Merge branch 'ClickHouse:master' into aliasFeature

.github/workflows/master.yml

@@ -93,21 +93,21 @@ jobs:
     with:
       stage: Builds_2
       data: ${{ needs.RunConfig.outputs.data }}
-  Tests_2:
+  Tests_2_ww:
     needs: [RunConfig, Builds_2]
+    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2_ww') }}
+    uses: ./.github/workflows/reusable_test_stage.yml
+    with:
+      stage: Tests_2_ww
+      data: ${{ needs.RunConfig.outputs.data }}
+  Tests_2:
+    # Test_3 should not wait for Test_1/Test_2 and should not be blocked by them on master branch since all jobs need to run there.
+    needs: [RunConfig, Builds_1]
     if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2') }}
     uses: ./.github/workflows/reusable_test_stage.yml
     with:
       stage: Tests_2
       data: ${{ needs.RunConfig.outputs.data }}
-  Tests_3:
-    # Test_3 should not wait for Test_1/Test_2 and should not be blocked by them on master branch since all jobs need to run there.
-    needs: [RunConfig, Builds_1]
-    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_3') }}
-    uses: ./.github/workflows/reusable_test_stage.yml
-    with:
-      stage: Tests_3
-      data: ${{ needs.RunConfig.outputs.data }}
 
   ################################# Reports #################################
   # Reports should run even if Builds_1/2 fail - run them separately, not in Tests_1/2/3
@@ -123,7 +123,7 @@ jobs:
 
   FinishCheck:
     if: ${{ !cancelled() }}
-    needs: [RunConfig, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
+    needs: [RunConfig, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
     runs-on: [self-hosted, style-checker-aarch64]
     steps:
       - name: Check out repository code
@@ -133,6 +133,7 @@ jobs:
           cd "$GITHUB_WORKSPACE/tests/ci"
           python3 finish_check.py --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
       - name: Check Workflow results
+        if: ${{ !cancelled() }}
         run: |
           export WORKFLOW_RESULT_FILE="/tmp/workflow_results.json"
           cat > "$WORKFLOW_RESULT_FILE" << 'EOF'

.github/workflows/pull_request.yml

@@ -123,20 +123,20 @@ jobs:
       stage: Builds_2
       data: ${{ needs.RunConfig.outputs.data }}
   # stage for running non-required checks without being blocked by required checks (Test_1) if corresponding settings is selected
-  Tests_2:
+  Tests_2_ww:
     needs: [RunConfig, Builds_1]
+    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2_ww') }}
+    uses: ./.github/workflows/reusable_test_stage.yml
+    with:
+      stage: Tests_2_ww
+      data: ${{ needs.RunConfig.outputs.data }}
+  Tests_2:
+    needs: [RunConfig, Builds_1, Tests_1]
     if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_2') }}
     uses: ./.github/workflows/reusable_test_stage.yml
     with:
       stage: Tests_2
       data: ${{ needs.RunConfig.outputs.data }}
-  Tests_3:
-    needs: [RunConfig, Builds_1, Tests_1]
-    if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_3') }}
-    uses: ./.github/workflows/reusable_test_stage.yml
-    with:
-      stage: Tests_3
-      data: ${{ needs.RunConfig.outputs.data }}
 
   ################################# Reports #################################
   # Reports should run even if Builds_1/2 fail - run them separately (not in Tests_1/2/3)
@@ -154,7 +154,7 @@ jobs:
     if: ${{ !cancelled() }}
     # Test_2 or Test_3 do not have the jobs required for Mergeable check,
     #  however, set them as "needs" to get all checks results before the automatic merge occurs.
-    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
+    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
     runs-on: [self-hosted, style-checker-aarch64]
     steps:
       - name: Check out repository code
@@ -178,7 +178,7 @@ jobs:
   #
   FinishCheck:
     if: ${{ !failure() && !cancelled() }}
-    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2, Tests_3]
+    needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_Report, Tests_1, Tests_2_ww, Tests_2]
     runs-on: [self-hosted, style-checker-aarch64]
     steps:
       - name: Check out repository code

.gitmodules

@@ -372,3 +372,6 @@
 [submodule "contrib/double-conversion"]
 	path = contrib/double-conversion
 	url = https://github.com/ClickHouse/double-conversion.git
+[submodule "contrib/numactl"]
+	path = contrib/numactl
+	url = https://github.com/ClickHouse/numactl.git

CHANGELOG.md

@@ -18,6 +18,7 @@
 * Metric `KeeperOutstandingRequets` was renamed to `KeeperOutstandingRequests`. [#66206](https://github.com/ClickHouse/ClickHouse/pull/66206) ([Robert Schulze](https://github.com/rschu1ze)).
 * Remove `is_deterministic` field from the `system.functions` table. [#66630](https://github.com/ClickHouse/ClickHouse/pull/66630) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
 * Function `tuple` will now try to construct named tuples in query (controlled by `enable_named_columns_in_function_tuple`). Introduce function `tupleNames` to extract names from tuples. [#54881](https://github.com/ClickHouse/ClickHouse/pull/54881) ([Amos Bird](https://github.com/amosbird)).
+* Change how deduplication for Materialized Views works. Fixed a lot of cases like: - on destination table: data is split for 2 or more blocks and that blocks is considered as duplicate when that block is inserted in parallel. - on MV destination table: the equal blocks are deduplicated, that happens when MV often produces equal data as a result for different input data due to performing aggregation. - on MV destination table: the equal blocks which comes from different MV are deduplicated. [#61601](https://github.com/ClickHouse/ClickHouse/pull/61601) ([Sema Checherinda](https://github.com/CheSema)).
 
 #### New Feature
 * Add `ASOF JOIN` support for `full_sorting_join` algorithm. [#55051](https://github.com/ClickHouse/ClickHouse/pull/55051) ([vdimir](https://github.com/vdimir)).
@@ -32,23 +33,23 @@
 * Add a new setting to disable/enable writing page index into parquet files. [#65475](https://github.com/ClickHouse/ClickHouse/pull/65475) ([lgbo](https://github.com/lgbo-ustc)).
 * Introduce `logger.console_log_level` server config to control the log level to the console (if enabled). [#65559](https://github.com/ClickHouse/ClickHouse/pull/65559) ([Azat Khuzhin](https://github.com/azat)).
 * Automatically append a wildcard `*` to the end of a directory path with table function `file`. [#66019](https://github.com/ClickHouse/ClickHouse/pull/66019) ([Zhidong (David) Guo](https://github.com/Gun9niR)).
-* Add `--memory-usage` option to client in non interactive mode. [#66393](https://github.com/ClickHouse/ClickHouse/pull/66393) ([vdimir](https://github.com/vdimir)).
+* Add `--memory-usage` option to client in non-interactive mode. [#66393](https://github.com/ClickHouse/ClickHouse/pull/66393) ([vdimir](https://github.com/vdimir)).
 * Make an interactive client for clickhouse-disks, add local disk from the local directory. [#64446](https://github.com/ClickHouse/ClickHouse/pull/64446) ([Daniil Ivanik](https://github.com/divanik)).
 * When lightweight delete happens on a table with projection(s), users have choices either throw an exception (by default) or drop the projection [#65594](https://github.com/ClickHouse/ClickHouse/pull/65594) ([jsc0218](https://github.com/jsc0218)).
+* Add system tables with main information about all detached tables. [#65400](https://github.com/ClickHouse/ClickHouse/pull/65400) ([Konstantin Morozov](https://github.com/k-morozov)).
 
 #### Experimental Feature
-* Change binary serialization of Variant data type: add `compact` mode to avoid writing the same discriminator multiple times for granules with single variant or with only NULL values. Add MergeTree setting `use_compact_variant_discriminators_serialization` that is enabled by default. Note that Variant type is still experimental and backward-incompatible change in serialization is ok. [#62774](https://github.com/ClickHouse/ClickHouse/pull/62774) ([Kruglov Pavel](https://github.com/Avogar)).
+* Change binary serialization of the `Variant` data type: add `compact` mode to avoid writing the same discriminator multiple times for granules with single variant or with only NULL values. Add MergeTree setting `use_compact_variant_discriminators_serialization` that is enabled by default. Note that Variant type is still experimental and backward-incompatible change in serialization is ok. [#62774](https://github.com/ClickHouse/ClickHouse/pull/62774) ([Kruglov Pavel](https://github.com/Avogar)).
-* Support rocksdb as backend storage of keeper. [#56626](https://github.com/ClickHouse/ClickHouse/pull/56626) ([Han Fei](https://github.com/hanfei1991)).
+* Support on-disk backend storage for clickhouse-keeper. [#56626](https://github.com/ClickHouse/ClickHouse/pull/56626) ([Han Fei](https://github.com/hanfei1991)).
 * Refactor JSONExtract functions, support more types including experimental Dynamic type. [#66046](https://github.com/ClickHouse/ClickHouse/pull/66046) ([Kruglov Pavel](https://github.com/Avogar)).
-* Support null map subcolumn for Variant and Dynamic subcolumns. [#66178](https://github.com/ClickHouse/ClickHouse/pull/66178) ([Kruglov Pavel](https://github.com/Avogar)).
+* Support null map subcolumn for `Variant` and `Dynamic` subcolumns. [#66178](https://github.com/ClickHouse/ClickHouse/pull/66178) ([Kruglov Pavel](https://github.com/Avogar)).
-* Fix reading dynamic subcolumns from altered Memory table. Previously if `max_types` parameter of a Dynamic type was changed in Memory table via alter, further subcolumns reading can return wrong result. [#66066](https://github.com/ClickHouse/ClickHouse/pull/66066) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix reading `Dynamic` subcolumns from altered `Memory` table. Previously if `max_types` parameter of a Dynamic type was changed in Memory table via alter, further subcolumns reading can return wrong result. [#66066](https://github.com/ClickHouse/ClickHouse/pull/66066) ([Kruglov Pavel](https://github.com/Avogar)).
 * Add support for `cluster_for_parallel_replicas` when using custom key parallel replicas. It allows you to use parallel replicas with custom key with MergeTree tables. [#65453](https://github.com/ClickHouse/ClickHouse/pull/65453) ([Antonio Andelic](https://github.com/antonio2368)).
 
 #### Performance Improvement
-* Enable `optimize_functions_to_subcolumns` by default. [#58661](https://github.com/ClickHouse/ClickHouse/pull/58661) ([Anton Popov](https://github.com/CurtizJ)).
 * Replace int to string algorithm with a faster one (from a modified amdn/itoa to a modified jeaiii/itoa). [#61661](https://github.com/ClickHouse/ClickHouse/pull/61661) ([Raúl Marín](https://github.com/Algunenano)).
-* Sizes of hash tables created by join (`parallel_hash` algorithm) is collected and cached now. This information will be used to preallocate space in hash tables for subsequent query executions and save time on hash table resizes. [#64553](https://github.com/ClickHouse/ClickHouse/pull/64553) ([Nikita Taranov](https://github.com/nickitat)).
+* Sizes of hash tables created by join (`parallel_hash` algorithm) are collected and cached now. This information will be used to preallocate space in hash tables for subsequent query executions and save time on hash table resizes. [#64553](https://github.com/ClickHouse/ClickHouse/pull/64553) ([Nikita Taranov](https://github.com/nickitat)).
-* Optimized queries with `ORDER BY` primary key and `WHERE` that have a condition with high selectivity by using of buffering. It is controlled by setting `read_in_order_use_buffering` (enabled by default) and can increase memory usage of query. [#64607](https://github.com/ClickHouse/ClickHouse/pull/64607) ([Anton Popov](https://github.com/CurtizJ)).
+* Optimized queries with `ORDER BY` primary key and `WHERE` that have a condition with high selectivity by using buffering. It is controlled by setting `read_in_order_use_buffering` (enabled by default) and can increase memory usage of query. [#64607](https://github.com/ClickHouse/ClickHouse/pull/64607) ([Anton Popov](https://github.com/CurtizJ)).
 * Improve performance of loading `plain_rewritable` metadata. [#65634](https://github.com/ClickHouse/ClickHouse/pull/65634) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
 * Attaching tables on read-only disks will use fewer resources by not loading outdated parts. [#65635](https://github.com/ClickHouse/ClickHouse/pull/65635) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
 * Support minmax hyperrectangle for Set indices. [#65676](https://github.com/ClickHouse/ClickHouse/pull/65676) ([AntiTopQuark](https://github.com/AntiTopQuark)).
@@ -60,11 +61,10 @@
 * DatabaseCatalog drops tables faster by using up to database_catalog_drop_table_concurrency threads. [#66065](https://github.com/ClickHouse/ClickHouse/pull/66065) ([Sema Checherinda](https://github.com/CheSema)).
 
 #### Improvement
+* Improved ZooKeeper load balancing. The current session doesn't expire until the optimal nodes become available despite `fallback_session_lifetime`. Added support for AZ-aware balancing. [#65570](https://github.com/ClickHouse/ClickHouse/pull/65570) ([Alexander Tokmakov](https://github.com/tavplubix)).
 * The setting `optimize_trivial_insert_select` is disabled by default. In most cases, it should be beneficial. Nevertheless, if you are seeing slower INSERT SELECT or increased memory usage, you can enable it back or `SET compatibility = '24.6'`. [#58970](https://github.com/ClickHouse/ClickHouse/pull/58970) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
 * Print stacktrace and diagnostic info if `clickhouse-client` or `clickhouse-local` crashes. [#61109](https://github.com/ClickHouse/ClickHouse/pull/61109) ([Alexander Tokmakov](https://github.com/tavplubix)).
 * The result of `SHOW INDEX | INDEXES | INDICES | KEYS` was previously sorted by the primary key column names. Since this was unintuitive, the result is now sorted by the position of the primary key columns within the primary key. [#61131](https://github.com/ClickHouse/ClickHouse/pull/61131) ([Robert Schulze](https://github.com/rschu1ze)).
-* Change how deduplication for Materialized Views works. Fixed a lot of cases like: - on destination table: data is split for 2 or more blocks and that blocks is considered as duplicate when that block is inserted in parallel. - on MV destination table: the equal blocks are deduplicated, that happens when MV often produces equal data as a result for different input data due to performing aggregation. - on MV destination table: the equal blocks which comes from different MV are deduplicated. [#61601](https://github.com/ClickHouse/ClickHouse/pull/61601) ([Sema Checherinda](https://github.com/CheSema)).
-* Allow matching column names in a case insensitive manner when reading json files (`input_format_json_case_insensitive_column_matching`). [#61750](https://github.com/ClickHouse/ClickHouse/pull/61750) ([kevinyhzou](https://github.com/KevinyhZou)).
 * Support reading partitioned data DeltaLake data. Infer DeltaLake schema by reading metadata instead of data. [#63201](https://github.com/ClickHouse/ClickHouse/pull/63201) ([Kseniia Sumarokova](https://github.com/kssenii)).
 * In composable protocols TLS layer accepted only `certificateFile` and `privateKeyFile` parameters. https://clickhouse.com/docs/en/operations/settings/composable-protocols. [#63985](https://github.com/ClickHouse/ClickHouse/pull/63985) ([Anton Ivashkin](https://github.com/ianton-ru)).
 * Added profile event `SelectQueriesWithPrimaryKeyUsage` which indicates how many SELECT queries use the primary key to evaluate the WHERE clause. [#64492](https://github.com/ClickHouse/ClickHouse/pull/64492) ([0x01f](https://github.com/0xfei)).
@@ -72,7 +72,6 @@
 * Support aliases in parametrized view function (only new analyzer). [#65190](https://github.com/ClickHouse/ClickHouse/pull/65190) ([Kseniia Sumarokova](https://github.com/kssenii)).
 * Updated to mask account key in logs in azureBlobStorage. [#65273](https://github.com/ClickHouse/ClickHouse/pull/65273) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
 * Partition pruning for `IN` predicates when filter expression is a part of `PARTITION BY` expression. [#65335](https://github.com/ClickHouse/ClickHouse/pull/65335) ([Eduard Karacharov](https://github.com/korowa)).
-* Add system tables with main information about all detached tables. [#65400](https://github.com/ClickHouse/ClickHouse/pull/65400) ([Konstantin Morozov](https://github.com/k-morozov)).
 * `arrayMin`/`arrayMax` can be applicable to all data types that are comparable. [#65455](https://github.com/ClickHouse/ClickHouse/pull/65455) ([pn](https://github.com/chloro-pn)).
 * Improved memory accounting for cgroups v2 to exclude the amount occupied by the page cache. [#65470](https://github.com/ClickHouse/ClickHouse/pull/65470) ([Nikita Taranov](https://github.com/nickitat)).
 * Do not create format settings for each row when serializing chunks to insert to EmbeddedRocksDB table. [#65474](https://github.com/ClickHouse/ClickHouse/pull/65474) ([Duc Canh Le](https://github.com/canhld94)).
@@ -81,36 +80,35 @@
 * Disable filesystem cache background download by default. It will be enabled back when we fix the issue with possible "Memory limit exceeded" because memory deallocation is done outside of query context (while buffer is allocated inside of query context) if we use background download threads. Plus we need to add a separate setting to define max size to download for background workers (currently it is limited by max_file_segment_size, which might be too big). [#65534](https://github.com/ClickHouse/ClickHouse/pull/65534) ([Kseniia Sumarokova](https://github.com/kssenii)).
 * Add new option to config `<config_reload_interval_ms>` which allow to specify how often clickhouse will reload config. [#65545](https://github.com/ClickHouse/ClickHouse/pull/65545) ([alesapin](https://github.com/alesapin)).
 * Implement binary encoding for ClickHouse data types and add its specification in docs. Use it in Dynamic binary serialization, allow to use it in RowBinaryWithNamesAndTypes and Native formats under settings. [#65546](https://github.com/ClickHouse/ClickHouse/pull/65546) ([Kruglov Pavel](https://github.com/Avogar)).
-* Improved ZooKeeper load balancing. The current session doesn't expire until the optimal nodes become available despite `fallback_session_lifetime`. Added support for AZ-aware balancing. [#65570](https://github.com/ClickHouse/ClickHouse/pull/65570) ([Alexander Tokmakov](https://github.com/tavplubix)).
 * Server settings `compiled_expression_cache_size` and `compiled_expression_cache_elements_size` are now shown in `system.server_settings`. [#65584](https://github.com/ClickHouse/ClickHouse/pull/65584) ([Robert Schulze](https://github.com/rschu1ze)).
 * Add support for user identification based on x509 SubjectAltName extension. [#65626](https://github.com/ClickHouse/ClickHouse/pull/65626) ([Anton Kozlov](https://github.com/tonickkozlov)).
 * `clickhouse-local` will respect the `max_server_memory_usage` and `max_server_memory_usage_to_ram_ratio` from the configuration file. It will also set the max memory usage to 90% of the system memory by default, like `clickhouse-server` does. [#65697](https://github.com/ClickHouse/ClickHouse/pull/65697) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
 * Add a script to backup your files to ClickHouse. [#65699](https://github.com/ClickHouse/ClickHouse/pull/65699) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
-* PostgreSQL source support cancel. [#65722](https://github.com/ClickHouse/ClickHouse/pull/65722) ([Maksim Kita](https://github.com/kitaisreal)).
+* PostgreSQL source to support query cancellations. [#65722](https://github.com/ClickHouse/ClickHouse/pull/65722) ([Maksim Kita](https://github.com/kitaisreal)).
-* Make allow_experimental_analyzer be controlled by the initiator for distributed queries. This ensures compatibility and correctness during operations in mixed version clusters. [#65777](https://github.com/ClickHouse/ClickHouse/pull/65777) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Make `allow_experimental_analyzer` be controlled by the initiator for distributed queries. This ensures compatibility and correctness during operations in mixed version clusters. [#65777](https://github.com/ClickHouse/ClickHouse/pull/65777) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
 * Respect cgroup CPU limit in Keeper. [#65819](https://github.com/ClickHouse/ClickHouse/pull/65819) ([Antonio Andelic](https://github.com/antonio2368)).
-* Allow to use `concat` function with empty arguments ``` sql :) select concat();. [#65887](https://github.com/ClickHouse/ClickHouse/pull/65887) ([李扬](https://github.com/taiyang-li)).
+* Allow to use `concat` function with empty arguments `:) select concat();`. [#65887](https://github.com/ClickHouse/ClickHouse/pull/65887) ([李扬](https://github.com/taiyang-li)).
-* Allow controlling named collections in clickhouse-local. [#65973](https://github.com/ClickHouse/ClickHouse/pull/65973) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Allow controlling named collections in `clickhouse-local`. [#65973](https://github.com/ClickHouse/ClickHouse/pull/65973) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
-* Improve Azure profile events. [#65999](https://github.com/ClickHouse/ClickHouse/pull/65999) ([alesapin](https://github.com/alesapin)).
+* Improve Azure-related profile events. [#65999](https://github.com/ClickHouse/ClickHouse/pull/65999) ([alesapin](https://github.com/alesapin)).
-* Support ORC file read by writer time zone. [#66025](https://github.com/ClickHouse/ClickHouse/pull/66025) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Support ORC file read by writer's time zone. [#66025](https://github.com/ClickHouse/ClickHouse/pull/66025) ([kevinyhzou](https://github.com/KevinyhZou)).
-* Add settings to control connection to the PostgreSQL. * Setting `postgresql_connection_attempt_timeout` specifies the value passed to `connect_timeout` parameter of connection URL. * Setting `postgresql_connection_pool_retries` specifies the number of retries to establish a connection to the PostgreSQL end-point. [#66232](https://github.com/ClickHouse/ClickHouse/pull/66232) ([Dmitry Novik](https://github.com/novikd)).
+* Add settings to control connections to PostgreSQL. The setting `postgresql_connection_attempt_timeout` specifies the value passed to `connect_timeout` parameter of connection URL. The setting `postgresql_connection_pool_retries` specifies the number of retries to establish a connection to the PostgreSQL end-point. [#66232](https://github.com/ClickHouse/ClickHouse/pull/66232) ([Dmitry Novik](https://github.com/novikd)).
-* Reduce inaccuracy of input_wait_elapsed_us/input_wait_elapsed_us/elapsed_us. [#66239](https://github.com/ClickHouse/ClickHouse/pull/66239) ([Azat Khuzhin](https://github.com/azat)).
+* Reduce inaccuracy of `input_wait_elapsed_us`/`elapsed_us` in the `system.processors_profile_log`. [#66239](https://github.com/ClickHouse/ClickHouse/pull/66239) ([Azat Khuzhin](https://github.com/azat)).
-* Improve FilesystemCache ProfileEvents. [#66249](https://github.com/ClickHouse/ClickHouse/pull/66249) ([zhukai](https://github.com/nauu)).
+* Improve ProfileEvents for the filesystem cache. [#66249](https://github.com/ClickHouse/ClickHouse/pull/66249) ([zhukai](https://github.com/nauu)).
-* Add settings to ignore ON CLUSTER clause in queries for named collection management with replicated storage. [#66288](https://github.com/ClickHouse/ClickHouse/pull/66288) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
+* Add settings to ignore the `ON CLUSTER` clause in queries for named collection management with the replicated storage. [#66288](https://github.com/ClickHouse/ClickHouse/pull/66288) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
 * Function `generateSnowflakeID` now allows to specify a machine ID as a parameter to prevent collisions in large clusters. [#66374](https://github.com/ClickHouse/ClickHouse/pull/66374) ([ZAWA_ll](https://github.com/Zawa-ll)).
-* Disable suspending on Ctrl+Z in interactive mode. This is a common trap and is not expected behavior for almost all users. I imagine only a few extreme power users could appreciate suspending terminal applications to the background, but I don't know any. [#66511](https://github.com/ClickHouse/ClickHouse/pull/66511) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Disable suspending on `Ctrl+Z` in interactive mode. This is a common trap and is not expected behavior for almost all users. I imagine only a few extreme power users could appreciate suspending terminal applications to the background, but I don't know any. [#66511](https://github.com/ClickHouse/ClickHouse/pull/66511) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
-* Add option for validating the Primary key type in Dictionaries. Without this option for simple layouts any column type will be implicitly converted to UInt64. ### Documentation entry for user-facing changes. [#66595](https://github.com/ClickHouse/ClickHouse/pull/66595) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
+* Add option for validating the primary key type in Dictionaries. Without this option for simple layouts any column type will be implicitly converted to UInt64. [#66595](https://github.com/ClickHouse/ClickHouse/pull/66595) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
 
 #### Bug Fix (user-visible misbehavior in an official stable release)
-* Fix unexpected size of low cardinality column in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
 * Check cyclic dependencies on CREATE/REPLACE/RENAME/EXCHANGE queries and throw an exception if there is a cyclic dependency. Previously such cyclic dependencies could lead to a deadlock during server startup. Also fix some bugs in dependencies creation. [#65405](https://github.com/ClickHouse/ClickHouse/pull/65405) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix unexpected sizes of `LowCardinality` columns in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
 * Fix crash in maxIntersections. [#65689](https://github.com/ClickHouse/ClickHouse/pull/65689) ([Raúl Marín](https://github.com/Algunenano)).
-* Fix the VALID UNTIL clause in the user definition resetting after a restart. [#66409](https://github.com/ClickHouse/ClickHouse/pull/66409) ([Nikolay Degterinsky](https://github.com/evillique)).
+* Fix the `VALID UNTIL` clause in the user definition resetting after a restart. [#66409](https://github.com/ClickHouse/ClickHouse/pull/66409) ([Nikolay Degterinsky](https://github.com/evillique)).
-* Fix SHOW MERGES remaining time. [#66735](https://github.com/ClickHouse/ClickHouse/pull/66735) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix the remaining time column in `SHOW MERGES`. [#66735](https://github.com/ClickHouse/ClickHouse/pull/66735) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
 * `Query was cancelled` might have been printed twice in clickhouse-client. This behaviour is fixed. [#66005](https://github.com/ClickHouse/ClickHouse/pull/66005) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
-* Fixed crash while using MaterializedMySQL with TABLE OVERRIDE that maps MySQL NULL field into ClickHouse not NULL field. [#54649](https://github.com/ClickHouse/ClickHouse/pull/54649) ([Filipp Ozinov](https://github.com/bakwc)).
+* Fixed crash while using `MaterializedMySQL` (which is an unsupported, experimental feature) with TABLE OVERRIDE that maps MySQL NULL field into ClickHouse not NULL field. [#54649](https://github.com/ClickHouse/ClickHouse/pull/54649) ([Filipp Ozinov](https://github.com/bakwc)).
-* Fix logical error when PREWHERE expression read no columns and table has no adaptive index granularity (very old table). [#59173](https://github.com/ClickHouse/ClickHouse/pull/59173) ([Alexander Gololobov](https://github.com/davenger)).
+* Fix logical error when `PREWHERE` expression read no columns and table has no adaptive index granularity (very old table). [#59173](https://github.com/ClickHouse/ClickHouse/pull/59173) ([Alexander Gololobov](https://github.com/davenger)).
-* Fix bug with cancellation buffer when canceling a query. [#64478](https://github.com/ClickHouse/ClickHouse/pull/64478) ([Sema Checherinda](https://github.com/CheSema)).
+* Fix bug with the cancellation buffer when canceling a query. [#64478](https://github.com/ClickHouse/ClickHouse/pull/64478) ([Sema Checherinda](https://github.com/CheSema)).
 * Fix filling parts columns from metadata (when columns.txt does not exists). [#64757](https://github.com/ClickHouse/ClickHouse/pull/64757) ([Azat Khuzhin](https://github.com/azat)).
 * Fix crash for `ALTER TABLE ... ON CLUSTER ... MODIFY SQL SECURITY`. [#64957](https://github.com/ClickHouse/ClickHouse/pull/64957) ([pufit](https://github.com/pufit)).
 * Fix crash on destroying AccessControl: add explicit shutdown. [#64993](https://github.com/ClickHouse/ClickHouse/pull/64993) ([Vitaly Baranov](https://github.com/vitlibar)).
@@ -179,9 +177,6 @@
 * Fix `indexHint` function case found by fuzzer. [#66286](https://github.com/ClickHouse/ClickHouse/pull/66286) ([Anton Popov](https://github.com/CurtizJ)).
 * Fix AST formatting of 'create table b empty as a'. [#64951](https://github.com/ClickHouse/ClickHouse/pull/64951) ([Michael Kolupaev](https://github.com/al13n321)).
 
