
**See Also**
- [any](../reference/any.md)

View File

@ -5,17 +5,21 @@ sidebar_position: 105
# anyLast
Selects the last value encountered. The result is just as indeterminate as for the [any](../../../sql-reference/aggregate-functions/reference/any.md) function.
Selects the last value encountered, ignoring any `NULL` values by default. The result is just as indeterminate as for the [any](../../../sql-reference/aggregate-functions/reference/any.md) function.
**Syntax**
```sql
anyLast(column)
anyLast(column) [RESPECT NULLS]
```
**Parameters**
- `column`: The column name.
:::note
Supports the `RESPECT NULLS` modifier after the function name. Using this modifier will ensure the function selects the first value passed, regardless of whether it is `NULL` or not.
:::
**Returned value**
- The last value encountered.

View File

@ -1,39 +0,0 @@
---
slug: /en/sql-reference/aggregate-functions/reference/anylast_respect_nulls
sidebar_position: 106
---
# anyLast_respect_nulls
Selects the last value encountered, irregardless of whether it is `NULL` or not.
**Syntax**
```sql
anyLast_respect_nulls(column)
```
**Parameters**
- `column`: The column name.
**Returned value**
- The last value encountered, irregardless of whether it is `NULL` or not.
**Example**
Query:
```sql
CREATE TABLE any_last_nulls (city Nullable(String)) ENGINE=Log;
INSERT INTO any_last_nulls (city) VALUES ('Amsterdam'),(NULL),('New York'),('Tokyo'),('Valencia'),(NULL);
SELECT anyLast(city), anyLast_respect_nulls(city) FROM any_last_nulls;
```
```response
┌─anyLast(city)─┬─anyLast_respect_nulls(city)─┐
│ Valencia │ ᴺᵁᴸᴸ │
└───────────────┴─────────────────────────────┘
```

View File

@ -45,10 +45,9 @@ ClickHouse-specific aggregate functions:
- [aggThrow](../reference/aggthrow.md)
- [analysisOfVariance](../reference/analysis_of_variance.md)
- [any](../reference/any_respect_nulls.md)
- [any](../reference/any.md)
- [anyHeavy](../reference/anyheavy.md)
- [anyLast](../reference/anylast.md)
- [anyLast](../reference/anylast_respect_nulls.md)
- [boundingRatio](../reference/boundrat.md)
- [first_value](../reference/first_value.md)
- [last_value](../reference/last_value.md)

View File

@ -5,23 +5,45 @@ sidebar_position: 165
# maxMap
Syntax: `maxMap(key, value)` or `maxMap(Tuple(key, value))`
Calculates the maximum from `value` array according to the keys specified in the `key` array.
Passing a tuple of keys and value arrays is identical to passing two arrays of keys and values.
**Syntax**
The number of elements in `key` and `value` must be the same for each row that is totaled.
```sql
maxMap(key, value)
```
or
```sql
maxMap(Tuple(key, value))
```
Returns a tuple of two arrays: keys and values calculated for the corresponding keys.
Alias: `maxMappedArrays`
Example:
:::note
- Passing a tuple of keys and value arrays is identical to passing two arrays of keys and values.
- The number of elements in `key` and `value` must be the same for each row that is totaled.
:::
**Parameters**
- `key` — Array of keys. [Array](../../data-types/array.md).
- `value` — Array of values. [Array](../../data-types/array.md).
**Returned value**
- Returns a tuple of two arrays: keys in sorted order, and values calculated for the corresponding keys. [Tuple](../../data-types/tuple.md)([Array](../../data-types/array.md), [Array](../../data-types/array.md)).
**Example**
Query:
``` sql
SELECT maxMap(a, b)
FROM values('a Array(Char), b Array(Int64)', (['x', 'y'], [2, 2]), (['y', 'z'], [3, 1]))
```
Result:
``` text
┌─maxMap(a, b)───────────┐
│ [['x','y','z'],[2,3,1]]│

View File

@ -5,23 +5,45 @@ sidebar_position: 169
# minMap
Syntax: `minMap(key, value)` or `minMap(Tuple(key, value))`
Calculates the minimum from `value` array according to the keys specified in the `key` array.
Passing a tuple of keys and value arrays is identical to passing two arrays of keys and values.
**Syntax**
The number of elements in `key` and `value` must be the same for each row that is totaled.
```sql
`minMap(key, value)`
```
or
```sql
minMap(Tuple(key, value))
```
Returns a tuple of two arrays: keys in sorted order, and values calculated for the corresponding keys.
Alias: `minMappedArrays`
Example:
:::note
- Passing a tuple of keys and value arrays is identical to passing an array of keys and an array of values.
- The number of elements in `key` and `value` must be the same for each row that is totaled.
:::
**Parameters**
- `key` — Array of keys. [Array](../../data-types/array.md).
- `value` — Array of values. [Array](../../data-types/array.md).
**Returned value**
- Returns a tuple of two arrays: keys in sorted order, and values calculated for the corresponding keys. [Tuple](../../data-types/tuple.md)([Array](../../data-types/array.md), [Array](../../data-types/array.md)).
**Example**
Query:
``` sql
SELECT minMap(a, b)
FROM values('a Array(Int32), b Array(Int64)', ([1, 2], [2, 2]), ([2, 3], [1, 1]))
```
Result:
``` text
┌─minMap(a, b)──────┐
│ ([1,2,3],[2,1,1]) │

View File

@ -16,7 +16,7 @@ singleValueOrNull(x)
**Parameters**
- `x` — Column of any [data type](../../data-types/index.md).
- `x` — Column of any [data type](../../data-types/index.md) (except [Map](../../data-types/map.md), [Array](../../data-types/array.md) or [Tuple](../../data-types/tuple) which cannot be of type [Nullable](../../data-types/nullable.md)).
**Returned values**

