Merge remote-tracking branch 'origin/master' into simplify_lwd_projection_drop_logic

Author: jsc0218

CMakeLists.txt

@@ -204,11 +204,6 @@ option(OMIT_HEAVY_DEBUG_SYMBOLS
     ${OMIT_HEAVY_DEBUG_SYMBOLS_DEFAULT})
 
 option(BUILD_STANDALONE_KEEPER "Build keeper as small standalone binary" OFF)
-if (NOT BUILD_STANDALONE_KEEPER)
-    option(CREATE_KEEPER_SYMLINK "Create symlink for clickhouse-keeper to main server binary" ON)
-else ()
-    option(CREATE_KEEPER_SYMLINK "Create symlink for clickhouse-keeper to main server binary" OFF)
-endif ()
 
 # Create BuildID when using lld. For other linkers it is created by default.
 # (NOTE: LINKER_NAME can be either path or name, and in different variants)

ci/jobs/scripts/functional_tests/setup_ch_cluster.sh

@@ -110,7 +110,7 @@ else
     fi
     clickhouse-client --query "CREATE TABLE test.hits_s3  (WatchID UInt64, JavaEnable UInt8, Title String, GoodEvent Int16, EventTime DateTime, EventDate Date, CounterID UInt32, ClientIP UInt32, ClientIP6 FixedString(16), RegionID UInt32, UserID UInt64, CounterClass Int8, OS UInt8, UserAgent UInt8, URL String, Referer String, URLDomain String, RefererDomain String, Refresh UInt8, IsRobot UInt8, RefererCategories Array(UInt16), URLCategories Array(UInt16), URLRegions Array(UInt32), RefererRegions Array(UInt32), ResolutionWidth UInt16, ResolutionHeight UInt16, ResolutionDepth UInt8, FlashMajor UInt8, FlashMinor UInt8, FlashMinor2 String, NetMajor UInt8, NetMinor UInt8, UserAgentMajor UInt16, UserAgentMinor FixedString(2), CookieEnable UInt8, JavascriptEnable UInt8, IsMobile UInt8, MobilePhone UInt8, MobilePhoneModel String, Params String, IPNetworkID UInt32, TraficSourceID Int8, SearchEngineID UInt16, SearchPhrase String, AdvEngineID UInt8, IsArtifical UInt8, WindowClientWidth UInt16, WindowClientHeight UInt16, ClientTimeZone Int16, ClientEventTime DateTime, SilverlightVersion1 UInt8, SilverlightVersion2 UInt8, SilverlightVersion3 UInt32, SilverlightVersion4 UInt16, PageCharset String, CodeVersion UInt32, IsLink UInt8, IsDownload UInt8, IsNotBounce UInt8, FUniqID UInt64, HID UInt32, IsOldCounter UInt8, IsEvent UInt8, IsParameter UInt8, DontCountHits UInt8, WithHash UInt8, HitColor FixedString(1), UTCEventTime DateTime, Age UInt8, Sex UInt8, Income UInt8, Interests UInt16, Robotness UInt8, GeneralInterests Array(UInt16), RemoteIP UInt32, RemoteIP6 FixedString(16), WindowName Int32, OpenerName Int32, HistoryLength Int16, BrowserLanguage FixedString(2), BrowserCountry FixedString(2), SocialNetwork String, SocialAction String, HTTPError UInt16, SendTiming Int32, DNSTiming Int32, ConnectTiming Int32, ResponseStartTiming Int32, ResponseEndTiming Int32, FetchTiming Int32, RedirectTiming Int32, DOMInteractiveTiming Int32, DOMContentLoadedTiming Int32, DOMCompleteTiming Int32, LoadEventStartTiming Int32, LoadEventEndTiming Int32, NSToDOMContentLoadedTiming Int32, FirstPaintTiming Int32, RedirectCount Int8, SocialSourceNetworkID UInt8, SocialSourcePage String, ParamPrice Int64, ParamOrderID String, ParamCurrency FixedString(3), ParamCurrencyID UInt16, GoalsReached Array(UInt32), OpenstatServiceName String, OpenstatCampaignID String, OpenstatAdID String, OpenstatSourceID String, UTMSource String, UTMMedium String, UTMCampaign String, UTMContent String, UTMTerm String, FromTag String, HasGCLID UInt8, RefererHash UInt64, URLHash UInt64, CLID UInt32, YCLID UInt64, ShareService String, ShareURL String, ShareTitle String, ParsedParams Nested(Key1 String, Key2 String, Key3 String, Key4 String, Key5 String, ValueDouble Float64), IslandID FixedString(16), RequestNum UInt32, RequestTry UInt8) ENGINE = MergeTree() PARTITION BY toYYYYMM(EventDate) ORDER BY (CounterID, EventDate, intHash32(UserID)) SAMPLE BY intHash32(UserID) SETTINGS index_granularity = 8192, storage_policy='s3_cache'"
     # AWS S3 is very inefficient, so increase memory even further:
-    clickhouse-client --max_memory_usage 30G --max_memory_usage_for_user 30G --query "INSERT INTO test.hits_s3 SELECT * FROM test.hits SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
+    clickhouse-client --max_execution_time 600 --max_memory_usage 30G --max_memory_usage_for_user 30G --query "INSERT INTO test.hits_s3 SELECT * FROM test.hits SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
 fi
 
