Merge branch 'master' into uwu

.git-blame-ignore-revs

@@ -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

.github/actionlint.yml

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

.github/workflows/create_release.yml

@@ -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: Generate ChangeLog
+        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

.github/workflows/pull_request.yml

@@ -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:

README.md

@@ -34,14 +34,12 @@ 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
 
 Keep an eye out for upcoming meetups and events around the world. Somewhere else you want us to be? Please feel free to reach out to tyler `<at>` clickhouse `<dot>` com. You can also peruse [ClickHouse Events](https://clickhouse.com/company/news-events) for a list of all upcoming trainings, meetups, speaking engagements, etc.
 
-* [AWS Summit in DC](https://clickhouse.com/company/events/2024-06-aws-summit-dc) - Jun 26
-* [ClickHouse Meetup in Amsterdam](https://www.meetup.com/clickhouse-netherlands-user-group/events/300781068/) - Jun 27
 * [ClickHouse Meetup in Paris](https://www.meetup.com/clickhouse-france-user-group/events/300783448/) - Jul 9
 * [ClickHouse Cloud - Live Update Call](https://clickhouse.com/company/events/202407-cloud-update-live) - Jul 9
 * [ClickHouse Meetup @ Ramp - New York City](https://www.meetup.com/clickhouse-new-york-user-group/events/300595845/) - Jul 9

base/base/demangle.h

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

base/base/extended_types.h

@@ -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; };

base/base/isSharedPtrUnique.h

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

base/poco/Foundation/include/Poco/Format.h

@@ -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().
 

base/poco/Foundation/include/Poco/Logger.h

@@ -21,6 +21,8 @@
 #include <atomic>
 #include <cstddef>
 #include <map>
+#include <memory>
+#include <unordered_map>
 #include <vector>
 
 #include "Poco/Channel.h"

base/poco/Foundation/include/Poco/Message.h

@@ -19,6 +19,7 @@
 
 
 #include <map>
+#include <vector>
 #include "Poco/Foundation.h"
 #include "Poco/Timestamp.h"
 

base/poco/Foundation/include/Poco/RefCountedObject.h

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

base/poco/Foundation/src/Format.cpp

@@ -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)

base/poco/MongoDB/src/ObjectId.cpp

@@ -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;
 }

base/poco/MongoDB/src/OpMsgCursor.cpp

@@ -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);

base/poco/Net/include/Poco/Net/NameValueCollection.h

@@ -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.

base/poco/Net/src/HTTPMessage.cpp

@@ -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);

base/poco/Net/src/NameValueCollection.cpp

@@ -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);

cmake/limit_jobs.cmake

@@ -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).")

cmake/target.cmake

@@ -84,5 +84,5 @@ if (CMAKE_CROSSCOMPILING)
         message (FATAL_ERROR "Trying to cross-compile to unsupported system: ${CMAKE_SYSTEM_NAME}!")
     endif ()
 
-    message (STATUS "Cross-compiling for target: ${CMAKE_CXX_COMPILE_TARGET}")
+    message (STATUS "Cross-compiling for target: ${CMAKE_CXX_COMPILER_TARGET}")
 endif ()

contrib/CMakeLists.txt

@@ -228,6 +228,8 @@ add_contrib (ulid-c-cmake ulid-c)
 
 add_contrib (libssh-cmake libssh)
 
+add_contrib (prometheus-protobufs-cmake prometheus-protobufs prometheus-protobufs-gogo)
+
 # Put all targets defined here and in subdirectories under "contrib/<immediate-subdir>" folders in GUI-based IDEs.
 # Some of third-party projects may override CMAKE_FOLDER or FOLDER property of their targets, so they would not appear
 # in "contrib/..." as originally planned, so we workaround this by fixing FOLDER properties of all targets manually,

contrib/avro

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

contrib/aws-cmake/CMakeLists.txt

@@ -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})
 

contrib/azure

@@ -1 +1 @@
-Subproject commit 6262a76ef4c4c330c84e58dd4f6f13f4e6230fcd
+Subproject commit ea3e19a7be08519134c643177d56c7484dfec884

contrib/google-protobuf-cmake/protobuf_generate.cmake

@@ -157,15 +157,13 @@ function(protobuf_generate)
 
   set(_generated_srcs_all)
   foreach(_proto ${protobuf_generate_PROTOS})
-    get_filename_component(_abs_file ${_proto} ABSOLUTE)
-    get_filename_component(_abs_dir ${_abs_file} DIRECTORY)
-    get_filename_component(_basename ${_proto} NAME_WE)
-    file(RELATIVE_PATH _rel_dir ${CMAKE_CURRENT_SOURCE_DIR} ${_abs_dir})
-
-    set(_possible_rel_dir)
-    if (NOT protobuf_generate_APPEND_PATH)
-        set(_possible_rel_dir ${_rel_dir}/)
-    endif()
+    # The protobuf compiler doesn't return paths to the files it generates so we have to calculate those paths here:
+    # _abs_file - absolute path to a .proto file,
+    # _possible_rel_dir - relative path to the .proto file from some import directory specified in Protobuf_IMPORT_DIRS,
+    # _basename - filename of the .proto file (without path and without extenstion).
+    get_proto_absolute_path(_abs_file "${_proto}" ${_protobuf_include_path})
+    get_proto_relative_path(_possible_rel_dir "${_abs_file}" ${_protobuf_include_path})
+    get_filename_component(_basename "${_abs_file}" NAME_WE)
 
     set(_generated_srcs)
     foreach(_ext ${protobuf_generate_GENERATE_EXTENSIONS})
@@ -173,7 +171,7 @@ function(protobuf_generate)
     endforeach()
 
     if(protobuf_generate_DESCRIPTORS AND protobuf_generate_LANGUAGE STREQUAL cpp)
-      set(_descriptor_file "${CMAKE_CURRENT_BINARY_DIR}/${_basename}.desc")
+      set(_descriptor_file "${protobuf_generate_PROTOC_OUT_DIR}/${_possible_rel_dir}${_basename}.desc")
       set(_dll_desc_out "--descriptor_set_out=${_descriptor_file}")
       list(APPEND _generated_srcs ${_descriptor_file})
     endif()
@@ -196,3 +194,36 @@ function(protobuf_generate)
     target_sources(${protobuf_generate_TARGET} PRIVATE ${_generated_srcs_all})
   endif()
 endfunction()
+
+# Calculates the absolute path to a .proto file.
+function(get_proto_absolute_path result proto)
+  cmake_path(IS_ABSOLUTE proto _is_abs_path)
+  if(_is_abs_path)
+    set(${result} "${proto}" PARENT_SCOPE)
+    return()
+  endif()
+  foreach(_include_dir ${ARGN})
+    if(EXISTS "${_include_dir}/${proto}")
+      set(${result} "${_include_dir}/${proto}" PARENT_SCOPE)
+      return()
+    endif()
+  endforeach()
+  message(SEND_ERROR "Not found protobuf ${proto} in Protobuf_IMPORT_DIRS: ${ARGN}")
+endfunction()
+
+# Calculates a relative path to a .proto file. The returned path is relative to one of include directories.
+function(get_proto_relative_path result abs_path)
+  set(${result} "" PARENT_SCOPE)
+  get_filename_component(_abs_dir "${abs_path}" DIRECTORY)
+  foreach(_include_dir ${ARGN})
+    cmake_path(IS_PREFIX _include_dir "${_abs_dir}" _is_prefix)
+    if(_is_prefix)
+      file(RELATIVE_PATH _rel_dir "${_include_dir}" "${_abs_dir}")
+      if(NOT _rel_dir STREQUAL "")
+        set(${result} "${_rel_dir}/" PARENT_SCOPE)
+      endif()
+      return()
+    endif()
+  endforeach()
+  message(WARNING "Not found protobuf ${abs_path} in Protobuf_IMPORT_DIRS: ${ARGN}")
+endfunction()

contrib/grpc

@@ -1 +1 @@
-Subproject commit 77b2737a709d43d8c6895e3f03ca62b00bd9201c
+Subproject commit f5b7fdc2dff09ada06dbf6c75df298fb40f898df

contrib/jemalloc-cmake/CMakeLists.txt

@@ -34,7 +34,11 @@ if (OS_LINUX)
     # avoid spurious latencies and additional work associated with
     # MADV_DONTNEED. See
     # https://github.com/ClickHouse/ClickHouse/issues/11121 for motivation.
-    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")
+    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()
 else()
     set (JEMALLOC_CONFIG_MALLOC_CONF "oversize_threshold:0,muzzy_decay_ms:0,dirty_decay_ms:5000")
 endif()
@@ -175,12 +179,19 @@ 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

contrib/libpq-cmake/CMakeLists.txt

@@ -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})

contrib/openssl

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

contrib/orc

@@ -1 +1 @@
-Subproject commit 947cebaf9432d708253ac08dc3012daa6b4ede6f
+Subproject commit bcc025c09828c556f54cfbdf83a66b9acae7d17f

