Antalya 26.1 - Update regression hash

.github/actions/create_workflow_report/create_workflow_report.py

@@ -807,6 +807,7 @@ def create_workflow_report(
             )
         except Exception as e:
             pr_info_html = e
+            pr_info = {}
 
     fail_results["job_statuses"] = backfill_skipped_statuses(
         fail_results["job_statuses"], pr_number, branch_name, commit_sha

.github/workflows/master.yml

@@ -4482,7 +4482,7 @@ jobs:
     secrets: inherit
     with:
       docker_image: altinityinfra/clickhouse-server
-      version: ${{ fromJson(needs.config_workflow.outputs.data).custom_data.version.string }}
+      version: ${{ fromJson(needs.config_workflow.outputs.data).JOB_KV_DATA.version.string }}
       tag-suffix: ${{ matrix.suffix }}
   GrypeScanKeeper:
       needs: [config_workflow, docker_keeper_image]
@@ -4491,7 +4491,7 @@ jobs:
       secrets: inherit
       with:
         docker_image: altinityinfra/clickhouse-keeper
-        version: ${{ fromJson(needs.config_workflow.outputs.data).custom_data.version.string }}
+        version: ${{ fromJson(needs.config_workflow.outputs.data).JOB_KV_DATA.version.string }}
 
   RegressionTestsRelease:
     needs: [config_workflow, build_amd_binary]
@@ -4500,7 +4500,7 @@ jobs:
     secrets: inherit
     with:
       runner_type: altinity-regression-tester
-      commit: c5cae9b244e0839fb307a9fb67a40fe80d93810b
+      commit: 979bb27171f92724bcd8f086989ba623f2e03fdc
       arch: release
       build_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout_minutes: 300
@@ -4512,7 +4512,7 @@ jobs:
     secrets: inherit
     with:
       runner_type: altinity-regression-tester-aarch64
-      commit: c5cae9b244e0839fb307a9fb67a40fe80d93810b
+      commit: 979bb27171f92724bcd8f086989ba623f2e03fdc
       arch: aarch64
       build_sha: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout_minutes: 300
@@ -4650,7 +4650,7 @@ jobs:
         if: ${{ !cancelled() }}
         uses: ./.github/actions/create_workflow_report
         with:
-          workflow_config: ${{ needs.config_workflow.outputs.data.workflow_config }}
+          workflow_config: ${{ toJson(needs) }}
           final: true
 
   SourceUpload:
@@ -4660,7 +4660,7 @@ jobs:
     env:
         COMMIT_SHA: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
         PR_NUMBER: ${{ github.event.pull_request.number || 0 }}
-        VERSION: ${{ fromJson(needs.config_workflow.outputs.data).custom_data.version.string }}
+        VERSION: ${{ fromJson(needs.config_workflow.outputs.data).JOB_KV_DATA.version.string }}
     steps:
       - name: Check out repository code
         uses: Altinity/checkout@19599efdf36c4f3f30eb55d5bb388896faea69f6

.github/workflows/release_builds.yml

@@ -1207,7 +1207,7 @@ jobs:
     secrets: inherit
     with:
       docker_image: altinityinfra/clickhouse-server
-      version: ${{ fromJson(needs.config_workflow.outputs.data).custom_data.version.string }}
+      version: ${{ fromJson(needs.config_workflow.outputs.data).JOB_KV_DATA.version.string }}
       tag-suffix: ${{ matrix.suffix }}
   GrypeScanKeeper:
       needs: [config_workflow, docker_keeper_image]
@@ -1216,7 +1216,7 @@ jobs:
       secrets: inherit
       with:
         docker_image: altinityinfra/clickhouse-keeper
-        version: ${{ fromJson(needs.config_workflow.outputs.data).custom_data.version.string }}
+        version: ${{ fromJson(needs.config_workflow.outputs.data).JOB_KV_DATA.version.string }}
 
   SignRelease:
     needs: [config_workflow, build_amd_release]
@@ -1278,7 +1278,7 @@ jobs:
         if: ${{ !cancelled() }}
         uses: ./.github/actions/create_workflow_report
         with:
-          workflow_config: ${{ needs.config_workflow.outputs.data.workflow_config }}
+          workflow_config: ${{ toJson(needs) }}
           final: true
 