View File

@ -96,3 +96,22 @@ Result:
│ 1 │ [2] │ [[4,1]] │
└───────────┴───────────┴───────────┘
```
## Reading nested subcolumns from Array
If nested type `T` inside `Array` has subcolumns (for example, if it's a [named tuple](./tuple.md)), you can read its subcolumns from an `Array(T)` type with the same subcolumn names. The type of a subcolumn will be `Array` of the type of original subcolumn.
**Example**
```sql
CREATE TABLE t_arr (arr Array(Tuple(field1 UInt32, field2 String))) ENGINE = MergeTree ORDER BY tuple();
INSERT INTO t_arr VALUES ([(1, 'Hello'), (2, 'World')]), ([(3, 'This'), (4, 'is'), (5, 'subcolumn')]);
SELECT arr.field1, toTypeName(arr.field1), arr.field2, toTypeName(arr.field2) from t_arr;
```
```test
┌─arr.field1─┬─toTypeName(arr.field1)─┬─arr.field2────────────────┬─toTypeName(arr.field2)─┐
│ [1,2] │ Array(UInt32) │ ['Hello','World'] │ Array(String) │
│ [3,4,5] │ Array(UInt32) │ ['This','is','subcolumn'] │ Array(String) │
└────────────┴────────────────────────┴───────────────────────────┴────────────────────────┘
```

View File

@ -0,0 +1,115 @@
---
slug: /en/sql-reference/data-types/data-types-binary-encoding
sidebar_position: 56
sidebar_label: Data types binary encoding specification.
---
# Data types binary encoding specification
This specification describes the binary format that can be used for binary encoding and decoding of ClickHouse data types. This format is used in `Dynamic` column [binary serialization](dynamic.md#binary-output-format) and can be used in input/output formats [RowBinaryWithNamesAndTypes](../../interfaces/formats.md#rowbinarywithnamesandtypes) and [Native](../../interfaces/formats.md#native) under corresponding settings.
The table below describes how each data type is represented in binary format. Each data type encoding consist of 1 byte that indicates the type and some optional additional information.
`var_uint` in the binary encoding means that the size is encoded using Variable-Length Quantity compression.
| ClickHouse data type | Binary encoding |
|--------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `Nothing` | `0x00` |
| `UInt8` | `0x01` |
| `UInt16` | `0x02` |
| `UInt32` | `0x03` |
| `UInt64` | `0x04` |
| `UInt128` | `0x05` |
| `UInt256` | `0x06` |
| `Int8` | `0x07` |
| `Int16` | `0x08` |
| `Int32` | `0x09` |
| `Int64` | `0x0A` |
| `Int128` | `0x0B` |
| `Int256` | `0x0C` |
| `Float32` | `0x0D` |
| `Float64` | `0x0E` |
| `Date` | `0x0F` |
| `Date32` | `0x10` |
| `DateTime` | `0x11` |
| `DateTime(time_zone)` | `0x12<var_uint_time_zone_name_size><time_zone_name_data>` |
| `DateTime64(P)` | `0x13<uint8_precision>` |
| `DateTime64(P, time_zone)` | `0x14<uint8_precision><var_uint_time_zone_name_size><time_zone_name_data>` |
| `String` | `0x15` |
| `FixedString(N)` | `0x16<var_uint_size>` |
| `Enum8` | `0x17<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><int8_value_1>...<var_uint_name_size_N><name_data_N><int8_value_N>` |
| `Enum16` | `0x18<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><int16_little_endian_value_1>...><var_uint_name_size_N><name_data_N><int16_little_endian_value_N>` |
| `Decimal32(P, S)` | `0x19<uint8_precision><uint8_scale>` |
| `Decimal64(P, S)` | `0x1A<uint8_precision><uint8_scale>` |
| `Decimal128(P, S)` | `0x1B<uint8_precision><uint8_scale>` |
| `Decimal256(P, S)` | `0x1C<uint8_precision><uint8_scale>` |
| `UUID` | `0x1D` |
| `Array(T)` | `0x1E<nested_type_encoding>` |
| `Tuple(T1, ..., TN)` | `0x1F<var_uint_number_of_elements><nested_type_encoding_1>...<nested_type_encoding_N>` |
| `Tuple(name1 T1, ..., nameN TN)` | `0x20<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><nested_type_encoding_1>...<var_uint_name_size_N><name_data_N><nested_type_encoding_N>` |
| `Set` | `0x21` |
| `Interval` | `0x22<interval_kind>` (see [interval kind binary encoding](#interval-kind-binary-encoding)) |
| `Nullable(T)` | `0x23<nested_type_encoding>` |
| `Function` | `0x24<var_uint_number_of_arguments><argument_type_encoding_1>...<argument_type_encoding_N><return_type_encoding>` |
| `AggregateFunction(function_name(param_1, ..., param_N), arg_T1, ..., arg_TN)` | `0x25<var_uint_version><var_uint_function_name_size><function_name_data><var_uint_number_of_parameters><param_1>...<param_N><var_uint_number_of_arguments><argument_type_encoding_1>...<argument_type_encoding_N>` (see [aggregate function parameter binary encoding](#aggregate-function-parameter-binary-encoding)) |
| `LowCardinality(T)` | `0x26<nested_type_encoding>` |
| `Map(K, V)` | `0x27<key_type_encoding><value_type_encoding>` |
| `IPv4` | `0x28` |
| `IPv6` | `0x29` |
| `Variant(T1, ..., TN)` | `0x2A<var_uint_number_of_variants><variant_type_encoding_1>...<variant_type_encoding_N>` |
| `Dynamic(max_types=N)` | `0x2B<uint8_max_types>` |
| `Custom type` (`Ring`, `Polygon`, etc) | `0x2C<var_uint_type_name_size><type_name_data>` |
| `Bool` | `0x2D` |
| `SimpleAggregateFunction(function_name(param_1, ..., param_N), arg_T1, ..., arg_TN)` | `0x2E<var_uint_function_name_size><function_name_data><var_uint_number_of_parameters><param_1>...<param_N><var_uint_number_of_arguments><argument_type_encoding_1>...<argument_type_encoding_N>` (see [aggregate function parameter binary encoding](#aggregate-function-parameter-binary-encoding)) |
| `Nested(name1 T1, ..., nameN TN)` | `0x2F<var_uint_number_of_elements><var_uint_name_size_1><name_data_1><nested_type_encoding_1>...<var_uint_name_size_N><name_data_N><nested_type_encoding_N>` |
### Interval kind binary encoding
The table below describes how different interval kinds of `Interval` data type are encoded.
| Interval kind | Binary encoding |
|---------------|-----------------|
| `Nanosecond` | `0x00` |
| `Microsecond` | `0x01` |
| `Millisecond` | `0x02` |
| `Second` | `0x03` |
| `Minute` | `0x04` |
| `Hour` | `0x05` |
| `Day` | `0x06` |
| `Week` | `0x07` |
| `Month` | `0x08` |
| `Quarter` | `0x09` |
| `Year` | `0x1A` |
### Aggregate function parameter binary encoding
The table below describes how parameters of `AggragateFunction` and `SimpleAggregateFunction` are encoded.
The encoding of a parameter consists of 1 byte indicating the type of the parameter and the value itself.
| Parameter type | Binary encoding |
|--------------------------|--------------------------------------------------------------------------------------------------------------------------------|
| `Null` | `0x00` |
| `UInt64` | `0x01<var_uint_value>` |
| `Int64` | `0x02<var_int_value>` |
| `UInt128` | `0x03<uint128_little_endian_value>` |
| `Int128` | `0x04<int128_little_endian_value>` |
| `UInt128` | `0x05<uint128_little_endian_value>` |
| `Int128` | `0x06<int128_little_endian_value>` |
| `Float64` | `0x07<float64_little_endian_value>` |
| `Decimal32` | `0x08<var_uint_scale><int32_little_endian_value>` |
| `Decimal64` | `0x09<var_uint_scale><int64_little_endian_value>` |
| `Decimal128` | `0x0A<var_uint_scale><int128_little_endian_value>` |
| `Decimal256` | `0x0B<var_uint_scale><int256_little_endian_value>` |
| `String` | `0x0C<var_uint_size><data>` |
| `Array` | `0x0D<var_uint_size><value_encoding_1>...<value_encoding_N>` |
| `Tuple` | `0x0E<var_uint_size><value_encoding_1>...<value_encoding_N>` |
| `Map` | `0x0F<var_uint_size><key_encoding_1><value_encoding_1>...<key_endoding_N><value_encoding_N>` |
| `IPv4` | `0x10<uint32_little_endian_value>` |
| `IPv6` | `0x11<uint128_little_endian_value>` |
| `UUID` | `0x12<uuid_value>` |
| `Bool` | `0x13<bool_value>` |
| `Object` | `0x14<var_uint_size><var_uint_key_size_1><key_data_1><value_encoding_1>...<var_uint_key_size_N><key_data_N><value_encoding_N>` |
| `AggregateFunctionState` | `0x15<var_uint_name_size><name_data><var_uint_data_size><data>` |
| `Negative infinity` | `0xFE` |
| `Positive infinity` | `0xFF` |

View File

@ -1,6 +1,6 @@
---
slug: /en/sql-reference/data-types/dynamic
sidebar_position: 56
sidebar_position: 62
sidebar_label: Dynamic
---
@ -493,3 +493,44 @@ SELECT count(), dynamicType(d), _part FROM test GROUP BY _part, dynamicType(d) O
```
As we can see, ClickHouse kept the most frequent types `UInt64` and `Array(UInt64)` and casted all other types to `String`.
## JSONExtract functions with Dynamic
All `JSONExtract*` functions support `Dynamic` type:
