Merge remote-tracking branch 'upstream/master' into azure-remove-redundant-list

Author: jkartseva

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/defs/job_configs.py

@@ -281,6 +281,7 @@ class JobConfigs:
             RunnerLabels.BUILDER_ARM,  # fuzzers
         ],
     )
+    builds_for_tests = [b.name for b in build_jobs] + [tidy_build_jobs[0]]
     install_check_jobs = Job.Config(
         name=JobNames.INSTALL_TEST,
         runs_on=["..."],

ci/jobs/docs_job.py

@@ -1,7 +1,7 @@
 import os
 
 from ci.praktika.result import Result
-from ci.praktika.utils import Shell, Utils
+from ci.praktika.utils import Utils
 
 if __name__ == "__main__":
 
@@ -39,7 +39,7 @@
     results.append(
         Result.from_commands_run(
             name=testname,
-            command=[f"yarn run-markdown-linter"],
+            command=[f"yarn check-markdown"],
             workdir="/opt/clickhouse-docs",
         )
     )

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

@@ -33,6 +33,7 @@ Approximative
 ArrayJoin
 ArrowCompression
 ArrowStream
+aspell
 AsyncInsertCacheSize
 AsynchronousHeavyMetricsCalculationTimeSpent
 AsynchronousHeavyMetricsUpdateInterval
@@ -129,6 +130,7 @@ CMPLNT
 CMake
 CMakeLists
 CODECS
+codespell
 CORS
 COVID
 CPUFrequencyMHz
@@ -659,6 +661,7 @@ Multiqueries
 Multithreading
 Multiword
 MurmurHash
+mypy
 MySQLConnection
 MySQLDataTypesSupport
 MySQLDump

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"

ci/jobs/scripts/workflow_hooks/can_be_merged.py

@@ -9,6 +9,8 @@ def check():
     forbidden_labels = [
         Labels.CI_PERFORMANCE,
         Labels.NO_FAST_TESTS,
+        Labels.CI_INTEGRATION_FLAKY,
+        Labels.CI_FUNCTIONAL_FLAKY,
         Labels.CI_INTEGRATION,
         Labels.CI_FUNCTIONAL,
     ]

ci/jobs/scripts/workflow_hooks/feature_docs.py

@@ -5,7 +5,7 @@
 from ci.jobs.scripts.workflow_hooks.pr_description import Labels
 
 files_for_which_docs_autogenerated = [
-    "src/storages/MergeTree/MergeTreeSettings.cpp",
+    "src/Storages/MergeTree/MergeTreeSettings.cpp",
     "src/Core/Settings.cpp",
 ]
 

ci/jobs/scripts/workflow_hooks/filter_job.py

@@ -1,6 +1,7 @@
 from ci.defs.defs import JobNames
 from ci.jobs.scripts.workflow_hooks.pr_description import Labels
 from ci.praktika.info import Info
+from ci.defs.job_configs import JobConfigs
 
 
 def only_docs(changed_files):
@@ -32,12 +33,12 @@ def only_docs(changed_files):
     "Build (arm_tidy)",
 ]
 
-INTEGRATION_TEST_CHECK_JOBS = [
+INTEGRATION_TEST_FLAKY_CHECK_JOBS = [
     "Build (amd_asan)",
     "Integration tests (asan, flaky check)",
 ]
 
-FUNCTIONAL_TEST_CHECK_JOBS = [
+FUNCTIONAL_TEST_FLAKY_CHECK_JOBS = [
     "Build (amd_asan)",
     "Stateless tests (asan, flaky check)",
 ]
@@ -65,17 +66,34 @@ def should_skip_job(job_name):
         return True, f"Skipped, labeled with '{Labels.NO_FAST_TESTS}'"
 
     if (
-        Labels.CI_INTEGRATION in _info_cache.pr_labels
-        and job_name not in INTEGRATION_TEST_CHECK_JOBS
+        Labels.CI_INTEGRATION_FLAKY in _info_cache.pr_labels
+        and job_name not in INTEGRATION_TEST_FLAKY_CHECK_JOBS
     ):
         return (
             True,
-            f"Skipped, labeled with '{Labels.CI_INTEGRATION}' - run integration test jobs only",
+            f"Skipped, labeled with '{Labels.CI_INTEGRATION_FLAKY}' - run integration test jobs only",
         )
 
     if (
-        Labels.CI_FUNCTIONAL in _info_cache.pr_labels
-        and job_name not in FUNCTIONAL_TEST_CHECK_JOBS
+        Labels.CI_FUNCTIONAL_FLAKY in _info_cache.pr_labels
+        and job_name not in FUNCTIONAL_TEST_FLAKY_CHECK_JOBS
+    ):
+        return (
+            True,
+            f"Skipped, labeled with '{Labels.CI_FUNCTIONAL_FLAKY}' - run stateless test jobs only",
+        )
+
+    if Labels.CI_INTEGRATION in _info_cache.pr_labels and (
+        job_name.startswith(JobNames.INTEGRATION) or job_name in JobConfigs.builds_for_tests
+    ):
+        return (
+            True,
+            f"Skipped, labeled with '{Labels.CI_INTEGRATION}' - run integration test jobs only",
+        )
+
+    if Labels.CI_FUNCTIONAL in _info_cache.pr_labels and (
+        job_name.startswith(JobNames.STATELESS)
+        or job_name.startswith(JobNames.STATEFUL or job_name in JobConfigs.builds_for_tests)
     ):
         return (
             True,

ci/jobs/scripts/workflow_hooks/pr_description.py

@@ -69,7 +69,10 @@ class Labels:
 
     CI_PERFORMANCE = "ci-performance"
 
+    CI_INTEGRATION_FLAKY = "ci-integration-test-flaky"
     CI_INTEGRATION = "ci-integration-test"
+
+    CI_FUNCTIONAL_FLAKY = "ci-functional-test-flaky"
     CI_FUNCTIONAL = "ci-functional-test"
 
     # automatic backport for critical bug fixes

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 \