   SourceUpload:
@@ -1288,7 +1288,7 @@ jobs:
     env:
         COMMIT_SHA: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
         PR_NUMBER: ${{ github.event.pull_request.number || 0 }}
-        VERSION: ${{ fromJson(needs.config_workflow.outputs.data).custom_data.version.string }}
+        VERSION: ${{ fromJson(needs.config_workflow.outputs.data).JOB_KV_DATA.version.string }}
     steps:
       - name: Check out repository code
         uses: Altinity/checkout@19599efdf36c4f3f30eb55d5bb388896faea69f6

ci/defs/job_configs.py

@@ -73,7 +73,7 @@
         ],
     ),
     result_name_for_cidb="Tests",
-    timeout=int(3600 * 2.5),
+    timeout=int(3600 * 3),
 )
 
 common_stress_job_config = Job.Config(
@@ -109,7 +109,7 @@
             "./ci/jobs/scripts/docker_in_docker.sh",
         ],
     ),
-    run_in_docker=f"altinityinfra/integration-tests-runner+root+--memory={LIMITED_MEM}+--privileged+--dns-search='.'+--security-opt seccomp=unconfined+--cap-add=SYS_PTRACE+{docker_sock_mount}+--volume=clickhouse_integration_tests_volume:/var/lib/docker+--cgroupns=host",
+    run_in_docker=f"altinityinfra/integration-tests-runner+root+--memory={LIMITED_MEM}+--privileged+--dns-search='.'+--security-opt seccomp=unconfined+--cap-add=SYS_PTRACE+{docker_sock_mount}+--volume=clickhouse_integration_tests_volume:/var/lib/docker+--cgroupns=host+--env=CLICKHOUSE_TEST_STAT_URL=$CLICKHOUSE_TEST_STAT_URL+--env=CLICKHOUSE_TEST_STAT_LOGIN=$CLICKHOUSE_TEST_STAT_LOGIN+--env=CLICKHOUSE_TEST_STAT_PASSWORD=$CLICKHOUSE_TEST_STAT_PASSWORD",
 )
 
 BINARY_DOCKER_COMMAND = (
@@ -1045,7 +1045,7 @@ class JobConfigs:
     docker_keeper = Job.Config(
         name=JobNames.DOCKER_KEEPER,
         runs_on=RunnerLabels.STYLE_CHECK_AMD,
-        command="python3 ./ci/jobs/docker_server.py --tag-type head --allow-build-reuse",
+        command="python3 ./ci/jobs/docker_server.py --tag-type head --allow-build-reuse --push",
         digest_config=Job.CacheDigestConfig(
             include_paths=[
                 "./ci/jobs/docker_server.py",

ci/jobs/docker_server.py

@@ -58,10 +58,10 @@ def docker_login(relogin: bool = True) -> None:
         "docker system info | grep --quiet -E 'Username|Registry'"
     ):
         Shell.check(
-            "docker login --username 'robotclickhouse' --password-stdin",
+            "docker login --username 'altinityinfra' --password-stdin",
             strict=True,
             stdin_str=Secret.Config(
-                "dockerhub_robot_password", type=Secret.Type.AWS_SSM_PARAMETER
+                "DOCKER_PASSWORD", type=Secret.Type.GH_SECRET
             ).get_value(),
             encoding="utf-8",
         )
@@ -310,6 +310,7 @@ def main():
     version_dict = None
     if not info.is_local_run:
         version_dict = info.get_kv_data("version")
+        print(f"Version dict from kv data: {version_dict}")
     if not version_dict:
         version_dict = CHVersion.get_current_version_as_dict()
         if not info.is_local_run:
@@ -319,6 +320,7 @@ def main():
             info.add_workflow_report_message(
                 "WARNING: ClickHouse version has not been found in workflow kv storage"
             )
+        print(f"Version dict from repo: {version_dict}")
     assert version_dict
 
     if not info.is_local_run:
@@ -395,7 +397,7 @@ def main():
                     repo_urls,
                     os_,
                     tag,
-                    version_dict["describe"],
+                    version_dict["string"],
                     direct_urls,
                     run_url=info.run_url,
                     sha=info.sha,