contrib/pocketfft

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

contrib/prometheus-protobufs-cmake/CMakeLists.txt

@@ -0,0 +1,34 @@
+option(ENABLE_PROMETHEUS_PROTOBUFS "Enable Prometheus Protobufs" ${ENABLE_PROTOBUF})
+
+if(NOT ENABLE_PROMETHEUS_PROTOBUFS)
+  message(STATUS "Not using prometheus-protobufs")
+  return()
+endif()
+
+set(Protobuf_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/google-protobuf/src")
+set(Prometheus_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/prometheus-protobufs")
+set(GogoProto_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/prometheus-protobufs-gogo")
+
+# Protobuf_IMPORT_DIRS specify where the protobuf compiler will look for .proto files.
+set(Old_Protobuf_IMPORT_DIRS ${Protobuf_IMPORT_DIRS})
+list(APPEND Protobuf_IMPORT_DIRS "${Protobuf_INCLUDE_DIR}" "${Prometheus_INCLUDE_DIR}" "${GogoProto_INCLUDE_DIR}")
+
+PROTOBUF_GENERATE_CPP(prometheus_protobufs_sources prometheus_protobufs_headers
+    "prompb/remote.proto"
+    "prompb/types.proto"
+    "gogoproto/gogo.proto"
+)
+
+set(Protobuf_IMPORT_DIRS ${Old_Protobuf_IMPORT_DIRS})
+
+# Ignore warnings while compiling protobuf-generated *.pb.h and *.pb.cpp files.
+set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -w")
+
+# Disable clang-tidy for protobuf-generated *.pb.h and *.pb.cpp files.
+set (CMAKE_CXX_CLANG_TIDY "")
+
+add_library(_prometheus_protobufs ${prometheus_protobufs_sources} ${prometheus_protobufs_headers})
+target_include_directories(_prometheus_protobufs SYSTEM PUBLIC "${CMAKE_CURRENT_BINARY_DIR}")
+target_link_libraries (_prometheus_protobufs PUBLIC ch_contrib::protobuf)
+
+add_library (ch_contrib::prometheus_protobufs ALIAS _prometheus_protobufs)

contrib/prometheus-protobufs-gogo/LICENSE

@@ -0,0 +1,35 @@
+Copyright (c) 2022, The Cosmos SDK Authors. All rights reserved.
+Copyright (c) 2013, The GoGo Authors. All rights reserved.
+
+Protocol Buffers for Go with Gadgets
+
+Go support for Protocol Buffers - Google's data interchange format
+
+Copyright 2010 The Go Authors.  All rights reserved.
+https://github.com/golang/protobuf
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+    * Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above
+copyright notice, this list of conditions and the following disclaimer
+in the documentation and/or other materials provided with the
+distribution.
+    * Neither the name of Google Inc. nor the names of its
+contributors may be used to endorse or promote products derived from
+this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

contrib/prometheus-protobufs-gogo/README

@@ -0,0 +1,4 @@
+File "gogoproto/gogo.proto" was downloaded from the "Protocol Buffers for Go with Gadgets" project:
+https://github.com/cosmos/gogoproto/blob/main/gogoproto/gogo.proto
+
+File "gogoproto/gogo.proto" is used in ClickHouse to compile prometheus protobufs.

contrib/prometheus-protobufs-gogo/gogoproto/gogo.proto

@@ -0,0 +1,145 @@
+// Protocol Buffers for Go with Gadgets
+//
+// Copyright (c) 2013, The GoGo Authors. All rights reserved.
+// http://github.com/cosmos/gogoproto
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+// notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+// copyright notice, this list of conditions and the following disclaimer
+// in the documentation and/or other materials provided with the
+// distribution.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+syntax = "proto2";
+package gogoproto;
+
+import "google/protobuf/descriptor.proto";
+
+option java_package = "com.google.protobuf";
+option java_outer_classname = "GoGoProtos";
+option go_package = "github.com/cosmos/gogoproto/gogoproto";
+
+extend google.protobuf.EnumOptions {
+	optional bool goproto_enum_prefix = 62001;
+	optional bool goproto_enum_stringer = 62021;
+	optional bool enum_stringer = 62022;
+	optional string enum_customname = 62023;
+	optional bool enumdecl = 62024;
+}
+
+extend google.protobuf.EnumValueOptions {
+	optional string enumvalue_customname = 66001;
+}
+
+extend google.protobuf.FileOptions {
+	optional bool goproto_getters_all = 63001;
+	optional bool goproto_enum_prefix_all = 63002;
+	optional bool goproto_stringer_all = 63003;
+	optional bool verbose_equal_all = 63004;
+	optional bool face_all = 63005;
+	optional bool gostring_all = 63006;
+	optional bool populate_all = 63007;
+	optional bool stringer_all = 63008;
+	optional bool onlyone_all = 63009;
+
+	optional bool equal_all = 63013;
+	optional bool description_all = 63014;
+	optional bool testgen_all = 63015;
+	optional bool benchgen_all = 63016;
+	optional bool marshaler_all = 63017;
+	optional bool unmarshaler_all = 63018;
+	optional bool stable_marshaler_all = 63019;
+
+	optional bool sizer_all = 63020;
+
+	optional bool goproto_enum_stringer_all = 63021;
+	optional bool enum_stringer_all = 63022;
+
+	optional bool unsafe_marshaler_all = 63023;
+	optional bool unsafe_unmarshaler_all = 63024;
+
+	optional bool goproto_extensions_map_all = 63025;
+	optional bool goproto_unrecognized_all = 63026;
+	optional bool gogoproto_import = 63027;
+	optional bool protosizer_all = 63028;
+	optional bool compare_all = 63029;
+    optional bool typedecl_all = 63030;
+    optional bool enumdecl_all = 63031;
+
+	optional bool goproto_registration = 63032;
+	optional bool messagename_all = 63033;
+
+	optional bool goproto_sizecache_all = 63034;
+	optional bool goproto_unkeyed_all = 63035;
+}
+
+extend google.protobuf.MessageOptions {
+	optional bool goproto_getters = 64001;
+	optional bool goproto_stringer = 64003;
+	optional bool verbose_equal = 64004;
+	optional bool face = 64005;
+	optional bool gostring = 64006;
+	optional bool populate = 64007;
+	optional bool stringer = 67008;
+	optional bool onlyone = 64009;
+
+	optional bool equal = 64013;
+	optional bool description = 64014;
+	optional bool testgen = 64015;
+	optional bool benchgen = 64016;
+	optional bool marshaler = 64017;
+	optional bool unmarshaler = 64018;
+	optional bool stable_marshaler = 64019;
+
+	optional bool sizer = 64020;
+
+	optional bool unsafe_marshaler = 64023;
+	optional bool unsafe_unmarshaler = 64024;
+
+	optional bool goproto_extensions_map = 64025;
+	optional bool goproto_unrecognized = 64026;
+
+	optional bool protosizer = 64028;
+	optional bool compare = 64029;
+
+	optional bool typedecl = 64030;
+
+	optional bool messagename = 64033;
+
+	optional bool goproto_sizecache = 64034;
+	optional bool goproto_unkeyed = 64035;
+}
+
+extend google.protobuf.FieldOptions {
+	optional bool nullable = 65001;
+	optional bool embed = 65002;
+	optional string customtype = 65003;
+	optional string customname = 65004;
+	optional string jsontag = 65005;
+	optional string moretags = 65006;
+	optional string casttype = 65007;
+	optional string castkey = 65008;
+	optional string castvalue = 65009;
+
+	optional bool stdtime = 65010;
+	optional bool stdduration = 65011;
+	optional bool wktpointer = 65012;
+
+	optional string castrepeated = 65013;
+}

contrib/prometheus-protobufs/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

contrib/prometheus-protobufs/README

@@ -0,0 +1,2 @@
+Files "prompb/remote.proto" and "prompb/types.proto" were downloaded from the Prometheus repository:
+https://github.com/prometheus/prometheus/tree/main/prompb

contrib/prometheus-protobufs/prompb/remote.proto

@@ -0,0 +1,88 @@
+// Copyright 2016 Prometheus Team
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+package prometheus;
+
+option go_package = "prompb";
+
+import "prompb/types.proto";
+import "gogoproto/gogo.proto";
+
+message WriteRequest {
+  repeated prometheus.TimeSeries timeseries = 1 [(gogoproto.nullable) = false];
+  // Cortex uses this field to determine the source of the write request.
+  // We reserve it to avoid any compatibility issues.
+  reserved  2;
+  repeated prometheus.MetricMetadata metadata = 3 [(gogoproto.nullable) = false];
+}
+
+// ReadRequest represents a remote read request.
+message ReadRequest {
+  repeated Query queries = 1;
+
+  enum ResponseType {
+    // Server will return a single ReadResponse message with matched series that includes list of raw samples.
+    // It's recommended to use streamed response types instead.
+    //
+    // Response headers:
+    // Content-Type: "application/x-protobuf"
+    // Content-Encoding: "snappy"
+    SAMPLES = 0;
+    // Server will stream a delimited ChunkedReadResponse message that
+    // contains XOR or HISTOGRAM(!) encoded chunks for a single series.
+    // Each message is following varint size and fixed size bigendian
+    // uint32 for CRC32 Castagnoli checksum.
+    //
+    // Response headers:
+    // Content-Type: "application/x-streamed-protobuf; proto=prometheus.ChunkedReadResponse"
+    // Content-Encoding: ""
+    STREAMED_XOR_CHUNKS = 1;
+  }
+
+  // accepted_response_types allows negotiating the content type of the response.
+  //
+  // Response types are taken from the list in the FIFO order. If no response type in `accepted_response_types` is
+  // implemented by server, error is returned.
+  // For request that do not contain `accepted_response_types` field the SAMPLES response type will be used.
+  repeated ResponseType accepted_response_types = 2;
+}
+
+// ReadResponse is a response when response_type equals SAMPLES.
+message ReadResponse {
+  // In same order as the request's queries.
+  repeated QueryResult results = 1;
+}
+
+message Query {
+  int64 start_timestamp_ms = 1;
+  int64 end_timestamp_ms = 2;
+  repeated prometheus.LabelMatcher matchers = 3;
+  prometheus.ReadHints hints = 4;
+}
+
+message QueryResult {
+  // Samples within a time series must be ordered by time.
+  repeated prometheus.TimeSeries timeseries = 1;
+}
+
+// ChunkedReadResponse is a response when response_type equals STREAMED_XOR_CHUNKS.
+// We strictly stream full series after series, optionally split by time. This means that a single frame can contain
+// partition of the single series, but once a new series is started to be streamed it means that no more chunks will
+// be sent for previous one. Series are returned sorted in the same way TSDB block are internally.
+message ChunkedReadResponse {
+  repeated prometheus.ChunkedSeries chunked_series = 1;
+
+  // query_index represents an index of the query from ReadRequest.queries these chunks relates to.
+  int64 query_index = 2;
+}