```sql
SELECT JSONExtract('{"a" : [1, 2, 3]}', 'a', 'Dynamic') AS dynamic, dynamicType(dynamic) AS dynamic_type;
```
```text
┌─dynamic─┬─dynamic_type───────────┐
│ [1,2,3] │ Array(Nullable(Int64)) │
└─────────┴────────────────────────┘
```
```sql
SELECT JSONExtract('{"obj" : {"a" : 42, "b" : "Hello", "c" : [1,2,3]}}', 'obj', 'Map(String, Variant(UInt32, String, Array(UInt32)))') AS map_of_dynamics, mapApply((k, v) -> (k, variantType(v)), map_of_dynamics) AS map_of_dynamic_types```
```text
┌─map_of_dynamics──────────────────┬─map_of_dynamic_types────────────────────────────┐
│ {'a':42,'b':'Hello','c':[1,2,3]} │ {'a':'UInt32','b':'String','c':'Array(UInt32)'} │
└──────────────────────────────────┴─────────────────────────────────────────────────┘
```
```sql
SELECT JSONExtractKeysAndValues('{"a" : 42, "b" : "Hello", "c" : [1,2,3]}', 'Variant(UInt32, String, Array(UInt32))') AS dynamics, arrayMap(x -> (x.1, variantType(x.2)), dynamics) AS dynamic_types```
```
```text
┌─dynamics───────────────────────────────┬─dynamic_types─────────────────────────────────────────┐
│ [('a',42),('b','Hello'),('c',[1,2,3])] │ [('a','UInt32'),('b','String'),('c','Array(UInt32)')] │
└────────────────────────────────────────┴───────────────────────────────────────────────────────┘
```
### Binary output format
In RowBinary format values of `Dynamic` type are serialized in the following format:
```text
<binary_encoded_data_type><value_in_binary_format_according_to_the_data_type>
```

View File

@ -5,11 +5,11 @@ sidebar_label: Object Data Type
keywords: [object, data type]
---
# Object Data Type
# Object Data Type (deprecated)
:::note
This feature is not production-ready and is now deprecated. If you need to work with JSON documents, consider using [this guide](/docs/en/integrations/data-ingestion/data-formats/json) instead. A new implementation to support JSON object is in progress and can be tracked [here](https://github.com/ClickHouse/ClickHouse/issues/54864)
:::
**This feature is not production-ready and is now deprecated.** If you need to work with JSON documents, consider using [this guide](/docs/en/integrations/data-ingestion/data-formats/json) instead. A new implementation to support JSON object is in progress and can be tracked [here](https://github.com/ClickHouse/ClickHouse/issues/54864).
<hr />
Stores JavaScript Object Notation (JSON) documents in a single column.

View File

@ -56,7 +56,6 @@ Functions:
## Related content
- [Reducing ClickHouse Storage Cost with the Low Cardinality Type Lessons from an Instana Engineer](https://altinity.com/blog/2020-5-20-reducing-clickhouse-storage-cost-with-the-low-cardinality-type-lessons-from-an-instana-engineer)
- [String Optimization (video presentation in Russian)](https://youtu.be/rqf-ILRgBdY?list=PL0Z2YDlm0b3iwXCpEFiOOYmwXzVmjJfEt). [Slides in English](https://github.com/ClickHouse/clickhouse-presentations/raw/master/meetup19/string_optimization.pdf)
- Blog: [Optimizing ClickHouse with Schemas and Codecs](https://clickhouse.com/blog/optimize-clickhouse-codecs-compression-schema)
- Blog: [Working with time series data in ClickHouse](https://clickhouse.com/blog/working-with-time-series-data-and-functions-ClickHouse)
- [String Optimization (video presentation in Russian)](https://youtu.be/rqf-ILRgBdY?list=PL0Z2YDlm0b3iwXCpEFiOOYmwXzVmjJfEt). [Slides in English](https://github.com/ClickHouse/clickhouse-presentations/raw/master/meetup19/string_optimization.pdf)

View File

@ -3080,4 +3080,4 @@ Result:
## Distance functions
All supported functions are described in [distance functions documentation](../../sql-reference/functions/distance-functions.md).
All supported functions are described in [distance functions documentation](../../sql-reference/functions/distance-functions.md).

View File

@ -2698,6 +2698,204 @@ Like function `YYYYMMDDhhmmssToDate()` but produces a [DateTime64](../data-types
Accepts an additional, optional `precision` parameter after the `timezone` parameter.
## changeYear
Changes the year component of a date or date time.
**Syntax**
``` sql
changeYear(date_or_datetime, value)
```
**Arguments**
- `date_or_datetime` - a [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md)
- `value` - a new value of the year. [Integer](../../sql-reference/data-types/int-uint.md).
**Returned value**
- The same type as `date_or_datetime`.
**Example**
``` sql
SELECT changeYear(toDate('1999-01-01'), 2000), changeYear(toDateTime64('1999-01-01 00:00:00.000', 3), 2000);
```
Result:
```
┌─changeYear(toDate('1999-01-01'), 2000)─┬─changeYear(toDateTime64('1999-01-01 00:00:00.000', 3), 2000)─┐
│ 2000-01-01 │ 2000-01-01 00:00:00.000 │
└────────────────────────────────────────┴──────────────────────────────────────────────────────────────┘
```
## changeMonth
Changes the month component of a date or date time.
**Syntax**
``` sql
changeMonth(date_or_datetime, value)
```
**Arguments**
- `date_or_datetime` - a [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md)
- `value` - a new value of the month. [Integer](../../sql-reference/data-types/int-uint.md).
**Returned value**
- Returns a value of same type as `date_or_datetime`.
**Example**
``` sql
SELECT changeMonth(toDate('1999-01-01'), 2), changeMonth(toDateTime64('1999-01-01 00:00:00.000', 3), 2);
```
Result:
```
┌─changeMonth(toDate('1999-01-01'), 2)─┬─changeMonth(toDateTime64('1999-01-01 00:00:00.000', 3), 2)─┐
│ 1999-02-01 │ 1999-02-01 00:00:00.000 │
└──────────────────────────────────────┴────────────────────────────────────────────────────────────┘
```
## changeDay
Changes the day component of a date or date time.
**Syntax**
``` sql
changeDay(date_or_datetime, value)
```
**Arguments**
- `date_or_datetime` - a [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md)
- `value` - a new value of the day. [Integer](../../sql-reference/data-types/int-uint.md).
**Returned value**
- Returns a value of same type as `date_or_datetime`.
**Example**
``` sql
SELECT changeDay(toDate('1999-01-01'), 5), changeDay(toDateTime64('1999-01-01 00:00:00.000', 3), 5);
```
Result:
```
┌─changeDay(toDate('1999-01-01'), 5)─┬─changeDay(toDateTime64('1999-01-01 00:00:00.000', 3), 5)─┐
│ 1999-01-05 │ 1999-01-05 00:00:00.000 │
└────────────────────────────────────┴──────────────────────────────────────────────────────────┘
```
## changeHour
Changes the hour component of a date or date time.
**Syntax**
``` sql
changeHour(date_or_datetime, value)
```
**Arguments**
- `date_or_datetime` - a [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md)
- `value` - a new value of the hour. [Integer](../../sql-reference/data-types/int-uint.md).
**Returned value**
- Returns a value of same type as `date_or_datetime`. If the input is a [Date](../data-types/date.md), return [DateTime](../data-types/datetime.md). If the input is a [Date32](../data-types/date32.md), return [DateTime64](../data-types/datetime64.md).
**Example**
``` sql
SELECT changeHour(toDate('1999-01-01'), 14), changeHour(toDateTime64('1999-01-01 00:00:00.000', 3), 14);
```
Result:
```
┌─changeHour(toDate('1999-01-01'), 14)─┬─changeHour(toDateTime64('1999-01-01 00:00:00.000', 3), 14)─┐
│ 1999-01-01 14:00:00 │ 1999-01-01 14:00:00.000 │
└──────────────────────────────────────┴────────────────────────────────────────────────────────────┘
```
## changeMinute
Changes the minute component of a date or date time.
**Syntax**
``` sql
changeMinute(date_or_datetime, value)
```
**Arguments**
- `date_or_datetime` - a [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md)
- `value` - a new value of the minute. [Integer](../../sql-reference/data-types/int-uint.md).
**Returned value**
- Returns a value of same type as `date_or_datetime`. If the input is a [Date](../data-types/date.md), return [DateTime](../data-types/datetime.md). If the input is a [Date32](../data-types/date32.md), return [DateTime64](../data-types/datetime64.md).
**Example**
``` sql
SELECT changeMinute(toDate('1999-01-01'), 15), changeMinute(toDateTime64('1999-01-01 00:00:00.000', 3), 15);
```
Result:
```
┌─changeMinute(toDate('1999-01-01'), 15)─┬─changeMinute(toDateTime64('1999-01-01 00:00:00.000', 3), 15)─┐
│ 1999-01-01 00:15:00 │ 1999-01-01 00:15:00.000 │