-#### Build/Testing/Packaging Improvement
-* Instantiate template methods ahead in different .cpp files, avoid too large translation units during compiling. [#64818](https://github.com/ClickHouse/ClickHouse/pull/64818) ([lgbo](https://github.com/lgbo-ustc)).
-
 ### <a id="246"></a> ClickHouse release 24.6, 2024-07-01
 
 #### Backward Incompatible Change

SECURITY.md

@@ -14,9 +14,10 @@ The following versions of ClickHouse server are currently supported with securit
 
 | Version | Supported |
 |:-|:-|
+| 24.7 | ✔️ |
 | 24.6 | ✔️ |
 | 24.5 | ✔️ |
-| 24.4 | ✔️ |
+| 24.4 | ❌ |
 | 24.3 | ✔️ |
 | 24.2 | ❌ |
 | 24.1 | ❌ |

base/base/CMakeLists.txt

@@ -32,6 +32,7 @@ set (SRCS
     StringRef.cpp
     safeExit.cpp
     throwError.cpp
+    Numa.cpp
 )
 
 add_library (common ${SRCS})
@@ -46,6 +47,10 @@ if (TARGET ch_contrib::crc32_s390x)
     target_link_libraries(common PUBLIC ch_contrib::crc32_s390x)
 endif()
 
+if (TARGET ch_contrib::numactl)
+    target_link_libraries(common PUBLIC ch_contrib::numactl)
+endif()
+
 target_include_directories(common PUBLIC .. "${CMAKE_CURRENT_BINARY_DIR}/..")
 
 target_link_libraries (common

base/base/Numa.cpp

@@ -0,0 +1,37 @@
+#include <base/Numa.h>
+
+#include "config.h"
+
+#if USE_NUMACTL
+#    include <numa.h>
+#endif
+
+namespace DB
+{
+
+std::optional<size_t> getNumaNodesTotalMemory()
+{
+    std::optional<size_t> total_memory;
+#if USE_NUMACTL
+    if (numa_available() != -1)
+    {
+        auto * membind = numa_get_membind();
+        if (!numa_bitmask_equal(membind, numa_all_nodes_ptr))
+        {
+            total_memory.emplace(0);
+            auto max_node = numa_max_node();
+            for (int i = 0; i <= max_node; ++i)
+            {
+                if (numa_bitmask_isbitset(membind, i))
+                    *total_memory += numa_node_size(i, nullptr);
+            }
+        }
+
+        numa_bitmask_free(membind);
+    }
+
+#endif
+    return total_memory;
+}
+
+}

base/base/Numa.h

@@ -0,0 +1,12 @@
+#pragma once
+
+#include <optional>
+
+namespace DB
+{
+
+/// return total memory of NUMA nodes the process is bound to
+/// if NUMA is not supported or process can use all nodes, std::nullopt is returned
+std::optional<size_t> getNumaNodesTotalMemory();
+
+}

base/base/getMemoryAmount.cpp

@@ -2,15 +2,14 @@
 
 #include <base/cgroupsv2.h>
 #include <base/getPageSize.h>
+#include <base/Numa.h>
 
 #include <fstream>
-#include <stdexcept>
 
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/param.h>
 
-
 namespace
 {
 
@@ -63,6 +62,9 @@ uint64_t getMemoryAmountOrZero()
 
     uint64_t memory_amount = num_pages * page_size;
 
+    if (auto total_numa_memory = DB::getNumaNodesTotalMemory(); total_numa_memory.has_value())
+        memory_amount = *total_numa_memory;
+
     /// Respect the memory limit set by cgroups v2.
     auto limit_v2 = getCgroupsV2MemoryLimit();
     if (limit_v2.has_value() && *limit_v2 < memory_amount)

base/glibc-compatibility/CMakeLists.txt

@@ -18,6 +18,16 @@ if (GLIBC_COMPATIBILITY)
         message (FATAL_ERROR "glibc_compatibility can only be used on x86_64 or aarch64.")
     endif ()
 
+    if (SANITIZE STREQUAL thread)
+        # Disable TSAN instrumentation that conflicts with re-exec due to high ASLR entropy using getauxval
+        # See longer comment in __auxv_init_procfs
+        # In the case of tsan we need to make sure getauxval is not instrumented as that would introduce tsan
+        # internal calls to functions that depend on a state that isn't initialized yet
+        set_source_files_properties(
+                musl/getauxval.c
+                PROPERTIES COMPILE_FLAGS "-mllvm -tsan-instrument-func-entry-exit=false")
+    endif()
+
     # Need to omit frame pointers to match the performance of glibc
     set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fomit-frame-pointer")
 

base/glibc-compatibility/musl/getauxval.c

@@ -75,6 +75,44 @@ unsigned long NO_SANITIZE_THREAD __getauxval_procfs(unsigned long type)
 }
 static unsigned long NO_SANITIZE_THREAD __auxv_init_procfs(unsigned long type)
 {
+#if defined(__x86_64__) && defined(__has_feature)
+#    if __has_feature(memory_sanitizer) || __has_feature(thread_sanitizer)
+    /// Sanitizers are not compatible with high ASLR entropy, which is the default on modern Linux distributions, and
+    /// to workaround this limitation, TSAN and MSAN (couldn't see other sanitizers doing the same), re-exec the binary
+    /// without ASLR (see https://github.com/llvm/llvm-project/commit/0784b1eefa36d4acbb0dacd2d18796e26313b6c5)
+
+    /// The problem we face is that, in order to re-exec, the sanitizer wants to use the original pathname in the call
+    /// and to get its value it uses getauxval (https://github.com/llvm/llvm-project/blob/20eff684203287828d6722fc860b9d3621429542/compiler-rt/lib/sanitizer_common/sanitizer_linux_libcdep.cpp#L985-L988).
+    /// Since we provide getauxval ourselves (to minimize the version dependency on runtime glibc), we are the ones
+    // being called and we fail horribly:
+    ///
+    ///    ==301455==ERROR: MemorySanitizer: SEGV on unknown address 0x2ffc6d721550 (pc 0x5622c1cc0073 bp 0x000000000003 sp 0x7ffc6d721530 T301455)
+    ///    ==301455==The signal is caused by a WRITE memory access.
+    /// #0 0x5622c1cc0073 in __auxv_init_procfs ./ClickHouse/base/glibc-compatibility/musl/getauxval.c:129:5
+    /// #1 0x5622c1cbffe9 in getauxval ./ClickHouse/base/glibc-compatibility/musl/getauxval.c:240:12
+    /// #2 0x5622c0d7bfb4 in __sanitizer::ReExec() crtstuff.c
+    /// #3 0x5622c0df7bfc in __msan::InitShadowWithReExec(bool) crtstuff.c
+    /// #4 0x5622c0d95356 in __msan_init (./ClickHouse/build_msan/contrib/google-protobuf-cmake/protoc+0x256356) (BuildId: 6411d3c88b898ba3f7d49760555977d3e61f0741)
+    /// #5 0x5622c0dfe878 in msan.module_ctor main.cc
+    /// #6 0x5622c1cc156c in __libc_csu_init (./ClickHouse/build_msan/contrib/google-protobuf-cmake/protoc+0x118256c) (BuildId: 6411d3c88b898ba3f7d49760555977d3e61f0741)
+    /// #7 0x73dc05dd7ea3 in __libc_start_main /usr/src/debug/glibc/glibc/csu/../csu/libc-start.c:343:6
+    /// #8 0x5622c0d6b7cd in _start (./ClickHouse/build_msan/contrib/google-protobuf-cmake/protoc+0x22c7cd) (BuildId: 6411d3c88b898ba3f7d49760555977d3e61f0741)
+
+    /// The source of the issue above is that, at this point in time during __msan_init, we can't really do much as
+    /// most global variables aren't initialized or available yet, so we can't initiate the auxiliary vector.
+    /// Normal glibc / musl getauxval doesn't have this problem since they initiate their auxval vector at the very
+    /// start of __libc_start_main (just keeping track of argv+argc+1), but we don't have such option (otherwise
+    /// this complexity of reading "/proc/self/auxv" or using __environ would not be necessary).
+
+    /// To avoid this crashes on the re-exec call (see above how it would fail when creating `aux`, and if we used
+    /// __auxv_init_environ then it would SIGSEV on READing `__environ`) we capture this call for `AT_EXECFN` and
+    /// unconditionally return "/proc/self/exe" without any preparation. Theoretically this should be fine in
+    /// our case, as we don't load any libraries. That's the theory at least.
+    if (type == AT_EXECFN)
+        return (unsigned long)"/proc/self/exe";
+#    endif
+#endif
+
     // For debugging:
     // - od -t dL /proc/self/auxv
     // - LD_SHOW_AUX= ls
@@ -199,7 +237,7 @@ static unsigned long NO_SANITIZE_THREAD __auxv_init_environ(unsigned long type)
 // - __auxv_init_procfs -> __auxv_init_environ -> __getauxval_environ
 static void * volatile getauxval_func = (void *)__auxv_init_procfs;
 
-unsigned long getauxval(unsigned long type)
+unsigned long NO_SANITIZE_THREAD getauxval(unsigned long type)
 {
     return ((unsigned long (*)(unsigned long))getauxval_func)(type);
 }

base/poco/Util/include/Poco/Util/Application.h

@@ -261,6 +261,11 @@ namespace Util
         ///
         /// Throws a NullPointerException if no Application instance exists.
 
+        static Application * instanceRawPtr();
+        /// Returns a raw pointer to the Application singleton.
+        ///
+        /// The caller should check whether the result is nullptr.
+
         const Poco::Timestamp & startTime() const;
         /// Returns the application start time (UTC).
 
@@ -448,6 +453,12 @@ namespace Util
     }
 
 
+    inline Application * Application::instanceRawPtr()
+    {
+        return _pInstance;
+    }
+
+
     inline const Poco::Timestamp & Application::startTime() const
     {
         return _startTime;

contrib/CMakeLists.txt

@@ -230,6 +230,8 @@ add_contrib (libssh-cmake libssh)
 
 add_contrib (prometheus-protobufs-cmake prometheus-protobufs prometheus-protobufs-gogo)
 
+add_contrib(numactl-cmake numactl)
+
 # 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/azure

@@ -1 +1 @@
-Subproject commit ea3e19a7be08519134c643177d56c7484dfec884
+Subproject commit 67272b7ee0adff6b69921b26eb071ba1a353062c

contrib/icu

@@ -1 +1 @@
-Subproject commit a56dde820dc35665a66f2e9ee8ba58e75049b668
+Subproject commit 7750081bda4b3bc1768ae03849ec70f67ea10625

contrib/icu-cmake/CMakeLists.txt

@@ -4,7 +4,9 @@ else ()
     option(ENABLE_ICU "Enable ICU" 0)
 endif ()
 
-if (NOT ENABLE_ICU)
+# Temporarily disabled s390x because the ICU build links a blob (icudt71b_dat.S) and our friends from IBM did not explain how they generated
+# the blob on s390x: https://github.com/ClickHouse/icudata/pull/2#issuecomment-2226957255
+if (NOT ENABLE_ICU OR ARCH_S390X)
     message(STATUS "Not using ICU")
     return()
 endif()
@@ -12,8 +14,6 @@ endif()
 set(ICU_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/icu/icu4c/source")
 set(ICUDATA_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/icudata/")
 
-set (CMAKE_CXX_STANDARD 17)
-
 # These lists of sources were generated from build log of the original ICU build system (configure + make).
 
 set(ICUUC_SOURCES
@@ -462,9 +462,9 @@ file(GENERATE OUTPUT "${CMAKE_CURRENT_BINARY_DIR}/empty.cpp" CONTENT " ")
 enable_language(ASM)
 
 if (ARCH_S390X)
-    set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt70b_dat.S" )
+    set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt75b_dat.S" )
 else()
-    set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt70l_dat.S" )
+    set(ICUDATA_SOURCE_FILE "${ICUDATA_SOURCE_DIR}/icudt75l_dat.S" )
 endif()
 
 set(ICUDATA_SOURCES

contrib/icudata

@@ -1 +1 @@
-Subproject commit c8e717892a557b4d2852317c7d628aacc0a0e5ab
+Subproject commit d345d6ac22f381c882420de9053d30ae1ff38d75

contrib/numactl

@@ -0,0 +1 @@
+Subproject commit 8d13d63a05f0c3cd88bf777cbb61541202b7da08

contrib/numactl-cmake/CMakeLists.txt

@@ -0,0 +1,30 @@
+if (NOT (
+    OS_LINUX AND (ARCH_AMD64 OR ARCH_AARCH64 OR ARCH_LOONGARCH64))
+)
+    if (ENABLE_NUMACTL)
+        message (${RECONFIGURE_MESSAGE_LEVEL}
+            "numactl is disabled implicitly because the OS or architecture is not supported. Use -DENABLE_NUMACTL=0")
+    endif ()
+    set (ENABLE_NUMACTL OFF)
+else()
+    option (ENABLE_NUMACTL "Enable numactl" ${ENABLE_LIBRARIES})
+endif()
+
+if (NOT ENABLE_NUMACTL)
+    message (STATUS "Not using numactl")
+    return()
+endif ()
+
+set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/numactl")
+
+set (SRCS
+    "${LIBRARY_DIR}/libnuma.c"
+    "${LIBRARY_DIR}/syscall.c"
+)
+
+add_library(_numactl ${SRCS})
+
+target_include_directories(_numactl SYSTEM PRIVATE include)
+target_include_directories(_numactl SYSTEM PUBLIC "${LIBRARY_DIR}")
+
+add_library(ch_contrib::numactl ALIAS _numactl)

contrib/numactl-cmake/include/config.h

@@ -0,0 +1,82 @@
+/* config.h.  Generated from config.h.in by configure.  */
+/* config.h.in.  Generated from configure.ac by autoheader.  */
+
+/* Checking for symver attribute */
+#define HAVE_ATTRIBUTE_SYMVER 0
+
+/* Define to 1 if you have the <dlfcn.h> header file. */
+#define HAVE_DLFCN_H 1
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#define HAVE_INTTYPES_H 1
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#define HAVE_STDINT_H 1
+
+/* Define to 1 if you have the <stdio.h> header file. */
+#define HAVE_STDIO_H 1
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#define HAVE_STDLIB_H 1
+
+/* Define to 1 if you have the <strings.h> header file. */
+#define HAVE_STRINGS_H 1
+
+/* Define to 1 if you have the <string.h> header file. */
+#define HAVE_STRING_H 1
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#define HAVE_SYS_STAT_H 1
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#define HAVE_SYS_TYPES_H 1
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#define HAVE_UNISTD_H 1
+
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
+#define LT_OBJDIR ".libs/"
+
+/* Name of package */
+#define PACKAGE "numactl"
+
+/* Define to the address where bug reports for this package should be sent. */
+#define PACKAGE_BUGREPORT ""
+
+/* Define to the full name of this package. */
+#define PACKAGE_NAME "numactl"
+
+/* Define to the full name and version of this package. */
+#define PACKAGE_STRING "numactl 2.1"
+
+/* Define to the one symbol short name of this package. */
+#define PACKAGE_TARNAME "numactl"
+
+/* Define to the home page for this package. */
+#define PACKAGE_URL ""
+
+/* Define to the version of this package. */
+#define PACKAGE_VERSION "2.1"
+
+/* Define to 1 if all of the C89 standard headers exist (not just the ones
+   required in a freestanding environment). This macro is provided for
+   backward compatibility; new code need not use it. */
+#define STDC_HEADERS 1
+
+/* If the compiler supports a TLS storage class define it to that here */
+#define TLS __thread
+
+/* Version number of package */
+#define VERSION "2.1"
+
+/* Number of bits in a file offset, on hosts where this is settable. */
+/* #undef _FILE_OFFSET_BITS */
+
+/* Define to 1 on platforms where this makes off_t a 64-bit type. */
+/* #undef _LARGE_FILES */
+
+/* Number of bits in time_t, on hosts where this is settable. */
+/* #undef _TIME_BITS */
+
+/* Define to 1 on platforms where this makes time_t a 64-bit type. */
+/* #undef __MINGW_USE_VC2005_COMPAT */

contrib/rocksdb

@@ -1 +1 @@
-Subproject commit be366233921293bd07a84dc4ea6991858665f202
+Subproject commit 01e43568fa9f3f7bf107b2b66c00b286b456f33e

contrib/rocksdb-cmake/CMakeLists.txt

@@ -5,6 +5,9 @@ if (NOT ENABLE_ROCKSDB)
   return()
 endif()
 
+# not in original build system, otherwise xxHash.cc fails to compile with ClickHouse C++23 default
+set (CMAKE_CXX_STANDARD 20)
+
 # Always disable jemalloc for rocksdb by default because it introduces non-standard jemalloc APIs
 option(WITH_JEMALLOC "build with JeMalloc" OFF)
 
@@ -16,14 +19,6 @@ option(WITH_LZ4 "build with lz4" ON)
 option(WITH_ZLIB "build with zlib" ON)
 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")
-  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
-else()
-  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
-endif()
-
 if(WITH_SNAPPY)
   add_definitions(-DSNAPPY)
   list(APPEND THIRDPARTY_LIBS ch_contrib::snappy)
@@ -44,7 +39,7 @@ if(WITH_ZSTD)
   list(APPEND THIRDPARTY_LIBS ch_contrib::zstd)
 endif()
 
-option(PORTABLE "build a portable binary" ON)
+add_definitions(-DROCKSDB_PORTABLE)
 
 if(ENABLE_SSE42 AND ENABLE_PCLMULQDQ)
   add_definitions(-DHAVE_SSE42)
@@ -59,11 +54,6 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64|AARCH64")
   # 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)
-endif()
-
 if(CMAKE_SYSTEM_NAME MATCHES "Darwin")
   add_definitions(-DOS_MACOSX)
 elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
@@ -89,19 +79,21 @@ set(ROCKSDB_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/rocksdb")
 
 include_directories(${ROCKSDB_SOURCE_DIR})
 include_directories("${ROCKSDB_SOURCE_DIR}/include")
-if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-  include_directories("${ROCKSDB_SOURCE_DIR}/third-party/folly")
-endif()
 
 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_helpers.cc
     ${ROCKSDB_SOURCE_DIR}/cache/cache_reservation_manager.cc
+    ${ROCKSDB_SOURCE_DIR}/cache/charged_cache.cc
     ${ROCKSDB_SOURCE_DIR}/cache/clock_cache.cc
+    ${ROCKSDB_SOURCE_DIR}/cache/compressed_secondary_cache.cc
     ${ROCKSDB_SOURCE_DIR}/cache/lru_cache.cc
+    ${ROCKSDB_SOURCE_DIR}/cache/secondary_cache.cc
     ${ROCKSDB_SOURCE_DIR}/cache/sharded_cache.cc
     ${ROCKSDB_SOURCE_DIR}/db/arena_wrapped_db_iter.cc
+    ${ROCKSDB_SOURCE_DIR}/db/blob/blob_contents.cc
     ${ROCKSDB_SOURCE_DIR}/db/blob/blob_fetcher.cc
     ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_addition.cc
     ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_builder.cc
@@ -113,6 +105,7 @@ 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/blob_source.cc
     ${ROCKSDB_SOURCE_DIR}/db/blob/prefetch_buffer_collection.cc
     ${ROCKSDB_SOURCE_DIR}/db/builder.cc
     ${ROCKSDB_SOURCE_DIR}/db/c.cc
@@ -124,7 +117,11 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_fifo.cc
     ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_level.cc
     ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_universal.cc
+    ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_service_job.cc
+    ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_state.cc
+    ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_outputs.cc
     ${ROCKSDB_SOURCE_DIR}/db/compaction/sst_partitioner.cc
+    ${ROCKSDB_SOURCE_DIR}/db/compaction/subcompaction_state.cc
     ${ROCKSDB_SOURCE_DIR}/db/convenience.cc
     ${ROCKSDB_SOURCE_DIR}/db/db_filesnapshot.cc
     ${ROCKSDB_SOURCE_DIR}/db/db_impl/compacted_db_impl.cc
@@ -159,10 +156,11 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/db/merge_helper.cc
     ${ROCKSDB_SOURCE_DIR}/db/merge_operator.cc
     ${ROCKSDB_SOURCE_DIR}/db/output_validator.cc
-    ${ROCKSDB_SOURCE_DIR}/db/periodic_work_scheduler.cc
+    ${ROCKSDB_SOURCE_DIR}/db/periodic_task_scheduler.cc
     ${ROCKSDB_SOURCE_DIR}/db/range_del_aggregator.cc
     ${ROCKSDB_SOURCE_DIR}/db/range_tombstone_fragmenter.cc
     ${ROCKSDB_SOURCE_DIR}/db/repair.cc
+    ${ROCKSDB_SOURCE_DIR}/db/seqno_to_time_mapping.cc
     ${ROCKSDB_SOURCE_DIR}/db/snapshot_impl.cc
     ${ROCKSDB_SOURCE_DIR}/db/table_cache.cc
     ${ROCKSDB_SOURCE_DIR}/db/table_properties_collector.cc
@@ -174,6 +172,8 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/db/version_set.cc
     ${ROCKSDB_SOURCE_DIR}/db/wal_edit.cc
     ${ROCKSDB_SOURCE_DIR}/db/wal_manager.cc
+    ${ROCKSDB_SOURCE_DIR}/db/wide/wide_column_serialization.cc
+    ${ROCKSDB_SOURCE_DIR}/db/wide/wide_columns.cc
     ${ROCKSDB_SOURCE_DIR}/db/write_batch.cc
     ${ROCKSDB_SOURCE_DIR}/db/write_batch_base.cc
     ${ROCKSDB_SOURCE_DIR}/db/write_controller.cc
@@ -182,7 +182,6 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/env/env.cc
     ${ROCKSDB_SOURCE_DIR}/env/env_chroot.cc
     ${ROCKSDB_SOURCE_DIR}/env/env_encryption.cc
-    ${ROCKSDB_SOURCE_DIR}/env/env_hdfs.cc
     ${ROCKSDB_SOURCE_DIR}/env/file_system.cc
     ${ROCKSDB_SOURCE_DIR}/env/file_system_tracer.cc
     ${ROCKSDB_SOURCE_DIR}/env/fs_remap.cc
@@ -233,16 +232,17 @@ set(SOURCES
     ${ROCKSDB_SOURCE_DIR}/options/options.cc
     ${ROCKSDB_SOURCE_DIR}/options/options_helper.cc
     ${ROCKSDB_SOURCE_DIR}/options/options_parser.cc
+    ${ROCKSDB_SOURCE_DIR}/port/mmap.cc
     ${ROCKSDB_SOURCE_DIR}/port/stack_trace.cc
     ${ROCKSDB_SOURCE_DIR}/table/adaptive/adaptive_table_factory.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/binary_search_index_reader.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block.cc
-    ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_filter_block.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_builder.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_factory.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_iterator.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_reader.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block_builder.cc
+    ${ROCKSDB_SOURCE_DIR}/table/block_based/block_cache.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block_prefetcher.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/block_prefix_index.cc
     ${ROCKSDB_SOURCE_DIR}/table/block_based/data_block_hash_index.cc
@@ -300,9 +300,12 @@ set(SOURCES
     ${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/async_file_reader.cc
+    ${ROCKSDB_SOURCE_DIR}/util/cleanable.cc
     ${ROCKSDB_SOURCE_DIR}/util/coding.cc
     ${ROCKSDB_SOURCE_DIR}/util/compaction_job_stats_impl.cc
     ${ROCKSDB_SOURCE_DIR}/util/comparator.cc
+    ${ROCKSDB_SOURCE_DIR}/util/compression.cc
     ${ROCKSDB_SOURCE_DIR}/util/compression_context_cache.cc
     ${ROCKSDB_SOURCE_DIR}/util/concurrent_task_limiter_impl.cc
     ${ROCKSDB_SOURCE_DIR}/util/crc32c.cc
@@ -311,16 +314,17 @@ 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
     ${ROCKSDB_SOURCE_DIR}/util/status.cc
+    ${ROCKSDB_SOURCE_DIR}/util/stderr_logger.cc
     ${ROCKSDB_SOURCE_DIR}/util/string_util.cc
     ${ROCKSDB_SOURCE_DIR}/util/thread_local.cc
     ${ROCKSDB_SOURCE_DIR}/util/threadpool_imp.cc
     ${ROCKSDB_SOURCE_DIR}/util/xxhash.cc
-    ${ROCKSDB_SOURCE_DIR}/utilities/backupable/backupable_db.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/agg_merge/agg_merge.cc
+    ${ROCKSDB_SOURCE_DIR}/utilities/backup/backup_engine.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_compaction_filter.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db_impl.cc
@@ -335,6 +339,7 @@ set(SOURCES
     ${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/counted_fs.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/debug.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/env_mirror.cc
     ${ROCKSDB_SOURCE_DIR}/utilities/env_timed.cc
@@ -422,15 +427,6 @@ list(APPEND SOURCES
     "${ROCKSDB_SOURCE_DIR}/env/fs_posix.cc"
     "${ROCKSDB_SOURCE_DIR}/env/io_posix.cc")
 
-if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-  list(APPEND SOURCES
-    "${ROCKSDB_SOURCE_DIR}/third-party/folly/folly/detail/Futex.cpp"
-    "${ROCKSDB_SOURCE_DIR}/third-party/folly/folly/synchronization/AtomicNotification.cpp"
-    "${ROCKSDB_SOURCE_DIR}/third-party/folly/folly/synchronization/DistributedMutex.cpp"
-    "${ROCKSDB_SOURCE_DIR}/third-party/folly/folly/synchronization/ParkingLot.cpp"
-    "${ROCKSDB_SOURCE_DIR}/third-party/folly/folly/synchronization/WaitOptions.cpp")
-endif()
-
 add_library(_rocksdb ${SOURCES})
 add_library(ch_contrib::rocksdb ALIAS _rocksdb)
 target_link_libraries(_rocksdb PRIVATE ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})

contrib/rocksdb-cmake/build_version.cc

@@ -1,16 +1,33 @@
 // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-/// This file was edited for ClickHouse.
 