contrib/prometheus-protobufs/prompb/types.proto

@@ -0,0 +1,187 @@
+// Copyright 2017 Prometheus Team
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+package prometheus;
+
+option go_package = "prompb";
+
+import "gogoproto/gogo.proto";
+
+message MetricMetadata {
+  enum MetricType {
+    UNKNOWN        = 0;
+    COUNTER        = 1;
+    GAUGE          = 2;
+    HISTOGRAM      = 3;
+    GAUGEHISTOGRAM = 4;
+    SUMMARY        = 5;
+    INFO           = 6;
+    STATESET       = 7;
+  }
+
+  // Represents the metric type, these match the set from Prometheus.
+  // Refer to github.com/prometheus/common/model/metadata.go for details.
+  MetricType type = 1;
+  string metric_family_name = 2;
+  string help = 4;
+  string unit = 5;
+}
+
+message Sample {
+  double value    = 1;
+  // timestamp is in ms format, see model/timestamp/timestamp.go for
+  // conversion from time.Time to Prometheus timestamp.
+  int64 timestamp = 2;
+}
+
+message Exemplar {
+  // Optional, can be empty.
+  repeated Label labels = 1 [(gogoproto.nullable) = false];
+  double value = 2;
+  // timestamp is in ms format, see model/timestamp/timestamp.go for
+  // conversion from time.Time to Prometheus timestamp.
+  int64 timestamp = 3;
+}
+
+// A native histogram, also known as a sparse histogram.
+// Original design doc:
+// https://docs.google.com/document/d/1cLNv3aufPZb3fNfaJgdaRBZsInZKKIHo9E6HinJVbpM/edit
+// The appendix of this design doc also explains the concept of float
+// histograms. This Histogram message can represent both, the usual
+// integer histogram as well as a float histogram.
+message Histogram {
+  enum ResetHint {
+    UNKNOWN = 0; // Need to test for a counter reset explicitly.
+    YES     = 1; // This is the 1st histogram after a counter reset.
+    NO      = 2; // There was no counter reset between this and the previous Histogram.
+    GAUGE   = 3; // This is a gauge histogram where counter resets don't happen.
+  }
+
+  oneof count { // Count of observations in the histogram.
+    uint64 count_int   = 1;
+    double count_float = 2;
+  }
+  double sum = 3; // Sum of observations in the histogram.
+  // The schema defines the bucket schema. Currently, valid numbers
+  // are -4 <= n <= 8. They are all for base-2 bucket schemas, where 1
+  // is a bucket boundary in each case, and then each power of two is
+  // divided into 2^n logarithmic buckets. Or in other words, each
+  // bucket boundary is the previous boundary times 2^(2^-n). In the
+  // future, more bucket schemas may be added using numbers < -4 or >
+  // 8.
+  sint32 schema             = 4;
+  double zero_threshold     = 5; // Breadth of the zero bucket.
+  oneof zero_count { // Count in zero bucket.
+    uint64 zero_count_int     = 6;
+    double zero_count_float   = 7;
+  }
+
+  // Negative Buckets.
+  repeated BucketSpan negative_spans =  8 [(gogoproto.nullable) = false];
+  // Use either "negative_deltas" or "negative_counts", the former for
+  // regular histograms with integer counts, the latter for float
+  // histograms.
+  repeated sint64 negative_deltas    =  9; // Count delta of each bucket compared to previous one (or to zero for 1st bucket).
+  repeated double negative_counts    = 10; // Absolute count of each bucket.
+
+  // Positive Buckets.
+  repeated BucketSpan positive_spans = 11 [(gogoproto.nullable) = false];
+  // Use either "positive_deltas" or "positive_counts", the former for
+  // regular histograms with integer counts, the latter for float
+  // histograms.
+  repeated sint64 positive_deltas    = 12; // Count delta of each bucket compared to previous one (or to zero for 1st bucket).
+  repeated double positive_counts    = 13; // Absolute count of each bucket.
+
+  ResetHint reset_hint               = 14;
+  // timestamp is in ms format, see model/timestamp/timestamp.go for
+  // conversion from time.Time to Prometheus timestamp.
+  int64 timestamp = 15;
+}
+
+// A BucketSpan defines a number of consecutive buckets with their
+// offset. Logically, it would be more straightforward to include the
+// bucket counts in the Span. However, the protobuf representation is
+// more compact in the way the data is structured here (with all the
+// buckets in a single array separate from the Spans).
+message BucketSpan {
+  sint32 offset = 1; // Gap to previous span, or starting point for 1st span (which can be negative).
+  uint32 length = 2; // Length of consecutive buckets.
+}
+
+// TimeSeries represents samples and labels for a single time series.
+message TimeSeries {
+  // For a timeseries to be valid, and for the samples and exemplars
+  // to be ingested by the remote system properly, the labels field is required.
+  repeated Label labels         = 1 [(gogoproto.nullable) = false];
+  repeated Sample samples       = 2 [(gogoproto.nullable) = false];
+  repeated Exemplar exemplars   = 3 [(gogoproto.nullable) = false];
+  repeated Histogram histograms = 4 [(gogoproto.nullable) = false];
+}
+
+message Label {
+  string name  = 1;
+  string value = 2;
+}
+
+message Labels {
+  repeated Label labels = 1 [(gogoproto.nullable) = false];
+}
+
+// Matcher specifies a rule, which can match or set of labels or not.
+message LabelMatcher {
+  enum Type {
+    EQ  = 0;
+    NEQ = 1;
+    RE  = 2;
+    NRE = 3;
+  }
+  Type type    = 1;
+  string name  = 2;
+  string value = 3;
+}
+
+message ReadHints {
+  int64 step_ms = 1;  // Query step size in milliseconds.
+  string func = 2;    // String representation of surrounding function or aggregation.
+  int64 start_ms = 3; // Start time in milliseconds.
+  int64 end_ms = 4;   // End time in milliseconds.
+  repeated string grouping = 5; // List of label names used in aggregation.
+  bool by = 6; // Indicate whether it is without or by.
+  int64 range_ms = 7; // Range vector selector range in milliseconds.
+}
+
+// Chunk represents a TSDB chunk.
+// Time range [min, max] is inclusive.
+message Chunk {
+  int64 min_time_ms = 1;
+  int64 max_time_ms = 2;
+
+  // We require this to match chunkenc.Encoding.
+  enum Encoding {
+    UNKNOWN         = 0;
+    XOR             = 1;
+    HISTOGRAM       = 2;
+    FLOAT_HISTOGRAM = 3;
+  }
+  Encoding type  = 3;
+  bytes data     = 4;
+}
+
+// ChunkedSeries represents single, encoded time series.
+message ChunkedSeries {
+  // Labels should be sorted.
+  repeated Label labels = 1 [(gogoproto.nullable) = false];
+  // Chunks will be in start time order and may overlap.
+  repeated Chunk chunks = 2 [(gogoproto.nullable) = false];
+}

contrib/rocksdb

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

contrib/rocksdb-cmake/CMakeLists.txt

@@ -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")

contrib/s2geometry

@@ -1 +1 @@
-Subproject commit 0547c38371777a1c1c8be263a6f05c3bf71bb05b
+Subproject commit 6522a40338d58752c2a4227a3fc2bc4107c73e43

contrib/s2geometry-cmake/CMakeLists.txt

@@ -1,7 +1,7 @@
-option(ENABLE_S2_GEOMETRY "Enable S2 geometry library" ${ENABLE_LIBRARIES})
+option(ENABLE_S2_GEOMETRY "Enable S2 Geometry" ${ENABLE_LIBRARIES})
 
 if (NOT ENABLE_S2_GEOMETRY)
-    message(STATUS "Not using S2 geometry")
+    message(STATUS "Not using S2 Geometry")
     return()
 endif()
 