ci/jobs/functional_tests.py

@@ -92,7 +92,7 @@ def run_tests(
     if "--no-zookeeper" not in extra_args:
         extra_args += " --zookeeper"
     # Remove --report-logs-stats, it hides sanitizer errors in def reportLogStats(args): clickhouse_execute(args, "SYSTEM FLUSH LOGS")
-    command = f"clickhouse-test --testname --check-zookeeper-session --hung-check --memory-limit {5*2**30} --trace \
+    command = f"clickhouse-test --testname --check-zookeeper-session --hung-check --memory-limit {10*2**30} --trace \
                 --capture-client-stacktrace --queries ./tests/queries --test-runs {rerun_count} \
                 {extra_args} \
                 --queries ./tests/queries {('--order=random' if random_order else '')} -- {' '.join(tests) if tests else ''} | ts '%Y-%m-%d %H:%M:%S' \

ci/jobs/integration_test_job.py

@@ -5,6 +5,9 @@
 from pathlib import Path
 from typing import List, Tuple
 
+import yaml  # NOTE (strtgbb): Used for loading broken tests rules
+import re
+
 from ci.jobs.scripts.find_tests import Targeting
 from ci.jobs.scripts.integration_tests_configs import IMAGES_ENV, get_optimal_test_batch
 from ci.praktika.info import Info
@@ -22,6 +25,106 @@
 MAX_MEM_PER_WORKER = 11
 
 
+def get_broken_tests_rules(broken_tests_file_path: str) -> dict:
+    if (
+        not os.path.isfile(broken_tests_file_path)
+        or os.path.getsize(broken_tests_file_path) == 0
+    ):
+        raise ValueError(
+            "There is something wrong with getting broken tests rules: "
+            f"file '{broken_tests_file_path}' is empty or does not exist."
+        )
+
+    with open(broken_tests_file_path, "r", encoding="utf-8") as broken_tests_file:
+        broken_tests = yaml.safe_load(broken_tests_file)
+
+    compiled_rules = {"exact": {}, "pattern": {}}
+
+    for test in broken_tests:
+        regex = test.get("regex") is True
+        rule = {
+            "reason": test["reason"],
+        }
+
+        if test.get("message"):
+            rule["message"] = re.compile(test["message"]) if regex else test["message"]
+
+        if test.get("not_message"):
+            rule["not_message"] = (
+                re.compile(test["not_message"]) if regex else test["not_message"]
+            )
+        if test.get("check_types"):
+            rule["check_types"] = test["check_types"]
+
+        if regex:
+            rule["regex"] = True
+            compiled_rules["pattern"][re.compile(test["name"])] = rule
+        else:
+            compiled_rules["exact"][test["name"]] = rule
+
+    return compiled_rules
+
+
+def test_is_known_fail(broken_tests_rules, test_name, test_logs, job_flags):
+    matching_rules = []
+
+    def matches_substring(substring, log, is_regex):
+        if log is None:
+            return False
+        if is_regex:
+            return bool(substring.search(log))
+        return substring in log
+
+    broken_tests_log = f"{temp_path}/broken_tests_handler.log"
+
+    with open(broken_tests_log, "a") as log_file:
+
+        log_file.write(f"Checking known broken tests for failed test: {test_name}\n")
+        log_file.write("Potential matching rules:\n")
+        exact_rule = broken_tests_rules["exact"].get(test_name)
+        if exact_rule:
+            log_file.write(f"{test_name} - {exact_rule}\n")
+            matching_rules.append(exact_rule)
+
+        for name_re, data in broken_tests_rules["pattern"].items():
+            if name_re.fullmatch(test_name):
+                log_file.write(f"{name_re} - {data}\n")
+                matching_rules.append(data)
+
+        if not matching_rules:
+            return False
+
+        log_file.write(f"First line of test logs: {test_logs.splitlines()[0]}\n")
+
+        for rule_data in matching_rules:
+            if rule_data.get("check_types") and not any(
+                ct in job_flags for ct in rule_data["check_types"]
+            ):
+                log_file.write(
+                    f"Skip rule: Check types didn't match: '{rule_data['check_types']}' not in '{job_flags}'\n"
+                )
+                continue  # check_types didn't match → skip rule
+
+            is_regex = rule_data.get("regex", False)
+            not_message = rule_data.get("not_message")
+            if not_message and matches_substring(not_message, test_logs, is_regex):
+                log_file.write(
+                    f"Skip rule: Not message matched: '{rule_data['not_message']}'\n"
+                )
+                continue  # not_message matched → skip rule
+            message = rule_data.get("message")
+            if message and not matches_substring(message, test_logs, is_regex):
+                log_file.write(
+                    f"Skip rule: Message didn't match: '{rule_data['message']}'\n"
+                )
+                continue
+
+            log_file.write(f"Matched rule: {rule_data}\n")
+            return rule_data["reason"]
+
+        return False
+
+
 def _start_docker_in_docker():
     with open("./ci/tmp/docker-in-docker.log", "w") as log_file:
         dockerd_proc = subprocess.Popen(
@@ -387,7 +490,7 @@ def main():
 