 #include <memory>
 
 #include "rocksdb/version.h"
+#include "rocksdb/utilities/object_registry.h"
 #include "util/string_util.h"
 
 // The build script may replace these values with real values based
 // on whether or not GIT is available and the platform settings
-static const std::string rocksdb_build_git_sha  = "rocksdb_build_git_sha:0";
+static const std::string rocksdb_build_git_sha  = "rocksdb_build_git_sha:72438a678872544809393b831c7273794c074215";
-static const std::string rocksdb_build_git_tag = "rocksdb_build_git_tag:master";
+static const std::string rocksdb_build_git_tag = "rocksdb_build_git_tag:main";
-static const std::string rocksdb_build_date = "rocksdb_build_date:2000-01-01";
+#define HAS_GIT_CHANGES 0
+#if HAS_GIT_CHANGES == 0
+// If HAS_GIT_CHANGES is 0, the GIT date is used.
+// Use the time the branch/tag was last modified
+static const std::string rocksdb_build_date = "rocksdb_build_date:2024-07-12 16:01:57";
+#else
+// If HAS_GIT_CHANGES is > 0, the branch/tag has modifications.
+// Use the time the build was created.
+static const std::string rocksdb_build_date = "rocksdb_build_date:2024-07-13 17:15:50";
+#endif
+
+extern "C" {
+
+} // extern "C"
+
+std::unordered_map<std::string, ROCKSDB_NAMESPACE::RegistrarFunc> ROCKSDB_NAMESPACE::ObjectRegistry::builtins_ = {
+  
+};
 
 namespace ROCKSDB_NAMESPACE {
 static void AddProperty(std::unordered_map<std::string, std::string> *props, const std::string& name) {
@@ -39,9 +56,9 @@ const std::unordered_map<std::string, std::string>& GetRocksBuildProperties() {
 }
 
 std::string GetRocksVersionAsString(bool with_patch) {
-  std::string version = ToString(ROCKSDB_MAJOR) + "." + ToString(ROCKSDB_MINOR);
+  std::string version = std::to_string(ROCKSDB_MAJOR) + "." + std::to_string(ROCKSDB_MINOR);
   if (with_patch) {
-    return version + "." + ToString(ROCKSDB_PATCH);
+    return version + "." + std::to_string(ROCKSDB_PATCH);
   } else {
     return version;
  }

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="24.6.2.17"
+ARG VERSION="24.7.1.2915"
 ARG PACKAGES="clickhouse-keeper"
 ARG DIRECT_DOWNLOAD_URLS=""
 

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="24.6.2.17"
+ARG VERSION="24.7.1.2915"
 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="24.6.2.17"
+ARG VERSION="24.7.1.2915"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
 
 #docker-official-library:off

docker/test/performance-comparison/run.sh

@@ -13,6 +13,7 @@ entry="/usr/share/clickhouse-test/performance/scripts/entrypoint.sh"
 # https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt
 # Double-escaped backslashes are a tribute to the engineering wonder of docker --
 # it gives '/bin/sh: 1: [bash,: not found' otherwise.
+numactl --hardware
 node=$(( RANDOM % $(numactl --hardware | sed -n 's/^.*available:\(.*\)nodes.*$/\1/p') ));
 echo Will bind to NUMA node $node;
 numactl --cpunodebind=$node --membind=$node $entry

docs/changelogs/v24.4.4.107-stable.md

@@ -0,0 +1,70 @@
+---
+sidebar_position: 1
+sidebar_label: 2024
+---
+
+# 2024 Changelog
+
+### ClickHouse release v24.4.4.107-stable (af0ed6b197e) FIXME as compared to v24.4.3.25-stable (a915dd4eda4)
+
+#### Improvement
+* Backported in [#65884](https://github.com/ClickHouse/ClickHouse/issues/65884): Always start Keeper with sufficient amount of threads in global thread pool. [#64444](https://github.com/ClickHouse/ClickHouse/pull/64444) ([Duc Canh Le](https://github.com/canhld94)).
+* Backported in [#65303](https://github.com/ClickHouse/ClickHouse/issues/65303): Returned back the behaviour of how ClickHouse works and interprets Tuples in CSV format. This change effectively reverts https://github.com/ClickHouse/ClickHouse/pull/60994 and makes it available only under a few settings: `output_format_csv_serialize_tuple_into_separate_columns`, `input_format_csv_deserialize_separate_columns_into_tuple` and `input_format_csv_try_infer_strings_from_quoted_tuples`. [#65170](https://github.com/ClickHouse/ClickHouse/pull/65170) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Backported in [#65894](https://github.com/ClickHouse/ClickHouse/issues/65894): Respect cgroup CPU limit in Keeper. [#65819](https://github.com/ClickHouse/ClickHouse/pull/65819) ([Antonio Andelic](https://github.com/antonio2368)).
+
+#### Critical Bug Fix (crash, LOGICAL_ERROR, data loss, RBAC)
+* Backported in [#65372](https://github.com/ClickHouse/ClickHouse/issues/65372): Fix a bug in ClickHouse Keeper that causes digest mismatch during closing session. [#65198](https://github.com/ClickHouse/ClickHouse/pull/65198) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Backported in [#66883](https://github.com/ClickHouse/ClickHouse/issues/66883): Fix unexpeced size of low cardinality column in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#65435](https://github.com/ClickHouse/ClickHouse/issues/65435): Forbid `QUALIFY` clause in the old analyzer. The old analyzer ignored `QUALIFY`, so it could lead to unexpected data removal in mutations. [#65356](https://github.com/ClickHouse/ClickHouse/pull/65356) ([Dmitry Novik](https://github.com/novikd)).
+* Backported in [#65448](https://github.com/ClickHouse/ClickHouse/issues/65448): Use correct memory alignment for Distinct combinator. Previously, crash could happen because of invalid memory allocation when the combinator was used. [#65379](https://github.com/ClickHouse/ClickHouse/pull/65379) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#65710](https://github.com/ClickHouse/ClickHouse/issues/65710): Fix crash in maxIntersections. [#65689](https://github.com/ClickHouse/ClickHouse/pull/65689) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#66689](https://github.com/ClickHouse/ClickHouse/issues/66689): Fix the VALID UNTIL clause in the user definition resetting after a restart. Closes [#66405](https://github.com/ClickHouse/ClickHouse/issues/66405). [#66409](https://github.com/ClickHouse/ClickHouse/pull/66409) ([Nikolay Degterinsky](https://github.com/evillique)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+* Backported in [#65353](https://github.com/ClickHouse/ClickHouse/issues/65353): Fix possible abort on uncaught exception in ~WriteBufferFromFileDescriptor in StatusFile. [#64206](https://github.com/ClickHouse/ClickHouse/pull/64206) ([Kruglov Pavel](https://github.com/Avogar)).
+* Backported in [#65060](https://github.com/ClickHouse/ClickHouse/issues/65060): Fix the `Expression nodes list expected 1 projection names` and `Unknown expression or identifier` errors for queries with aliases to `GLOBAL IN.`. [#64517](https://github.com/ClickHouse/ClickHouse/pull/64517) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#65329](https://github.com/ClickHouse/ClickHouse/issues/65329): Fix the crash loop when restoring from backup is blocked by creating an MV with a definer that hasn't been restored yet. [#64595](https://github.com/ClickHouse/ClickHouse/pull/64595) ([pufit](https://github.com/pufit)).
+* Backported in [#64833](https://github.com/ClickHouse/ClickHouse/issues/64833): Fix bug which could lead to non-working TTLs with expressions. [#64694](https://github.com/ClickHouse/ClickHouse/pull/64694) ([alesapin](https://github.com/alesapin)).
+* Backported in [#65086](https://github.com/ClickHouse/ClickHouse/issues/65086): Fix removing the `WHERE` and `PREWHERE` expressions, which are always true (for the new analyzer). [#64695](https://github.com/ClickHouse/ClickHouse/pull/64695) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#65540](https://github.com/ClickHouse/ClickHouse/issues/65540): Fix crash for `ALTER TABLE ... ON CLUSTER ... MODIFY SQL SECURITY`. [#64957](https://github.com/ClickHouse/ClickHouse/pull/64957) ([pufit](https://github.com/pufit)).
+* Backported in [#65578](https://github.com/ClickHouse/ClickHouse/issues/65578): Fix crash on destroying AccessControl: add explicit shutdown. [#64993](https://github.com/ClickHouse/ClickHouse/pull/64993) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Backported in [#65161](https://github.com/ClickHouse/ClickHouse/issues/65161): Fix pushing arithmetic operations out of aggregation. In the new analyzer, optimization was applied only once. [#65104](https://github.com/ClickHouse/ClickHouse/pull/65104) ([Dmitry Novik](https://github.com/novikd)).
+* Backported in [#65616](https://github.com/ClickHouse/ClickHouse/issues/65616): Fix aggregate function name rewriting in the new analyzer. [#65110](https://github.com/ClickHouse/ClickHouse/pull/65110) ([Dmitry Novik](https://github.com/novikd)).
+* Backported in [#65730](https://github.com/ClickHouse/ClickHouse/issues/65730): Eliminate injective function in argument of functions `uniq*` recursively. This used to work correctly but was broken in the new analyzer. [#65140](https://github.com/ClickHouse/ClickHouse/pull/65140) ([Duc Canh Le](https://github.com/canhld94)).
+* Backported in [#65668](https://github.com/ClickHouse/ClickHouse/issues/65668): Disable `non-intersecting-parts` optimization for queries with `FINAL` in case of `read-in-order` optimization was enabled. This could lead to an incorrect query result. As a workaround, disable `do_not_merge_across_partitions_select_final` and `split_parts_ranges_into_intersecting_and_non_intersecting_final` before this fix is merged. [#65505](https://github.com/ClickHouse/ClickHouse/pull/65505) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#65786](https://github.com/ClickHouse/ClickHouse/issues/65786): Fixed bug in MergeJoin. Column in sparse serialisation might be treated as a column of its nested type though the required conversion wasn't performed. [#65632](https://github.com/ClickHouse/ClickHouse/pull/65632) ([Nikita Taranov](https://github.com/nickitat)).
+* Backported in [#65810](https://github.com/ClickHouse/ClickHouse/issues/65810): Fix invalid exceptions in function `parseDateTime` with `%F` and `%D` placeholders. [#65768](https://github.com/ClickHouse/ClickHouse/pull/65768) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#65931](https://github.com/ClickHouse/ClickHouse/issues/65931): 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)).
+* Backported in [#65826](https://github.com/ClickHouse/ClickHouse/issues/65826): Fix a bug in short circuit logic when old analyzer and dictGetOrDefault is used. [#65802](https://github.com/ClickHouse/ClickHouse/pull/65802) ([jsc0218](https://github.com/jsc0218)).
+* Backported in [#66299](https://github.com/ClickHouse/ClickHouse/issues/66299): Better handling of join conditions involving `IS NULL` checks (for example `ON (a = b AND (a IS NOT NULL) AND (b IS NOT NULL) ) OR ( (a IS NULL) AND (b IS NULL) )` is rewritten to `ON a <=> b`), fix incorrect optimization when condition other then `IS NULL` are present. [#65835](https://github.com/ClickHouse/ClickHouse/pull/65835) ([vdimir](https://github.com/vdimir)).
+* Backported in [#66326](https://github.com/ClickHouse/ClickHouse/issues/66326): Add missing settings `input_format_csv_skip_first_lines/input_format_tsv_skip_first_lines/input_format_csv_try_infer_numbers_from_strings/input_format_csv_try_infer_strings_from_quoted_tuples` in schema inference cache because they can change the resulting schema. It prevents from incorrect result of schema inference with these settings changed. [#65980](https://github.com/ClickHouse/ClickHouse/pull/65980) ([Kruglov Pavel](https://github.com/Avogar)).
+* Backported in [#66153](https://github.com/ClickHouse/ClickHouse/issues/66153): Fixed buffer overflow bug in `unbin`/`unhex` implementation. [#66106](https://github.com/ClickHouse/ClickHouse/pull/66106) ([Nikita Taranov](https://github.com/nickitat)).
+* Backported in [#66459](https://github.com/ClickHouse/ClickHouse/issues/66459): Fixed a bug in ZooKeeper client: a session could get stuck in unusable state after receiving a hardware error from ZooKeeper. For example, this might happen due to "soft memory limit" in ClickHouse Keeper. [#66140](https://github.com/ClickHouse/ClickHouse/pull/66140) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#66224](https://github.com/ClickHouse/ClickHouse/issues/66224): Fix issue in SumIfToCountIfVisitor and signed integers. [#66146](https://github.com/ClickHouse/ClickHouse/pull/66146) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#66267](https://github.com/ClickHouse/ClickHouse/issues/66267): Don't throw `TIMEOUT_EXCEEDED` for `none_only_active` mode of `distributed_ddl_output_mode`. [#66218](https://github.com/ClickHouse/ClickHouse/pull/66218) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#66678](https://github.com/ClickHouse/ClickHouse/issues/66678): Fix handling limit for `system.numbers_mt` when no index can be used. [#66231](https://github.com/ClickHouse/ClickHouse/pull/66231) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Backported in [#66603](https://github.com/ClickHouse/ClickHouse/issues/66603): Fixed how the ClickHouse server detects the maximum number of usable CPU cores as specified by cgroups v2 if the server runs in a container such as Docker. In more detail, containers often run their process in the root cgroup which has an empty name. In that case, ClickHouse ignored the CPU limits set by cgroups v2. [#66237](https://github.com/ClickHouse/ClickHouse/pull/66237) ([filimonov](https://github.com/filimonov)).
+* Backported in [#66358](https://github.com/ClickHouse/ClickHouse/issues/66358): Fix the `Not-ready set` error when a subquery with `IN` is used in the constraint. [#66261](https://github.com/ClickHouse/ClickHouse/pull/66261) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#66971](https://github.com/ClickHouse/ClickHouse/issues/66971): Fix `Column identifier is already registered` error with `group_by_use_nulls=true` and new analyzer. [#66400](https://github.com/ClickHouse/ClickHouse/pull/66400) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#66968](https://github.com/ClickHouse/ClickHouse/issues/66968): Fix `Cannot find column` error for queries with constant expression in `GROUP BY` key and new analyzer enabled. [#66433](https://github.com/ClickHouse/ClickHouse/pull/66433) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#66719](https://github.com/ClickHouse/ClickHouse/issues/66719): Correctly track memory for `Allocator::realloc`. [#66548](https://github.com/ClickHouse/ClickHouse/pull/66548) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#66950](https://github.com/ClickHouse/ClickHouse/issues/66950): Fix an invalid result for queries with `WINDOW`. This could happen when `PARTITION` columns have sparse serialization and window functions are executed in parallel. [#66579](https://github.com/ClickHouse/ClickHouse/pull/66579) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#66947](https://github.com/ClickHouse/ClickHouse/issues/66947): Fix `Method getResultType is not supported for QUERY query node` error when scalar subquery was used as the first argument of IN (with new analyzer). [#66655](https://github.com/ClickHouse/ClickHouse/pull/66655) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#67195](https://github.com/ClickHouse/ClickHouse/issues/67195): TRUNCATE DATABASE used to stop replication as if it was a DROP DATABASE query, it's fixed. [#67129](https://github.com/ClickHouse/ClickHouse/pull/67129) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#67377](https://github.com/ClickHouse/ClickHouse/issues/67377): Fix error `Cannot convert column because it is non constant in source stream but must be constant in result.` for a query that reads from the `Merge` table over the `Distriburted` table with one shard. [#67146](https://github.com/ClickHouse/ClickHouse/pull/67146) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#67240](https://github.com/ClickHouse/ClickHouse/issues/67240): This closes [#67156](https://github.com/ClickHouse/ClickHouse/issues/67156). This closes [#66447](https://github.com/ClickHouse/ClickHouse/issues/66447). The bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/62907. [#67178](https://github.com/ClickHouse/ClickHouse/pull/67178) ([Maksim Kita](https://github.com/kitaisreal)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Backported in [#65410](https://github.com/ClickHouse/ClickHouse/issues/65410): Re-enable OpenSSL session caching. [#65111](https://github.com/ClickHouse/ClickHouse/pull/65111) ([Robert Schulze](https://github.com/rschu1ze)).
+* Backported in [#65903](https://github.com/ClickHouse/ClickHouse/issues/65903): Fix bug with session closing in Keeper. [#65735](https://github.com/ClickHouse/ClickHouse/pull/65735) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#66385](https://github.com/ClickHouse/ClickHouse/issues/66385): Disable broken cases from 02911_join_on_nullsafe_optimization. [#66310](https://github.com/ClickHouse/ClickHouse/pull/66310) ([vdimir](https://github.com/vdimir)).
+* Backported in [#66424](https://github.com/ClickHouse/ClickHouse/issues/66424): Ignore subquery for IN in DDLLoadingDependencyVisitor. [#66395](https://github.com/ClickHouse/ClickHouse/pull/66395) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#66542](https://github.com/ClickHouse/ClickHouse/issues/66542): Add additional log masking in CI. [#66523](https://github.com/ClickHouse/ClickHouse/pull/66523) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#66857](https://github.com/ClickHouse/ClickHouse/issues/66857): Fix data race in S3::ClientCache. [#66644](https://github.com/ClickHouse/ClickHouse/pull/66644) ([Konstantin Morozov](https://github.com/k-morozov)).
+* Backported in [#66873](https://github.com/ClickHouse/ClickHouse/issues/66873): Support one more case in JOIN ON ... IS NULL. [#66725](https://github.com/ClickHouse/ClickHouse/pull/66725) ([vdimir](https://github.com/vdimir)).
+* Backported in [#67057](https://github.com/ClickHouse/ClickHouse/issues/67057): Increase asio pool size in case the server is tiny. [#66761](https://github.com/ClickHouse/ClickHouse/pull/66761) ([alesapin](https://github.com/alesapin)).
+* Backported in [#66944](https://github.com/ClickHouse/ClickHouse/issues/66944): Small fix in realloc memory tracking. [#66820](https://github.com/ClickHouse/ClickHouse/pull/66820) ([Antonio Andelic](https://github.com/antonio2368)).
+* Backported in [#67250](https://github.com/ClickHouse/ClickHouse/issues/67250): Followup [#66725](https://github.com/ClickHouse/ClickHouse/issues/66725). [#66869](https://github.com/ClickHouse/ClickHouse/pull/66869) ([vdimir](https://github.com/vdimir)).
+* Backported in [#67410](https://github.com/ClickHouse/ClickHouse/issues/67410): CI: Fix build results for release branches. [#67402](https://github.com/ClickHouse/ClickHouse/pull/67402) ([Max K.](https://github.com/maxknv)).
+