@@ -38,6 +38,7 @@ set(S2_SRCS
     "${S2_SOURCE_DIR}/s2/s2cell_index.cc"
     "${S2_SOURCE_DIR}/s2/s2cell_union.cc"
     "${S2_SOURCE_DIR}/s2/s2centroids.cc"
+    "${S2_SOURCE_DIR}/s2/s2chain_interpolation_query.cc"
     "${S2_SOURCE_DIR}/s2/s2closest_cell_query.cc"
     "${S2_SOURCE_DIR}/s2/s2closest_edge_query.cc"
     "${S2_SOURCE_DIR}/s2/s2closest_point_query.cc"
@@ -46,6 +47,7 @@ set(S2_SRCS
     "${S2_SOURCE_DIR}/s2/s2coords.cc"
     "${S2_SOURCE_DIR}/s2/s2crossing_edge_query.cc"
     "${S2_SOURCE_DIR}/s2/s2debug.cc"
+    "${S2_SOURCE_DIR}/s2/s2density_tree.cc"
     "${S2_SOURCE_DIR}/s2/s2earth.cc"
     "${S2_SOURCE_DIR}/s2/s2edge_clipping.cc"
     "${S2_SOURCE_DIR}/s2/s2edge_crosser.cc"
@@ -53,8 +55,10 @@ set(S2_SRCS
     "${S2_SOURCE_DIR}/s2/s2edge_distances.cc"
     "${S2_SOURCE_DIR}/s2/s2edge_tessellator.cc"
     "${S2_SOURCE_DIR}/s2/s2error.cc"
+    "${S2_SOURCE_DIR}/s2/s2fractal.cc"
     "${S2_SOURCE_DIR}/s2/s2furthest_edge_query.cc"
     "${S2_SOURCE_DIR}/s2/s2hausdorff_distance_query.cc"
+    "${S2_SOURCE_DIR}/s2/s2index_cell_data.cc"
     "${S2_SOURCE_DIR}/s2/s2latlng.cc"
     "${S2_SOURCE_DIR}/s2/s2latlng_rect.cc"
     "${S2_SOURCE_DIR}/s2/s2latlng_rect_bounder.cc"
@@ -63,10 +67,10 @@ set(S2_SRCS
     "${S2_SOURCE_DIR}/s2/s2lax_polyline_shape.cc"
     "${S2_SOURCE_DIR}/s2/s2loop.cc"
     "${S2_SOURCE_DIR}/s2/s2loop_measures.cc"
+    "${S2_SOURCE_DIR}/s2/s2max_distance_targets.cc"
     "${S2_SOURCE_DIR}/s2/s2measures.cc"
     "${S2_SOURCE_DIR}/s2/s2memory_tracker.cc"
     "${S2_SOURCE_DIR}/s2/s2metrics.cc"
-    "${S2_SOURCE_DIR}/s2/s2max_distance_targets.cc"
     "${S2_SOURCE_DIR}/s2/s2min_distance_targets.cc"
     "${S2_SOURCE_DIR}/s2/s2padded_cell.cc"
     "${S2_SOURCE_DIR}/s2/s2point_compression.cc"
@@ -80,10 +84,11 @@ set(S2_SRCS
     "${S2_SOURCE_DIR}/s2/s2predicates.cc"
     "${S2_SOURCE_DIR}/s2/s2projections.cc"
     "${S2_SOURCE_DIR}/s2/s2r2rect.cc"
-    "${S2_SOURCE_DIR}/s2/s2region.cc"
-    "${S2_SOURCE_DIR}/s2/s2region_term_indexer.cc"
+    "${S2_SOURCE_DIR}/s2/s2random.cc"
     "${S2_SOURCE_DIR}/s2/s2region_coverer.cc"
     "${S2_SOURCE_DIR}/s2/s2region_intersection.cc"
+    "${S2_SOURCE_DIR}/s2/s2region_sharder.cc"
+    "${S2_SOURCE_DIR}/s2/s2region_term_indexer.cc"
     "${S2_SOURCE_DIR}/s2/s2region_union.cc"
     "${S2_SOURCE_DIR}/s2/s2shape_index.cc"
     "${S2_SOURCE_DIR}/s2/s2shape_index_buffered_region.cc"
@@ -94,9 +99,12 @@ set(S2_SRCS
     "${S2_SOURCE_DIR}/s2/s2shapeutil_coding.cc"
     "${S2_SOURCE_DIR}/s2/s2shapeutil_contains_brute_force.cc"
     "${S2_SOURCE_DIR}/s2/s2shapeutil_conversion.cc"
+    "${S2_SOURCE_DIR}/s2/s2shapeutil_count_vertices.cc"
     "${S2_SOURCE_DIR}/s2/s2shapeutil_edge_iterator.cc"
+    "${S2_SOURCE_DIR}/s2/s2shapeutil_edge_wrap.cc"
     "${S2_SOURCE_DIR}/s2/s2shapeutil_get_reference_point.cc"
     "${S2_SOURCE_DIR}/s2/s2shapeutil_visit_crossing_edge_pairs.cc"
+    "${S2_SOURCE_DIR}/s2/s2testing.cc"
     "${S2_SOURCE_DIR}/s2/s2text_format.cc"
     "${S2_SOURCE_DIR}/s2/s2wedge_relations.cc"
     "${S2_SOURCE_DIR}/s2/s2winding_operation.cc"
@@ -140,6 +148,7 @@ target_link_libraries(_s2 PRIVATE
     absl::strings
     absl::type_traits
     absl::utility
+    absl::vlog_is_on
 )
 
 target_include_directories(_s2 SYSTEM BEFORE PUBLIC "${S2_SOURCE_DIR}/")

docker/keeper/Dockerfile

@@ -34,7 +34,7 @@ RUN arch=${TARGETARCH:-amd64} \
 # lts / testing / prestable / etc
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
-ARG VERSION="24.6.1.4423"
+ARG VERSION="24.6.2.17"
 ARG PACKAGES="clickhouse-keeper"
 ARG DIRECT_DOWNLOAD_URLS=""
 

docker/reqgenerator.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+# To run this script you must install docker and piddeptree python package
+#
+
+import subprocess
+import os
+import sys
+
+
+def build_docker_deps(image_name, imagedir):
+    cmd = f"""docker run  --entrypoint "/bin/bash" {image_name} -c "pip install pipdeptree 2>/dev/null 1>/dev/null && pipdeptree --freeze  --warn silence | sed 's/ \+//g' | sort | uniq" > {imagedir}/requirements.txt"""
+    subprocess.check_call(cmd, shell=True)
+
+
+def check_docker_file_install_with_pip(filepath):
+    image_name = None
+    with open(filepath, "r") as f:
+        for line in f:
+            if "docker build" in line:
+                arr = line.split(" ")
+                if len(arr) > 4:
+                    image_name = arr[4]
+            if "pip3 install" in line or "pip install" in line:
+                return image_name, True
+    return image_name, False
+
+
+def process_affected_images(images_dir):
+    for root, _dirs, files in os.walk(images_dir):
+        for f in files:
+            if f == "Dockerfile":
+                docker_file_path = os.path.join(root, f)
+                print("Checking image on path", docker_file_path)
+                image_name, has_pip = check_docker_file_install_with_pip(
+                    docker_file_path
+                )
+                if has_pip:
+                    print("Find pip in", image_name)
+                    try:
+                        build_docker_deps(image_name, root)
+                    except Exception as ex:
+                        print(ex)
+                else:
+                    print("Pip not found in", docker_file_path)
+
+
+process_affected_images(sys.argv[1])

docker/server/Dockerfile.alpine

@@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
 # lts / testing / prestable / etc
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
-ARG VERSION="24.6.1.4423"
+ARG VERSION="24.6.2.17"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 ARG DIRECT_DOWNLOAD_URLS=""
 

docker/server/Dockerfile.ubuntu

@@ -28,7 +28,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
 
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
-ARG VERSION="24.6.1.4423"
+ARG VERSION="24.6.2.17"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 #docker-official-library:off

docker/test/fasttest/Dockerfile

@@ -19,10 +19,7 @@ RUN apt-get update \
         odbcinst \
         psmisc \
         python3 \
-        python3-lxml \
         python3-pip \
-        python3-requests \
-        python3-termcolor \
         unixodbc \
         pv \
         jq \
@@ -31,7 +28,8 @@ RUN apt-get update \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
-RUN pip3 install numpy==1.26.3 scipy==1.12.0 pandas==1.5.3 Jinja2==3.1.3
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
 
 # This symlink is required by gcc to find the lld linker
 RUN ln -s /usr/bin/lld-${LLVM_VERSION} /usr/bin/ld.lld
@@ -39,6 +37,10 @@ RUN ln -s /usr/bin/lld-${LLVM_VERSION} /usr/bin/ld.lld
 # https://salsa.debian.org/pkg-llvm-team/llvm-toolchain/-/commit/992e52c0b156a5ba9c6a8a54f8c4857ddd3d371d
 RUN sed -i '/_IMPORT_CHECK_FILES_FOR_\(mlir-\|llvm-bolt\|merge-fdata\|MLIR\)/ {s|^|#|}' /usr/lib/llvm-${LLVM_VERSION}/lib/cmake/llvm/LLVMExports-*.cmake
 
