Merge branch 'master' of github.com:ClickHouse/ClickHouse into patch-8

Author: nikitamikhaylov

README.md

@@ -47,14 +47,19 @@ 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.
 
 Upcoming meetups
-* [Jakarta Meetup with AWS](https://www.meetup.com/clickhouse-indonesia-user-group/events/306973747/) - April 22, 2025
-* [Denver Meetup](https://www.meetup.com/clickhouse-denver-user-group/events/306934991/) - April 23, 2025
 * [Austin Meetup](https://www.meetup.com/clickhouse-austin-user-group/events/307289908) - May 13, 2025
 * [London Meetup](https://www.meetup.com/clickhouse-london-user-group/events/306047172/) - May 14, 2025
 * [Istanbul Meetup](https://www.meetup.com/clickhouse-turkiye-meetup-group/events/306978337/) - May 15, 2025
 * [Shenzhen Meetup](https://www.huodongxing.com/event/7803892350511) - May 17, 2025
+* [Seattle Meetup](https://www.meetup.com/clickhouse-seattle-user-group/events/307622716/) - May 20, 2025
+* [Washington DC Meetup](https://www.meetup.com/clickhouse-dc-user-group/events/307622954/) - June 12, 2025
+* [Atlanta Meetup](https://www.meetup.com/clickhouse-atlanta-meetup-group/events/307627590/) - July 8, 2025
+* [New York Meetup](https://www.meetup.com/clickhouse-new-york-user-group/events/307627675/) - July 15, 2025
+
 
 Recent meetups
+* [Denver Meetup](https://www.meetup.com/clickhouse-denver-user-group/events/306934991/) - April 23, 2025
+* [Jakarta Meetup with AWS](https://www.meetup.com/clickhouse-indonesia-user-group/events/306973747/) - April 22, 2025
 * [Kuala Lumper Meetup with CNCF](https://www.meetup.com/clickhouse-malaysia-meetup-group/events/306697678/) - April 16, 2025
 * [Tokyo Meetup with Confluent](https://www.meetup.com/clickhouse-tokyo-user-group/events/306832118/) - April 15, 2025
 * [Ho Chi Minh Meetup with AWS & Infinite Lambda](https://www.meetup.com/clickhouse-vietnam-meetup-group/events/306810105/) - April 12, 2025
@@ -73,12 +78,7 @@ Recent meetups
 * [Seattle Meetup](https://www.meetup.com/clickhouse-seattle-user-group/events/305916325) - March 5, 2025
 * [Paris Meetup](https://www.meetup.com/clickhouse-france-user-group/events/305792997) - March 4, 2025
 * [Shanghai Meetup](https://www.huodongxing.com/event/3794544969111?td=3894807410019) - March 1, 2025
-* [Singapore Meetup](https://www.meetup.com/clickhouse-singapore-meetup-group/events/305917892/) - Feb 25, 2025
-* [Los Angeles Meetup (with DevOpsDays)](https://www.meetup.com/clickhouse-los-angeles-user-group/events/305952193) - Feb 20, 2025
-* [Wellington Meetup](https://www.meetup.com/clickhouse-wellington-user-group/events/305666164/) - Feb 20, 2025
-* [Auckland Meetup](https://www.meetup.com/clickhouse-auckland-meetup-group/events/305666103/) - Feb 19, 2025
-* [Dubai Meetup](https://www.meetup.com/clickhouse-dubai-meetup-group/events/303096989/) - Feb 10, 2025
-* [Bangalore Meetup](https://www.meetup.com/clickhouse-bangalore-user-group/events/305497951/) - Feb 8, 2025
+
 
 
 

base/base/find_symbols.h

@@ -274,7 +274,7 @@ inline const char * find_first_symbols_sse42(const char * const begin, const cha
     const char * pos = begin;
 
 #if defined(__SSE4_2__)
-    constexpr int mode = _SIDD_UBYTE_OPS | _SIDD_CMP_EQUAL_ANY | _SIDD_LEAST_SIGNIFICANT;
+    constexpr int mode = _SIDD_UBYTE_OPS | _SIDD_CMP_EQUAL_ANY | _SIDD_LEAST_SIGNIFICANT;  // NOLINT(misc-redundant-expression)
 