docs/changelogs/v24.7.1.2915-stable.md

@@ -0,0 +1,524 @@
+---
+sidebar_position: 1
+sidebar_label: 2024
+---
+
+# 2024 Changelog
+
+### ClickHouse release v24.7.1.2915-stable (a37d2d43da7) FIXME as compared to v24.7.1.1-new (aa023477a92)
+
+#### Backward Incompatible Change
+* Change binary serialization of Variant data type: add `compact` mode to avoid writing the same discriminator multiple times for granules with single variant or with only NULL values. Add MergeTree setting `use_compact_variant_discriminators_serialization` that is enabled by default. Note that Variant type is still experimental and backward-incompatible change in serialization is ok. [#62774](https://github.com/ClickHouse/ClickHouse/pull/62774) ([Kruglov Pavel](https://github.com/Avogar)).
+* Forbid `CREATE MATERIALIZED VIEW ... ENGINE Replicated*MergeTree POPULATE AS SELECT ...` with Replicated databases. [#63963](https://github.com/ClickHouse/ClickHouse/pull/63963) ([vdimir](https://github.com/vdimir)).
+* `clickhouse-keeper-client` will only accept paths in string literals, such as `ls '/hello/world'`, not bare strings such as `ls /hello/world`. [#65494](https://github.com/ClickHouse/ClickHouse/pull/65494) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Metric `KeeperOutstandingRequets` was renamed to `KeeperOutstandingRequests`. This fixes a typo reported in [#66179](https://github.com/ClickHouse/ClickHouse/issues/66179). [#66206](https://github.com/ClickHouse/ClickHouse/pull/66206) ([Robert Schulze](https://github.com/rschu1ze)).
+* Remove `is_deterministic` field from the `system.functions` table. [#66630](https://github.com/ClickHouse/ClickHouse/pull/66630) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### New Feature
+* Extend function `tuple` to construct named tuples in query. Introduce function `tupleNames` to extract names from tuples. [#54881](https://github.com/ClickHouse/ClickHouse/pull/54881) ([Amos Bird](https://github.com/amosbird)).
+* `ASOF JOIN` support for `full_sorting_join` algorithm Close [#54493](https://github.com/ClickHouse/ClickHouse/issues/54493). [#55051](https://github.com/ClickHouse/ClickHouse/pull/55051) ([vdimir](https://github.com/vdimir)).
+* A new table function, `fuzzQuery,` was added. This function allows you to modify a given query string with random variations. Example: `SELECT query FROM fuzzQuery('SELECT 1');`. [#62103](https://github.com/ClickHouse/ClickHouse/pull/62103) ([pufit](https://github.com/pufit)).
+* Add new window function `percent_rank`. [#62747](https://github.com/ClickHouse/ClickHouse/pull/62747) ([lgbo](https://github.com/lgbo-ustc)).
+* Support JWT authentication in `clickhouse-client`. [#62829](https://github.com/ClickHouse/ClickHouse/pull/62829) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Add SQL functions `changeYear`, `changeMonth`, `changeDay`, `changeHour`, `changeMinute`, `changeSecond`. For example, `SELECT changeMonth(toDate('2024-06-14'), 7)` returns date `2024-07-14`. [#63186](https://github.com/ClickHouse/ClickHouse/pull/63186) ([cucumber95](https://github.com/cucumber95)).
+* Introduce startup scripts, which allow the execution of preconfigured queries at the startup stage. [#64889](https://github.com/ClickHouse/ClickHouse/pull/64889) ([pufit](https://github.com/pufit)).
+* Support accept_invalid_certificate in client's config in order to allow for client to connect over secure TCP to a server running with self-signed certificate - can be used as a shorthand for corresponding `openSSL` client settings `verificationMode=none` + `invalidCertificateHandler.name=AcceptCertificateHandler`. [#65238](https://github.com/ClickHouse/ClickHouse/pull/65238) ([peacewalker122](https://github.com/peacewalker122)).
+* Add system.error_log which contains history of error values from table system.errors, periodically flushed to disk. [#65381](https://github.com/ClickHouse/ClickHouse/pull/65381) ([Pablo Marcos](https://github.com/pamarcos)).
+* Add aggregate function `groupConcat`. About the same as `arrayStringConcat( groupArray(column), ',')` Can receive 2 parameters: a string delimiter and the number of elements to be processed. [#65451](https://github.com/ClickHouse/ClickHouse/pull/65451) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Add AzureQueue storage. [#65458](https://github.com/ClickHouse/ClickHouse/pull/65458) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Add a new setting to disable/enable writing page index into parquet files. [#65475](https://github.com/ClickHouse/ClickHouse/pull/65475) ([lgbo](https://github.com/lgbo-ustc)).
+* Allow system administrators to configure `logger.console_log_level`. [#65559](https://github.com/ClickHouse/ClickHouse/pull/65559) ([Azat Khuzhin](https://github.com/azat)).
+* Automatically append a wildcard `*` to the end of a directory path with table function `file`. [#66019](https://github.com/ClickHouse/ClickHouse/pull/66019) ([Zhidong (David) Guo](https://github.com/Gun9niR)).
+* Add `--memory-usage` option to client in non interactive mode. [#66393](https://github.com/ClickHouse/ClickHouse/pull/66393) ([vdimir](https://github.com/vdimir)).
+
+#### Performance Improvement
+* Enable `optimize_functions_to_subcolumns` by default. [#58661](https://github.com/ClickHouse/ClickHouse/pull/58661) ([Anton Popov](https://github.com/CurtizJ)).
+* Replace int to string algorithm with a faster one (from a modified amdn/itoa to a modified jeaiii/itoa). [#61661](https://github.com/ClickHouse/ClickHouse/pull/61661) ([Raúl Marín](https://github.com/Algunenano)).
+* Sizes of hash tables created by join (`parallel_hash` algorithm) is collected and cached now. This information will be used to preallocate space in hash tables for subsequent query executions and save time on hash table resizes. [#64553](https://github.com/ClickHouse/ClickHouse/pull/64553) ([Nikita Taranov](https://github.com/nickitat)).
+* Optimized queries with `ORDER BY` primary key and `WHERE` that have a condition with high selectivity by using of buffering. It is controlled by setting `read_in_order_use_buffering` (enabled by default) and can increase memory usage of query. [#64607](https://github.com/ClickHouse/ClickHouse/pull/64607) ([Anton Popov](https://github.com/CurtizJ)).
+* Improve performance of loading `plain_rewritable` metadata. [#65634](https://github.com/ClickHouse/ClickHouse/pull/65634) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Attaching tables on read-only disks will use fewer resources by not loading outdated parts. [#65635](https://github.com/ClickHouse/ClickHouse/pull/65635) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Support minmax hyperrectangle for Set indices. [#65676](https://github.com/ClickHouse/ClickHouse/pull/65676) ([AntiTopQuark](https://github.com/AntiTopQuark)).
+* Unload primary index of outdated parts to reduce total memory usage. [#65852](https://github.com/ClickHouse/ClickHouse/pull/65852) ([Anton Popov](https://github.com/CurtizJ)).
+* Functions `replaceRegexpAll` and `replaceRegexpOne` are now significantly faster if the pattern is trivial, i.e. contains no metacharacters, pattern classes, flags, grouping characters etc. (Thanks to Taiyang Li). [#66185](https://github.com/ClickHouse/ClickHouse/pull/66185) ([Robert Schulze](https://github.com/rschu1ze)).
+
+#### Improvement
+* Support rocksdb as backend storage of keeper. [#56626](https://github.com/ClickHouse/ClickHouse/pull/56626) ([Han Fei](https://github.com/hanfei1991)).
+* The setting `optimize_trivial_insert_select` is disabled by default. In most cases, it should be beneficial. Nevertheless, if you are seeing slower INSERT SELECT or increased memory usage, you can enable it back or `SET compatibility = '24.6'`. [#58970](https://github.com/ClickHouse/ClickHouse/pull/58970) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Print stacktrace and diagnostic info if `clickhouse-client` or `clickhouse-local` crashes. [#61109](https://github.com/ClickHouse/ClickHouse/pull/61109) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* The result of `SHOW INDEX | INDEXES | INDICES | KEYS` was previously sorted by the primary key column names. Since this was unintuitive, the result is now sorted by the position of the primary key columns within the primary key. [#61131](https://github.com/ClickHouse/ClickHouse/pull/61131) ([Robert Schulze](https://github.com/rschu1ze)).
+* This PR changes how deduplication for MV works. Fixed a lot of cases like: - on destination table: data is split for 2 or more blocks and that blocks is considered as duplicate when that block is inserted in parallel. - on MV destination table: the equal blocks are deduplicated, that happens when MV often produces equal data as a result for different input data due to performing aggregation. - on MV destination table: the equal blocks which comes from different MV are deduplicated. [#61601](https://github.com/ClickHouse/ClickHouse/pull/61601) ([Sema Checherinda](https://github.com/CheSema)).
+* Allow matching column names in a case insensitive manner when reading json files (`input_format_json_case_insensitive_column_matching`). [#61750](https://github.com/ClickHouse/ClickHouse/pull/61750) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Support reading partitioned data DeltaLake data. Infer DeltaLake schema by reading metadata instead of data. [#63201](https://github.com/ClickHouse/ClickHouse/pull/63201) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* In composable protocols TLS layer accepted only `certificateFile` and `privateKeyFile` parameters. https://clickhouse.com/docs/en/operations/settings/composable-protocols. [#63985](https://github.com/ClickHouse/ClickHouse/pull/63985) ([Anton Ivashkin](https://github.com/ianton-ru)).
+* Make an interactive client for clickhouse-disks, add local disk from the local directory. Fixes [#56791](https://github.com/ClickHouse/ClickHouse/issues/56791). [#64446](https://github.com/ClickHouse/ClickHouse/pull/64446) ([Daniil Ivanik](https://github.com/divanik)).
+* Added profile event `SelectQueriesWithPrimaryKeyUsage` which indicates how many SELECT queries use the primary key to evaluate the WHERE clause. [#64492](https://github.com/ClickHouse/ClickHouse/pull/64492) ([0x01f](https://github.com/0xfei)).
+* `StorageS3Queue` related fixes and improvements. Deduce a default value of `s3queue_processing_threads_num` according to the number of physical cpu cores on the server (instead of the previous default value as 1). Set default value of `s3queue_loading_retries` to 10. Fix possible vague "Uncaught exception" in exception column of `system.s3queue`. Do not increment retry count on `MEMORY_LIMIT_EXCEEDED` exception. Move files commit to a stage after insertion into table fully finished to avoid files being commited while not inserted. Add settings `s3queue_max_processed_files_before_commit`, `s3queue_max_processed_rows_before_commit`, `s3queue_max_processed_bytes_before_commit`, `s3queue_max_processing_time_sec_before_commit`, to better control commit and flush time. [#65046](https://github.com/ClickHouse/ClickHouse/pull/65046) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fixed broken multiple columns aggregation on s390x. [#65062](https://github.com/ClickHouse/ClickHouse/pull/65062) ([Harry Lee](https://github.com/HarryLeeIBM)).
+* Support aliases in parametrized view function (only new analyzer). [#65190](https://github.com/ClickHouse/ClickHouse/pull/65190) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* S3. reduce retires time for queries, increase retries count for backups. 8.5 minutes and 100 retires for queries, 1.2 hours and 1000 retries for backup restore. [#65232](https://github.com/ClickHouse/ClickHouse/pull/65232) ([Sema Checherinda](https://github.com/CheSema)).
+* Updated to mask account key in logs in azureBlobStorage. [#65273](https://github.com/ClickHouse/ClickHouse/pull/65273) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
+* Partition pruning for `IN` predicates when filter expression is a part of `PARTITION BY` expression. [#65335](https://github.com/ClickHouse/ClickHouse/pull/65335) ([Eduard Karacharov](https://github.com/korowa)).
+* Add system tables with main information about all detached tables. [#65400](https://github.com/ClickHouse/ClickHouse/pull/65400) ([Konstantin Morozov](https://github.com/k-morozov)).
+* Add support for `cluster_for_parallel_replicas` when using custom key parallel replicas. It allows you to use parallel replicas with custom key with MergeTree tables. [#65453](https://github.com/ClickHouse/ClickHouse/pull/65453) ([Antonio Andelic](https://github.com/antonio2368)).
+* Support query plan LIMIT optimization. Support LIMIT pushdown for PostgreSQL storage and table function. [#65454](https://github.com/ClickHouse/ClickHouse/pull/65454) ([Maksim Kita](https://github.com/kitaisreal)).
+* Arraymin/max can be applicable to all data types that are comparable. [#65455](https://github.com/ClickHouse/ClickHouse/pull/65455) ([pn](https://github.com/chloro-pn)).
+* Improved memory accounting for cgroups v2 to exclude the amount occupied by the page cache. [#65470](https://github.com/ClickHouse/ClickHouse/pull/65470) ([Nikita Taranov](https://github.com/nickitat)).
+* Do not create format settings for each rows when serializing chunks to insert to EmbeddedRocksDB table. [#65474](https://github.com/ClickHouse/ClickHouse/pull/65474) ([Duc Canh Le](https://github.com/canhld94)).
+* Fixed out-of-range exception in parsing Dwarf5 on s390x. [#65501](https://github.com/ClickHouse/ClickHouse/pull/65501) ([Harry Lee](https://github.com/HarryLeeIBM)).
+* Reduce `clickhouse-local` prompt to just `:)`. `getFQDNOrHostName()` takes too long on macOS, and we don't want a hostname in the prompt for `clickhouse-local` anyway. [#65510](https://github.com/ClickHouse/ClickHouse/pull/65510) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Avoid printing a message from jemalloc about per-CPU arenas on low-end virtual machines. [#65532](https://github.com/ClickHouse/ClickHouse/pull/65532) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Disable filesystem cache background download by default. It will be enabled back when we fix the issue with possible "Memory limit exceeded" because memory deallocation is done outside of query context (while buffer is allocated inside of query context) if we use background download threads. Plus we need to add a separate setting to define max size to download for background workers (currently it is limited by max_file_segment_size, which might be too big). [#65534](https://github.com/ClickHouse/ClickHouse/pull/65534) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Add new option to config `<config_reload_interval_ms>` which allow to specify how often clickhouse will reload config. [#65545](https://github.com/ClickHouse/ClickHouse/pull/65545) ([alesapin](https://github.com/alesapin)).
+* Implement binary encoding for ClickHouse data types and add its specification in docs. Use it in Dynamic binary serialization, allow to use it in RowBinaryWithNamesAndTypes and Native formats under settings. [#65546](https://github.com/ClickHouse/ClickHouse/pull/65546) ([Kruglov Pavel](https://github.com/Avogar)).
+* Improved ZooKeeper load balancing. The current session doesn't expire until the optimal nodes become available despite `fallback_session_lifetime`. Added support for AZ-aware balancing. [#65570](https://github.com/ClickHouse/ClickHouse/pull/65570) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Server settings `compiled_expression_cache_size` and `compiled_expression_cache_elements_size` are now shown in `system.server_settings`. [#65584](https://github.com/ClickHouse/ClickHouse/pull/65584) ([Robert Schulze](https://github.com/rschu1ze)).
+* When lightweight delete happens on a table with projection(s), users have choices either throw an exception (by default) or drop the projection lightweight delete would happen. [#65594](https://github.com/ClickHouse/ClickHouse/pull/65594) ([jsc0218](https://github.com/jsc0218)).
+* Add support for user identification based on x509 SubjectAltName extension. [#65626](https://github.com/ClickHouse/ClickHouse/pull/65626) ([Anton Kozlov](https://github.com/tonickkozlov)).
+* `clickhouse-local` will respect the `max_server_memory_usage` and `max_server_memory_usage_to_ram_ratio` from the configuration file. It will also set the max memory usage to 90% of the system memory by default, like `clickhouse-server` does. This closes [#65695](https://github.com/ClickHouse/ClickHouse/issues/65695). [#65697](https://github.com/ClickHouse/ClickHouse/pull/65697) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add a script to backup your files to ClickHouse. This is strange, but works. [#65699](https://github.com/ClickHouse/ClickHouse/pull/65699) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* PostgreSQL source support cancel. [#65722](https://github.com/ClickHouse/ClickHouse/pull/65722) ([Maksim Kita](https://github.com/kitaisreal)).
+* Make allow_experimental_analyzer be controlled by the initiator for distributed queries. This ensures compatibility and correctness during operations in mixed version clusters. [#65777](https://github.com/ClickHouse/ClickHouse/pull/65777) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Respect cgroup CPU limit in Keeper. [#65819](https://github.com/ClickHouse/ClickHouse/pull/65819) ([Antonio Andelic](https://github.com/antonio2368)).
+* Allow to use `concat` function with empty arguments ``` sql :) select concat();. [#65887](https://github.com/ClickHouse/ClickHouse/pull/65887) ([李扬](https://github.com/taiyang-li)).
+* Allow controlling named collections in clickhouse-local. [#65973](https://github.com/ClickHouse/ClickHouse/pull/65973) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Improve Azure profile events. [#65999](https://github.com/ClickHouse/ClickHouse/pull/65999) ([alesapin](https://github.com/alesapin)).
+* `Query was cancelled` might have been printed twice in clickhouse-client. This behaviour is fixed. [#66005](https://github.com/ClickHouse/ClickHouse/pull/66005) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Support ORC file read by writer time zone. [#66025](https://github.com/ClickHouse/ClickHouse/pull/66025) ([kevinyhzou](https://github.com/KevinyhZou)).
+* Refactor JSONExtract functions, support more types including experimental Dynamic type. [#66046](https://github.com/ClickHouse/ClickHouse/pull/66046) ([Kruglov Pavel](https://github.com/Avogar)).
+* DatabaseCatalog drops tables faster by using up to database_catalog_drop_table_concurrency threads. [#66065](https://github.com/ClickHouse/ClickHouse/pull/66065) ([Sema Checherinda](https://github.com/CheSema)).
+* This PR changes how deduplication for MV works. Fixed a lot of cases like: - on destination table: data is split for 2 or more blocks and that blocks is considered as duplicate when that block is inserted in parallel. - on MV destination table: the equal blocks are deduplicated, that happens when MV often produces equal data as a result for different input data due to performing aggregation. - on MV destination table: the equal blocks which comes from different MV are deduplicated. [#66144](https://github.com/ClickHouse/ClickHouse/pull/66144) ([Sema Checherinda](https://github.com/CheSema)).
+* Support null map subcolumn for Variant and Dynamic subcolumns. [#66178](https://github.com/ClickHouse/ClickHouse/pull/66178) ([Kruglov Pavel](https://github.com/Avogar)).
+* Add settings to control connection to the PostgreSQL. * Setting `postgresql_connection_attempt_timeout` specifies the value passed to `connect_timeout` parameter of connection URL. * Setting `postgresql_connection_pool_retries` specifies the number of retries to establish a connection to the PostgreSQL end-point. [#66232](https://github.com/ClickHouse/ClickHouse/pull/66232) ([Dmitry Novik](https://github.com/novikd)).
+* Reduce inaccuracy of input_wait_elapsed_us/input_wait_elapsed_us/elapsed_us. [#66239](https://github.com/ClickHouse/ClickHouse/pull/66239) ([Azat Khuzhin](https://github.com/azat)).
+* Improve FilesystemCache ProfileEvents. [#66249](https://github.com/ClickHouse/ClickHouse/pull/66249) ([zhukai](https://github.com/nauu)).
+* Add settings to ignore ON CLUSTER clause in queries for named collection management with replicated storage. [#66288](https://github.com/ClickHouse/ClickHouse/pull/66288) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
+* Upgraded `pocketfft` dependency to the recent commit https://github.com/mreineck/pocketfft/commit/f4c1aa8aa9ce79ad39e80f2c9c41b92ead90fda3. [#66291](https://github.com/ClickHouse/ClickHouse/pull/66291) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Upgraded `azure-sdk-for-cpp` to the recent commit https://github.com/ClickHouse/azure-sdk-for-cpp/commit/ea3e19a7be08519134c643177d56c7484dfec884. [#66292](https://github.com/ClickHouse/ClickHouse/pull/66292) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Function `generateSnowflakeID` now allows to specify a machine ID as a parameter to prevent collisions in large clusters. [#66374](https://github.com/ClickHouse/ClickHouse/pull/66374) ([ZAWA_ll](https://github.com/Zawa-ll)).
+* Disable suspending on Ctrl+Z in interactive mode. This is a common trap and is not expected behavior for almost all users. I imagine only a few extreme power users could appreciate suspending terminal applications to the background, but I don't know any. [#66511](https://github.com/ClickHouse/ClickHouse/pull/66511) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add option for validating the Primary key type in Dictionaries. Without this option for simple layouts any column type will be implicitly converted to UInt64. ### Documentation entry for user-facing changes. [#66595](https://github.com/ClickHouse/ClickHouse/pull/66595) ([MikhailBurdukov](https://github.com/MikhailBurdukov)).
+* Fix SHOW MERGES remaining time. [#66735](https://github.com/ClickHouse/ClickHouse/pull/66735) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+
+#### Critical Bug Fix (crash, LOGICAL_ERROR, data loss, RBAC)
+* Fix unexpeced size of low cardinality column in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
+* Check cyclic dependencies on CREATE/REPLACE/RENAME/EXCHANGE queries and throw an exception if there is a cyclic dependency. Previously such cyclic dependencies could lead to a deadlock during server startup. Closes [#65355](https://github.com/ClickHouse/ClickHouse/issues/65355). Also fix some bugs in dependencies creation. [#65405](https://github.com/ClickHouse/ClickHouse/pull/65405) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix crash in maxIntersections. [#65689](https://github.com/ClickHouse/ClickHouse/pull/65689) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix the VALID UNTIL clause in the user definition resetting after a restart. Closes [#66405](https://github.com/ClickHouse/ClickHouse/issues/66405). [#66409](https://github.com/ClickHouse/ClickHouse/pull/66409) ([Nikolay Degterinsky](https://github.com/evillique)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+* Fixed crash while using MaterializedMySQL with TABLE OVERRIDE that maps MySQL NULL field into ClickHouse not NULL field. [#54649](https://github.com/ClickHouse/ClickHouse/pull/54649) ([Filipp Ozinov](https://github.com/bakwc)).
+* Fix logical error when PREWHERE expression read no columns and table has no adaptive index granularity (very old table). Fix [#56640](https://github.com/ClickHouse/ClickHouse/issues/56640). [#59173](https://github.com/ClickHouse/ClickHouse/pull/59173) ([Alexander Gololobov](https://github.com/davenger)).
+* Fix bug with cancelation buffer when canceling a query. [#64478](https://github.com/ClickHouse/ClickHouse/pull/64478) ([Sema Checherinda](https://github.com/CheSema)).
+* Fix filling parts columns from metadata (when columns.txt does not exists). [#64757](https://github.com/ClickHouse/ClickHouse/pull/64757) ([Azat Khuzhin](https://github.com/azat)).
+* Fix AST formatting of 'create table b empty as a'. [#64951](https://github.com/ClickHouse/ClickHouse/pull/64951) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fix crash for `ALTER TABLE ... ON CLUSTER ... MODIFY SQL SECURITY`. [#64957](https://github.com/ClickHouse/ClickHouse/pull/64957) ([pufit](https://github.com/pufit)).
+* Fix crash on destroying AccessControl: add explicit shutdown. [#64993](https://github.com/ClickHouse/ClickHouse/pull/64993) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Eliminate injective function in argument of functions `uniq*` recursively. This used to work correctly but was broken in the new analyzer. [#65140](https://github.com/ClickHouse/ClickHouse/pull/65140) ([Duc Canh Le](https://github.com/canhld94)).
+* Fix unexpected projection name when query with CTE. [#65267](https://github.com/ClickHouse/ClickHouse/pull/65267) ([wudidapaopao](https://github.com/wudidapaopao)).
+* Require `dictGet` privilege when accessing dictionaries via direct query or the `Dictionary` table engine. [#65359](https://github.com/ClickHouse/ClickHouse/pull/65359) ([Joe Lynch](https://github.com/joelynch)).
+* Fix user-specific S3 auth with incremental backups. [#65481](https://github.com/ClickHouse/ClickHouse/pull/65481) ([Antonio Andelic](https://github.com/antonio2368)).
+* Disable `non-intersecting-parts` optimization for queries with `FINAL` in case of `read-in-order` optimization was enabled. This could lead to an incorrect query result. As a workaround, disable `do_not_merge_across_partitions_select_final` and `split_parts_ranges_into_intersecting_and_non_intersecting_final` before this fix is merged. [#65505](https://github.com/ClickHouse/ClickHouse/pull/65505) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix getting exception `Index out of bound for blob metadata` in case all files from list batch were filtered out. [#65523](https://github.com/ClickHouse/ClickHouse/pull/65523) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix NOT_FOUND_COLUMN_IN_BLOCK for deduplicate merge of projection. [#65573](https://github.com/ClickHouse/ClickHouse/pull/65573) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Fixed bug in MergeJoin. Column in sparse serialisation might be treated as a column of its nested type though the required conversion wasn't performed. [#65632](https://github.com/ClickHouse/ClickHouse/pull/65632) ([Nikita Taranov](https://github.com/nickitat)).
+* Fixed a bug that compatibility level '23.4' was not properly applied. [#65737](https://github.com/ClickHouse/ClickHouse/pull/65737) ([cw5121](https://github.com/cw5121)).
+* Fix odbc table with nullable fields. [#65738](https://github.com/ClickHouse/ClickHouse/pull/65738) ([Rodolphe Dugé de Bernonville](https://github.com/RodolpheDuge)).
+* Fix data race in `TCPHandler`, which could happen on fatal error. [#65744](https://github.com/ClickHouse/ClickHouse/pull/65744) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix invalid exceptions in function `parseDateTime` with `%F` and `%D` placeholders. [#65768](https://github.com/ClickHouse/ClickHouse/pull/65768) ([Antonio Andelic](https://github.com/antonio2368)).
+* 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)).
+* Fix a bug in short circuit logic when old analyzer and dictGetOrDefault is used. [#65802](https://github.com/ClickHouse/ClickHouse/pull/65802) ([jsc0218](https://github.com/jsc0218)).
+* Fix a bug leads to EmbeddedRocksDB with TTL write corrupted SST files. [#65816](https://github.com/ClickHouse/ClickHouse/pull/65816) ([Duc Canh Le](https://github.com/canhld94)).
+* Functions `bitTest`, `bitTestAll`, and `bitTestAny` now return an error if the specified bit index is out-of-bounds (issue [#65517](https://github.com/ClickHouse/ClickHouse/issues/65517)). [#65818](https://github.com/ClickHouse/ClickHouse/pull/65818) ([Pablo Marcos](https://github.com/pamarcos)).
+* Setting `join_any_take_last_row` is supported in any query with hash join. [#65820](https://github.com/ClickHouse/ClickHouse/pull/65820) ([vdimir](https://github.com/vdimir)).
+* Better handling of join conditions involving `IS NULL` checks (for example `ON (a = b AND (a IS NOT NULL) AND (b IS NOT NULL) ) OR ( (a IS NULL) AND (b IS NULL) )` is rewritten to `ON a <=> b`), fix incorrect optimization when condition other then `IS NULL` are present. [#65835](https://github.com/ClickHouse/ClickHouse/pull/65835) ([vdimir](https://github.com/vdimir)).
+* Functions `bitShiftLeft` and `bitShitfRight` return an error for out of bounds shift positions (issue [#65516](https://github.com/ClickHouse/ClickHouse/issues/65516)). [#65838](https://github.com/ClickHouse/ClickHouse/pull/65838) ([Pablo Marcos](https://github.com/pamarcos)).
+* Fix growing memory usage in S3Queue. [#65839](https://github.com/ClickHouse/ClickHouse/pull/65839) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix tie handling in `arrayAUC` to match sklearn. [#65840](https://github.com/ClickHouse/ClickHouse/pull/65840) ([gabrielmcg44](https://github.com/gabrielmcg44)).
+* Fix possible issues with MySQL server protocol TLS connections. [#65917](https://github.com/ClickHouse/ClickHouse/pull/65917) ([Azat Khuzhin](https://github.com/azat)).
+* Fix possible issues with MySQL client protocol TLS connections. [#65938](https://github.com/ClickHouse/ClickHouse/pull/65938) ([Azat Khuzhin](https://github.com/azat)).
+* Fix handling of `SSL_ERROR_WANT_READ`/`SSL_ERROR_WANT_WRITE` with zero timeout. [#65941](https://github.com/ClickHouse/ClickHouse/pull/65941) ([Azat Khuzhin](https://github.com/azat)).
+* Add missing settings `input_format_csv_skip_first_lines/input_format_tsv_skip_first_lines/input_format_csv_try_infer_numbers_from_strings/input_format_csv_try_infer_strings_from_quoted_tuples` in schema inference cache because they can change the resulting schema. It prevents from incorrect result of schema inference with these settings changed. [#65980](https://github.com/ClickHouse/ClickHouse/pull/65980) ([Kruglov Pavel](https://github.com/Avogar)).
+* Column _size in s3 engine and s3 table function denotes the size of a file inside the archive, not a size of the archive itself. [#65993](https://github.com/ClickHouse/ClickHouse/pull/65993) ([Daniil Ivanik](https://github.com/divanik)).
+* Fix resolving dynamic subcolumns in analyzer, avoid reading the whole column on dynamic subcolumn reading. [#66004](https://github.com/ClickHouse/ClickHouse/pull/66004) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix config merging for from_env with replace overrides. [#66034](https://github.com/ClickHouse/ClickHouse/pull/66034) ([Azat Khuzhin](https://github.com/azat)).
+* Fix a possible hanging in `GRPCServer` during shutdown. This PR fixes [#65622](https://github.com/ClickHouse/ClickHouse/issues/65622). [#66061](https://github.com/ClickHouse/ClickHouse/pull/66061) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix reading dynamic subcolumns from altered Memory table. Previously if `max_types` peremeter of a Dynamic type was changed in Memory table via alter, further subcolumns reading can return wrong result. [#66066](https://github.com/ClickHouse/ClickHouse/pull/66066) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fixed several cases in function `has` with non-constant `LowCardinality` arguments. [#66088](https://github.com/ClickHouse/ClickHouse/pull/66088) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix for `groupArrayIntersect`. It had incorrect behavior in the `merge()` function. Also, fixed behavior in `deserialise()` for numeric and general data. [#66103](https://github.com/ClickHouse/ClickHouse/pull/66103) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fixed buffer overflow bug in `unbin`/`unhex` implementation. [#66106](https://github.com/ClickHouse/ClickHouse/pull/66106) ([Nikita Taranov](https://github.com/nickitat)).
+* Disable the `merge-filters` optimization introduced in [#64760](https://github.com/ClickHouse/ClickHouse/issues/64760). It may cause an exception if optimization merges two filter expressions and does not apply a short-circuit evaluation. [#66126](https://github.com/ClickHouse/ClickHouse/pull/66126) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fixed the issue when the server failed to parse Avro files with negative block size arrays encoded, which is now allowed by the Avro specification. [#66130](https://github.com/ClickHouse/ClickHouse/pull/66130) ([Serge Klochkov](https://github.com/slvrtrn)).
+* Fixed a bug in ZooKeeper client: a session could get stuck in unusable state after receiving a hardware error from ZooKeeper. For example, this might happen due to "soft memory limit" in ClickHouse Keeper. [#66140](https://github.com/ClickHouse/ClickHouse/pull/66140) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Fix issue in SumIfToCountIfVisitor and signed integers. [#66146](https://github.com/ClickHouse/ClickHouse/pull/66146) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix rare case with missing data in the result of distributed query, close [#61432](https://github.com/ClickHouse/ClickHouse/issues/61432). [#66174](https://github.com/ClickHouse/ClickHouse/pull/66174) ([vdimir](https://github.com/vdimir)).