└────────────────────────────────────────┴──────────────────────────────────────────────────────────────┘
```
## changeSecond
Changes the second component of a date or date time.
**Syntax**
``` sql
changeSecond(date_or_datetime, value)
```
**Arguments**
- `date_or_datetime` - a [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md)
- `value` - a new value of the second. [Integer](../../sql-reference/data-types/int-uint.md).
**Returned value**
- Returns a value of same type as `date_or_datetime`. If the input is a [Date](../data-types/date.md), return [DateTime](../data-types/datetime.md). If the input is a [Date32](../data-types/date32.md), return [DateTime64](../data-types/datetime64.md).
**Example**
``` sql
SELECT changeSecond(toDate('1999-01-01'), 15), changeSecond(toDateTime64('1999-01-01 00:00:00.000', 3), 15);
```
Result:
```
┌─changeSecond(toDate('1999-01-01'), 15)─┬─changeSecond(toDateTime64('1999-01-01 00:00:00.000', 3), 15)─┐
│ 1999-01-01 00:00:15 │ 1999-01-01 00:00:15.000 │
└────────────────────────────────────────┴──────────────────────────────────────────────────────────────┘
```
## addYears
Adds a specified number of years to a date, a date with time or a string-encoded date / date with time.
@ -2714,6 +2912,7 @@ addYears(date, num)
- `num`: Number of years to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` years. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -2751,6 +2950,7 @@ addQuarters(date, num)
- `num`: Number of quarters to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` quarters. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -2788,6 +2988,7 @@ addMonths(date, num)
- `num`: Number of months to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` months. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -2825,6 +3026,7 @@ addWeeks(date, num)
- `num`: Number of weeks to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` weeks. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -2862,6 +3064,7 @@ addDays(date, num)
- `num`: Number of days to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` days. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -2899,6 +3102,7 @@ addHours(date, num)
- `num`: Number of hours to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
o
- Returns `date` plus `num` hours. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -2936,6 +3140,7 @@ addMinutes(date, num)
- `num`: Number of minutes to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` minutes. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -2973,6 +3178,7 @@ addSeconds(date, num)
- `num`: Number of seconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` plus `num` seconds. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3010,6 +3216,7 @@ addMilliseconds(date_time, num)
- `num`: Number of milliseconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` plus `num` milliseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -3045,6 +3252,7 @@ addMicroseconds(date_time, num)
- `num`: Number of microseconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` plus `num` microseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -3080,6 +3288,7 @@ addNanoseconds(date_time, num)
- `num`: Number of nanoseconds to add. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` plus `num` nanoseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -3115,6 +3324,7 @@ addInterval(interval_1, interval_2)
- `interval_2`: Second interval to be added. [interval](../data-types/special-data-types/interval.md).
**Returned value**
- Returns a tuple of intervals. [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
:::note
@ -3161,6 +3371,7 @@ addTupleOfIntervals(interval_1, interval_2)
- `intervals`: Tuple of intervals to add to `date`. [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
**Returned value**
- Returns `date` with added `intervals`. [date](../data-types/date.md)/[date32](../data-types/date32.md)/[datetime](../data-types/datetime.md)/[datetime64](../data-types/datetime64.md).
**Example**
@ -3195,6 +3406,7 @@ subtractYears(date, num)
- `num`: Number of years to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` years. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3232,6 +3444,7 @@ subtractQuarters(date, num)
- `num`: Number of quarters to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` quarters. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3269,6 +3482,7 @@ subtractMonths(date, num)
- `num`: Number of months to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` months. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3306,6 +3520,7 @@ subtractWeeks(date, num)
- `num`: Number of weeks to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` weeks. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3343,6 +3558,7 @@ subtractDays(date, num)
- `num`: Number of days to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` days. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3380,6 +3596,7 @@ subtractHours(date, num)
- `num`: Number of hours to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` hours. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[Datetime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3417,6 +3634,7 @@ subtractMinutes(date, num)
- `num`: Number of minutes to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` minutes. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3454,6 +3672,7 @@ subtractSeconds(date, num)
- `num`: Number of seconds to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date` minus `num` seconds. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**
@ -3491,6 +3710,7 @@ subtractMilliseconds(date_time, num)
- `num`: Number of milliseconds to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` minus `num` milliseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -3526,6 +3746,7 @@ subtractMicroseconds(date_time, num)
- `num`: Number of microseconds to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` minus `num` microseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -3561,6 +3782,7 @@ subtractNanoseconds(date_time, num)
- `num`: Number of nanoseconds to subtract. [(U)Int*](../data-types/int-uint.md), [Float*](../data-types/float.md).
**Returned value**
- Returns `date_time` minus `num` nanoseconds. [DateTime64](../data-types/datetime64.md).
**Example**
@ -3596,6 +3818,7 @@ subtractInterval(interval_1, interval_2)
- `interval_2`: Second interval to be negated. [interval](../data-types/special-data-types/interval.md).
**Returned value**
- Returns a tuple of intervals. [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
:::note
@ -3642,6 +3865,7 @@ subtractTupleOfIntervals(interval_1, interval_2)
- `intervals`: Tuple of intervals to subtract from `date`. [tuple](../data-types/tuple.md)([interval](../data-types/special-data-types/interval.md)).
**Returned value**
- Returns `date` with subtracted `intervals`. [Date](../data-types/date.md)/[Date32](../data-types/date32.md)/[DateTime](../data-types/datetime.md)/[DateTime64](../data-types/datetime64.md).
**Example**

View File

@ -314,10 +314,71 @@ SELECT groupBitXor(cityHash64(*)) FROM table
Calculates a 32-bit hash code from any type of integer.
This is a relatively fast non-cryptographic hash function of average quality for numbers.
**Syntax**
```sql
intHash32(int)
```
**Arguments**
- `int` — Integer to hash. [(U)Int*](../data-types/int-uint.md).
**Returned value**
- 32-bit hash code. [UInt32](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT intHash32(42);
```
Result:
```response
┌─intHash32(42)─┐
│ 1228623923 │
└───────────────┘
```
## intHash64
Calculates a 64-bit hash code from any type of integer.
It works faster than intHash32. Average quality.
This is a relatively fast non-cryptographic hash function of average quality for numbers.
It works faster than [intHash32](#inthash32).
**Syntax**
```sql
intHash64(int)
```
**Arguments**
- `int` — Integer to hash. [(U)Int*](../data-types/int-uint.md).
**Returned value**
- 64-bit hash code. [UInt64](../data-types/int-uint.md).
**Example**
Query:
```sql
SELECT intHash64(42);
```
Result:
```response
┌────────intHash64(42)─┐
│ 11490350930367293593 │
└──────────────────────┘
```
## SHA1, SHA224, SHA256, SHA512, SHA512_256