 clickhouse-client --query "SHOW TABLES FROM test"

cmake/darwin/default_libs.cmake

@@ -15,5 +15,18 @@ set(CMAKE_OSX_DEPLOYMENT_TARGET 10.15)
 set(THREADS_PREFER_PTHREAD_FLAG ON)
 find_package(Threads REQUIRED)
 
+if(NOT CMAKE_CROSSCOMPILING)
+    execute_process(
+        COMMAND xcrun --sdk macosx --show-sdk-version
+        OUTPUT_VARIABLE OS_DARWIN_SDK_VERSION
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+    )
+    if(${OS_DARWIN_SDK_VERSION} MATCHES "^[0-9]+\\.[0-9]+")
+        message(STATUS "Detected OSX SDK Version: ${OS_DARWIN_SDK_VERSION}")
+    else ()
+        message(WARNING "Unexpected OSX SDK Version: ${OS_DARWIN_SDK_VERSION}")
+    endif()
+endif()
+
 include (cmake/unwind.cmake)
-include (cmake/cxx.cmake)
+include (cmake/cxx.cmake)

contrib/postgres-cmake/CMakeLists.txt

@@ -79,6 +79,13 @@ if (OS_DARWIN OR OS_FREEBSD OR USE_MUSL)
     target_compile_definitions(_libpq PRIVATE -DSTRERROR_R_INT=1)
 endif()
 
+# Mac 15.4 / Xcode 16.3 started defining srtchrnul
+# Could be cleaned up if properly resolved in upstream
+# https://www.postgresql.org/message-id/flat/385134.1743523038%40sss.pgh.pa.us
+if (OS_DARWIN AND OS_DARWIN_SDK_VERSION AND OS_DARWIN_SDK_VERSION VERSION_GREATER_EQUAL 15.4)
+    target_compile_definitions(_libpq PRIVATE -DHAVE_STRCHRNUL)
+endif()
+
 target_link_libraries (_libpq PRIVATE OpenSSL::SSL)
 
 add_library(ch_contrib::libpq ALIAS _libpq)

docker/test/integration/runner/Dockerfile

@@ -63,18 +63,17 @@ RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - \
 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 \
-    && tar xzvf spark-3.3.2-bin-hadoop3.tgz -C / \
-    && rm spark-3.3.2-bin-hadoop3.tgz
+RUN curl -fsSL -O https://archive.apache.org/dist/spark/spark-3.5.5/spark-3.5.5-bin-hadoop3.tgz \
+    && tar xzvf spark-3.5.5-bin-hadoop3.tgz -C / \
+    && rm spark-3.5.5-bin-hadoop3.tgz
 