+* Fix order of parsing metadata fields in StorageDeltaLake. [#66211](https://github.com/ClickHouse/ClickHouse/pull/66211) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Don't throw `TIMEOUT_EXCEEDED` for `none_only_active` mode of `distributed_ddl_output_mode`. [#66218](https://github.com/ClickHouse/ClickHouse/pull/66218) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Fix handling limit for `system.numbers_mt` when no index can be used. [#66231](https://github.com/ClickHouse/ClickHouse/pull/66231) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fixed how the ClickHouse server detects the maximum number of usable CPU cores as specified by cgroups v2 if the server runs in a container such as Docker. In more detail, containers often run their process in the root cgroup which has an empty name. In that case, ClickHouse ignored the CPU limits set by cgroups v2. [#66237](https://github.com/ClickHouse/ClickHouse/pull/66237) ([filimonov](https://github.com/filimonov)).
+* Fix the `Not-ready set` error when a subquery with `IN` is used in the constraint. [#66261](https://github.com/ClickHouse/ClickHouse/pull/66261) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix indexHint function case found by fuzzer. [#66286](https://github.com/ClickHouse/ClickHouse/pull/66286) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix error reporting while copying to S3 or AzureBlobStorage. [#66295](https://github.com/ClickHouse/ClickHouse/pull/66295) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Prevent watchdog from keeping descriptors of unlinked(rotated) log files. [#66334](https://github.com/ClickHouse/ClickHouse/pull/66334) ([Aleksei Filatov](https://github.com/aalexfvk)).
+* Fix the bug that logicalexpressionoptimizerpass lost logical type of constant. closes [#64487](https://github.com/ClickHouse/ClickHouse/issues/64487). [#66344](https://github.com/ClickHouse/ClickHouse/pull/66344) ([pn](https://github.com/chloro-pn)).
+* Fix `Column identifier is already registered` error with `group_by_use_nulls=true` and new analyzer. [#66400](https://github.com/ClickHouse/ClickHouse/pull/66400) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix possible incorrect result for queries joining and filtering table external engine (like PostgreSQL), due to too aggressive filter pushdown. Since now, conditions from where section won't be send to external database in case of outer join with external table. [#66402](https://github.com/ClickHouse/ClickHouse/pull/66402) ([vdimir](https://github.com/vdimir)).
+* Added missing column materialization for cross join. [#66413](https://github.com/ClickHouse/ClickHouse/pull/66413) ([lgbo](https://github.com/lgbo-ustc)).
+* Fix `Cannot find column` error for queries with constant expression in `GROUP BY` key and new analyzer enabled. [#66433](https://github.com/ClickHouse/ClickHouse/pull/66433) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Avoid possible logical error during import from Npy format in case of bad array nesting level, fix testing of other kinds of errors. [#66461](https://github.com/ClickHouse/ClickHouse/pull/66461) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fix wrong count() result when there is non-deterministic function in predicate. [#66510](https://github.com/ClickHouse/ClickHouse/pull/66510) ([Duc Canh Le](https://github.com/canhld94)).
+* Correctly track memory for `Allocator::realloc`. [#66548](https://github.com/ClickHouse/ClickHouse/pull/66548) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix reading of uninitialized memory when hashing empty tuples. This closes [#66559](https://github.com/ClickHouse/ClickHouse/issues/66559). [#66562](https://github.com/ClickHouse/ClickHouse/pull/66562) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix an invalid result for queries with `WINDOW`. This could happen when `PARTITION` columns have sparse serialization and window functions are executed in parallel. [#66579](https://github.com/ClickHouse/ClickHouse/pull/66579) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix removing named collections in local storage. [#66599](https://github.com/ClickHouse/ClickHouse/pull/66599) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fix logical error in `PrometheusRequestHandler`. [#66621](https://github.com/ClickHouse/ClickHouse/pull/66621) ([Vitaly Baranov](https://github.com/vitlibar)).
+* `column_length` is not updated in `ColumnTuple::insertManyFrom`. [#66626](https://github.com/ClickHouse/ClickHouse/pull/66626) ([lgbo](https://github.com/lgbo-ustc)).
+* Fix `Unknown identifier` and `Column is not under aggregate function` errors for queries with the expression `(column IS NULL).` The bug was triggered by [#65088](https://github.com/ClickHouse/ClickHouse/issues/65088), with the disabled analyzer only. [#66654](https://github.com/ClickHouse/ClickHouse/pull/66654) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix `Method getResultType is not supported for QUERY query node` error when scalar subquery was used as the first argument of IN (with new analyzer). [#66655](https://github.com/ClickHouse/ClickHouse/pull/66655) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix possible PARAMETER_OUT_OF_BOUND error during reading variant subcolumn. [#66659](https://github.com/ClickHouse/ClickHouse/pull/66659) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix rare case of stuck merge after drop column. [#66707](https://github.com/ClickHouse/ClickHouse/pull/66707) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix assertion `isUniqTypes` when insert select from remote sources. [#66722](https://github.com/ClickHouse/ClickHouse/pull/66722) ([Sema Checherinda](https://github.com/CheSema)).
+* Backported in [#67026](https://github.com/ClickHouse/ClickHouse/issues/67026): In rare cases ClickHouse could consider parts as broken because of some unexpected projections on disk. Now it's fixed. [#66898](https://github.com/ClickHouse/ClickHouse/pull/66898) ([alesapin](https://github.com/alesapin)).
+* Backported in [#67443](https://github.com/ClickHouse/ClickHouse/issues/67443): Forbid create as select even when database_replicated_allow_heavy_create is set. It was unconditionally forbidden in 23.12 and accidentally allowed under the setting in unreleased 24.7. [#66980](https://github.com/ClickHouse/ClickHouse/pull/66980) ([vdimir](https://github.com/vdimir)).
+* Backported in [#67201](https://github.com/ClickHouse/ClickHouse/issues/67201): TRUNCATE DATABASE used to stop replication as if it was a DROP DATABASE query, it's fixed. [#67129](https://github.com/ClickHouse/ClickHouse/pull/67129) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Backported in [#67383](https://github.com/ClickHouse/ClickHouse/issues/67383): Fix error `Cannot convert column because it is non constant in source stream but must be constant in result.` for a query that reads from the `Merge` table over the `Distriburted` table with one shard. [#67146](https://github.com/ClickHouse/ClickHouse/pull/67146) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Backported in [#67246](https://github.com/ClickHouse/ClickHouse/issues/67246): This closes [#67156](https://github.com/ClickHouse/ClickHouse/issues/67156). This closes [#66447](https://github.com/ClickHouse/ClickHouse/issues/66447). The bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/62907. [#67178](https://github.com/ClickHouse/ClickHouse/pull/67178) ([Maksim Kita](https://github.com/kitaisreal)).
+
+#### Build/Testing/Packaging Improvement
+* Instantiate template methods ahead in different .cpp files, avoid too large translation units during compiling. [#64818](https://github.com/ClickHouse/ClickHouse/pull/64818) ([lgbo](https://github.com/lgbo-ustc)).
+* Stateless tests: Improve tests speed and decrease number of parallel jobs. [#65186](https://github.com/ClickHouse/ClickHouse/pull/65186) ([Nikita Fomichev](https://github.com/fm4v)).
+* Add tests for `base64URLEncode` and `base64URLDecode`. Add analyzer tests. [#65979](https://github.com/ClickHouse/ClickHouse/pull/65979) ([Nikita Fomichev](https://github.com/fm4v)).
+* Fix problem when github terminate instances by timeout and artifacts are not collected and full test report is not generated. [#66036](https://github.com/ClickHouse/ClickHouse/pull/66036) ([Nikita Fomichev](https://github.com/fm4v)).
+* Fix test [test_grpc_protocol/test.py::test_progress](https://s3.amazonaws.com/clickhouse-test-reports/57695/188f8a3df74caf830ad1ced3c4cf6dfb0aa90093/integration_tests__asan__old_analyzer__[4_6].html). [#66063](https://github.com/ClickHouse/ClickHouse/pull/66063) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Stateless tests: Improve tests speed and decrease number of parallel jobs. [#66305](https://github.com/ClickHouse/ClickHouse/pull/66305) ([Nikita Fomichev](https://github.com/fm4v)).
+* Stateless tests: Improve tests speed and decrease number of parallel jobs 3. [#66363](https://github.com/ClickHouse/ClickHouse/pull/66363) ([Nikita Fomichev](https://github.com/fm4v)).
+* Tests: fix tests hang up in cases when gdb catches error. [#66411](https://github.com/ClickHouse/ClickHouse/pull/66411) ([Nikita Fomichev](https://github.com/fm4v)).
+* ... since [Release v24.6.1.4423-stable](https://github.com/ClickHouse/ClickHouse/releases/tag/v24.6.1.4423-stable) when build in ppc64le with dynamic openssl build (`cmake -DENABLE_OPENSSL_DYNAMIC=1 -DCMAKE_TOOLCHAIN_FILE= cmake/linux/toolchain-ppc64le.cmake `) got error: ` ld.lld: error: duplicate symbol: OPENSSL_cleanse`. [#66733](https://github.com/ClickHouse/ClickHouse/pull/66733) ([Yong Wang](https://github.com/kashwy)).
+
+#### NO CL CATEGORY
+
+* Backported in [#67084](https://github.com/ClickHouse/ClickHouse/issues/67084):. [#67040](https://github.com/ClickHouse/ClickHouse/pull/67040) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#67452](https://github.com/ClickHouse/ClickHouse/issues/67452):. [#67392](https://github.com/ClickHouse/ClickHouse/pull/67392) ([alesapin](https://github.com/alesapin)).
+
+#### NO CL ENTRY
+
+* NO CL ENTRY:  'Revert "Revert "Small fix for 02340_parts_refcnt_mergetree""'. [#65155](https://github.com/ClickHouse/ClickHouse/pull/65155) ([Nikita Taranov](https://github.com/nickitat)).
+* NO CL ENTRY:  'Revert "Use 1MB HTTP buffers to avoid frequent send syscalls"'. [#65498](https://github.com/ClickHouse/ClickHouse/pull/65498) ([Sergei Trifonov](https://github.com/serxa)).
+* NO CL ENTRY:  'Revert "Resubmit http_external_tables_memory_tracking test"'. [#65500](https://github.com/ClickHouse/ClickHouse/pull/65500) ([Nikita Taranov](https://github.com/nickitat)).
+* NO CL ENTRY:  'Revert "Add an assertion in ReplicatedMergeTreeQueue"'. [#65686](https://github.com/ClickHouse/ClickHouse/pull/65686) ([Raúl Marín](https://github.com/Algunenano)).
+* NO CL ENTRY:  'Revert "insertion deduplication on retries for materialised views"'. [#66134](https://github.com/ClickHouse/ClickHouse/pull/66134) ([Sema Checherinda](https://github.com/CheSema)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Return and fix 01600_parts_states_metrics_long test. [#58748](https://github.com/ClickHouse/ClickHouse/pull/58748) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Add azure_cache as storage policy to tests. [#59943](https://github.com/ClickHouse/ClickHouse/pull/59943) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
+* Minor: replaced expression with LEGACY_MAX_LEVEL. [#61268](https://github.com/ClickHouse/ClickHouse/pull/61268) ([Vasily Nemkov](https://github.com/Enmk)).
+* Make write to temporary data in cache do all checks and assertions as during write to ordinary cache. [#63348](https://github.com/ClickHouse/ClickHouse/pull/63348) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Refactoring near azure blob storage. [#63636](https://github.com/ClickHouse/ClickHouse/pull/63636) ([Anton Popov](https://github.com/CurtizJ)).
+* Everything should work with Analyzer. [#63643](https://github.com/ClickHouse/ClickHouse/pull/63643) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* add some log for non using detached tables. [#64992](https://github.com/ClickHouse/ClickHouse/pull/64992) ([Konstantin Morozov](https://github.com/k-morozov)).
+* Remove dag flags. [#65234](https://github.com/ClickHouse/ClickHouse/pull/65234) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix flaky autocompletion test. [#65246](https://github.com/ClickHouse/ClickHouse/pull/65246) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Disable userspace page cache by default. [#65305](https://github.com/ClickHouse/ClickHouse/pull/65305) ([Michael Kolupaev](https://github.com/al13n321)).
+* Update version_date.tsv and changelogs after v24.4.3.25-stable. [#65308](https://github.com/ClickHouse/ClickHouse/pull/65308) ([robot-clickhouse](https://github.com/robot-clickhouse)).
+* Do not raise a NOT_IMPLEMENTED error when getting s3 metrics with a multiple disk configuration. [#65403](https://github.com/ClickHouse/ClickHouse/pull/65403) ([Elena Torró](https://github.com/elenatorro)).
+* Dodging reading from wrong table with parallel replicas. [#65417](https://github.com/ClickHouse/ClickHouse/pull/65417) ([Nikita Taranov](https://github.com/nickitat)).
+* Fix: return error if can't connect to any replicas chosen for query execution. [#65467](https://github.com/ClickHouse/ClickHouse/pull/65467) ([Igor Nikonov](https://github.com/devcrafter)).
+* Fix `AzureObjectStorage::exists` method. [#65471](https://github.com/ClickHouse/ClickHouse/pull/65471) ([Anton Popov](https://github.com/CurtizJ)).
+* Update version after release. [#65483](https://github.com/ClickHouse/ClickHouse/pull/65483) ([Raúl Marín](https://github.com/Algunenano)).
+* Generate 24.6 changelog. [#65485](https://github.com/ClickHouse/ClickHouse/pull/65485) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix of `PlanSquashingTransform`: pipeline stuck. [#65487](https://github.com/ClickHouse/ClickHouse/pull/65487) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fix bad test `02922_deduplication_with_zero_copy`. [#65492](https://github.com/ClickHouse/ClickHouse/pull/65492) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Disable clang-format in special areas. [#65495](https://github.com/ClickHouse/ClickHouse/pull/65495) ([Nikita Taranov](https://github.com/nickitat)).
+* Fix `test_keeper_snapshots`. [#65497](https://github.com/ClickHouse/ClickHouse/pull/65497) ([Antonio Andelic](https://github.com/antonio2368)).
+* Update to libunwind 8.1.7. [#65509](https://github.com/ClickHouse/ClickHouse/pull/65509) ([Michael Kolupaev](https://github.com/al13n321)).
+* Setting `uniform_snowflake_conversion_functions` (not in any release yet) was replaced by setting `allow_deprecated_snowflake_conversion_functions`. The latter controls if the legacy snowflake conversion functions are available (by default, they are not). [#65522](https://github.com/ClickHouse/ClickHouse/pull/65522) ([Robert Schulze](https://github.com/rschu1ze)).
+* Try CI without RerunCheck, jobs can be easily rerun manually though extra amount of work in CI will follow on workflow restart. [#65524](https://github.com/ClickHouse/ClickHouse/pull/65524) ([Max K.](https://github.com/maxknv)).
+* Bump re2 to latest HEAD. [#65526](https://github.com/ClickHouse/ClickHouse/pull/65526) ([Robert Schulze](https://github.com/rschu1ze)).
+* OpenSSL: Replace temporary fix for unsynchronized access by official fix. [#65529](https://github.com/ClickHouse/ClickHouse/pull/65529) ([Robert Schulze](https://github.com/rschu1ze)).
+* Update README.md. [#65531](https://github.com/ClickHouse/ClickHouse/pull/65531) ([Tyler Hannan](https://github.com/tylerhannan)).
+* CI: some time there are timeouts on DROP TABLES for random tests. [#65535](https://github.com/ClickHouse/ClickHouse/pull/65535) ([Sema Checherinda](https://github.com/CheSema)).
+* Synchronize `MARK_CACHE_SIZE` value in default settings and config. [#65547](https://github.com/ClickHouse/ClickHouse/pull/65547) ([Denny Crane](https://github.com/den-crane)).
+* CI: Skip removed test files in stateless flaky check job. [#65553](https://github.com/ClickHouse/ClickHouse/pull/65553) ([Max K.](https://github.com/maxknv)).
+* Renames Build report jobs. [#65554](https://github.com/ClickHouse/ClickHouse/pull/65554) ([Max K.](https://github.com/maxknv)).
+* Parse user from URL for dashboard.html (useful for sharing). [#65556](https://github.com/ClickHouse/ClickHouse/pull/65556) ([Azat Khuzhin](https://github.com/azat)).
+* Remove tech debt. [#65561](https://github.com/ClickHouse/ClickHouse/pull/65561) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Maybe fix test `00763_lock_buffer_long.sh`. [#65562](https://github.com/ClickHouse/ClickHouse/pull/65562) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix clickhouse-keeper with not system-wide directories and provide override for local development. [#65563](https://github.com/ClickHouse/ClickHouse/pull/65563) ([Azat Khuzhin](https://github.com/azat)).
+* Re-configure yamllint to allow document-start. [#65565](https://github.com/ClickHouse/ClickHouse/pull/65565) ([Azat Khuzhin](https://github.com/azat)).
+* Fix flaky test `01254_dict_load_after_detach_attach.sql`. [#65571](https://github.com/ClickHouse/ClickHouse/pull/65571) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Improve flaky test to provide more diagnostics. [#65586](https://github.com/ClickHouse/ClickHouse/pull/65586) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix test_parallel_replicas_distributed_skip_shards flakiness. [#65588](https://github.com/ClickHouse/ClickHouse/pull/65588) ([Igor Nikonov](https://github.com/devcrafter)).
+* Fix an error in the test about metadata_type. [#65592](https://github.com/ClickHouse/ClickHouse/pull/65592) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix slow test. [#65593](https://github.com/ClickHouse/ClickHouse/pull/65593) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* fix flaky 02864_statistics_uniq. [#65599](https://github.com/ClickHouse/ClickHouse/pull/65599) ([Han Fei](https://github.com/hanfei1991)).
+* Fix 03172_error_log_table_not_empty. [#65604](https://github.com/ClickHouse/ClickHouse/pull/65604) ([Pablo Marcos](https://github.com/pamarcos)).
+* Enable realtime digest for Jepsen tests. [#65608](https://github.com/ClickHouse/ClickHouse/pull/65608) ([Antonio Andelic](https://github.com/antonio2368)).
+* CI: Return Job Rerun check. [#65613](https://github.com/ClickHouse/ClickHouse/pull/65613) ([Max K.](https://github.com/maxknv)).
+* Update CHANGELOG.md. [#65624](https://github.com/ClickHouse/ClickHouse/pull/65624) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Module is required for authenticating in GH (in cloud). [#65628](https://github.com/ClickHouse/ClickHouse/pull/65628) ([Max K.](https://github.com/maxknv)).
+* Update IObjectStorage.h. [#65631](https://github.com/ClickHouse/ClickHouse/pull/65631) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix 02834_apache_arrow_abort flakiness with MSAN. [#65640](https://github.com/ClickHouse/ClickHouse/pull/65640) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fix overflow in StorageWindowView. [#65641](https://github.com/ClickHouse/ClickHouse/pull/65641) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fix inconsistent AST formatting when a keyword is used as type name. [#65648](https://github.com/ClickHouse/ClickHouse/pull/65648) ([Michael Kolupaev](https://github.com/al13n321)).
+* CI: Single point of setting mergeable check status. [#65658](https://github.com/ClickHouse/ClickHouse/pull/65658) ([Max K.](https://github.com/maxknv)).
+* Miscellaneous and insignificant changes around Client/ClientBase. [#65669](https://github.com/ClickHouse/ClickHouse/pull/65669) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Add Replicated database names to ZooKeeper for introspection. [#65675](https://github.com/ClickHouse/ClickHouse/pull/65675) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Introduce type contract checks in `IColumn`. [#65687](https://github.com/ClickHouse/ClickHouse/pull/65687) ([Nikita Taranov](https://github.com/nickitat)).
+* Print slightly more information in 02982_aggregation_states_destruction. [#65688](https://github.com/ClickHouse/ClickHouse/pull/65688) ([Michael Kolupaev](https://github.com/al13n321)).
+* Disable stacktrace collection in GWPAsan by default. [#65701](https://github.com/ClickHouse/ClickHouse/pull/65701) ([Antonio Andelic](https://github.com/antonio2368)).
+* Build jemalloc with profiler. [#65702](https://github.com/ClickHouse/ClickHouse/pull/65702) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix duplicate symbol linkage error. [#65705](https://github.com/ClickHouse/ClickHouse/pull/65705) ([Nikita Taranov](https://github.com/nickitat)).
+* Fix server restarts in performance tests. [#65717](https://github.com/ClickHouse/ClickHouse/pull/65717) ([Antonio Andelic](https://github.com/antonio2368)).
+* Update 03002_part_log_rmt_fetch_mutate_error.sql. [#65720](https://github.com/ClickHouse/ClickHouse/pull/65720) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Fix bug with session closing in Keeper. [#65735](https://github.com/ClickHouse/ClickHouse/pull/65735) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix flaky `02265_column_ttl`. Closes [#65719](https://github.com/ClickHouse/ClickHouse/issues/65719). [#65742](https://github.com/ClickHouse/ClickHouse/pull/65742) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* See [#65745](https://github.com/ClickHouse/ClickHouse/issues/65745). It doesn't solve the issue, but helps a bit. [#65746](https://github.com/ClickHouse/ClickHouse/pull/65746) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Update CHANGELOG.md. [#65752](https://github.com/ClickHouse/ClickHouse/pull/65752) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* document declarative ssh-keys authentication. [#65756](https://github.com/ClickHouse/ClickHouse/pull/65756) ([Tobias Florek](https://github.com/ibotty)).
+* `base64En/Decode64Url` --> `base64En/Decode64URL`. [#65760](https://github.com/ClickHouse/ClickHouse/pull/65760) ([Robert Schulze](https://github.com/rschu1ze)).
+* Fix for issue [#65757](https://github.com/ClickHouse/ClickHouse/issues/65757). [#65763](https://github.com/ClickHouse/ClickHouse/pull/65763) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
+* Fix flaky `test_replicated_database::test_alter_attach`. [#65766](https://github.com/ClickHouse/ClickHouse/pull/65766) ([Antonio Andelic](https://github.com/antonio2368)).
+* Fix: progress bar for read in order queries. [#65769](https://github.com/ClickHouse/ClickHouse/pull/65769) ([Igor Nikonov](https://github.com/devcrafter)).
+* CI: Fix for Builds report job in backports and releases. [#65774](https://github.com/ClickHouse/ClickHouse/pull/65774) ([Max K.](https://github.com/maxknv)).
+* CI: New create release workflow. [#65775](https://github.com/ClickHouse/ClickHouse/pull/65775) ([Max K.](https://github.com/maxknv)).
+* fixed misspelled word. [#65778](https://github.com/ClickHouse/ClickHouse/pull/65778) ([Linh Giang](https://github.com/linhgiang24)).
+* Refactor statistics interface. [#65792](https://github.com/ClickHouse/ClickHouse/pull/65792) ([Robert Schulze](https://github.com/rschu1ze)).
+* Try to make `test_ldap_external_user_directory` less flaky. [#65794](https://github.com/ClickHouse/ClickHouse/pull/65794) ([Andrey Zvonov](https://github.com/zvonand)).
+* AMI image with gh and jwt. [#65795](https://github.com/ClickHouse/ClickHouse/pull/65795) ([Max K.](https://github.com/maxknv)).
+* Forbid join algorithm randomisation for 03094_one_thousand_joins. [#65798](https://github.com/ClickHouse/ClickHouse/pull/65798) ([Nikita Taranov](https://github.com/nickitat)).
+* Fix 02931_rewrite_sum_column_and_constant flakiness. [#65800](https://github.com/ClickHouse/ClickHouse/pull/65800) ([Michael Kolupaev](https://github.com/al13n321)).
+* Update StorageMaterializedView.cpp. [#65801](https://github.com/ClickHouse/ClickHouse/pull/65801) ([Nikolay Degterinsky](https://github.com/evillique)).
+* Fix slow `getFQDNOrHostNameImpl` on macOS. [#65803](https://github.com/ClickHouse/ClickHouse/pull/65803) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* No jemalloc profiler for non-Linux. [#65834](https://github.com/ClickHouse/ClickHouse/pull/65834) ([Antonio Andelic](https://github.com/antonio2368)).
+* Add missing workload identity changes. [#65848](https://github.com/ClickHouse/ClickHouse/pull/65848) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
+* Fix rocksdb. [#65858](https://github.com/ClickHouse/ClickHouse/pull/65858) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Update the list of easy tasks. [#65865](https://github.com/ClickHouse/ClickHouse/pull/65865) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Update CHANGELOG.md. [#65866](https://github.com/ClickHouse/ClickHouse/pull/65866) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* This closes [#43003](https://github.com/ClickHouse/ClickHouse/issues/43003). [#65870](https://github.com/ClickHouse/ClickHouse/pull/65870) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Uninteresting changes. [#65871](https://github.com/ClickHouse/ClickHouse/pull/65871) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Max sessions for user tests improvements. [#65888](https://github.com/ClickHouse/ClickHouse/pull/65888) ([Alexey Gerasimchuck](https://github.com/Demilivor)).
+* Update version_date.tsv and changelogs after v24.6.1.4423-stable. [#65909](https://github.com/ClickHouse/ClickHouse/pull/65909) ([robot-clickhouse](https://github.com/robot-clickhouse)).
+* Remove standalone Keeper build. [#65910](https://github.com/ClickHouse/ClickHouse/pull/65910) ([Antonio Andelic](https://github.com/antonio2368)).
+* Add extra profiling helpers for Keeper. [#65918](https://github.com/ClickHouse/ClickHouse/pull/65918) ([Antonio Andelic](https://github.com/antonio2368)).
+* PostgreSQL source cancel query comments. [#65919](https://github.com/ClickHouse/ClickHouse/pull/65919) ([Maksim Kita](https://github.com/kitaisreal)).
+* Remove mysqlxx::Pool::Entry assignment operator. [#65920](https://github.com/ClickHouse/ClickHouse/pull/65920) ([Azat Khuzhin](https://github.com/azat)).
+* No random settings for a test with `Object(JSON)`. [#65921](https://github.com/ClickHouse/ClickHouse/pull/65921) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* 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)).
+* add restriction for storage join. [#65936](https://github.com/ClickHouse/ClickHouse/pull/65936) ([Han Fei](https://github.com/hanfei1991)).
+* Update version_date.tsv and changelogs after v24.5.4.49-stable. [#65937](https://github.com/ClickHouse/ClickHouse/pull/65937) ([robot-clickhouse](https://github.com/robot-clickhouse)).
+* Add table name to MergeTreeSource spans. [#65940](https://github.com/ClickHouse/ClickHouse/pull/65940) ([Nikita Taranov](https://github.com/nickitat)).
+* Fix SettingsChangesHistory 24.7. [#65945](https://github.com/ClickHouse/ClickHouse/pull/65945) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix logical error "Expected ReadBufferFromFile, but got DB::EmptyReadBuffer". [#65949](https://github.com/ClickHouse/ClickHouse/pull/65949) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Use -Og instead of -O0 for debug builds. [#65953](https://github.com/ClickHouse/ClickHouse/pull/65953) ([Michael Kolupaev](https://github.com/al13n321)).
+* Fix data race for Keeper snapshot queue. [#65970](https://github.com/ClickHouse/ClickHouse/pull/65970) ([Antonio Andelic](https://github.com/antonio2368)).
+* Minor changes in CHANGELOG. [#65971](https://github.com/ClickHouse/ClickHouse/pull/65971) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Remove unnatural punctuation from Parquet. [#65972](https://github.com/ClickHouse/ClickHouse/pull/65972) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Try fix "Check timeout expired" without any server logs in report in stateless tests. [#65977](https://github.com/ClickHouse/ClickHouse/pull/65977) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Fix support of non-const scale arguments in rounding functions. [#65983](https://github.com/ClickHouse/ClickHouse/pull/65983) ([Mikhail Gorshkov](https://github.com/mgorshkov)).
+* More aesthetic error messages. [#65985](https://github.com/ClickHouse/ClickHouse/pull/65985) ([Robert Schulze](https://github.com/rschu1ze)).
+* Fix race in s3queue. [#65986](https://github.com/ClickHouse/ClickHouse/pull/65986) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Now it's possible to specify `s3-storage`, `azure-object-storage` and in general `object-storage`. [#65988](https://github.com/ClickHouse/ClickHouse/pull/65988) ([alesapin](https://github.com/alesapin)).
+* Fix flaky test_storage_s3_queue tests. [#66009](https://github.com/ClickHouse/ClickHouse/pull/66009) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Relax the check in 02982_aggregation_states_destruction. [#66011](https://github.com/ClickHouse/ClickHouse/pull/66011) ([Nikita Taranov](https://github.com/nickitat)).
+* Fix `01158_zookeeper_log_long`. [#66012](https://github.com/ClickHouse/ClickHouse/pull/66012) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Remove scary jemalloc log. [#66028](https://github.com/ClickHouse/ClickHouse/pull/66028) ([Antonio Andelic](https://github.com/antonio2368)).
+* Move experimental settings to the experimental block. [#66030](https://github.com/ClickHouse/ClickHouse/pull/66030) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix lock-order-inversion in DatabaseCatalog. [#66038](https://github.com/ClickHouse/ClickHouse/pull/66038) ([Nikolay Degterinsky](https://github.com/evillique)).
+* Try disabling jemalloc background threads. [#66041](https://github.com/ClickHouse/ClickHouse/pull/66041) ([Antonio Andelic](https://github.com/antonio2368)).
+* Try to avoid conflicts in `SettingsChangesHistory.cpp`. [#66042](https://github.com/ClickHouse/ClickHouse/pull/66042) ([Anton Popov](https://github.com/CurtizJ)).
+* Add profile events for regex cache. [#66050](https://github.com/ClickHouse/ClickHouse/pull/66050) ([Antonio Andelic](https://github.com/antonio2368)).
+* Bump vectorscan to 5.4.10.1. [#66056](https://github.com/ClickHouse/ClickHouse/pull/66056) ([Robert Schulze](https://github.com/rschu1ze)).
+* Remove obsolete comment. [#66059](https://github.com/ClickHouse/ClickHouse/pull/66059) ([Robert Schulze](https://github.com/rschu1ze)).
+* Maybe fix tsan assert in `test_mysql_killed_while_insert_8_0`. [#66064](https://github.com/ClickHouse/ClickHouse/pull/66064) ([Robert Schulze](https://github.com/rschu1ze)).
+* Move some of `HTTPHandler` stuff to separate source files in order to reuse it in `PrometheusRequestHandler`. This PR is required for https://github.com/ClickHouse/ClickHouse/pull/64183. [#66067](https://github.com/ClickHouse/ClickHouse/pull/66067) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Bump rocksdb to v6.23.3. [#66068](https://github.com/ClickHouse/ClickHouse/pull/66068) ([Robert Schulze](https://github.com/rschu1ze)).
+* Add protobufs for `Prometheus` `remote-write` / `remote-read` protocols to our repository. Fix cmake script for compiling protobufs. [#66069](https://github.com/ClickHouse/ClickHouse/pull/66069) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Use pinned versions of all python packages in CI docker images. Also makes clang-18.1.8 work with sanitizers and surprisingly fixes [#66049](https://github.com/ClickHouse/ClickHouse/issues/66049). [#66070](https://github.com/ClickHouse/ClickHouse/pull/66070) ([alesapin](https://github.com/alesapin)).
+* Clean-up custom LLVM 15 patches. [#66072](https://github.com/ClickHouse/ClickHouse/pull/66072) ([Robert Schulze](https://github.com/rschu1ze)).
+* Minor JWT client fixes. [#66073](https://github.com/ClickHouse/ClickHouse/pull/66073) ([Konstantin Bogdanov](https://github.com/thevar1able)).
+* Bump vectorscan to 5.4.11. [#66082](https://github.com/ClickHouse/ClickHouse/pull/66082) ([Robert Schulze](https://github.com/rschu1ze)).
+* Print stacktrace in case of abort after logical error. [#66091](https://github.com/ClickHouse/ClickHouse/pull/66091) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* fix flaky 03172_error_log_table_not_empty. [#66093](https://github.com/ClickHouse/ClickHouse/pull/66093) ([Sema Checherinda](https://github.com/CheSema)).
+* Bump s2geometry to latest master. [#66094](https://github.com/ClickHouse/ClickHouse/pull/66094) ([Robert Schulze](https://github.com/rschu1ze)).
+* update keeper bench example config file. [#66095](https://github.com/ClickHouse/ClickHouse/pull/66095) ([Han Fei](https://github.com/hanfei1991)).
+* Avoid using source directory for generated files. [#66097](https://github.com/ClickHouse/ClickHouse/pull/66097) ([Azat Khuzhin](https://github.com/azat)).
+* More precise warning message about sanitizers. [#66098](https://github.com/ClickHouse/ClickHouse/pull/66098) ([Anton Popov](https://github.com/CurtizJ)).
+* Slightly better calculation of primary index. [#66099](https://github.com/ClickHouse/ClickHouse/pull/66099) ([Anton Popov](https://github.com/CurtizJ)).
+* Bump Azure to 1.12. [#66100](https://github.com/ClickHouse/ClickHouse/pull/66100) ([Robert Schulze](https://github.com/rschu1ze)).