+# LLVM changes paths for compiler-rt libraries. For some reason clang-18.1.8 cannot catch up libraries from default install path.
+# It's very dirty workaround, better to build compiler and LLVM ourself and use it. Details: https://github.com/llvm/llvm-project/issues/95792
+RUN test ! -d /usr/lib/llvm-18/lib/clang/18/lib/x86_64-pc-linux-gnu || ln -s /usr/lib/llvm-18/lib/clang/18/lib/x86_64-pc-linux-gnu /usr/lib/llvm-18/lib/clang/18/lib/x86_64-unknown-linux-gnu
+
 ARG CCACHE_VERSION=4.6.1
 RUN mkdir /tmp/ccache \
     && cd /tmp/ccache \

docker/test/fasttest/requirements.txt

@@ -0,0 +1,41 @@
+Jinja2==3.1.3
+MarkupSafe==2.1.5
+PyJWT==2.3.0
+PyYAML==6.0.1
+Pygments==2.11.2
+SecretStorage==3.3.1
+blinker==1.4
+certifi==2020.6.20
+chardet==4.0.0
+cryptography==3.4.8
+dbus-python==1.2.18
+distro==1.7.0
+httplib2==0.20.2
+idna==3.3
+importlib-metadata==4.6.4
+jeepney==0.7.1
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+lxml==4.8.0
+more-itertools==8.10.0
+numpy==1.26.3
+oauthlib==3.2.0
+packaging==24.1
+pandas==1.5.3
+pip==24.1.1
+pipdeptree==2.23.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+python-dateutil==2.9.0.post0
+pytz==2024.1
+requests==2.32.3
+scipy==1.12.0
+setuptools==59.6.0
+six==1.16.0
+termcolor==1.1.0
+urllib3==1.26.5
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/fasttest/run.sh

@@ -84,6 +84,8 @@ function start_server
     echo "ClickHouse server pid '$server_pid' started and responded"
 }
 
+export -f start_server
+
 function clone_root
 {
     [ "$UID" -eq 0 ] && git config --global --add safe.directory "$FASTTEST_SOURCE"
@@ -254,6 +256,19 @@ function configure
     rm -f "$FASTTEST_DATA/config.d/secure_ports.xml"
 }
 
+function timeout_with_logging() {
+    local exit_code=0
+
+    timeout -s TERM --preserve-status "${@}" || exit_code="${?}"
+
+    if [[ "${exit_code}" -eq "124" ]]
+    then
+      echo "The command 'timeout ${*}' has been killed by timeout"
+    fi
+
+    return $exit_code
+}
+
 function run_tests
 {
     clickhouse-server --version
@@ -269,6 +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
@@ -292,6 +312,8 @@ function run_tests
     clickhouse stop --pid-path "$FASTTEST_DATA"
 }
 
+export -f run_tests
+
 case "$stage" in
 "")
     ls -la
@@ -315,7 +337,7 @@ case "$stage" in
     configure 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/install_log.txt"
     ;&
 "run_tests")
-    run_tests
+    timeout_with_logging 35m bash -c run_tests ||:
     /process_functional_tests_result.py --in-results-dir "$FASTTEST_OUTPUT/" \
         --out-results-file "$FASTTEST_OUTPUT/test_results.tsv" \
         --out-status-file "$FASTTEST_OUTPUT/check_status.tsv" || echo -e "failure\tCannot parse results" > "$FASTTEST_OUTPUT/check_status.tsv"

docker/test/fuzzer/Dockerfile

@@ -31,7 +31,8 @@ RUN apt-get update \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
-RUN pip3 install Jinja2
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
 
 COPY * /
 

docker/test/fuzzer/requirements.txt

@@ -0,0 +1,27 @@
+blinker==1.4
+cryptography==3.4.8
+dbus-python==1.2.18
+distro==1.7.0
+httplib2==0.20.2
+importlib-metadata==4.6.4
+jeepney==0.7.1
+Jinja2==3.1.4
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+MarkupSafe==2.1.5
+more-itertools==8.10.0
+oauthlib==3.2.0
+packaging==24.1
+pip==24.1.1
+pipdeptree==2.23.0
+PyJWT==2.3.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+SecretStorage==3.3.1
+setuptools==59.6.0
+six==1.16.0
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/integration/base/Dockerfile

@@ -33,7 +33,8 @@ RUN apt-get update \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
-RUN pip3 install pycurl
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r requirements.txt && rm -rf /root/.cache/pip
 
 # Architecture of the image when BuildKit/buildx is used
 ARG TARGETARCH

docker/test/integration/base/requirements.txt

@@ -0,0 +1,26 @@
+blinker==1.4
+cryptography==3.4.8
+dbus-python==1.2.18
+distro==1.7.0
+httplib2==0.20.2
+importlib-metadata==4.6.4
+jeepney==0.7.1
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+more-itertools==8.10.0
+oauthlib==3.2.0
+packaging==24.1
+pip==24.1.1
+pipdeptree==2.23.0
+pycurl==7.45.3
+PyJWT==2.3.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+SecretStorage==3.3.1
+setuptools==59.6.0
+six==1.16.0
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/integration/resolver/Dockerfile

@@ -2,4 +2,5 @@
 # Helper docker container to run python bottle apps
 
 FROM python:3
-RUN python -m pip install bottle
+COPY requirements.txt /
+RUN python -m pip install --no-cache-dir -r requirements.txt

docker/test/integration/resolver/requirements.txt

@@ -0,0 +1,6 @@
+bottle==0.12.25
+packaging==24.1
+pip==23.2.1
+pipdeptree==2.23.0
+setuptools==69.0.3
+wheel==0.42.0

docker/test/integration/runner/Dockerfile

@@ -26,7 +26,6 @@ RUN apt-get update \
     libicu-dev \
     bsdutils \
     curl \
-    python3-pika \
     liblua5.1-dev \
     luajit \
     libssl-dev \
@@ -61,49 +60,8 @@ RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - \
 
 # kazoo 2.10.0 is broken
 # https://s3.amazonaws.com/clickhouse-test-reports/59337/524625a1d2f4cc608a3f1059e3df2c30f353a649/integration_tests__asan__analyzer__[5_6].html
-RUN python3 -m pip install --no-cache-dir \
-    PyMySQL==1.1.0 \
-    asyncio==3.4.3 \
-    avro==1.10.2 \
-    azure-storage-blob==12.19.0 \
-    boto3==1.34.24 \
-    cassandra-driver==3.29.0 \
-    confluent-kafka==2.3.0 \
-    delta-spark==2.3.0 \
-    dict2xml==1.7.4 \
-    dicttoxml==1.7.16 \
-    docker==6.1.3 \
-    docker-compose==1.29.2 \
-    grpcio==1.60.0 \
-    grpcio-tools==1.60.0 \
-    kafka-python==2.0.2 \
-    lz4==4.3.3 \
-    minio==7.2.3 \
-    nats-py==2.6.0 \
-    protobuf==4.25.2 \
-    kazoo==2.9.0 \
-    psycopg2-binary==2.9.6 \
-    pyhdfs==0.3.1 \
-    pymongo==3.11.0 \
-    pyspark==3.3.2 \
-    pytest==7.4.4 \
-    pytest-order==1.0.0 \
-    pytest-random==0.2 \
-    pytest-repeat==0.9.3 \
-    pytest-timeout==2.2.0 \
-    pytest-xdist==3.5.0 \
-    pytest-reportlog==0.4.0 \
-    pytz==2023.3.post1 \
-    pyyaml==5.3.1 \
-    redis==5.0.1 \
-    requests-kerberos==0.14.0 \
-    tzlocal==2.1 \
-    retry==0.9.2 \
-    bs4==0.0.2 \
-    lxml==5.1.0 \
-    urllib3==2.0.7 \
-    jwcrypto==1.5.6
-# bs4, lxml are for cloud tests, do not delete
+COPY requirements.txt /
+RUN python3 -m pip install --no-cache-dir -r requirements.txt
 
 # Hudi supports only spark 3.3.*, not 3.4
 RUN curl -fsSL -O https://archive.apache.org/dist/spark/spark-3.3.2/spark-3.3.2-bin-hadoop3.tgz \

docker/test/integration/runner/requirements.txt

@@ -0,0 +1,113 @@
+PyHDFS==0.3.1
+PyJWT==2.3.0
+PyMySQL==1.1.0
+PyNaCl==1.5.0
+PyYAML==5.3.1
+SecretStorage==3.3.1
+argon2-cffi-bindings==21.2.0
+argon2-cffi==23.1.0
+async-timeout==4.0.3
+asyncio==3.4.3
+attrs==23.2.0
+avro==1.10.2
+azure-core==1.30.1
+azure-storage-blob==12.19.0
+bcrypt==4.1.3
+beautifulsoup4==4.12.3
+blinker==1.4
+boto3==1.34.24
+botocore==1.34.101
+bs4==0.0.2
+cassandra-driver==3.29.0
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+confluent-kafka==2.3.0
+cryptography==3.4.8
+dbus-python==1.2.18
+decorator==5.1.1
+delta-spark==2.3.0
+dict2xml==1.7.4
+dicttoxml==1.7.16
+distro-info==1.1+ubuntu0.2
+distro==1.7.0
+docker-compose==1.29.2
+docker==6.1.3
+dockerpty==0.4.1
+docopt==0.6.2
+exceptiongroup==1.2.1
+execnet==2.1.1
+geomet==0.2.1.post1
+grpcio-tools==1.60.0
+grpcio==1.60.0
+gssapi==1.8.3
+httplib2==0.20.2
+idna==3.7
+importlib-metadata==4.6.4
+iniconfig==2.0.0
+isodate==0.6.1
+jeepney==0.7.1
+jmespath==1.0.1
+jsonschema==3.2.0
+jwcrypto==1.5.6
+kafka-python==2.0.2
+kazoo==2.9.0
+keyring==23.5.0
+krb5==0.5.1
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+lxml==5.1.0
+lz4==4.3.3
+minio==7.2.3
+more-itertools==8.10.0
+nats-py==2.6.0
+oauthlib==3.2.0
+packaging==24.0
+paramiko==3.4.0
+pika==1.2.0
+pip==24.1.1
+pipdeptree==2.23.0
+pluggy==1.5.0
+protobuf==4.25.2
+psycopg2-binary==2.9.6
+py4j==0.10.9.5
+py==1.11.0
+pycparser==2.22
+pycryptodome==3.20.0
+pymongo==3.11.0
+pyparsing==2.4.7
+pyrsistent==0.20.0
+pyspark==3.3.2
+pyspnego==0.10.2
+pytest-order==1.0.0
+pytest-random==0.2
+pytest-repeat==0.9.3
+pytest-reportlog==0.4.0
+pytest-timeout==2.2.0
+pytest-xdist==3.5.0
+pytest==7.4.4
+python-apt==2.4.0+ubuntu3
+python-dateutil==2.9.0.post0
+python-dotenv==0.21.1
+pytz==2023.3.post1
+redis==5.0.1
+requests-kerberos==0.14.0
+requests==2.31.0
+retry==0.9.2
+s3transfer==0.10.1
+setuptools==59.6.0
+simplejson==3.19.2
+six==1.16.0
+soupsieve==2.5
+texttable==1.7.0
+tomli==2.0.1
+typing_extensions==4.11.0
+tzlocal==2.1
+unattended-upgrades==0.1
+urllib3==2.0.7
+wadllib==1.3.6
+websocket-client==0.59.0
+wheel==0.37.1
+zipp==1.0.0