View File

@ -76,7 +76,7 @@ WHERE macro = 'test';
└───────┴──────────────┘
```
## FQDN
## fqdn
Returns the fully qualified domain name of the ClickHouse server.
@ -86,7 +86,7 @@ Returns the fully qualified domain name of the ClickHouse server.
fqdn();
```
Aliases: `fullHostName`, 'FQDN'.
Aliases: `fullHostName`, `FQDN`.
**Returned value**
@ -2984,6 +2984,66 @@ Result:
└─────────┘
```
## partitionID
Computes the [partition ID](../../engines/table-engines/mergetree-family/custom-partitioning-key.md).
:::note
This function is slow and should not be called for large amount of rows.
:::
**Syntax**
```sql
partitionID(x[, y, ...]);
```
**Arguments**
- `x` — Column for which to return the partition ID.
- `y, ...` — Remaining N columns for which to return the partition ID (optional).
**Returned Value**
- Partition ID that the row would belong to. [String](../data-types/string.md).
**Example**
Query:
```sql
DROP TABLE IF EXISTS tab;
CREATE TABLE tab
(
i int,
j int
)
ENGINE = MergeTree
PARTITION BY i
ORDER BY tuple();
INSERT INTO tab VALUES (1, 1), (1, 2), (1, 3), (2, 4), (2, 5), (2, 6);
SELECT i, j, partitionID(i), _partition_id FROM tab ORDER BY i, j;
```
Result:
```response
┌─i─┬─j─┬─partitionID(i)─┬─_partition_id─┐
│ 1 │ 1 │ 1 │ 1 │
│ 1 │ 2 │ 1 │ 1 │
│ 1 │ 3 │ 1 │ 1 │
└───┴───┴────────────────┴───────────────┘
┌─i─┬─j─┬─partitionID(i)─┬─_partition_id─┐
│ 2 │ 4 │ 2 │ 2 │
│ 2 │ 5 │ 2 │ 2 │
│ 2 │ 6 │ 2 │ 2 │
└───┴───┴────────────────┴───────────────┘
```
## shardNum
Returns the index of a shard which processes a part of data in a distributed query. Indices are started from `1`.

View File

@ -12,9 +12,7 @@ Functions for [searching](string-search-functions.md) in strings and for [replac
## empty
Checks whether the input string is empty.
A string is considered non-empty if it contains at least one byte, even if this byte is a space or the null byte.
Checks whether the input string is empty. A string is considered non-empty if it contains at least one byte, even if this byte is a space or the null byte.
The function is also available for [arrays](array-functions.md#function-empty) and [UUIDs](uuid-functions.md#empty).
@ -48,9 +46,7 @@ Result:
## notEmpty
Checks whether the input string is non-empty.
A string is considered non-empty if it contains at least one byte, even if this byte is a space or the null byte.
Checks whether the input string is non-empty. A string is considered non-empty if it contains at least one byte, even if this byte is a space or the null byte.
The function is also available for [arrays](array-functions.md#function-notempty) and [UUIDs](uuid-functions.md#notempty).
@ -96,7 +92,7 @@ length(s)
**Parameters**
- `s`: An input string or array. [String](../data-types/string)/[Array](../data-types/array).
- `s` An input string or array. [String](../data-types/string)/[Array](../data-types/array).
**Returned value**
@ -149,7 +145,7 @@ lengthUTF8(s)
**Parameters**
- `s`: String containing valid UTF-8 encoded text. [String](../data-types/string).
- `s` String containing valid UTF-8 encoded text. [String](../data-types/string).
**Returned value**
@ -183,8 +179,8 @@ left(s, offset)
**Parameters**
- `s`: The string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset`: The number of bytes of the offset. [UInt*](../data-types/int-uint).
- `s` The string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset` The number of bytes of the offset. [UInt*](../data-types/int-uint).
**Returned value**
@ -230,8 +226,8 @@ leftUTF8(s, offset)
**Parameters**
- `s`: The UTF-8 encoded string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset`: The number of bytes of the offset. [UInt*](../data-types/int-uint).
- `s` The UTF-8 encoded string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset` The number of bytes of the offset. [UInt*](../data-types/int-uint).
**Returned value**
@ -347,8 +343,8 @@ right(s, offset)
**Parameters**
- `s`: The string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset`: The number of bytes of the offset. [UInt*](../data-types/int-uint).
- `s` The string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset` The number of bytes of the offset. [UInt*](../data-types/int-uint).
**Returned value**
@ -394,8 +390,8 @@ rightUTF8(s, offset)
**Parameters**
- `s`: The UTF-8 encoded string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset`: The number of bytes of the offset. [UInt*](../data-types/int-uint).
- `s` The UTF-8 encoded string to calculate a substring from. [String](../data-types/string.md) or [FixedString](../data-types/fixedstring.md).
- `offset` The number of bytes of the offset. [UInt*](../data-types/int-uint).
**Returned value**
@ -547,7 +543,7 @@ Alias: `ucase`
**Parameters**
- `input`: A string type [String](../data-types/string.md).
- `input` A string type [String](../data-types/string.md).
**Returned value**
@ -571,16 +567,47 @@ SELECT upper('clickhouse');
Converts a string to lowercase, assuming that the string contains valid UTF-8 encoded text. If this assumption is violated, no exception is thrown and the result is undefined.
Does not detect the language, e.g. for Turkish the result might not be exactly correct (i/İ vs. i/I).
:::note
Does not detect the language, e.g. for Turkish the result might not be exactly correct (i/İ vs. i/I). If the length of the UTF-8 byte sequence is different for upper and lower case of a code point (such as `ẞ` and `ß`), the result may be incorrect for this code point.
:::
If the length of the UTF-8 byte sequence is different for upper and lower case of a code point, the result may be incorrect for this code point.
**Syntax**
```sql
lowerUTF8(input)
```
**Parameters**
- `input` — A string type [String](../data-types/string.md).
**Returned value**
- A [String](../data-types/string.md) data type value.
**Example**
Query:
``` sql
SELECT lowerUTF8('MÜNCHEN') as Lowerutf8;
```
Result:
``` response
┌─Lowerutf8─┐
│ münchen │
└───────────┘
```
## upperUTF8
Converts a string to uppercase, assuming that the string contains valid UTF-8 encoded text. If this assumption is violated, no exception is thrown and the result is undefined.
If the length of the UTF-8 byte sequence is different for upper and lower case of a code point, the result may be incorrect for this code point.
:::note
Does not detect the language, e.g. for Turkish the result might not be exactly correct (i/İ vs. i/I). If the length of the UTF-8 byte sequence is different for upper and lower case of a code point (such as `ẞ` and `ß`), the result may be incorrect for this code point.
:::
**Syntax**
@ -590,7 +617,7 @@ upperUTF8(input)
**Parameters**
- `input`: A string type [String](../data-types/string.md).
- `input` A string type [String](../data-types/string.md).
**Returned value**
@ -604,6 +631,8 @@ Query:
SELECT upperUTF8('München') as Upperutf8;
```
Result:
``` response
┌─Upperutf8─┐
│ MÜNCHEN │
@ -614,6 +643,34 @@ SELECT upperUTF8('München') as Upperutf8;
Returns 1, if the set of bytes constitutes valid UTF-8-encoded text, otherwise 0.
**Syntax**
``` sql
isValidUTF8(input)
```
**Parameters**
- `input` — A string type [String](../data-types/string.md).
**Returned value**
- Returns `1`, if the set of bytes constitutes valid UTF-8-encoded text, otherwise `0`.
Query:
``` sql
SELECT isValidUTF8('\xc3\xb1') AS valid, isValidUTF8('\xc3\x28') AS invalid;
```
Result:
``` response
┌─valid─┬─invalid─┐
│ 1 │ 0 │
└───────┴─────────┘
```
## toValidUTF8
Replaces invalid UTF-8 characters by the `<60>` (U+FFFD) character. All running in a row invalid characters are collapsed into the one replacement character.