     __m128i set = _mm_setr_epi8(c01, c02, c03, c04, c05, c06, c07, c08, c09, c10, c11, c12, c13, c14, c15, c16);
 

base/poco/JSON/include/Poco/JSON/Array.h

@@ -208,7 +208,7 @@ namespace JSON
         //  The reason we have this flag here (rather than as argument to stringify())
         //  is because Array can be returned stringified from a Dynamic::Var:toString(),
         //  so it must know whether to escape unicode or not.
-        bool _escapeUnicode;
+        std::atomic<bool> _escapeUnicode;
     };
 
 

base/poco/JSON/include/Poco/JSON/Object.h

@@ -18,6 +18,7 @@
 #define JSON_Object_INCLUDED
 
 
+#include <atomic>
 #include <deque>
 #include <iostream>
 #include <map>
@@ -292,7 +293,7 @@ namespace JSON
         //  The reason for this flag (rather than as argument to stringify()) is
         //  because Object can be returned stringified from Dynamic::Var::toString(),
         //  so it must know whether to escape unicode or not.
-        bool _escapeUnicode;
+        std::atomic<bool> _escapeUnicode;
         mutable StructPtr _pStruct;
         mutable bool _modified;
     };

base/poco/JSON/src/Object.cpp

@@ -33,7 +33,7 @@ Object::Object(int options):
 
 Object::Object(const Object& other) : _values(other._values),
 	_preserveInsOrder(other._preserveInsOrder),
-	_escapeUnicode(other._escapeUnicode),
+	_escapeUnicode(other._escapeUnicode.load()),
 	_pStruct(!other._modified ? other._pStruct : 0),
 	_modified(other._modified)
 {
@@ -48,7 +48,7 @@ Object::Object(Object&& other) :
 	_values(std::move(other._values)),
 	_keys(std::move(other._keys)),
 	_preserveInsOrder(other._preserveInsOrder),
-	_escapeUnicode(other._escapeUnicode),
+	_escapeUnicode(other._escapeUnicode.load()),
 	_pStruct(!other._modified ? other._pStruct : 0),
 	_modified(other._modified)
 {
@@ -63,7 +63,7 @@ Object &Object::operator= (Object &&other)
 		_values = other._values;
 		_preserveInsOrder = other._preserveInsOrder;
 		syncKeys(other._keys);
-		_escapeUnicode = other._escapeUnicode;
+		_escapeUnicode = other._escapeUnicode.load();
 		_pStruct = !other._modified ? other._pStruct : 0;
 		_modified = other._modified;
 		other.clear();
@@ -87,7 +87,7 @@ Object &Object::operator= (const Object &other)
 		_values = other._values;
 		_keys = other._keys;
 		_preserveInsOrder = other._preserveInsOrder;
-		_escapeUnicode = other._escapeUnicode;
+		_escapeUnicode = other._escapeUnicode.load();
 		_pStruct = !other._modified ? other._pStruct : 0;
 		_modified = other._modified;
 	}

ci/defs/job_configs.py

@@ -2,6 +2,22 @@
 
 from ci.defs.defs import ArtifactNames, BuildTypes, JobNames, RunnerLabels
 
+build_digest_config = Job.CacheDigestConfig(
+    include_paths=[
+        "./src",
+        "./contrib/",
+        "./CMakeLists.txt",
+        "./PreLoad.cmake",
+        "./cmake",
+        "./base",
+        "./programs",
+        "./rust",
+        "./ci/jobs/build_clickhouse.py",
+        "./ci/jobs/scripts/job_hooks/build_profile_hook.py",
+    ],
+    with_git_submodules=True,
+)
+
 