docker/test/libfuzzer/Dockerfile

@@ -1,3 +1,4 @@
+# docker build -t clickhouse/libfuzzer .
 ARG FROM_TAG=latest
 FROM clickhouse/test-base:$FROM_TAG
 
@@ -29,7 +30,8 @@ RUN apt-get update \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
-RUN pip3 install Jinja2
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
 
 COPY * /
 

docker/test/libfuzzer/requirements.txt

@@ -0,0 +1,27 @@
+blinker==1.4
+cryptography==3.4.8
+dbus-python==1.2.18
+distro==1.7.0
+httplib2==0.20.2
+importlib-metadata==4.6.4
+jeepney==0.7.1
+Jinja2==3.1.4
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+MarkupSafe==2.1.5
+more-itertools==8.10.0
+oauthlib==3.2.0
+packaging==24.1
+pip==24.1.1
+pipdeptree==2.23.0
+PyJWT==2.3.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+SecretStorage==3.3.1
+setuptools==59.6.0
+six==1.16.0
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/libfuzzer/run_libfuzzer.py

@@ -27,19 +27,19 @@ def run_fuzzer(fuzzer: str):
             parser.read(path)
 
             if parser.has_section("asan"):
-                os.environ[
-                    "ASAN_OPTIONS"
-                ] = f"{os.environ['ASAN_OPTIONS']}:{':'.join('%s=%s' % (key, value) for key, value in parser['asan'].items())}"
+                os.environ["ASAN_OPTIONS"] = (
+                    f"{os.environ['ASAN_OPTIONS']}:{':'.join('%s=%s' % (key, value) for key, value in parser['asan'].items())}"
+                )
 
             if parser.has_section("msan"):
-                os.environ[
-                    "MSAN_OPTIONS"
-                ] = f"{os.environ['MSAN_OPTIONS']}:{':'.join('%s=%s' % (key, value) for key, value in parser['msan'].items())}"
+                os.environ["MSAN_OPTIONS"] = (
+                    f"{os.environ['MSAN_OPTIONS']}:{':'.join('%s=%s' % (key, value) for key, value in parser['msan'].items())}"
+                )
 
             if parser.has_section("ubsan"):
-                os.environ[
-                    "UBSAN_OPTIONS"
-                ] = f"{os.environ['UBSAN_OPTIONS']}:{':'.join('%s=%s' % (key, value) for key, value in parser['ubsan'].items())}"
+                os.environ["UBSAN_OPTIONS"] = (
+                    f"{os.environ['UBSAN_OPTIONS']}:{':'.join('%s=%s' % (key, value) for key, value in parser['ubsan'].items())}"
+                )
 
             if parser.has_section("libfuzzer"):
                 custom_libfuzzer_options = " ".join(

docker/test/performance-comparison/Dockerfile

@@ -23,7 +23,6 @@ RUN apt-get update \
             python3 \
             python3-dev \
             python3-pip \
-            python3-setuptools \
             rsync \
             tree \
             tzdata \
@@ -33,12 +32,14 @@ RUN apt-get update \
             cargo \
             ripgrep \
             zstd \
-    && pip3 --no-cache-dir install 'clickhouse-driver==0.2.1' scipy \
     && apt-get purge --yes python3-dev g++ \
     && apt-get autoremove --yes \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
+COPY requirements.txt /
+RUN pip3 --no-cache-dir install -r requirements.txt
+
 COPY run.sh /
 
 CMD ["bash", "/run.sh"]

docker/test/performance-comparison/requirements.txt

@@ -0,0 +1,32 @@
+blinker==1.4
+clickhouse-driver==0.2.7
+cryptography==3.4.8
+dbus-python==1.2.18
+distro==1.7.0
+httplib2==0.20.2
+importlib-metadata==4.6.4
+jeepney==0.7.1
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+more-itertools==8.10.0
+numpy==1.26.3
+oauthlib==3.2.0
+packaging==24.1
+pip==24.1.1
+pipdeptree==2.23.0
+Pygments==2.11.2
+PyJWT==2.3.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+pytz==2023.4
+PyYAML==6.0.1
+scipy==1.12.0
+SecretStorage==3.3.1
+setuptools==59.6.0
+six==1.16.0
+tzlocal==2.1
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/sqllogic/Dockerfile

@@ -18,11 +18,8 @@ RUN apt-get update --yes \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
-RUN pip3 install \
-    numpy \
-    pyodbc \
-    deepdiff \
-    sqlglot
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
 
 ARG odbc_driver_url="https://github.com/ClickHouse/clickhouse-odbc/releases/download/v1.1.6.20200320/clickhouse-odbc-1.1.6-Linux.tar.gz"
 

docker/test/sqllogic/requirements.txt

@@ -0,0 +1,30 @@
+blinker==1.4
+cryptography==3.4.8
+dbus-python==1.2.18
+deepdiff==7.0.1
+distro==1.7.0
+httplib2==0.20.2
+importlib-metadata==4.6.4
+jeepney==0.7.1
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+more-itertools==8.10.0
+numpy==1.26.4
+oauthlib==3.2.0
+ordered-set==4.1.0
+packaging==24.1
+pip==24.1.1
+pipdeptree==2.23.0
+PyJWT==2.3.0
+pyodbc==5.1.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+SecretStorage==3.3.1
+setuptools==59.6.0
+six==1.16.0
+sqlglot==23.16.0
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/sqltest/Dockerfile

@@ -14,9 +14,8 @@ RUN apt-get update --yes \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
-RUN pip3 install \
-    pyyaml \
-    clickhouse-driver
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
 
 ARG sqltest_repo="https://github.com/elliotchance/sqltest/"
 

docker/test/sqltest/requirements.txt

@@ -0,0 +1,29 @@
+blinker==1.4
+clickhouse-driver==0.2.7
+cryptography==3.4.8
+dbus-python==1.2.18
+distro==1.7.0
+httplib2==0.20.2
+importlib-metadata==4.6.4
+jeepney==0.7.1
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+more-itertools==8.10.0
+oauthlib==3.2.0
+packaging==24.1
+pip==24.1.1
+pipdeptree==2.23.0
+PyJWT==2.3.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+pytz==2024.1
+PyYAML==6.0.1
+SecretStorage==3.3.1
+setuptools==59.6.0
+six==1.16.0
+tzlocal==5.2
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/stateful/Dockerfile

@@ -6,7 +6,6 @@ FROM clickhouse/stateless-test:$FROM_TAG
 RUN apt-get update -y \
     && env DEBIAN_FRONTEND=noninteractive \
         apt-get install --yes --no-install-recommends \
-        python3-requests \
         nodejs \
         npm \
     && apt-get clean \

docker/test/stateful/run.sh

@@ -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/rubbish.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

docker/test/stateless/Dockerfile

@@ -25,10 +25,7 @@ RUN apt-get update -y \
             openssl \
             postgresql-client \
             python3 \
-            python3-lxml \
             python3-pip \
-            python3-requests \
-            python3-termcolor \
             qemu-user-static \
             sqlite3 \
             sudo \
@@ -51,7 +48,8 @@ RUN curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v${PR
     && unzip protoc-${PROTOC_VERSION}-linux-x86_64.zip -d /usr/local \
     && rm protoc-${PROTOC_VERSION}-linux-x86_64.zip
 
-RUN pip3 install numpy==1.26.3 scipy==1.12.0 pandas==1.5.3 Jinja2==3.1.3 pyarrow==15.0.0
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r /requirements.txt
 