@ -883,7 +940,7 @@ Returns the substring of a string `s` which starts at the specified byte index `
substring(s, offset[, length])
```
Alias:
Aliases:
- `substr`
- `mid`
- `byteSlice`
@ -926,9 +983,9 @@ substringUTF8(s, offset[, length])
**Arguments**
- `s`: The string to calculate a substring from. [String](../data-types/string.md), [FixedString](../data-types/fixedstring.md) or [Enum](../data-types/enum.md)
- `offset`: The starting position of the substring in `s` . [(U)Int*](../data-types/int-uint.md).
- `length`: The maximum length of the substring. [(U)Int*](../data-types/int-uint.md). Optional.
- `s` The string to calculate a substring from. [String](../data-types/string.md), [FixedString](../data-types/fixedstring.md) or [Enum](../data-types/enum.md)
- `offset` The starting position of the substring in `s` . [(U)Int*](../data-types/int-uint.md).
- `length` The maximum length of the substring. [(U)Int*](../data-types/int-uint.md). Optional.
**Returned value**
@ -964,9 +1021,9 @@ Alias: `SUBSTRING_INDEX`
**Arguments**
- s: The string to extract substring from. [String](../data-types/string.md).
- delim: The character to split. [String](../data-types/string.md).
- count: The number of occurrences of the delimiter to count before extracting the substring. If count is positive, everything to the left of the final delimiter (counting from the left) is returned. If count is negative, everything to the right of the final delimiter (counting from the right) is returned. [UInt or Int](../data-types/int-uint.md)
- s The string to extract substring from. [String](../data-types/string.md).
- delim The character to split. [String](../data-types/string.md).
- count The number of occurrences of the delimiter to count before extracting the substring. If count is positive, everything to the left of the final delimiter (counting from the left) is returned. If count is negative, everything to the right of the final delimiter (counting from the right) is returned. [UInt or Int](../data-types/int-uint.md)
**Example**
@ -995,9 +1052,9 @@ substringIndexUTF8(s, delim, count)
**Arguments**
- `s`: The string to extract substring from. [String](../data-types/string.md).
- `delim`: The character to split. [String](../data-types/string.md).
- `count`: The number of occurrences of the delimiter to count before extracting the substring. If count is positive, everything to the left of the final delimiter (counting from the left) is returned. If count is negative, everything to the right of the final delimiter (counting from the right) is returned. [UInt or Int](../data-types/int-uint.md)
- `s` The string to extract substring from. [String](../data-types/string.md).
- `delim` The character to split. [String](../data-types/string.md).
- `count` The number of occurrences of the delimiter to count before extracting the substring. If count is positive, everything to the left of the final delimiter (counting from the left) is returned. If count is negative, everything to the right of the final delimiter (counting from the right) is returned. [UInt or Int](../data-types/int-uint.md)
**Returned value**
@ -1277,7 +1334,7 @@ tryBase64Decode(encoded)
**Arguments**
- `encoded`: [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value, returns an empty string.
- `encoded` [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value, returns an empty string.
**Returned value**
@ -1309,7 +1366,7 @@ tryBase64URLDecode(encodedUrl)
**Parameters**
- `encodedURL`: [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, returns an empty string.
- `encodedURL` [String](../data-types/string.md) column or constant. If the string is not a valid Base64-encoded value with URL-specific modifications, returns an empty string.
**Returned value**
@ -1555,7 +1612,7 @@ The result type is UInt64.
## normalizeQuery
Replaces literals, sequences of literals and complex aliases with placeholders.
Replaces literals, sequences of literals and complex aliases (containing whitespace, more than two digits or at least 36 bytes long such as UUIDs) with placeholder `?`.
**Syntax**
@ -1573,6 +1630,8 @@ normalizeQuery(x)
**Example**
Query:
``` sql
SELECT normalizeQuery('[1, 2, 3, x]') AS query;
```
@ -1585,9 +1644,44 @@ Result:
└──────────┘
```
## normalizeQueryKeepNames
Replaces literals, sequences of literals with placeholder `?` but does not replace complex aliases (containing whitespace, more than two digits
or at least 36 bytes long such as UUIDs). This helps better analyze complex query logs.
**Syntax**
``` sql
normalizeQueryKeepNames(x)
```
**Arguments**
- `x` — Sequence of characters. [String](../data-types/string.md).
**Returned value**
- Sequence of characters with placeholders. [String](../data-types/string.md).
**Example**
Query:
``` sql
SELECT normalizeQuery('SELECT 1 AS aComplexName123'), normalizeQueryKeepNames('SELECT 1 AS aComplexName123');
```
Result:
```result
┌─normalizeQuery('SELECT 1 AS aComplexName123')─┬─normalizeQueryKeepNames('SELECT 1 AS aComplexName123')─┐
│ SELECT ? AS `?` │ SELECT ? AS aComplexName123 │
└───────────────────────────────────────────────┴────────────────────────────────────────────────────────┘
```
## normalizedQueryHash
Returns identical 64bit hash values without the values of literals for similar queries. Can be helpful to analyze query log.
Returns identical 64bit hash values without the values of literals for similar queries. Can be helpful to analyze query logs.
**Syntax**
@ -1605,6 +1699,8 @@ normalizedQueryHash(x)
**Example**
Query:
``` sql
SELECT normalizedQueryHash('SELECT 1 AS `xyz`') != normalizedQueryHash('SELECT 1 AS `abc`') AS res;
```
@ -1617,6 +1713,43 @@ Result:
└─────┘
```
## normalizedQueryHashKeepNames
Like [normalizedQueryHash](#normalizedqueryhash) it returns identical 64bit hash values without the values of literals for similar queries but it does not replace complex aliases (containing whitespace, more than two digits
or at least 36 bytes long such as UUIDs) with a placeholder before hashing. Can be helpful to analyze query logs.
**Syntax**
``` sql
normalizedQueryHashKeepNames(x)
```
**Arguments**
- `x` — Sequence of characters. [String](../data-types/string.md).
**Returned value**
- Hash value. [UInt64](../data-types/int-uint.md#uint-ranges).
**Example**
``` sql
SELECT normalizedQueryHash('SELECT 1 AS `xyz123`') != normalizedQueryHash('SELECT 1 AS `abc123`') AS normalizedQueryHash;
SELECT normalizedQueryHashKeepNames('SELECT 1 AS `xyz123`') != normalizedQueryHashKeepNames('SELECT 1 AS `abc123`') AS normalizedQueryHashKeepNames;
```
Result:
```result
┌─normalizedQueryHash─┐
│ 0 │
└─────────────────────┘
┌─normalizedQueryHashKeepNames─┐
│ 1 │
└──────────────────────────────┘
```
## normalizeUTF8NFC
Converts a string to [NFC normalized form](https://en.wikipedia.org/wiki/Unicode_equivalence#Normal_forms), assuming the string is valid UTF8-encoded text.
@ -1935,7 +2068,7 @@ soundex(val)
**Arguments**
- `val` - Input value. [String](../data-types/string.md)
- `val` Input value. [String](../data-types/string.md)
**Returned value**
@ -1968,7 +2101,7 @@ punycodeEncode(val)
**Arguments**
- `val` - Input value. [String](../data-types/string.md)
- `val` Input value. [String](../data-types/string.md)
**Returned value**
@ -2001,7 +2134,7 @@ punycodeEncode(val)
**Arguments**
- `val` - Punycode-encoded string. [String](../data-types/string.md)
- `val` Punycode-encoded string. [String](../data-types/string.md)
**Returned value**
@ -2027,7 +2160,7 @@ Like `punycodeDecode` but returns an empty string if no valid Punycode-encoded s