 # download spark and packages
 # if you change packages, don't forget to update them in tests/integration/helpers/cluster.py
-RUN packages="org.apache.hudi:hudi-spark3.3-bundle_2.12:0.13.0,\
-io.delta:delta-core_2.12:2.3.0,\
-org.apache.iceberg:iceberg-spark-runtime-3.3_2.12:1.1.0" \
-    && /spark-3.3.2-bin-hadoop3/bin/spark-shell --packages "$packages" > /dev/null \
-    && find /root/.ivy2/ -name '*.jar' -exec ln -sf {} /spark-3.3.2-bin-hadoop3/jars/ \;
+RUN packages="io.delta:delta-spark_2.12:3.1.0,\
+org.apache.hudi:hudi-spark3.5-bundle_2.12:1.0.1,\
+org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.4.3" \
+    && /spark-3.5.5-bin-hadoop3/bin/spark-shell --packages "$packages" > /dev/null \
+    && find /root/.ivy2/ -name '*.jar' -exec ln -sf {} /spark-3.5.5-bin-hadoop3/jars/ \;
 
 RUN set -x \
   && addgroup --system dockremap \

docker/test/integration/runner/dockerd-entrypoint.sh

@@ -54,7 +54,7 @@ set -e
 
 java_path="$(update-alternatives --config java | sed -n 's/.*(providing \/usr\/bin\/java): //p')"
 export JAVA_PATH=$java_path
-export SPARK_HOME="/spark-3.3.2-bin-hadoop3"
+export SPARK_HOME="/spark-3.5.5-bin-hadoop3"
 export PATH=$SPARK_HOME/bin:$PATH
 export JAVA_TOOL_OPTIONS="-Djdk.attach.allowAttachSelf=true"
 

docker/test/integration/runner/requirements.txt

@@ -28,8 +28,8 @@ cramjam==2.9.1
 cryptography==42.0.0
 datacompy==0.7.3
 decorator==5.1.1
-delta-spark==2.3.0
-deltalake==0.16.0
+delta-spark==3.3.0
+deltalake==0.25.5
 dict2xml==1.7.4
 dicttoxml==1.7.16
 docker==6.1.3
@@ -68,7 +68,7 @@ protobuf==4.25.2
 psycopg-binary==3.2.4
 psycopg2-binary==2.9.6
 psycopg==3.2.4
-py4j==0.10.9.5
+py4j==0.10.9.7
 pyarrow-hotfix==0.6
 pyarrow==17.0.0
 pycparser==2.22
@@ -79,7 +79,7 @@ pyiceberg==0.8.1
 pyiceberg[glue]==0.8.1
 pymongo==3.11.0
 pyparsing==3.1.0
-pyspark==3.3.2
+pyspark==3.5.5
 pyspnego==0.10.2
 pytest-order==1.0.0
 pytest-random-order==1.1.1

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

@@ -6,6 +6,8 @@ title: 'MergeTree tables settings'
 
 import ExperimentalBadge from '@theme/badges/ExperimentalBadge';
 import BetaBadge from '@theme/badges/BetaBadge';
+import SettingsInfoBlock from '@theme/SettingsInfoBlock/SettingsInfoBlock';
+import VersionHistory from '@theme/VersionHistory/VersionHistory';
 
 System table `system.merge_tree_settings` shows the globally set MergeTree settings.
 

docs/en/sql-reference/data-types/date.md

@@ -1,7 +1,7 @@
 ---
 description: 'Documentation for the Date data type in ClickHouse'
 sidebar_label: 'Date'
-sidebar_position: 34
+sidebar_position: 12
 slug: /sql-reference/data-types/date
 title: 'Date'
 ---

docs/en/sql-reference/data-types/date32.md

@@ -38,6 +38,7 @@ SELECT * FROM dt32;
 ┌──timestamp─┬─event_id─┐
 │ 2100-01-01 │        1 │
 │ 2100-01-01 │        2 │
+│ 2100-01-01 │        3 │
 └────────────┴──────────┘
 ```