+* Add a test for [#58998](https://github.com/ClickHouse/ClickHouse/issues/58998). [#66101](https://github.com/ClickHouse/ClickHouse/pull/66101) ([Anton Popov](https://github.com/CurtizJ)).
+* CI: Fix sync pr merge. [#66105](https://github.com/ClickHouse/ClickHouse/pull/66105) ([Max K.](https://github.com/maxknv)).
+* Remove flaky case from 02956_rocksdb_bulk_sink. [#66107](https://github.com/ClickHouse/ClickHouse/pull/66107) ([vdimir](https://github.com/vdimir)).
+* Fix bugfix checker. [#66120](https://github.com/ClickHouse/ClickHouse/pull/66120) ([Raúl Marín](https://github.com/Algunenano)).
+* Correctly print long processing requests in Keeper. [#66124](https://github.com/ClickHouse/ClickHouse/pull/66124) ([Antonio Andelic](https://github.com/antonio2368)).
+* Update version_date.tsv and changelogs after v24.6.2.17-stable. [#66127](https://github.com/ClickHouse/ClickHouse/pull/66127) ([robot-clickhouse](https://github.com/robot-clickhouse)).
+* Bump s2geometry again. [#66136](https://github.com/ClickHouse/ClickHouse/pull/66136) ([Robert Schulze](https://github.com/rschu1ze)).
+* Switch submodule `contrib/orc` to a proper commit in the [main](https://github.com/ClickHouse/orc/tree/main) branch. Previously a commit from a removed branch was used ([see](https://github.com/ClickHouse/orc/pull/13)). [#66137](https://github.com/ClickHouse/ClickHouse/pull/66137) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Finalize MergedBlockOutputStream in dtor. [#66138](https://github.com/ClickHouse/ClickHouse/pull/66138) ([Nikita Taranov](https://github.com/nickitat)).
+* Proper destruction order of AsyncLoader::Pool fields. [#66145](https://github.com/ClickHouse/ClickHouse/pull/66145) ([Sergei Trifonov](https://github.com/serxa)).
+* Playing minesweeper with build system. [#66147](https://github.com/ClickHouse/ClickHouse/pull/66147) ([Nikita Taranov](https://github.com/nickitat)).
+* Fix clang-tidy error in BufferWithOwnMemory.h. [#66161](https://github.com/ClickHouse/ClickHouse/pull/66161) ([Nikita Taranov](https://github.com/nickitat)).
+* Use peak_threads_usage instead of arrayUniq(thread_ids) in tests. [#66162](https://github.com/ClickHouse/ClickHouse/pull/66162) ([Azat Khuzhin](https://github.com/azat)).
+* Fix crash when adding empty tuple to query cache. [#66168](https://github.com/ClickHouse/ClickHouse/pull/66168) ([Michael Kolupaev](https://github.com/al13n321)).
+* tests: fix 01563_distributed_query_finish flakiness (due to system.*_log_sender). [#66171](https://github.com/ClickHouse/ClickHouse/pull/66171) ([Azat Khuzhin](https://github.com/azat)).
+* Refactor `OptimizeIfWithConstantConditionVisitor` using `InDepthNodeVisitor`. [#66184](https://github.com/ClickHouse/ClickHouse/pull/66184) ([zhongyuankai](https://github.com/zhongyuankai)).
+* Update README.md. [#66186](https://github.com/ClickHouse/ClickHouse/pull/66186) ([Tyler Hannan](https://github.com/tylerhannan)).
+* Fix 01246_buffer_flush flakiness. [#66188](https://github.com/ClickHouse/ClickHouse/pull/66188) ([Azat Khuzhin](https://github.com/azat)).
+* Avoid using harmful function `rand()` in grpc. [#66191](https://github.com/ClickHouse/ClickHouse/pull/66191) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Bump RocksDB. [#66216](https://github.com/ClickHouse/ClickHouse/pull/66216) ([Robert Schulze](https://github.com/rschu1ze)).
+* Update README.md. [#66217](https://github.com/ClickHouse/ClickHouse/pull/66217) ([Tyler Hannan](https://github.com/tylerhannan)).
+* Fixes peak_threads_usage metric when materialised views are involved. [#66230](https://github.com/ClickHouse/ClickHouse/pull/66230) ([Sema Checherinda](https://github.com/CheSema)).
+* Remove test as requested in https://github.com/ClickHouse/ClickHouse/pull/65277#issuecomment-2211361465. [#66233](https://github.com/ClickHouse/ClickHouse/pull/66233) ([Arthur Passos](https://github.com/arthurpassos)).
+* Fix test `00504_mergetree_arrays_rw.sql`. [#66248](https://github.com/ClickHouse/ClickHouse/pull/66248) ([Anton Popov](https://github.com/CurtizJ)).
+* CI: Do not finalize CI running status unless all success. [#66276](https://github.com/ClickHouse/ClickHouse/pull/66276) ([Max K.](https://github.com/maxknv)).
+* Collect core dumps in more tests. [#66281](https://github.com/ClickHouse/ClickHouse/pull/66281) ([Antonio Andelic](https://github.com/antonio2368)).
+* Add a stateless test for gRPC protocol. [#66284](https://github.com/ClickHouse/ClickHouse/pull/66284) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Log message: Failed to connect to replica ... [#66289](https://github.com/ClickHouse/ClickHouse/pull/66289) ([Igor Nikonov](https://github.com/devcrafter)).
+* Update run.sh. [#66290](https://github.com/ClickHouse/ClickHouse/pull/66290) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Some changes in the codebase as a preparation for LLVM 18. [#66293](https://github.com/ClickHouse/ClickHouse/pull/66293) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* There's some problem with iptables in parallel tests. [#66304](https://github.com/ClickHouse/ClickHouse/pull/66304) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Disable broken cases from 02911_join_on_nullsafe_optimization. [#66310](https://github.com/ClickHouse/ClickHouse/pull/66310) ([vdimir](https://github.com/vdimir)).
+* Build failure if ENABLE_AWS_S3 is OFF fixed. [#66335](https://github.com/ClickHouse/ClickHouse/pull/66335) ([Ilya Golshtein](https://github.com/ilejn)).
+* Enable checks in assert_cast under sanitizers. [#66336](https://github.com/ClickHouse/ClickHouse/pull/66336) ([Nikita Taranov](https://github.com/nickitat)).
+* Create release workflow. [#66339](https://github.com/ClickHouse/ClickHouse/pull/66339) ([Max K.](https://github.com/maxknv)).
+* Fix invalid XML. [#66342](https://github.com/ClickHouse/ClickHouse/pull/66342) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fix possible deadlock for jemalloc with enabled profiler. [#66346](https://github.com/ClickHouse/ClickHouse/pull/66346) ([Azat Khuzhin](https://github.com/azat)).
+* Fix test_parallel_replicas_custom_key. [#66349](https://github.com/ClickHouse/ClickHouse/pull/66349) ([Antonio Andelic](https://github.com/antonio2368)).
+* Collect logs from `minio` in stateless and statefull tests. [#66353](https://github.com/ClickHouse/ClickHouse/pull/66353) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Fix "Sending a batch of X files to Y (0.00 rows, 0.00 B bytes)." in case of batch restoring. [#66375](https://github.com/ClickHouse/ClickHouse/pull/66375) ([Azat Khuzhin](https://github.com/azat)).
+* Fix 03030_system_flush_distributed_settings flakiness. [#66376](https://github.com/ClickHouse/ClickHouse/pull/66376) ([Azat Khuzhin](https://github.com/azat)).
+* PR cleanup: remove redundant code. [#66380](https://github.com/ClickHouse/ClickHouse/pull/66380) ([Igor Nikonov](https://github.com/devcrafter)).
+* New slack bot to post messages about CI events - Post message if OOM. [#66392](https://github.com/ClickHouse/ClickHouse/pull/66392) ([Max K.](https://github.com/maxknv)).
+* Ignore subquery for IN in DDLLoadingDependencyVisitor. [#66395](https://github.com/ClickHouse/ClickHouse/pull/66395) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Update test_storage_rabbitmq/test.py. [#66396](https://github.com/ClickHouse/ClickHouse/pull/66396) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Add query elapsed time for non-default format in play UI. [#66398](https://github.com/ClickHouse/ClickHouse/pull/66398) ([Azat Khuzhin](https://github.com/azat)).
+* Untangle setting headers. [#66404](https://github.com/ClickHouse/ClickHouse/pull/66404) ([Raúl Marín](https://github.com/Algunenano)).
+* Remove noisy message. [#66406](https://github.com/ClickHouse/ClickHouse/pull/66406) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* If job detected as in-progress in PR workflow run - just remove it from todo list, as it not affected by the change. [#66407](https://github.com/ClickHouse/ClickHouse/pull/66407) ([Max K.](https://github.com/maxknv)).
+* CI: CIBuddy to post from master only. [#66417](https://github.com/ClickHouse/ClickHouse/pull/66417) ([Max K.](https://github.com/maxknv)).
+* Add a test for [#66333](https://github.com/ClickHouse/ClickHouse/issues/66333). [#66432](https://github.com/ClickHouse/ClickHouse/pull/66432) ([max-vostrikov](https://github.com/max-vostrikov)).
+* Limit number of linker jobs on arm to avoid OOM during build. [#66435](https://github.com/ClickHouse/ClickHouse/pull/66435) ([Nikita Taranov](https://github.com/nickitat)).
+* [RFC] Fix jemalloc assertion due to non-monotonic CLOCK_MONOTONIC_COARSE. [#66439](https://github.com/ClickHouse/ClickHouse/pull/66439) ([Azat Khuzhin](https://github.com/azat)).
+* CI: Do not block CI on few number of test failures. [#66440](https://github.com/ClickHouse/ClickHouse/pull/66440) ([Max K.](https://github.com/maxknv)).
+* Stateless tests: fix flaky tests 01037_polygon_dicts*. [#66445](https://github.com/ClickHouse/ClickHouse/pull/66445) ([Nikita Fomichev](https://github.com/fm4v)).
+* Related to https://github.com/ClickHouse/ClickHouse/pull/62067 https://s3.amazonaws.com/clickhouse-test-reports/66410/5557dce188cabc7477bb4e874d47e3b80278ee66/stateless_tests__release_.html ``` 2024-07-12 16:04:29 +Queries for alter_table did not finish automatically after 250+ seconds 2024-07-12 16:04:29 +==================== QUERIES ==================== 2024-07-12 16:04:29 +Row 1: 2024-07-12 16:04:29 +────── 2024-07-12 16:04:29 +is_initial_query: 1 2024-07-12 16:04:29 +user: default 2024-07-12 16:04:29 +query_id: b43ffd7d-aee6-4161-aa82-bf9fff9d78c0 2024-07-12 16:04:29 +address: ::1 2024-07-12 16:04:29 +port: 58360 2024-07-12 16:04:29 +initial_user: default 2024-07-12 16:04:29 +initial_query_id: b43ffd7d-aee6-4161-aa82-bf9fff9d78c0 ... 2024-07-12 16:04:29 +query: OPTIMIZE TABLE alter_table0 FINAL ```. [#66460](https://github.com/ClickHouse/ClickHouse/pull/66460) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* OOM error was not visible since process is killed and status is not set Change sets ERROR status if job was killed. [#66463](https://github.com/ClickHouse/ClickHouse/pull/66463) ([Max K.](https://github.com/maxknv)).
+* Add AST fuzzers jobs for CI caching so that they can be skipped in PRs not related to build or tests. [#66468](https://github.com/ClickHouse/ClickHouse/pull/66468) ([Max K.](https://github.com/maxknv)).
+* If job with the same digest has been seen in master's CI it should be skipped in PR run. [#66471](https://github.com/ClickHouse/ClickHouse/pull/66471) ([Max K.](https://github.com/maxknv)).
+* CI: Check job's exit status and report if killed. [#66477](https://github.com/ClickHouse/ClickHouse/pull/66477) ([Max K.](https://github.com/maxknv)).
+* This closes [#37557](https://github.com/ClickHouse/ClickHouse/issues/37557). [#66482](https://github.com/ClickHouse/ClickHouse/pull/66482) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* CI: Add retry for GH set_status_comment call. [#66488](https://github.com/ClickHouse/ClickHouse/pull/66488) ([Max K.](https://github.com/maxknv)).
+* OpenSSL: Minor follow-up to [#66064](https://github.com/ClickHouse/ClickHouse/issues/66064). [#66489](https://github.com/ClickHouse/ClickHouse/pull/66489) ([Robert Schulze](https://github.com/rschu1ze)).
+* CI: Fix for job filtering in PRs. [#66490](https://github.com/ClickHouse/ClickHouse/pull/66490) ([Max K.](https://github.com/maxknv)).
+* CI: Create release workflow updates. [#66498](https://github.com/ClickHouse/ClickHouse/pull/66498) ([Max K.](https://github.com/maxknv)).
+* Add one more revision to ignore. [#66499](https://github.com/ClickHouse/ClickHouse/pull/66499) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Unit tests vomit a ton of garbage, see https://s3.amazonaws.com/clickhouse-test-reports/66457/0c82dc91f07b29ba503d7579c7d3ebecba532b73/unit_tests__tsan_/run.log - remove it. [#66501](https://github.com/ClickHouse/ClickHouse/pull/66501) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix double whitespace in EXPLAIN AST CREATE. [#66505](https://github.com/ClickHouse/ClickHouse/pull/66505) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix bad test `02530_dictionaries_update_field`. [#66507](https://github.com/ClickHouse/ClickHouse/pull/66507) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Https://play.clickhouse.com/play?user=play#u0vmrunuignozwnrx3n0yxj0x3rpbwusignozwnrx25hbwusihrlc3rfbmftzswgcmvwb3j0x3vybapguk9nignozwnrcwpxsevsrsbjagvja19zdgfydf90aw1lid49ig5vdygpic0gsu5urvjwquwgmjqwiehpvvikicagieforcbwdwxsx3jlcxvlc3rfbnvtymvyid0gmaogicagqu5eihrlc3rfc3rhdhvzice9icdts0lquevejwogicagqu5eihrlc3rfc3rhdhvziexjs0ugj0yljwogicagqu5eignozwnrx3n0yxr1cyahpsanc3vjy2vzcyckicagieforcbwb3npdglvbih0zxn0x25hbwusicdhcgfjagvfyxjyb3cnksa+idakt1jervigqlkgy2hly2tfc3rhcnrfdgltzq==. [#66508](https://github.com/ClickHouse/ClickHouse/pull/66508) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix MSan report in GRPC. [#66509](https://github.com/ClickHouse/ClickHouse/pull/66509) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* CI: Fix for skipping Builds_2 in PRs' CI. [#66512](https://github.com/ClickHouse/ClickHouse/pull/66512) ([Max K.](https://github.com/maxknv)).
+* CI: Do not block Tests_3 unless MAX_FAILED_TESTS exceeded. [#66513](https://github.com/ClickHouse/ClickHouse/pull/66513) ([Max K.](https://github.com/maxknv)).
+* Fix `02918_parallel_replicas_custom_key_unavailable_replica`. [#66516](https://github.com/ClickHouse/ClickHouse/pull/66516) ([Antonio Andelic](https://github.com/antonio2368)).
+* Stateless tests: improvements related to OOM of test runs. [#66520](https://github.com/ClickHouse/ClickHouse/pull/66520) ([Nikita Fomichev](https://github.com/fm4v)).
+* Tests: rename bad log names. [#66522](https://github.com/ClickHouse/ClickHouse/pull/66522) ([Nikita Fomichev](https://github.com/fm4v)).
+* Add additional log masking in CI. [#66523](https://github.com/ClickHouse/ClickHouse/pull/66523) ([Raúl Marín](https://github.com/Algunenano)).
+* CI: Multiple fixes for handling killed jobs. [#66524](https://github.com/ClickHouse/ClickHouse/pull/66524) ([Max K.](https://github.com/maxknv)).
+* Allow GWP Asan allocations only when initialization is finished. [#66526](https://github.com/ClickHouse/ClickHouse/pull/66526) ([Alexey Katsman](https://github.com/alexkats)).
+* Update 02443_detach_attach_partition.sh. [#66529](https://github.com/ClickHouse/ClickHouse/pull/66529) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Follow up [#66435](https://github.com/ClickHouse/ClickHouse/issues/66435). [#66530](https://github.com/ClickHouse/ClickHouse/pull/66530) ([Nikita Taranov](https://github.com/nickitat)).
+* fix log in keeper tcp handler. [#66531](https://github.com/ClickHouse/ClickHouse/pull/66531) ([Han Fei](https://github.com/hanfei1991)).
+* CI: Report job start and finish to CI DB. [#66533](https://github.com/ClickHouse/ClickHouse/pull/66533) ([Max K.](https://github.com/maxknv)).
+* Update 01396_inactive_replica_cleanup_nodes_zookeeper.sh. [#66535](https://github.com/ClickHouse/ClickHouse/pull/66535) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Add dedicated runner to libfuzzer, update docker. [#66551](https://github.com/ClickHouse/ClickHouse/pull/66551) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* fix tidy build. [#66552](https://github.com/ClickHouse/ClickHouse/pull/66552) ([Sema Checherinda](https://github.com/CheSema)).
+* No-op env change. [#66553](https://github.com/ClickHouse/ClickHouse/pull/66553) ([Raúl Marín](https://github.com/Algunenano)).
+* Fix typo in new_delete.cpp. [#66554](https://github.com/ClickHouse/ClickHouse/pull/66554) ([alesapin](https://github.com/alesapin)).
+* Fix something in Fast Test. [#66558](https://github.com/ClickHouse/ClickHouse/pull/66558) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* update trusted contributors. [#66561](https://github.com/ClickHouse/ClickHouse/pull/66561) ([Xu Jia](https://github.com/XuJia0210)).
+* Delete bad test `02805_distributed_queries_timeouts`. [#66563](https://github.com/ClickHouse/ClickHouse/pull/66563) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* More clarity in the test `03001_consider_lwd_when_merge`. [#66564](https://github.com/ClickHouse/ClickHouse/pull/66564) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Stateless tests: temporary disable sequential tests in parallel. [#66585](https://github.com/ClickHouse/ClickHouse/pull/66585) ([Nikita Fomichev](https://github.com/fm4v)).
+* Move view targets to separate AST class `ASTViewTargets` in order to allow extending it to support more kinds of view targets. [#66590](https://github.com/ClickHouse/ClickHouse/pull/66590) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix bsdtar for @nikitamikhaylov. [#66592](https://github.com/ClickHouse/ClickHouse/pull/66592) ([alesapin](https://github.com/alesapin)).
+* CI: POC for Auto Releases. [#66593](https://github.com/ClickHouse/ClickHouse/pull/66593) ([Max K.](https://github.com/maxknv)).
+* Fix clang tidy after [#66402](https://github.com/ClickHouse/ClickHouse/issues/66402). [#66597](https://github.com/ClickHouse/ClickHouse/pull/66597) ([vdimir](https://github.com/vdimir)).
+* Adjust the runtime of some slow performance test. [#66619](https://github.com/ClickHouse/ClickHouse/pull/66619) ([Robert Schulze](https://github.com/rschu1ze)).
+* CI: Scale down AutoScaling Groups from runners. [#66622](https://github.com/ClickHouse/ClickHouse/pull/66622) ([Max K.](https://github.com/maxknv)).
+* Allow to run clang-tidy with clang-19. [#66625](https://github.com/ClickHouse/ClickHouse/pull/66625) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix terrible test @arthurpassos. [#66632](https://github.com/ClickHouse/ClickHouse/pull/66632) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix bad log message. [#66633](https://github.com/ClickHouse/ClickHouse/pull/66633) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Negative sign in prewhere optimization. [#66637](https://github.com/ClickHouse/ClickHouse/pull/66637) ([cangyin](https://github.com/cangyin)).
+* Closes [#66639](https://github.com/ClickHouse/ClickHouse/issues/66639#event-13533944949). [#66640](https://github.com/ClickHouse/ClickHouse/pull/66640) ([Kruglov Pavel](https://github.com/Avogar)).
+* Avoid generating named tuple for special keywords (null, true, false). [#66641](https://github.com/ClickHouse/ClickHouse/pull/66641) ([Amos Bird](https://github.com/amosbird)).
+* rearrange heavy tests 03008_deduplication. [#66642](https://github.com/ClickHouse/ClickHouse/pull/66642) ([Sema Checherinda](https://github.com/CheSema)).
+* Fix data race in S3::ClientCache. [#66644](https://github.com/ClickHouse/ClickHouse/pull/66644) ([Konstantin Morozov](https://github.com/k-morozov)).
+* CI: Remove aws lambda packages from oss. [#66651](https://github.com/ClickHouse/ClickHouse/pull/66651) ([Max K.](https://github.com/maxknv)).
+* Introduce separate DEBUG_OR_SANITIZER_BUILD macro. [#66652](https://github.com/ClickHouse/ClickHouse/pull/66652) ([Nikita Taranov](https://github.com/nickitat)).
+* Increase backoff because with slow builds sometimes 100ms is not enough to recover. [#66653](https://github.com/ClickHouse/ClickHouse/pull/66653) ([alesapin](https://github.com/alesapin)).
+* Fix wrong queries hung error because of 02044_url_glob_parallel_connection_refused. [#66657](https://github.com/ClickHouse/ClickHouse/pull/66657) ([Nikita Taranov](https://github.com/nickitat)).
+* add log for splitBlockIntoParts. [#66658](https://github.com/ClickHouse/ClickHouse/pull/66658) ([Han Fei](https://github.com/hanfei1991)).
+* Minor: Make `CaseSensitiveness` an enum class. [#66673](https://github.com/ClickHouse/ClickHouse/pull/66673) ([Robert Schulze](https://github.com/rschu1ze)).
+* Fix bad test `02210_processors_profile_log`. [#66684](https://github.com/ClickHouse/ClickHouse/pull/66684) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix something around clang-tidy. [#66694](https://github.com/ClickHouse/ClickHouse/pull/66694) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* ci: dump dmesg in case of OOM. [#66705](https://github.com/ClickHouse/ClickHouse/pull/66705) ([Azat Khuzhin](https://github.com/azat)).
+* fix clang tidy. [#66706](https://github.com/ClickHouse/ClickHouse/pull/66706) ([Han Fei](https://github.com/hanfei1991)).
+* Https://s3.amazonaws.com/clickhouse-test-reports/61109/5cf2b53f146c1a4f24d8212f9f810d587c46bfc0/stateless_tests__release_.html. [#66724](https://github.com/ClickHouse/ClickHouse/pull/66724) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Support one more case in JOIN ON ... IS NULL. [#66725](https://github.com/ClickHouse/ClickHouse/pull/66725) ([vdimir](https://github.com/vdimir)).
+* CI: Fix issue with a skipped Build report. [#66726](https://github.com/ClickHouse/ClickHouse/pull/66726) ([Max K.](https://github.com/maxknv)).
+* relax condition in test, remove unused counters. [#66730](https://github.com/ClickHouse/ClickHouse/pull/66730) ([Sema Checherinda](https://github.com/CheSema)).
+* Remove bad test `host_resolver_fail_count`. [#66731](https://github.com/ClickHouse/ClickHouse/pull/66731) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix bad test `03036_join_filter_push_down_equivalent_sets`. [#66736](https://github.com/ClickHouse/ClickHouse/pull/66736) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix bad tests `long_select_and_alter`. [#66737](https://github.com/ClickHouse/ClickHouse/pull/66737) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Add test test_storage_mysql/test.py::test_joins. [#66743](https://github.com/ClickHouse/ClickHouse/pull/66743) ([vdimir](https://github.com/vdimir)).
+* Disallow build exclusion only by CI settings (ci_include_, ci_exclude_) to avoid running builds in auto sync prs. [#66744](https://github.com/ClickHouse/ClickHouse/pull/66744) ([Max K.](https://github.com/maxknv)).
+* Use non-existent address to check connection error at table creation. [#66760](https://github.com/ClickHouse/ClickHouse/pull/66760) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Backported in [#67063](https://github.com/ClickHouse/ClickHouse/issues/67063): Increase asio pool size in case the server is tiny. [#66761](https://github.com/ClickHouse/ClickHouse/pull/66761) ([alesapin](https://github.com/alesapin)).
+* Fix flakiness of async insert tests due to adaptive timeout. [#66771](https://github.com/ClickHouse/ClickHouse/pull/66771) ([Raúl Marín](https://github.com/Algunenano)).
+* Attempt to fix flakiness of 01194_http_query_id. [#66774](https://github.com/ClickHouse/ClickHouse/pull/66774) ([Raúl Marín](https://github.com/Algunenano)).
+* Turn off randomization of harmful setting. [#66776](https://github.com/ClickHouse/ClickHouse/pull/66776) ([alesapin](https://github.com/alesapin)).
+* The number of batches was reduced in https://github.com/ClickHouse/ClickHouse/pull/65186, but then the parallel execution was disabled in https://github.com/ClickHouse/ClickHouse/pull/66585. So now tasks fail with timeout sometimes: https://s3.amazonaws.com/clickhouse-test-reports/66724/36275fdacc34206931f69087fe77539e25bbbedd/stateless_tests__tsan__s3_storage__[2_3].html. [#66783](https://github.com/ClickHouse/ClickHouse/pull/66783) ([Alexander Tokmakov](https://github.com/tavplubix)).
+* Remove obsolete code from CMakeLists. [#66786](https://github.com/ClickHouse/ClickHouse/pull/66786) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Stateless tests: split parallel tests more evenly. [#66787](https://github.com/ClickHouse/ClickHouse/pull/66787) ([Nikita Fomichev](https://github.com/fm4v)).
+* Fix test `02724_limit_num_mutations.sh`. [#66788](https://github.com/ClickHouse/ClickHouse/pull/66788) ([Anton Popov](https://github.com/CurtizJ)).
+* Better diagnostics in `test_disk_configuration`. [#66802](https://github.com/ClickHouse/ClickHouse/pull/66802) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix bad test `02950_part_log_bytes_uncompressed`. [#66803](https://github.com/ClickHouse/ClickHouse/pull/66803) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Better diagnostics for test trace_events_stress. [#66804](https://github.com/ClickHouse/ClickHouse/pull/66804) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Make test `00997_set_index_array` lighter. [#66817](https://github.com/ClickHouse/ClickHouse/pull/66817) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Miscellaneous. [#66818](https://github.com/ClickHouse/ClickHouse/pull/66818) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix inconsistent formatting of lambda functions inside composite types. [#66819](https://github.com/ClickHouse/ClickHouse/pull/66819) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Small fix in realloc memory tracking. [#66820](https://github.com/ClickHouse/ClickHouse/pull/66820) ([Antonio Andelic](https://github.com/antonio2368)).
+* Never await in CI on BuildReport - just redo (await can be longer) - Remove BuildReport if no build jobs in workflow (for instance: Docs change) - Do not fail CheckReadyForMerge job if the only non-green status is Cloud Sync. [#66822](https://github.com/ClickHouse/ClickHouse/pull/66822) ([Max K.](https://github.com/maxknv)).
+* Remove bad tests @azat. [#66823](https://github.com/ClickHouse/ClickHouse/pull/66823) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* CI: New Release workflow updates and fixes. [#66830](https://github.com/ClickHouse/ClickHouse/pull/66830) ([Max K.](https://github.com/maxknv)).
+* Fix signed integer overflow in function `age`. [#66831](https://github.com/ClickHouse/ClickHouse/pull/66831) ([Robert Schulze](https://github.com/rschu1ze)).
+* Fix RocksDB bs. [#66838](https://github.com/ClickHouse/ClickHouse/pull/66838) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Split a test for index. [#66839](https://github.com/ClickHouse/ClickHouse/pull/66839) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Fix inconsistent formatting of `NOT ((SELECT ...))`. [#66840](https://github.com/ClickHouse/ClickHouse/pull/66840) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Make test `01592_long_window_functions1` lighter. [#66841](https://github.com/ClickHouse/ClickHouse/pull/66841) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* What if I will change the test for SSL authentication?. [#66844](https://github.com/ClickHouse/ClickHouse/pull/66844) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
+* Functions `[a-g]*`: Iterate over `input_rows_count` where appropriate. [#66846](https://github.com/ClickHouse/ClickHouse/pull/66846) ([Robert Schulze](https://github.com/rschu1ze)).
+* Revert libunwind patch. [#66850](https://github.com/ClickHouse/ClickHouse/pull/66850) ([Antonio Andelic](https://github.com/antonio2368)).
+* Split test 03038_nested_dynamic_merges to avoid timeouts. [#66863](https://github.com/ClickHouse/ClickHouse/pull/66863) ([Kruglov Pavel](https://github.com/Avogar)).
+* CI: Print instance info in runner's init script. [#66868](https://github.com/ClickHouse/ClickHouse/pull/66868) ([Max K.](https://github.com/maxknv)).
+* Backported in [#67257](https://github.com/ClickHouse/ClickHouse/issues/67257): Followup [#66725](https://github.com/ClickHouse/ClickHouse/issues/66725). [#66869](https://github.com/ClickHouse/ClickHouse/pull/66869) ([vdimir](https://github.com/vdimir)).
+* CI: CI Buddy to notify about fatal workflow failures. [#66890](https://github.com/ClickHouse/ClickHouse/pull/66890) ([Max K.](https://github.com/maxknv)).
+* CI: Add ec2 instance lifecycle metadata to CIDB. [#66918](https://github.com/ClickHouse/ClickHouse/pull/66918) ([Max K.](https://github.com/maxknv)).
+* CI: Remove ci runners scripts from oss. [#66920](https://github.com/ClickHouse/ClickHouse/pull/66920) ([Max K.](https://github.com/maxknv)).
+* Backported in [#67209](https://github.com/ClickHouse/ClickHouse/issues/67209): Decrease rate limit in `01923_network_receive_time_metric_insert`. [#66924](https://github.com/ClickHouse/ClickHouse/pull/66924) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Backported in [#67227](https://github.com/ClickHouse/ClickHouse/issues/67227): Grouparrayintersect: fix serialization bug. [#66928](https://github.com/ClickHouse/ClickHouse/pull/66928) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#67207](https://github.com/ClickHouse/ClickHouse/issues/67207): Un-flake test_runtime_configurable_cache_size. [#66934](https://github.com/ClickHouse/ClickHouse/pull/66934) ([Robert Schulze](https://github.com/rschu1ze)).
+* Backported in [#66975](https://github.com/ClickHouse/ClickHouse/issues/66975): CI: Fixes docker server build for release branches. [#66955](https://github.com/ClickHouse/ClickHouse/pull/66955) ([Max K.](https://github.com/maxknv)).
+* Backported in [#67213](https://github.com/ClickHouse/ClickHouse/issues/67213): [CI Fest] Split dynamic tests and rewrite them from sh to sql to avoid timeouts. [#66981](https://github.com/ClickHouse/ClickHouse/pull/66981) ([Kruglov Pavel](https://github.com/Avogar)).
+* Backported in [#67033](https://github.com/ClickHouse/ClickHouse/issues/67033): [CI Fest] Fix use-of-uninitialized-value in JSONExtract* numeric functions. [#66984](https://github.com/ClickHouse/ClickHouse/pull/66984) ([Kruglov Pavel](https://github.com/Avogar)).
+* Backported in [#67051](https://github.com/ClickHouse/ClickHouse/issues/67051): CI: Fix for workflow results parsing. [#67000](https://github.com/ClickHouse/ClickHouse/pull/67000) ([Max K.](https://github.com/maxknv)).
+* Backported in [#67116](https://github.com/ClickHouse/ClickHouse/issues/67116): Disable setting `optimize_functions_to_subcolumns`. [#67046](https://github.com/ClickHouse/ClickHouse/pull/67046) ([Anton Popov](https://github.com/CurtizJ)).
+* Backported in [#67205](https://github.com/ClickHouse/ClickHouse/issues/67205): Increase max allocation size for sanitizers. [#67049](https://github.com/ClickHouse/ClickHouse/pull/67049) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Backported in [#67124](https://github.com/ClickHouse/ClickHouse/issues/67124): Very sad failure: ``` 2024.07.24 13:28:45.517777 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Debug> executeQuery: (from 172.16.11.1:55890) OPTIMIZE TABLE replicated_mt FINAL (stage: Complete) 2024.07.24 13:28:45.525945 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Trace> default.replicated_mt (ReplicatedMergeTreeQueue): Waiting for 4 entries to be processed: queue-0000000004, queue-0000000002, queue-0000000001, queue-0000000000 2024.07.24 13:29:15.528024 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Debug> default.replicated_mt (6581a6fb-8458-466d-8350-89951eb1ac8e) (MergerMutator): Selected 3 parts from all_0_0_0 to all_2_2_0 2024.07.24 13:29:15.530736 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Trace> default.replicated_mt (6581a6fb-8458-466d-8350-89951eb1ac8e): Created log entry /clickhouse/tables/replicated_mt/log/log-0000000004 for merge all_0_2_1 2024.07.24 13:29:15.530873 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Debug> default.replicated_mt (6581a6fb-8458-466d-8350-89951eb1ac8e): Waiting for node1 to process log entry 2024.07.24 13:29:15.530919 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Debug> default.replicated_mt (6581a6fb-8458-466d-8350-89951eb1ac8e): Waiting for node1 to pull log-0000000004 to queue 2024.07.24 13:29:15.534286 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Debug> default.replicated_mt (6581a6fb-8458-466d-8350-89951eb1ac8e): Looking for node corresponding to log-0000000004 in node1 queue 2024.07.24 13:29:15.534793 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Debug> default.replicated_mt (6581a6fb-8458-466d-8350-89951eb1ac8e): Waiting for queue-0000000005 to disappear from node1 queue 2024.07.24 13:29:15.585533 [ 10 ] {08745bf9-4bc1-4946-b9a8-c03d82ec55dc} <Debug> TCPHandler: Processed in 30.067804125 sec. ```. [#67067](https://github.com/ClickHouse/ClickHouse/pull/67067) ([alesapin](https://github.com/alesapin)).
+* Backported in [#67203](https://github.com/ClickHouse/ClickHouse/issues/67203): Fix flaky `test_seekable_formats_url` and `test_seekable_formats` S3 storage tests. [#67070](https://github.com/ClickHouse/ClickHouse/pull/67070) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
+* Backported in [#67222](https://github.com/ClickHouse/ClickHouse/issues/67222): Fix 2680 flasky. [#67078](https://github.com/ClickHouse/ClickHouse/pull/67078) ([jsc0218](https://github.com/jsc0218)).
+* Backported in [#67190](https://github.com/ClickHouse/ClickHouse/issues/67190): Attempt to fix flakiness of some window view tests. [#67130](https://github.com/ClickHouse/ClickHouse/pull/67130) ([Robert Schulze](https://github.com/rschu1ze)).
+* Backported in [#67272](https://github.com/ClickHouse/ClickHouse/issues/67272): Rename (unreleased) bad setting. [#67149](https://github.com/ClickHouse/ClickHouse/pull/67149) ([Raúl Marín](https://github.com/Algunenano)).
+* Backported in [#67441](https://github.com/ClickHouse/ClickHouse/issues/67441): Try to fix 2572. [#67158](https://github.com/ClickHouse/ClickHouse/pull/67158) ([jsc0218](https://github.com/jsc0218)).
+* Backported in [#67416](https://github.com/ClickHouse/ClickHouse/issues/67416): CI: Fix build results for release branches. [#67402](https://github.com/ClickHouse/ClickHouse/pull/67402) ([Max K.](https://github.com/maxknv)).
+