## idnaEncode
Returns the the ASCII representation (ToASCII algorithm) of a domain name according to the [Internationalized Domain Names in Applications](https://en.wikipedia.org/wiki/Internationalized_domain_name#Internationalizing_Domain_Names_in_Applications) (IDNA) mechanism.
Returns the ASCII representation (ToASCII algorithm) of a domain name according to the [Internationalized Domain Names in Applications](https://en.wikipedia.org/wiki/Internationalized_domain_name#Internationalizing_Domain_Names_in_Applications) (IDNA) mechanism.
The input string must be UTF-encoded and translatable to an ASCII string, otherwise an exception is thrown.
Note: No percent decoding or trimming of tabs, spaces or control characters is performed.
@ -2039,7 +2172,7 @@ idnaEncode(val)
**Arguments**
- `val` - Input value. [String](../data-types/string.md)
- `val` Input value. [String](../data-types/string.md)
**Returned value**
@ -2065,7 +2198,7 @@ Like `idnaEncode` but returns an empty string in case of an error instead of thr
## idnaDecode
Returns the the Unicode (UTF-8) representation (ToUnicode algorithm) of a domain name according to the [Internationalized Domain Names in Applications](https://en.wikipedia.org/wiki/Internationalized_domain_name#Internationalizing_Domain_Names_in_Applications) (IDNA) mechanism.
Returns the Unicode (UTF-8) representation (ToUnicode algorithm) of a domain name according to the [Internationalized Domain Names in Applications](https://en.wikipedia.org/wiki/Internationalized_domain_name#Internationalizing_Domain_Names_in_Applications) (IDNA) mechanism.
In case of an error (e.g. because the input is invalid), the input string is returned.
Note that repeated application of `idnaEncode()` and `idnaDecode()` does not necessarily return the original string due to case normalization.
@ -2077,7 +2210,7 @@ idnaDecode(val)
**Arguments**
- `val` - Input value. [String](../data-types/string.md)
- `val` Input value. [String](../data-types/string.md)
**Returned value**
@ -2121,7 +2254,7 @@ Result:
└───────────────────────────────────────────┘
```
Alias: mismatches
Alias: `mismatches`
## stringJaccardIndex
@ -2175,7 +2308,7 @@ Result:
└─────────────────────────────────────┘
```
Alias: levenshteinDistance
Alias: `levenshteinDistance`
## editDistanceUTF8
@ -2201,7 +2334,7 @@ Result:
└─────────────────────────────────────┘
```
Alias: levenshteinDistanceUTF8
Alias: `levenshteinDistanceUTF8`
## damerauLevenshteinDistance
@ -2279,13 +2412,93 @@ Result:
Convert the first letter of each word to upper case and the rest to lower case. Words are sequences of alphanumeric characters separated by non-alphanumeric characters.
:::note
Because `initCap` converts only the first letter of each word to upper case you may observe unexpected behaviour for words containing apostrophes or capital letters. For example:
```sql
SELECT initCap('mother''s daughter'), initCap('joe McAdam');
```
will return
```response
┌─initCap('mother\'s daughter')─┬─initCap('joe McAdam')─┐
│ Mother'S Daughter │ Joe Mcadam │
└───────────────────────────────┴───────────────────────┘
```
This is a known behaviour, with no plans currently to fix it.
:::
**Syntax**
```sql
initcap(val)
```
**Arguments**
- `val` — Input value. [String](../data-types/string.md).
**Returned value**
- `val` with the first letter of each word converted to upper case. [String](../data-types/string.md).
**Example**
Query:
```sql
SELECT initcap('building for fast');
```
Result:
```text
┌─initcap('building for fast')─┐
│ Building For Fast │
└──────────────────────────────┘
```
## initcapUTF8
Like [initcap](#initcap), assuming that the string contains valid UTF-8 encoded text. If this assumption is violated, no exception is thrown and the result is undefined.
Does not detect the language, e.g. for Turkish the result might not be exactly correct (i/İ vs. i/I).
Like [initcap](#initcap), `initcapUTF8` converts the first letter of each word to upper case and the rest to lower case. Assumes that the string contains valid UTF-8 encoded text.
If this assumption is violated, no exception is thrown and the result is undefined.
:::note
This function does not detect the language, e.g. for Turkish the result might not be exactly correct (i/İ vs. i/I).
If the length of the UTF-8 byte sequence is different for upper and lower case of a code point, the result may be incorrect for this code point.
:::
**Syntax**
```sql
initcapUTF8(val)
```
**Arguments**
- `val` — Input value. [String](../data-types/string.md).
**Returned value**
- `val` with the first letter of each word converted to upper case. [String](../data-types/string.md).
**Example**
Query:
```sql
SELECT initcapUTF8('не тормозит');
```
Result:
```text
┌─initcapUTF8('не тормозит')─┐
Не Тормозит │
└────────────────────────────┘
```
## firstLine
@ -2299,7 +2512,7 @@ firstLine(val)
**Arguments**
- `val` - Input value. [String](../data-types/string.md)
- `val` Input value. [String](../data-types/string.md)
**Returned value**

View File

@ -34,7 +34,7 @@ Alias: `replace`.
Replaces the first occurrence of the substring matching the regular expression `pattern` (in [re2 syntax](https://github.com/google/re2/wiki/Syntax)) in `haystack` by the `replacement` string.
`replacement` can containing substitutions `\0-\9`.
`replacement` can contain substitutions `\0-\9`.
Substitutions `\1-\9` correspond to the 1st to 9th capturing group (submatch), substitution `\0` corresponds to the entire match.
To use a verbatim `\` character in the `pattern` or `replacement` strings, escape it using `\`.

View File

@ -7,7 +7,7 @@ sidebar_label: Tuples
## tuple
A function that allows grouping multiple columns.
For columns with the types T1, T2, ..., it returns a Tuple(T1, T2, ...) type tuple containing these columns. There is no cost to execute the function.
For columns C1, C2, ... with the types T1, T2, ..., it returns a named Tuple(C1 T1, C2 T2, ...) type tuple containing these columns if their names are unique and can be treated as unquoted identifiers, otherwise a Tuple(T1, T2, ...) is returned. There is no cost to execute the function.
Tuples are normally used as intermediate values for an argument of IN operators, or for creating a list of formal parameters of lambda functions. Tuples cant be written to a table.
The function implements the operator `(x, y, ...)`.
@ -259,6 +259,60 @@ Result:
└───────────────────────────────────────┘
```
## tupleNames
Converts a tuple into an array of column names. For a tuple in the form `Tuple(a T, b T, ...)`, it returns an array of strings representing the named columns of the tuple. If the tuple elements do not have explicit names, their indices will be used as the column names instead.
**Syntax**
``` sql
tupleNames(tuple)
```
**Arguments**
- `tuple` — Named tuple. [Tuple](../../sql-reference/data-types/tuple.md) with any types of values.
**Returned value**
- An array with strings.
Type: [Array](../../sql-reference/data-types/array.md)([Tuple](../../sql-reference/data-types/tuple.md)([String](../../sql-reference/data-types/string.md), ...)).
**Example**
Query:
``` sql
CREATE TABLE tupletest (col Tuple(user_ID UInt64, session_ID UInt64)) ENGINE = Memory;
INSERT INTO tupletest VALUES (tuple(1, 2));
SELECT tupleNames(col) FROM tupletest;
```
Result:
``` text
┌─tupleNames(col)──────────┐
│ ['user_ID','session_ID'] │
└──────────────────────────┘
```
If you pass a simple tuple to the function, ClickHouse uses the indexes of the columns as their names:
``` sql
SELECT tupleNames(tuple(3, 2, 1));
```
Result:
``` text
┌─tupleNames((3, 2, 1))─┐
│ ['1','2','3'] │
└───────────────────────┘
```
## tuplePlus
Calculates the sum of corresponding values of two tuples of the same size.