 RUN mkdir -p /tmp/clickhouse-odbc-tmp \
   && cd /tmp/clickhouse-odbc-tmp \
@@ -88,6 +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

docker/test/stateless/requirements.txt

@@ -0,0 +1,53 @@
+awscli==1.22.34
+blinker==1.4
+botocore==1.23.34
+certifi==2020.6.20
+chardet==4.0.0
+colorama==0.4.4
+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
+importlib-metadata==4.6.4
+jeepney==0.7.1
+Jinja2==3.1.3
+jmespath==0.10.0
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+lxml==4.8.0
+MarkupSafe==2.1.5
+more-itertools==8.10.0
+numpy==1.26.3
+oauthlib==3.2.0
+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
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu3
+python-dateutil==2.8.1
+pytz==2024.1
+PyYAML==6.0.1
+requests==2.32.3
+roman==3.3
+rsa==4.8
+s3transfer==0.5.0
+scipy==1.12.0
+SecretStorage==3.3.1
+setuptools==59.6.0
+six==1.16.0
+termcolor==1.1.0
+urllib3==1.26.5
+wadllib==1.3.6
+wheel==0.37.1
+zipp==1.0.0

docker/test/stateless/run.sh

@@ -6,19 +6,30 @@ source /setup_export_logs.sh
 # fail on errors, verbose and export all env variables
 set -e -x -a
 
+MAX_RUN_TIME=${MAX_RUN_TIME:-7200}
+MAX_RUN_TIME=$((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=1
+
+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
 
@@ -43,6 +54,9 @@ source /utils.lib
 /usr/share/clickhouse-test/config/install.sh
 
 ./setup_minio.sh stateless
+m./c admin trace clickminio > /test_output/rubbish.log &
+MC_ADMIN_PID=$!
+
 ./setup_hdfs_minicluster.sh
 
 config_logs_export_cluster /etc/clickhouse-server/config.d/system_logs_export.yaml
@@ -55,12 +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<\/$1>/d" /etc/clickhouse-server/config.d/keeper_port.xml
@@ -93,10 +101,57 @@ if [ "$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
@@ -133,7 +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
@@ -213,15 +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 == $(clickhouse-client --query "SELECT value LIKE '%SANITIZE_COVERAGE%' FROM system.build_options WHERE name = 'CXX_FLAGS'") ]]; then
         # Coverage on a per-test basis could only be collected sequentially.
         # Do not set the --jobs parameter.
@@ -229,7 +284,11 @@ function run_tests()
     else
         # All other configurations are OK.
         ADDITIONAL_OPTIONS+=('--jobs')
-        ADDITIONAL_OPTIONS+=('8')
+        ADDITIONAL_OPTIONS+=('5')
+    fi
+
+    if [[ "$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
@@ -253,7 +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
@@ -262,14 +321,17 @@ function run_tests()
 
 export -f run_tests
 
+
+# This should be enough to setup job and collect artifacts
+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.
-    timeout_with_logging "$MAX_RUN_TIME" bash -c 'NUM_TRIES=1; USE_DATABASE_ORDINARY=1; run_tests' \
+    timeout_with_logging "$TIMEOUT" bash -c 'NUM_TRIES=1; USE_DATABASE_ORDINARY=1; run_tests' \
       | sed 's/All tests have finished//' | sed 's/No tests were run//' ||:
 fi
 
-timeout_with_logging "$MAX_RUN_TIME" bash -c run_tests ||:
+timeout_with_logging "$TIMEOUT" bash -c run_tests ||:
 
 echo "Files in current directory"
 ls -la ./
@@ -290,7 +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" != "${#err}"  ]] && failed_to_save_logs=1
@@ -299,7 +361,7 @@ do
         [[ "0" != "${#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
@@ -310,19 +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)
@@ -342,12 +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
@@ -383,7 +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 ||:
@@ -394,9 +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

docker/test/stateless/stress_tests.lib

@@ -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

docker/test/stateless/utils.lib

@@ -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
@@ -38,7 +43,7 @@ function fn_exists() {
 function timeout_with_logging() {
     local exit_code=0
 
-    timeout "${@}" || exit_code="${?}"
+    timeout -s TERM --preserve-status "${@}" || exit_code="${?}"
 
     if [[ "${exit_code}" -eq "124" ]]
     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

docker/test/stress/run.sh

@@ -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

docker/test/style/Dockerfile

@@ -23,22 +23,8 @@ RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
 # python-magic is the same version as in Ubuntu 22.04
-RUN pip3 install \
-        PyGithub \
-        black==23.12.0 \
-        boto3 \
-        codespell==2.2.1 \
-        mypy==1.8.0 \
-        pylint==3.1.0 \
-        python-magic==0.4.24 \
-        flake8==4.0.1 \
-        requests \
-        thefuzz \
-        tqdm==4.66.4 \
-        types-requests \
-        unidiff \
-        jwt \
-    && rm -rf /root/.cache/pip
+COPY requirements.txt /
+RUN pip3 install --no-cache-dir -r requirements.txt
 
 RUN echo "en_US.UTF-8 UTF-8" > /etc/locale.gen && locale-gen en_US.UTF-8
 ENV LC_ALL en_US.UTF-8

docker/test/style/requirements.txt

@@ -0,0 +1,58 @@
+aiohttp==3.9.5
+aiosignal==1.3.1
+astroid==3.1.0
+async-timeout==4.0.3
+attrs==23.2.0
+black==24.4.2
+boto3==1.34.131
+botocore==1.34.131
+certifi==2024.6.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+codespell==2.2.1
+cryptography==42.0.8
+Deprecated==1.2.14
+dill==0.3.8
+flake8==4.0.1
+frozenlist==1.4.1
+idna==3.7
+isort==5.13.2
+jmespath==1.0.1
+jwt==1.3.1
+mccabe==0.6.1
+multidict==6.0.5
+mypy==1.8.0
+mypy-extensions==1.0.0
+packaging==24.1
+pathspec==0.9.0
+pip==24.1.1
+pipdeptree==2.23.0
+platformdirs==4.2.2
+pycodestyle==2.8.0
+pycparser==2.22
+pyflakes==2.4.0
+PyGithub==2.3.0
+PyJWT==2.8.0
+pylint==3.1.0
+PyNaCl==1.5.0
+python-dateutil==2.9.0.post0
+python-magic==0.4.24
+PyYAML==6.0.1
+rapidfuzz==3.9.3
+requests==2.32.3
+s3transfer==0.10.1
+setuptools==59.6.0
+six==1.16.0
+thefuzz==0.22.1
+tomli==2.0.1
+tomlkit==0.12.5
+tqdm==4.66.4
+types-requests==2.32.0.20240622
+typing_extensions==4.12.2
+unidiff==0.7.5
+urllib3==2.2.2
+wheel==0.37.1
+wrapt==1.16.0
+yamllint==1.26.3
+yarl==1.9.4

docker/test/util/process_functional_tests_result.py

@@ -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")

docs/changelogs/v24.6.2.17-stable.md

@@ -0,0 +1,26 @@
+---
+sidebar_position: 1
+sidebar_label: 2024
+---
+
+# 2024 Changelog
+
+### ClickHouse release v24.6.2.17-stable (5710a8b5c0c) FIXME as compared to v24.6.1.4423-stable (dcced7c8478)
+
+#### New Feature
+* Backported in [#66002](https://github.com/ClickHouse/ClickHouse/issues/66002): Add AzureQueue storage. [#65458](https://github.com/ClickHouse/ClickHouse/pull/65458) ([Kseniia Sumarokova](https://github.com/kssenii)).
+
+#### Improvement
+* Backported in [#65898](https://github.com/ClickHouse/ClickHouse/issues/65898): Respect cgroup CPU limit in Keeper. [#65819](https://github.com/ClickHouse/ClickHouse/pull/65819) ([Antonio Andelic](https://github.com/antonio2368)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+* Backported in [#65935](https://github.com/ClickHouse/ClickHouse/issues/65935): For queries that read from `PostgreSQL`, cancel the internal `PostgreSQL` query if the ClickHouse query is finished. Otherwise, `ClickHouse` query cannot be canceled until the internal `PostgreSQL` query is finished. [#65771](https://github.com/ClickHouse/ClickHouse/pull/65771) ([Maksim Kita](https://github.com/kitaisreal)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Backported in [#65907](https://github.com/ClickHouse/ClickHouse/issues/65907): Fix bug with session closing in Keeper. [#65735](https://github.com/ClickHouse/ClickHouse/pull/65735) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#65962](https://github.com/ClickHouse/ClickHouse/issues/65962): Add missing workload identity changes. [#65848](https://github.com/ClickHouse/ClickHouse/pull/65848) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
+* Backported in [#66033](https://github.com/ClickHouse/ClickHouse/issues/66033): Follow up to [#65046](https://github.com/ClickHouse/ClickHouse/issues/65046). [#65928](https://github.com/ClickHouse/ClickHouse/pull/65928) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Backported in [#66076](https://github.com/ClickHouse/ClickHouse/issues/66076): Fix support of non-const scale arguments in rounding functions. [#65983](https://github.com/ClickHouse/ClickHouse/pull/65983) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
+* Backported in [#66017](https://github.com/ClickHouse/ClickHouse/issues/66017): Fix race in s3queue. [#65986](https://github.com/ClickHouse/ClickHouse/pull/65986) ([Kseniia Sumarokova](https://github.com/kssenii)).
+

docs/en/development/developer-instruction.md

@@ -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}
 

docs/en/engines/table-engines/integrations/s3queue.md

@@ -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.
 