docs/en/engines/table-engines/special/keepermap.md

@@ -54,7 +54,7 @@ CREATE TABLE keeper_map_table
     `v2` String,
     `v3` Float32
 )
-ENGINE = KeeperMap(/keeper_map_table, 4)
+ENGINE = KeeperMap('/keeper_map_table', 4)
 PRIMARY KEY key
 ```
 

docs/en/interfaces/formats.md

@@ -32,6 +32,7 @@ The supported formats are:
 | [Vertical](#vertical)                                                                     | ✗    | ✔     |
 | [JSON](#json)                                                                             | ✔    | ✔     |
 | [JSONAsString](#jsonasstring)                                                             | ✔    | ✗     |
+| [JSONAsObject](#jsonasobject)                                                             | ✔    | ✗     |
 | [JSONStrings](#jsonstrings)                                                               | ✔    | ✔     |
 | [JSONColumns](#jsoncolumns)                                                               | ✔    | ✔     |
 | [JSONColumnsWithMetadata](#jsoncolumnsmonoblock)                                          | ✔    | ✔     |
@@ -822,6 +823,67 @@ Result:
 └────────────────────────────┘
 ```
 
+## JSONAsObject {#jsonasobject}
+
+In this format, a single JSON object is interpreted as a single [Object('json')](/docs/en/sql-reference/data-types/json.md) value. If the input has several JSON objects (comma separated), they are interpreted as separate rows. If the input data is enclosed in square brackets, it is interpreted as an array of JSONs.
+
+This format can only be parsed for a table with a single field of type [Object('json')](/docs/en/sql-reference/data-types/json.md). The remaining columns must be set to [DEFAULT](/docs/en/sql-reference/statements/create/table.md/#default) or [MATERIALIZED](/docs/en/sql-reference/statements/create/table.md/#materialized).
+
+**Examples**
+
+Query:
+
+``` sql
+SET allow_experimental_object_type = 1;
+CREATE TABLE json_as_object (json Object('json')) ENGINE = Memory;
+INSERT INTO json_as_object (json) FORMAT JSONAsObject {"foo":{"bar":{"x":"y"},"baz":1}},{},{"any json stucture":1}
+SELECT * FROM json_as_object FORMAT JSONEachRow;
+```
+
+Result:
+
+``` response
+{"json":{"any json stucture":0,"foo":{"bar":{"x":"y"},"baz":1}}}
+{"json":{"any json stucture":0,"foo":{"bar":{"x":""},"baz":0}}}
+{"json":{"any json stucture":1,"foo":{"bar":{"x":""},"baz":0}}}
+```
+
+**An array of JSON objects**
+
+Query:
+
+``` sql
+SET allow_experimental_object_type = 1;
+CREATE TABLE json_square_brackets (field Object('json')) ENGINE = Memory;
+INSERT INTO json_square_brackets FORMAT JSONAsObject [{"id": 1, "name": "name1"}, {"id": 2, "name": "name2"}];
+
+SELECT * FROM json_square_brackets FORMAT JSONEachRow;
+```
+
+Result:
+
+```response
+{"field":{"id":1,"name":"name1"}}
+{"field":{"id":2,"name":"name2"}}
+```
+
+**Columns with default values**
+
+```sql
+SET allow_experimental_object_type = 1;
+CREATE TABLE json_as_object (json Object('json'), time DateTime MATERIALIZED now()) ENGINE = Memory;
+INSERT INTO json_as_object (json) FORMAT JSONAsObject {"foo":{"bar":{"x":"y"},"baz":1}};
+INSERT INTO json_as_object (json) FORMAT JSONAsObject {};
+INSERT INTO json_as_object (json) FORMAT JSONAsObject {"any json stucture":1}
+SELECT * FROM json_as_object FORMAT JSONEachRow
+```
+
+```resonse
+{"json":{"any json stucture":0,"foo":{"bar":{"x":"y"},"baz":1}},"time":"2024-07-25 17:02:45"}
+{"json":{"any json stucture":0,"foo":{"bar":{"x":""},"baz":0}},"time":"2024-07-25 17:02:47"}
+{"json":{"any json stucture":1,"foo":{"bar":{"x":""},"baz":0}},"time":"2024-07-25 17:02:50"}
+```
+
 ## JSONCompact {#jsoncompact}
 
 Differs from JSON only in that data rows are output in arrays, not in objects.

docs/en/sql-reference/functions/other-functions.md

@@ -346,7 +346,9 @@ Result:
 ## materialize
 
 Turns a constant into a full column containing a single value.
-Full columns and constants are represented differently in memory. Functions usually execute different code for normal and constant arguments, although the result should typically be the same. This function can be used to debug this behavior.
+Full columns and constants are represented differently in memory.
+Functions usually execute different code for normal and constant arguments, although the result should typically be the same. 
+This function can be used to debug this behavior.
 