View File

@ -567,12 +567,13 @@ While no standard or recommendation exists for the epoch of Snowflake IDs, imple
**Syntax**
``` sql
generateSnowflakeID([expr])
generateSnowflakeID([expr, [machine_id]])
```
**Arguments**
- `expr` — An arbitrary [expression](../../sql-reference/syntax.md#syntax-expressions) used to bypass [common subexpression elimination](../../sql-reference/functions/index.md#common-subexpression-elimination) if the function is called multiple times in a query. The value of the expression has no effect on the returned Snowflake ID. Optional.
- `machine_id` — A machine ID, the lowest 10 bits are used. [Int64](../data-types/int-uint.md). Optional.
**Returned value**
@ -608,6 +609,16 @@ SELECT generateSnowflakeID(1), generateSnowflakeID(2);
└────────────────────────┴────────────────────────┘
```
**Example with expression and a machine ID**
```
SELECT generateSnowflakeID('expr', 1);
┌─generateSnowflakeID('expr', 1)─┐
│ 7201148511606784002 │
└────────────────────────────────┘
```
## snowflakeToDateTime
:::warning

View File

@ -58,6 +58,8 @@ KILL QUERY WHERE query_id='2-857d-4a57-9ee0-327da5d60a90'
KILL QUERY WHERE user='username' SYNC
```
:::tip If you are killing a query in ClickHouse Cloud or in a self-managed cluster, then be sure to use the ```ON CLUSTER [cluster-name]``` option, in order to ensure the query is killed on all replicas:::
Read-only users can only stop their own queries.
By default, the asynchronous version of queries is used (`ASYNC`), which does not wait for confirmation that queries have stopped.
@ -131,6 +133,7 @@ KILL MUTATION WHERE database = 'default' AND table = 'table'
-- Cancel the specific mutation:
KILL MUTATION WHERE database = 'default' AND table = 'table' AND mutation_id = 'mutation_3.txt'
```
:::tip If you are killing a mutation in ClickHouse Cloud or in a self-managed cluster, then be sure to use the ```ON CLUSTER [cluster-name]``` option, in order to ensure the mutation is killed on all replicas:::
The query is useful when a mutation is stuck and cannot finish (e.g. if some function in the mutation query throws an exception when applied to the data contained in the table).

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