docs/en/getting-started/install.md

@@ -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

docs/en/interfaces/formats.md

@@ -1535,6 +1535,10 @@ 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}

docs/en/operations/backup.md

@@ -84,6 +84,7 @@ The BACKUP and RESTORE statements take a list of DATABASE and TABLE names, a des
     - [`compression_method`](/docs/en/sql-reference/statements/create/table.md/#column-compression-codecs) and compression_level
     - `password` for the file on disk
     - `base_backup`: the destination of the previous backup of this source.  For example, `Disk('backups', '1.zip')`
+    - `use_same_s3_credentials_for_base_backup`: whether base backup to S3 should inherit credentials from the query. Only works with `S3`.
     - `structure_only`: if enabled, allows to only backup or restore the CREATE statements without the data of tables
     - `storage_policy`: storage policy for the tables being restored. See [Using Multiple Block Devices for Data Storage](../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes). This setting is only applicable to the `RESTORE` command. The specified storage policy applies only to tables with an engine from the `MergeTree` family.
     - `s3_storage_class`: the storage class used for S3 backup. For example, `STANDARD`

docs/en/operations/opentelemetry.md

@@ -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.

docs/en/operations/settings/merge-tree-settings.md

@@ -974,6 +974,13 @@ Default value: false
 
 - [exclude_deleted_rows_for_part_size_in_merge](#exclude_deleted_rows_for_part_size_in_merge) setting
 
+## use_compact_variant_discriminators_serialization {#use_compact_variant_discriminators_serialization}
+
+Enables compact mode for binary serialization of discriminators in Variant data type.
+This mode allows to use significantly less memory for storing discriminators in parts when there is mostly one variant or a lot of NULL values.
+
+Default value: true
+
 ## merge_workload
 
 Used to regulate how resources are utilized and shared between merges and other workloads. Specified value is used as `workload` setting value for background merges of this table. If not specified (empty string), then server setting `merge_workload` is used instead.
@@ -1023,7 +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.

docs/en/operations/settings/settings-formats.md

@@ -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.

docs/en/operations/settings/settings.md

@@ -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.

docs/en/operations/startup-scripts.md

@@ -0,0 +1,30 @@
+---
+slug: /en/operations/startup-scripts
+sidebar_label: Startup Scripts
+---
+
+# Startup Scripts
+
+ClickHouse can run arbitrary SQL queries from the server configuration during startup. This can be useful for migrations or automatic schema creation.
+
+```xml
+<clickhouse>
+    <startup_scripts>
+        <scripts>
+            <query>CREATE ROLE OR REPLACE test_role</query>
+        </scripts>
+        <scripts>
+            <query>CREATE TABLE TestTable (id UInt64) ENGINE=TinyLog</query>
+            <condition>SELECT 1;</condition>
+        </scripts>
+    </startup_scripts>
+</clickhouse>
+```
+
+ClickHouse executes all queries from the `startup_scripts` sequentially in the specified order. If any of the queries fail, the execution of the following queries won't be interrupted.
+
+You can specify a conditional query in the config. In that case, the corresponding query executes only when the condition query returns the value `1` or `true`.
+
+:::note
+If the condition query returns any other value than `1` or `true`, the result will be interpreted as `false`, and the corresponding won't be executed.
+:::

docs/en/operations/system-tables/metrics.md

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

docs/en/operations/utilities/clickhouse-disks.md

@@ -4,35 +4,56 @@ sidebar_position: 59
 sidebar_label: clickhouse-disks
 ---
 
-# clickhouse-disks
+# Clickhouse-disks
 
-A utility providing filesystem-like operations for ClickHouse disks.
+A utility providing filesystem-like operations for ClickHouse disks. It can work in both interactive and not interactive modes.
 
-Program-wide options:
+## Program-wide options
 
 * `--config-file, -C` -- path to ClickHouse config, defaults to `/etc/clickhouse-server/config.xml`.
 * `--save-logs` -- Log progress of invoked commands to `/var/log/clickhouse-server/clickhouse-disks.log`.
 * `--log-level` -- What [type](../server-configuration-parameters/settings#server_configuration_parameters-logger) of events to log, defaults to `none`.
 * `--disk` -- what disk to use for `mkdir, move, read, write, remove` commands. Defaults to `default`.
+* `--query, -q` -- single query that can be executed without launching interactive mode
+* `--help, -h` -- print all the options and commands with description
+
+## Default Disks
+After the launch two disks are initialized. The first one is a disk `local` that is supposed to imitate local file system from which clickhouse-disks utility was launched. The second one is a disk `default` that is mounted to the local filesystem in the directory that can be found in config as a parameter `clickhouse/path` (default value is `/var/lib/clickhouse`).
+
+## Clickhouse-disks state
+For each disk that was added the utility stores current directory (as in a usual filesystem). User can change current directory and switch between disks.
+
+State is reflected in a prompt "`disk_name`:`path_name`" 
 
 ## Commands
 
-* `copy [--disk-from d1] [--disk-to d2] <FROM_PATH> <TO_PATH>`.
-  Recursively copy data from `FROM_PATH` at disk `d1` (defaults to `disk` value if not provided)
-  to `TO_PATH` at disk `d2` (defaults to `disk` value if not provided).
-* `move <FROM_PATH> <TO_PATH>`.
-  Move file or directory from `FROM_PATH` to `TO_PATH`.
-* `remove <PATH>`.
-  Remove `PATH` recursively.
-* `link <FROM_PATH> <TO_PATH>`.
-  Create a hardlink from `FROM_PATH` to `TO_PATH`.
-* `list [--recursive] <PATH>...`
-  List files at `PATH`s. Non-recursive by default.
-* `list-disks`.
+In these documentation file all mandatory positional arguments are referred as `<parameter>`, named arguments are referred as `[--parameter value]`. All positional parameters could be mentioned as a named parameter with a corresponding name.
+
+* `cd (change-dir, change_dir) [--disk disk] <path>`
+  Change directory to path `path` on disk `disk` (default value is a current disk). No disk switching happens.
+* `copy (cp) [--disk-from disk_1] [--disk-to disk_2] <path-from> <path-to>`.
+  Recursively copy data from `path-from` at disk `disk_1` (default value is a current disk (parameter `disk` in a non-interactive mode))
+  to `path-to` at disk `disk_2` (default value is a current disk (parameter `disk` in a non-interactive mode)).
+* `current_disk_with_path (current, current_disk, current_path)`
+  Print current state in format: 
+    `Disk: "current_disk" Path: "current path on current disk"`
+* `help [<command>]`
+  Print help message about command `command`. If `command` is not specified print information about all commands.
+* `move (mv) <path-from> <path-to>`.
+  Move file or directory from `path-from` to `path-to` within current disk.
+* `remove (rm, delete) <path>`.
+  Remove `path` recursively on a current disk.
+* `link (ln) <path-from> <path-to>`.
+  Create a hardlink from `path-from` to `path-to` on a current disk.
+* `list (ls) [--recursive] <path>`
+  List files at `path`s on a current disk. Non-recursive by default.
+* `list-disks (list_disks, ls-disks, ls_disks)`.
   List disks names.
-* `mkdir [--recursive] <PATH>`.
+* `mkdir [--recursive] <path>` on a current disk.
   Create a directory. Non-recursive by default.
-* `read: <FROM_PATH> [<TO_PATH>]`
-  Read a file from `FROM_PATH` to `TO_PATH` (`stdout` if not supplied).
-* `write [FROM_PATH] <TO_PATH>`.
-  Write a file from `FROM_PATH` (`stdin` if not supplied) to `TO_PATH`.
+* `read (r) <path-from> [--path-to path]`
+  Read a file from `path-from` to `path` (`stdout` if not supplied).
+* `switch-disk [--path path] <disk>`
+  Switch to disk `disk` on path `path` (if `path` is not specified default value is a previous path on disk `disk`). 
+* `write (w) [--path-from path] <path-to>`.
+  Write a file from `path` (`stdin` if `path` is not supplied, input must finish by Ctrl+D) to `path-to`.

docs/en/operations/utilities/clickhouse-local.md

@@ -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
 

docs/en/sql-reference/aggregate-functions/index.md

@@ -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:**
 

docs/en/sql-reference/aggregate-functions/reference/aggthrow.md

@@ -0,0 +1,37 @@
+---
+slug: /en/sql-reference/aggregate-functions/reference/aggthrow
+sidebar_position: 101
+---
+
+# aggThrow
+
+This function can be used for the purpose of testing exception safety. It will throw an exception on creation with the specified probability.
+
+**Syntax**
+
+```sql
+aggThrow(throw_prob)
+```
+
+**Arguments**
+
+- `throw_prob` — Probability to throw on creation. [Float64](../../data-types/float.md).
+
+**Returned value**
+
+- An exception: `Code: 503. DB::Exception: Aggregate function aggThrow has thrown exception successfully`.
+
+**Example**
+
+Query:
+
+```sql
+SELECT number % 2 AS even, aggThrow(number) FROM numbers(10) GROUP BY even;
+```
+
+Result:
+
+```response
+Received exception:
+Code: 503. DB::Exception: Aggregate function aggThrow has thrown exception successfully: While executing AggregatingTransform. (AGGREGATE_FUNCTION_THROW)
+```

docs/en/sql-reference/aggregate-functions/reference/any.md

@@ -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.

docs/en/sql-reference/aggregate-functions/reference/any_respect_nulls.md

@@ -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)

docs/en/sql-reference/aggregate-functions/reference/anylast.md

@@ -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.

docs/en/sql-reference/aggregate-functions/reference/anylast_respect_nulls.md

@@ -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                        │
-└───────────────┴─────────────────────────────┘
-```

docs/en/sql-reference/aggregate-functions/reference/index.md

@@ -43,11 +43,11 @@ Standard aggregate functions:
 
 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)