     has_error = False
     if not is_targeted_check:
-        session_timeout = 5400
+        session_timeout = 3600 * 2.5
     else:
         # For targeted jobs, use a shorter session timeout to keep feedback fast.
         # If this timeout is exceeded but all completed tests have passed, the
@@ -533,6 +636,28 @@ def main():
                 )
                 attached_files.append("./ci/tmp/dmesg.log")
 
+    broken_tests_rules = get_broken_tests_rules("tests/broken_tests.yaml")
+    for result in test_results:
+        if result.status == Result.StatusExtended.FAIL:
+            try:
+                known_fail_reason = test_is_known_fail(
+                    broken_tests_rules,
+                    result.name,
+                    result.info,
+                    job_params,
+                )
+            except Exception as e:
+                print(f"Error getting known fail reason for result {result.name}: {e}")
+                continue
+            else:
+                if not known_fail_reason:
+                    continue
+                result.status = Result.StatusExtended.BROKEN
+                result.info += f"\nMarked as broken: {known_fail_reason}"
+
+    if os.path.exists(f"{temp_path}/broken_tests_handler.log"):
+        attached_files.append(f"{temp_path}/broken_tests_handler.log")
+
     R = Result.create_from(results=test_results, stopwatch=sw, files=attached_files)
 
     if has_error:

ci/jobs/scripts/clickhouse_proc.py

@@ -624,8 +624,8 @@ def prepare_stateful_data(self, with_s3_storage, is_db_replicated):
         ENGINE = CollapsingMergeTree(Sign) PARTITION BY toYYYYMM(StartDate) ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
         SAMPLE BY intHash32(UserID) SETTINGS index_granularity = 8192, storage_policy='s3_cache'"
 
-    clickhouse-client --max_execution_time 600 --max_memory_usage 25G --query "INSERT INTO test.hits SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
-    clickhouse-client --max_execution_time 600 --max_memory_usage 25G --query "INSERT INTO test.visits SELECT * FROM datasets.visits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
+    clickhouse-client --max_execution_time 1800 --max_memory_usage 25G --query "INSERT INTO test.hits SELECT * FROM datasets.hits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
+    clickhouse-client --max_execution_time 1800 --max_memory_usage 25G --query "INSERT INTO test.visits SELECT * FROM datasets.visits_v1 SETTINGS enable_filesystem_cache_on_write_operations=0, max_insert_threads=16"
     clickhouse-client --query "DROP TABLE datasets.visits_v1 SYNC"
     clickhouse-client --query "DROP TABLE datasets.hits_v1 SYNC"
 else
@@ -634,7 +634,7 @@ def prepare_stateful_data(self, with_s3_storage, is_db_replicated):
 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_execution_time 900 --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, write_through_distributed_cache=0, max_insert_threads=16"
+clickhouse-client --max_execution_time 1200 --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, write_through_distributed_cache=0, max_insert_threads=16"
 
 clickhouse-client --query "SHOW TABLES FROM test"
 clickhouse-client --query "SELECT count() FROM test.hits"

ci/jobs/scripts/clickhouse_version.py

@@ -65,6 +65,10 @@ def get_release_version_as_dict(cls):
     @classmethod
     def get_current_version_as_dict(cls):
         version = cls.get_release_version_as_dict()
+
+        # NOTE (strtgbb): Just return, no need for the below logic
+        return version
+
         info = Info()
         try:
             # Check if the commit is directly on the first-parent chain