 class JobConfigs:
     docker_build_arm = Job.Config(
@@ -97,20 +113,7 @@ class JobConfigs:
         run_in_docker="clickhouse/binary-builder+--network=host",
         timeout=3600 * 4,
         allow_merge_on_failure=True,
-        digest_config=Job.CacheDigestConfig(
-            include_paths=[
-                "./src",
-                "./contrib/",
-                "./CMakeLists.txt",
-                "./PreLoad.cmake",
-                "./cmake",
-                "./base",
-                "./programs",
-                "./rust",
-                "./ci/jobs/build_clickhouse.py",
-            ],
-            with_git_submodules=True,
-        ),
+        digest_config=build_digest_config,
     ).parametrize(
         parameter=[
             BuildTypes.ARM_TIDY,
@@ -127,21 +130,11 @@ class JobConfigs:
         # --network=host required for ec2 metadata http endpoint to work
         run_in_docker="clickhouse/binary-builder+--network=host",
         timeout=3600 * 2,
-        digest_config=Job.CacheDigestConfig(
-            include_paths=[
-                "./src",
-                "./contrib/",
-                "./CMakeLists.txt",
-                "./PreLoad.cmake",
-                "./cmake",
-                "./base",
-                "./programs",
-                "./rust",
-                "./ci/jobs/build_clickhouse.py",
-            ],
-            with_git_submodules=True,
-        ),
-        post_hooks=["python3 ./ci/jobs/scripts/job_hooks/build_post_hook.py"],
+        digest_config=build_digest_config,
+        post_hooks=[
+            "python3 ./ci/jobs/scripts/job_hooks/build_master_head_hook.py",
+            "python3 ./ci/jobs/scripts/job_hooks/build_profile_hook.py",
+        ],
     ).parametrize(
         parameter=[
             BuildTypes.AMD_DEBUG,
@@ -225,21 +218,11 @@ class JobConfigs:
         # --network=host required for ec2 metadata http endpoint to work
         run_in_docker="clickhouse/binary-builder+--network=host",
         timeout=3600 * 2,
-        digest_config=Job.CacheDigestConfig(
-            include_paths=[
-                "./src",
-                "./contrib/",
-                "./CMakeLists.txt",
-                "./PreLoad.cmake",
-                "./cmake",
-                "./base",
-                "./programs",
-                "./rust",
-                "./ci/jobs/build_clickhouse.py",
-            ],
-            with_git_submodules=True,
-        ),
-        post_hooks=["python3 ./ci/jobs/scripts/job_hooks/build_post_hook.py"],
+        digest_config=build_digest_config,
+        post_hooks=[
+            "python3 ./ci/jobs/scripts/job_hooks/build_master_head_hook.py",
+            "python3 ./ci/jobs/scripts/job_hooks/build_profile_hook.py",
+        ],
     ).parametrize(
         parameter=[
             BuildTypes.AMD_DARWIN,

ci/docker/binary-builder/Dockerfile

@@ -5,7 +5,7 @@ ENV CC=clang-${LLVM_VERSION}
 ENV CXX=clang++-${LLVM_VERSION}
 
 # If the cctools is updated, then first build it in the CI, then update here in a different commit
-COPY --from=clickhouse/cctools:13cfebfd8f1bbc65ab49 /cctools /cctools
+COPY --from=clickhouse/cctools:4670e95dde3de689f103 /cctools /cctools
 
 # A cross-linker for RISC-V 64 (we need it, because LLVM's LLD does not work):
 RUN apt-get update \

ci/docker/fasttest/Dockerfile

@@ -67,7 +67,7 @@ RUN apt-get update \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/* /var/cache/debconf /tmp/*
 
-COPY --from=clickhouse/cctools:13cfebfd8f1bbc65ab49 /opt/gdb /opt/gdb
+COPY --from=clickhouse/cctools:4670e95dde3de689f103 /opt/gdb /opt/gdb
 # Give suid to gdb to grant it attach permissions
 RUN chmod u+s /opt/gdb/bin/gdb
 ENV PATH="/opt/gdb/bin:${PATH}"

ci/jobs/build_clickhouse.py

@@ -124,11 +124,12 @@ def main():
     results = []
 
     if res and JobStages.CHECKOUT_SUBMODULES in stages:
-        Shell.check(f"rm -rf {build_dir} && mkdir -p {build_dir}")
+        Shell.check(f"mkdir -p {build_dir}")
         results.append(
             Result.from_commands_run(
                 name="Checkout Submodules",
                 command=f"git submodule sync --recursive && git submodule init && git submodule update --depth 1 --recursive --jobs {min([Utils.cpu_count(), 20])}",
+                retries=3,
             )
         )
         res = results[-1].is_ok()

ci/jobs/scripts/check_style/aspell-ignore/en/aspell-dict.txt

@@ -1251,6 +1251,7 @@ aggthrow
 aiochclient
 alloc
 allocator
+allowlist
 alphaTokens
 amplab
 analysisOfVariance
@@ -1687,6 +1688,7 @@ denormalize
 denormalized
 denormalizing
 denormals
+denylist
 dequeued
 dequeues
 dereference
@@ -2836,6 +2838,8 @@ stochasticlinearregression
 stochasticlogisticregression
 storages
 storig
+stringBytesEntropy
+stringBytesUniq
 stringCompare
 stringJaccardIndex
 stringJaccardIndexUTF