 **Syntax**
 
@@ -354,6 +356,34 @@ Full columns and constants are represented differently in memory. Functions usua
 materialize(x)
 ```
 
+**Parameters**
+
+- `x` — A constant. [Constant](../functions/index.md/#constants).
+
+**Returned value**
+
+- A column containing a single value `x`.
+
+**Example**
+
+In the example below the `countMatches` function expects a constant second argument. 
+This behaviour can be debugged by using the `materialize` function to turn a constant into a full column, 
+verifying that the function throws an error for a non-constant argument.
+
+Query:
+
+```sql
+SELECT countMatches('foobarfoo', 'foo');
+SELECT countMatches('foobarfoo', materialize('foo'));
+```
+
+Result:
+
+```response
+2
+Code: 44. DB::Exception: Received from localhost:9000. DB::Exception: Illegal type of argument #2 'pattern' of function countMatches, expected constant String, got String
+```
+
 ## ignore
 
 Accepts any arguments, including `NULL` and does nothing. Always returns 0.

docs/en/sql-reference/window-functions/lagInFrame.md

@@ -23,7 +23,7 @@ For more detail on window function syntax see: [Window Functions - Syntax](./ind
 **Parameters**
 - `x` — Column name. 
 - `offset` — Offset to apply. [(U)Int*](../data-types/int-uint.md). (Optional - `1` by default).
-- `default` — Value to return if calculated row exceeds the boundaries of the window frame. (Optional - `null` by default).
+- `default` — Value to return if calculated row exceeds the boundaries of the window frame. (Optional - default value of column type when omitted).
 
 **Returned value**
 

docs/en/sql-reference/window-functions/leadInFrame.md

@@ -23,7 +23,7 @@ For more detail on window function syntax see: [Window Functions - Syntax](./ind
 **Parameters**
 - `x` — Column name.
 - `offset` — Offset to apply. [(U)Int*](../data-types/int-uint.md). (Optional - `1` by default).
-- `default` — Value to return if calculated row exceeds the boundaries of the window frame. (Optional - `null` by default).
+- `default` — Value to return if calculated row exceeds the boundaries of the window frame. (Optional - default value of column type when omitted).
 
 **Returned value**
 

programs/client/Client.cpp

@@ -1135,8 +1135,6 @@ void Client::processOptions(const OptionsDescription & options_description,
 
     if ((query_fuzzer_runs = options["query-fuzzer-runs"].as<int>()))
     {
-        // Fuzzer implies multiquery.
-        config().setBool("multiquery", true);
         // Ignore errors in parsing queries.
         config().setBool("ignore-error", true);
         ignore_error = true;
@@ -1144,8 +1142,6 @@ void Client::processOptions(const OptionsDescription & options_description,
 
     if ((create_query_fuzzer_runs = options["create-query-fuzzer-runs"].as<int>()))
     {
-        // Fuzzer implies multiquery.
-        config().setBool("multiquery", true);
         // Ignore errors in parsing queries.
         config().setBool("ignore-error", true);
 
@@ -1201,9 +1197,6 @@ void Client::processConfig()
     }
     print_stack_trace = config().getBool("stacktrace", false);
 
-    if (config().has("multiquery"))
-        is_multiquery = true;
-
     pager = config().getString("pager", "");
 
     setDefaultFormatsAndCompressionFromConfiguration();
@@ -1359,13 +1352,6 @@ void Client::readArguments(
                 allow_repeated_settings = true;
             else if (arg == "--allow_merge_tree_settings")
                 allow_merge_tree_settings = true;
-            else if (arg == "--multiquery" && (arg_num + 1) < argc && !std::string_view(argv[arg_num + 1]).starts_with('-'))
-            {
-                /// Transform the abbreviated syntax '--multiquery <SQL>' into the full syntax '--multiquery -q <SQL>'
-                ++arg_num;
-                arg = argv[arg_num];
-                addMultiquery(arg, common_arguments);
-            }
             else if (arg == "--password" && ((arg_num + 1) >= argc || std::string_view(argv[arg_num + 1]).starts_with('-')))
             {
                 common_arguments.emplace_back(arg);

programs/client/Client.h

@@ -1,14 +1,16 @@
 #pragma once
 
-#include <Client/ClientBase.h>
+#include <Client/ClientApplicationBase.h>
 
 
 namespace DB
 {
 
-class Client : public ClientBase
+class Client : public ClientApplicationBase
 {
 public:
+    using Arguments = ClientApplicationBase::Arguments;
+
     Client() = default;
 
     void initialize(Poco::Util::Application & self) override;

programs/keeper/Keeper.cpp

@@ -19,6 +19,7 @@
 #include <base/getMemoryAmount.h>
 #include <base/scope_guard.h>
 #include <base/safeExit.h>
+#include <base/Numa.h>
 #include <Poco/Net/NetException.h>
 #include <Poco/Net/TCPServerParams.h>
 #include <Poco/Net/TCPServer.h>
@@ -311,6 +312,12 @@ try
 
     MainThreadStatus::getInstance();
 
+    if (auto total_numa_memory = getNumaNodesTotalMemory(); total_numa_memory.has_value())
+    {
+        LOG_INFO(
+            log, "Keeper is bound to a subset of NUMA nodes. Total memory of all available nodes: {}", ReadableSize(*total_numa_memory));
+    }
+
 #if !defined(NDEBUG) || !defined(__OPTIMIZE__)
     LOG_WARNING(log, "Keeper was built in debug mode. It will work slowly.");
 #endif

programs/local/LocalServer.cpp

@@ -80,7 +80,7 @@ namespace ErrorCodes
 
 void applySettingsOverridesForLocal(ContextMutablePtr context)
 {
-    Settings settings = context->getSettings();
+    Settings settings = context->getSettingsCopy();
 
     settings.allow_introspection_functions = true;
     settings.storage_file_read_method = LocalFSReadMethod::mmap;
@@ -184,6 +184,11 @@ void LocalServer::initialize(Poco::Util::Application & self)
         cleanup_threads,
         0, // We don't need any threads one all the parts will be deleted
         cleanup_threads);
+
+    getDatabaseCatalogDropTablesThreadPool().initialize(
+        server_settings.database_catalog_drop_table_concurrency,
+        0, // We don't need any threads if there are no DROP queries.
+        server_settings.database_catalog_drop_table_concurrency);
 }
 
 
@@ -569,9 +574,6 @@ void LocalServer::processConfig()
     if (!queries.empty() && getClientConfiguration().has("queries-file"))
         throw Exception(ErrorCodes::BAD_ARGUMENTS, "Options '--query' and '--queries-file' cannot be specified at the same time");
 
-    if (getClientConfiguration().has("multiquery"))
-        is_multiquery = true;
-
     pager = getClientConfiguration().getString("pager", "");
 
     delayed_interactive = getClientConfiguration().has("interactive") && (!queries.empty() || getClientConfiguration().has("queries-file"));
@@ -936,13 +938,6 @@ void LocalServer::readArguments(int argc, char ** argv, Arguments & common_argum
                 query_parameters.emplace(param_continuation.substr(0, equal_pos), param_continuation.substr(equal_pos + 1));
             }
         }
-        else if (arg == "--multiquery" && (arg_num + 1) < argc && !std::string_view(argv[arg_num + 1]).starts_with('-'))
-        {
-            /// Transform the abbreviated syntax '--multiquery <SQL>' into the full syntax '--multiquery -q <SQL>'
-            ++arg_num;
-            arg = argv[arg_num];
-            addMultiquery(arg, common_arguments);
-        }
         else
         {
             common_arguments.emplace_back(arg);

programs/local/LocalServer.h

@@ -1,6 +1,6 @@
 #pragma once
 
-#include <Client/ClientBase.h>
+#include <Client/ClientApplicationBase.h>
 #include <Client/LocalConnection.h>
 
 #include <Core/ServerSettings.h>
@@ -21,7 +21,7 @@ namespace DB
 /// Lightweight Application for clickhouse-local
 /// No networking, no extra configs and working directories, no pid and status files, no dictionaries, no logging.
 /// Quiet mode by default
-class LocalServer : public ClientBase, public Loggers
+class LocalServer : public ClientApplicationBase, public Loggers
 {
 public:
     LocalServer() = default;

programs/server/Server.cpp

@@ -22,6 +22,7 @@
 #include <base/coverage.h>
 #include <base/getFQDNOrHostName.h>
 #include <base/safeExit.h>
+#include <base/Numa.h>
 #include <Common/PoolId.h>
 #include <Common/MemoryTracker.h>
 #include <Common/ClickHouseRevision.h>
@@ -140,6 +141,7 @@
 #   include <azure/core/diagnostics/logger.hpp>
 #endif
 
+
 #include <incbin.h>
 /// A minimal file used when the server is run without installation
 INCBIN(resource_embedded_xml, SOURCE_DIR "/programs/server/embedded.xml");
@@ -754,6 +756,12 @@ try
         setenv("OPENSSL_CONF", config_dir.c_str(), true); /// NOLINT
     }
 
+    if (auto total_numa_memory = getNumaNodesTotalMemory(); total_numa_memory.has_value())
+    {
+        LOG_INFO(
+            log, "ClickHouse is bound to a subset of NUMA nodes. Total memory of all available nodes: {}", ReadableSize(*total_numa_memory));
+    }
+
     registerInterpreters();
     registerFunctions();
     registerAggregateFunctions();
@@ -1035,6 +1043,11 @@ try
         0, // We don't need any threads once all the tables will be created
         max_database_replicated_create_table_thread_pool_size);
 
+    getDatabaseCatalogDropTablesThreadPool().initialize(
+        server_settings.database_catalog_drop_table_concurrency,
+        0, // We don't need any threads if there are no DROP queries.
+        server_settings.database_catalog_drop_table_concurrency);
+
     /// Initialize global local cache for remote filesystem.
     if (config().has("local_cache_for_remote_fs"))
     {
@@ -1582,6 +1595,8 @@ try
             global_context->setMacros(std::make_unique<Macros>(*config, "macros", log));
             global_context->setExternalAuthenticatorsConfig(*config);
 
+            global_context->setDashboardsConfig(config);
+
             if (global_context->isServerCompletelyStarted())
             {
                 /// It does not make sense to reload anything before server has started.

programs/server/config.xml

@@ -1312,6 +1312,31 @@
         <ttl>event_date + INTERVAL 30 DAY</ttl>
     </blob_storage_log>
 
+    <!-- Configure system.dashboards for dashboard.html.
+
+         Could have any query parameters, for which there will be an input on the page.
+         For instance an example from comments have the following:
+         - seconds
+         - rounding
+
+         NOTE: All default dashboards will be overwritten if it was set here. -->
+    <!-- Here is an example without merge() function, to make it work with readonly user -->
+    <!--
+    <dashboards>
+        <dashboard>
+            <dashboard>Overview</dashboard>
+            <title>Queries/second</title>
+            <query>
+                SELECT toStartOfInterval(event_time, INTERVAL {rounding:UInt32} SECOND)::INT AS t, avg(ProfileEvent_Query)
+                FROM system.metric_log
+                WHERE event_date >= toDate(now() - {seconds:UInt32}) AND event_time >= now() - {seconds:UInt32}
+                GROUP BY t
+                ORDER BY t WITH FILL STEP {rounding:UInt32}
+            </query>
+        </dashboard>
+    </dashboards>
+    -->
+
     <!-- <top_level_domains_path>/var/lib/clickhouse/top_level_domains/</top_level_domains_path> -->
     <!-- Custom TLD lists.
          Format: <name>/path/to/file</name>

src/Access/Common/AccessRightsElement.cpp

@@ -224,7 +224,11 @@ void AccessRightsElement::replaceEmptyDatabase(const String & current_database)
 
 String AccessRightsElement::toString() const { return toStringImpl(*this, true); }
 String AccessRightsElement::toStringWithoutOptions() const { return toStringImpl(*this, false); }
-
+String AccessRightsElement::toStringForAccessTypeSource() const
+{
+    String result{access_flags.toKeywords().front()};
+    return result + " ON *.*";
+}
 
 bool AccessRightsElements::empty() const { return std::all_of(begin(), end(), [](const AccessRightsElement & e) { return e.empty(); }); }
 

src/Access/Common/AccessRightsElement.h

@@ -89,6 +89,7 @@ struct AccessRightsElement
     /// Returns a human-readable representation like "GRANT SELECT, UPDATE(x, y) ON db.table".
     String toString() const;
     String toStringWithoutOptions() const;
+    String toStringForAccessTypeSource() const;
 };
 
 

src/Access/ContextAccess.cpp

@@ -38,6 +38,24 @@ namespace ErrorCodes
 
 namespace
 {
+    const std::vector<std::tuple<AccessFlags, std::string>> source_and_table_engines = {
+        {AccessType::FILE, "File"},
+        {AccessType::URL, "URL"},
+        {AccessType::REMOTE, "Distributed"},
+        {AccessType::MONGO, "MongoDB"},
+        {AccessType::REDIS, "Redis"},
+        {AccessType::MYSQL, "MySQL"},
+        {AccessType::POSTGRES, "PostgreSQL"},
+        {AccessType::SQLITE, "SQLite"},
+        {AccessType::ODBC, "ODBC"},
+        {AccessType::JDBC, "JDBC"},
+        {AccessType::HDFS, "HDFS"},
+        {AccessType::S3, "S3"},
+        {AccessType::HIVE, "Hive"},
+        {AccessType::AZURE, "AzureBlobStorage"}
+    };
+
+
     AccessRights mixAccessRightsFromUserAndRoles(const User & user, const EnabledRolesInfo & roles_info)
     {
         AccessRights res = user.access;
@@ -206,22 +224,6 @@ namespace
         }
 
         /// There is overlap between AccessType sources and table engines, so the following code avoids user granting twice.
-        static const std::vector<std::tuple<AccessFlags, std::string>> source_and_table_engines = {
-            {AccessType::FILE, "File"},
-            {AccessType::URL, "URL"},
-            {AccessType::REMOTE, "Distributed"},
-            {AccessType::MONGO, "MongoDB"},
-            {AccessType::REDIS, "Redis"},
-            {AccessType::MYSQL, "MySQL"},
-            {AccessType::POSTGRES, "PostgreSQL"},
-            {AccessType::SQLITE, "SQLite"},
-            {AccessType::ODBC, "ODBC"},
-            {AccessType::JDBC, "JDBC"},
-            {AccessType::HDFS, "HDFS"},
-            {AccessType::S3, "S3"},
-            {AccessType::HIVE, "Hive"},
-            {AccessType::AZURE, "AzureBlobStorage"}
-        };
 
         /// Sync SOURCE and TABLE_ENGINE, so only need to check TABLE_ENGINE later.
         if (access_control.doesTableEnginesRequireGrant())
@@ -267,6 +269,11 @@ namespace
 
     template <typename... OtherArgs>
     std::string_view getDatabase(std::string_view arg1, const OtherArgs &...) { return arg1; }
+
+    std::string_view getTableEngine() { return {}; }
+
+    template <typename... OtherArgs>
+    std::string_view getTableEngine(std::string_view arg1, const OtherArgs &...) { return arg1; }
 }
 
 
@@ -620,18 +627,58 @@ bool ContextAccess::checkAccessImplHelper(const ContextPtr & context, AccessFlag
 
     if (!granted)
     {
+        auto access_denied_no_grant = [&]<typename... FmtArgs>(AccessFlags access_flags, FmtArgs && ...fmt_args)
+        {
+            if (grant_option && acs->isGranted(access_flags, fmt_args...))
+            {
+                return access_denied(ErrorCodes::ACCESS_DENIED,
+                    "{}: Not enough privileges. "
+                    "The required privileges have been granted, but without grant option. "
+                    "To execute this query, it's necessary to have the grant {} WITH GRANT OPTION",
+                    AccessRightsElement{access_flags, fmt_args...}.toStringWithoutOptions());
+            }
+
+            return access_denied(ErrorCodes::ACCESS_DENIED,
+                "{}: Not enough privileges. To execute this query, it's necessary to have the grant {}",
+                AccessRightsElement{access_flags, fmt_args...}.toStringWithoutOptions() + (grant_option ? " WITH GRANT OPTION" : ""));
+        };
+
+        /// As we check the SOURCES from the Table Engine logic, direct prompt about Table Engine would be misleading
+        /// since SOURCES is not granted actually. In order to solve this, turn the prompt logic back to Sources.
+        if (flags & AccessType::TABLE_ENGINE && !access_control->doesTableEnginesRequireGrant())
+        {
+            AccessFlags new_flags;
+
+            String table_engine_name{getTableEngine(args...)};
+            for (const auto & source_and_table_engine : source_and_table_engines)
+            {
+                const auto & table_engine = std::get<1>(source_and_table_engine);
+                if (table_engine != table_engine_name) continue;
+                const auto & source = std::get<0>(source_and_table_engine);
+                /// Set the flags from Table Engine to SOURCES so that prompts can be meaningful.
+                new_flags = source;
+                break;
+            }
+
+            /// Might happen in the case of grant Table Engine on A (but not source), then revoke A.
+            if (new_flags.isEmpty())
+                return access_denied_no_grant(flags, args...);
+
             if (grant_option && acs->isGranted(flags, args...))
             {
                 return access_denied(ErrorCodes::ACCESS_DENIED,
                     "{}: Not enough privileges. "
                     "The required privileges have been granted, but without grant option. "
                     "To execute this query, it's necessary to have the grant {} WITH GRANT OPTION",
-                AccessRightsElement{flags, args...}.toStringWithoutOptions());
+                    AccessRightsElement{new_flags}.toStringForAccessTypeSource());
             }
 
             return access_denied(ErrorCodes::ACCESS_DENIED,
                 "{}: Not enough privileges. To execute this query, it's necessary to have the grant {}",
-            AccessRightsElement{flags, args...}.toStringWithoutOptions() + (grant_option ? " WITH GRANT OPTION" : ""));
+                AccessRightsElement{new_flags}.toStringForAccessTypeSource() + (grant_option ? " WITH GRANT OPTION" : ""));
+        }
+
+        return access_denied_no_grant(flags, args...);
     }
 
     struct PrecalculatedFlags

src/Analyzer/Passes/RewriteAggregateFunctionWithIfPass.cpp

@@ -2,6 +2,7 @@
 
 #include <DataTypes/DataTypesNumber.h>
 #include <DataTypes/DataTypeNullable.h>
+#include <DataTypes/DataTypeAggregateFunction.h>
 
 #include <AggregateFunctions/AggregateFunctionFactory.h>
 #include <AggregateFunctions/IAggregateFunction.h>
@@ -42,7 +43,7 @@ public:
         if (lower_name.ends_with("if"))
             return;
 
-        auto & function_arguments_nodes = function_node->getArguments().getNodes();
+        const auto & function_arguments_nodes = function_node->getArguments().getNodes();
         if (function_arguments_nodes.size() != 1)
             return;
 
@@ -50,6 +51,8 @@ public:
         if (!if_node || if_node->getFunctionName() != "if")
             return;
 
+        FunctionNodePtr replaced_node;
+
         auto if_arguments_nodes = if_node->getArguments().getNodes();
         auto * first_const_node = if_arguments_nodes[1]->as<ConstantNode>();
         auto * second_const_node = if_arguments_nodes[2]->as<ConstantNode>();
@@ -75,8 +78,11 @@ public:
                     new_arguments[0] = std::move(if_arguments_nodes[1]);
 
                 new_arguments[1] = std::move(if_arguments_nodes[0]);
-                function_arguments_nodes = std::move(new_arguments);
+
-                resolveAggregateFunctionNodeByName(*function_node, function_node->getFunctionName() + "If");
+                replaced_node = std::make_shared<FunctionNode>(function_node->getFunctionName() + "If");
+                replaced_node->getArguments().getNodes() = std::move(new_arguments);
+                replaced_node->getParameters().getNodes() = function_node->getParameters().getNodes();
+                resolveAggregateFunctionNodeByName(*replaced_node, replaced_node->getFunctionName());
             }
         }
         else if (first_const_node)
@@ -104,10 +110,26 @@ public:
                     FunctionFactory::instance().get("not", getContext())->build(not_function->getArgumentColumns()));
                 new_arguments[1] = std::move(not_function);
 
-                function_arguments_nodes = std::move(new_arguments);
+                replaced_node = std::make_shared<FunctionNode>(function_node->getFunctionName() + "If");
-                resolveAggregateFunctionNodeByName(*function_node, function_node->getFunctionName() + "If");
+                replaced_node->getArguments().getNodes() = std::move(new_arguments);
+                replaced_node->getParameters().getNodes() = function_node->getParameters().getNodes();
+                resolveAggregateFunctionNodeByName(*replaced_node, replaced_node->getFunctionName());
             }
         }
+
+        if (!replaced_node)
+            return;
+
+        auto prev_type = function_node->getResultType();
+        auto curr_type = replaced_node->getResultType();
+        if (!prev_type->equals(*curr_type))
+            return;
+
+        /// Just in case, CAST compatible aggregate function states.
+        if (WhichDataType(prev_type).isAggregateFunction() && !DataTypeAggregateFunction::strictEquals(prev_type, curr_type))
+            node = createCastFunction(std::move(replaced_node), prev_type, getContext());
+        else
+            node = std::move(replaced_node);
     }
 };
 

src/Analyzer/QueryTreeBuilder.cpp

@@ -237,7 +237,7 @@ QueryTreeNodePtr QueryTreeBuilder::buildSelectExpression(const ASTPtr & select_q
     /// Remove global settings limit and offset
     if (const auto & settings_ref = updated_context->getSettingsRef(); settings_ref.limit || settings_ref.offset)
     {
-        Settings settings = updated_context->getSettings();
+        Settings settings = updated_context->getSettingsCopy();
         limit = settings.limit;
         offset = settings.offset;
         settings.limit = 0;

src/Analyzer/Resolve/QueryAnalyzer.cpp

@@ -503,7 +503,7 @@ void QueryAnalyzer::evaluateScalarSubqueryIfNeeded(QueryTreeNodePtr & node, Iden
         ProfileEvents::increment(ProfileEvents::ScalarSubqueriesCacheMiss);
         auto subquery_context = Context::createCopy(context);
 
-        Settings subquery_settings = context->getSettings();
+        Settings subquery_settings = context->getSettingsCopy();
         subquery_settings.max_result_rows = 1;
         subquery_settings.extremes = false;
         subquery_context->setSettings(subquery_settings);

src/Analyzer/Utils.cpp

@@ -867,7 +867,7 @@ void updateContextForSubqueryExecution(ContextMutablePtr & mutable_context)
       *  max_rows_in_join, max_bytes_in_join, join_overflow_mode,
       *  which are checked separately (in the Set, Join objects).
       */
-    Settings subquery_settings = mutable_context->getSettings();
+    Settings subquery_settings = mutable_context->getSettingsCopy();
     subquery_settings.max_result_rows = 0;
     subquery_settings.max_result_bytes = 0;
     /// The calculation of extremes does not make sense and is not necessary (if you do it, then the extremes of the subquery can be taken for whole query).

src/Backups/BackupsWorker.cpp

@@ -384,6 +384,7 @@ BackupsWorker::BackupsWorker(ContextMutablePtr global_context, size_t num_backup
     , allow_concurrent_backups(global_context->getConfigRef().getBool("backups.allow_concurrent_backups", true))
     , allow_concurrent_restores(global_context->getConfigRef().getBool("backups.allow_concurrent_restores", true))
     , remove_backup_files_after_failure(global_context->getConfigRef().getBool("backups.remove_backup_files_after_failure", true))
+    , test_randomize_order(global_context->getConfigRef().getBool("backups.test_randomize_order", false))
     , test_inject_sleep(global_context->getConfigRef().getBool("backups.test_inject_sleep", false))
     , log(getLogger("BackupsWorker"))
     , backup_log(global_context->getBackupLog())
@@ -713,14 +714,25 @@ void BackupsWorker::writeBackupEntries(
     bool always_single_threaded = !backup->supportsWritingInMultipleThreads();
     auto & thread_pool = getThreadPool(ThreadPoolId::BACKUP_COPY_FILES);
 
+    std::vector<size_t> writing_order;
+    if (test_randomize_order)
+    {
+        /// Randomize the order in which we write backup entries to the backup.
+        writing_order.resize(backup_entries.size());
+        std::iota(writing_order.begin(), writing_order.end(), 0);
+        std::shuffle(writing_order.begin(), writing_order.end(), thread_local_rng);
+    }
+
     ThreadPoolCallbackRunnerLocal<void> runner(thread_pool, "BackupWorker");
     for (size_t i = 0; i != backup_entries.size(); ++i)
     {
         if (failed)
             break;
 
-        auto & entry = backup_entries[i].second;
+        size_t index = !writing_order.empty() ? writing_order[i] : i;
-        const auto & file_info = file_infos[i];
+
+        auto & entry = backup_entries[index].second;
+        const auto & file_info = file_infos[index];
 
         auto job = [&]()
         {

src/Backups/BackupsWorker.h

@@ -119,6 +119,7 @@ private:
     const bool allow_concurrent_backups;
     const bool allow_concurrent_restores;
     const bool remove_backup_files_after_failure;
+    const bool test_randomize_order;
     const bool test_inject_sleep;
 
     LoggerPtr log;

src/Bridge/IBridge.cpp

@@ -232,7 +232,7 @@ int IBridge::main(const std::vector<std::string> & /*args*/)
     auto context = Context::createGlobal(shared_context.get());
     context->makeGlobalContext();
 
-    auto settings = context->getSettings();
+    auto settings = context->getSettingsCopy();
     settings.set("http_max_field_value_size", http_max_field_value_size);
     context->setSettings(settings);
 

src/Client/ClientApplicationBase.cpp

@@ -0,0 +1,395 @@
+#include <Client/ClientApplicationBase.h>
+
+#include <base/argsToConfig.h>
+#include <base/safeExit.h>
+#include <Core/BaseSettingsProgramOptions.h>
+#include <Common/clearPasswordFromCommandLine.h>
+#include <Common/TerminalSize.h>
+#include <Common/Exception.h>
+#include <Common/SignalHandlers.h>
+
+#include <Common/config_version.h>
+#include "config.h"
+
+#include <unordered_set>
+#include <string>
+#include <boost/algorithm/string/case_conv.hpp>
+#include <boost/algorithm/string/replace.hpp>
+#include <boost/algorithm/string/split.hpp>
+
+using namespace std::literals;
+
+namespace CurrentMetrics
+{
+    extern const Metric MemoryTracking;
+}
+
+namespace DB
+{
+
+namespace ErrorCodes
+{
+    extern const int BAD_ARGUMENTS;
+    extern const int CANNOT_SET_SIGNAL_HANDLER;
+}
+
+static ClientInfo::QueryKind parseQueryKind(const String & query_kind)
+{
+    if (query_kind == "initial_query")
+        return ClientInfo::QueryKind::INITIAL_QUERY;
+    if (query_kind == "secondary_query")
+        return ClientInfo::QueryKind::SECONDARY_QUERY;
+    if (query_kind == "no_query")
+        return ClientInfo::QueryKind::NO_QUERY;
+    throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unknown query kind {}", query_kind);
+}
+
+/// This signal handler is set only for SIGINT and SIGQUIT.
+void interruptSignalHandler(int signum)
+{
+    /// Signal handler might be called even before the setup is fully finished
+    /// and client application started to process the query.
+    /// Because of that we have to manually check it.
+    if (auto * instance = ClientApplicationBase::instanceRawPtr(); instance)
+        if (auto * base = dynamic_cast<ClientApplicationBase *>(instance); base)
+            if (base->tryStopQuery())
+                safeExit(128 + signum);
+}
+
+ClientApplicationBase::~ClientApplicationBase()
+{
+    try
+    {
+        writeSignalIDtoSignalPipe(SignalListener::StopThread);
+        signal_listener_thread.join();
+        HandledSignals::instance().reset();
+    }
+    catch (...)
+    {
+        tryLogCurrentException(__PRETTY_FUNCTION__);
+    }
+}
+
+ClientApplicationBase::ClientApplicationBase() : ClientBase(STDIN_FILENO, STDOUT_FILENO, STDERR_FILENO, std::cin, std::cout, std::cerr) {}
+
+ClientApplicationBase & ClientApplicationBase::getInstance()
+{
+    return dynamic_cast<ClientApplicationBase&>(Poco::Util::Application::instance());
+}
+
+void ClientApplicationBase::setupSignalHandler()
+{
+    ClientApplicationBase::getInstance().stopQuery();
+
+    struct sigaction new_act;
+    memset(&new_act, 0, sizeof(new_act));
+
+    new_act.sa_handler = interruptSignalHandler;
+    new_act.sa_flags = 0;
+
+#if defined(OS_DARWIN)
+    sigemptyset(&new_act.sa_mask);
+#else
+    if (sigemptyset(&new_act.sa_mask))
+        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
+#endif
+
+    if (sigaction(SIGINT, &new_act, nullptr))
+        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
+
+    if (sigaction(SIGQUIT, &new_act, nullptr))
+        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
+}
+
+void ClientApplicationBase::addMultiquery(std::string_view query, Arguments & common_arguments) const
+{
+    common_arguments.emplace_back("--multiquery");
+    common_arguments.emplace_back("-q");
+    common_arguments.emplace_back(query);
+}
+
+Poco::Util::LayeredConfiguration & ClientApplicationBase::getClientConfiguration()
+{
+    return config();
+}
+
+void ClientApplicationBase::init(int argc, char ** argv)
+{
+    namespace po = boost::program_options;
+
+    /// Don't parse options with Poco library, we prefer neat boost::program_options.
+    stopOptionsProcessing();
+
+    stdin_is_a_tty = isatty(STDIN_FILENO);
+    stdout_is_a_tty = isatty(STDOUT_FILENO);
+    stderr_is_a_tty = isatty(STDERR_FILENO);
+    terminal_width = getTerminalWidth();
+
+    std::vector<Arguments> external_tables_arguments;
+    Arguments common_arguments = {""}; /// 0th argument is ignored.
+    std::vector<Arguments> hosts_and_ports_arguments;
+
+    if (argc)
+        argv0 = argv[0];
+    readArguments(argc, argv, common_arguments, external_tables_arguments, hosts_and_ports_arguments);
+
+    /// Support for Unicode dashes
+    /// Interpret Unicode dashes as default double-hyphen
+    for (auto & arg : common_arguments)
+    {
+        // replace em-dash(U+2014)
+        boost::replace_all(arg, "—", "--");
+        // replace en-dash(U+2013)
+        boost::replace_all(arg, "–", "--");
+        // replace mathematical minus(U+2212)
+        boost::replace_all(arg, "−", "--");
+    }
+
+
+    OptionsDescription options_description;
+    options_description.main_description.emplace(createOptionsDescription("Main options", terminal_width));
+
+    /// Common options for clickhouse-client and clickhouse-local.
+    options_description.main_description->add_options()
+        ("help", "print usage summary, combine with --verbose to display all options")
+        ("verbose", "print query and other debugging info")
+        ("version,V", "print version information and exit")
+        ("version-clean", "print version in machine-readable format and exit")
+
+        ("config-file,C", po::value<std::string>(), "config-file path")
+
+        ("query,q", po::value<std::vector<std::string>>()->multitoken(), R"(Query. Can be specified multiple times (--query "SELECT 1" --query "SELECT 2") or once with multiple comma-separated queries (--query "SELECT 1; SELECT 2;"). In the latter case, INSERT queries with non-VALUE format must be separated by empty lines.)")
+        ("queries-file", po::value<std::vector<std::string>>()->multitoken(), "file path with queries to execute; multiple files can be specified (--queries-file file1 file2...)")
+        ("multiquery,n", "Obsolete, does nothing")
+        ("multiline,m", "If specified, allow multiline queries (do not send the query on Enter)")
+        ("database,d", po::value<std::string>(), "database")
+        ("query_kind", po::value<std::string>()->default_value("initial_query"), "One of initial_query/secondary_query/no_query")
+        ("query_id", po::value<std::string>(), "query_id")
+
+        ("history_file", po::value<std::string>(), "path to history file")
+
+        ("stage", po::value<std::string>()->default_value("complete"), "Request query processing up to specified stage: complete,fetch_columns,with_mergeable_state,with_mergeable_state_after_aggregation,with_mergeable_state_after_aggregation_and_limit")
+        ("progress", po::value<ProgressOption>()->implicit_value(ProgressOption::TTY, "tty")->default_value(ProgressOption::DEFAULT, "default"), "Print progress of queries execution - to TTY: tty|on|1|true|yes; to STDERR non-interactive mode: err; OFF: off|0|false|no; DEFAULT - interactive to TTY, non-interactive is off")
+
+        ("disable_suggestion,A", "Disable loading suggestion data. Note that suggestion data is loaded asynchronously through a second connection to ClickHouse server. Also it is reasonable to disable suggestion if you want to paste a query with TAB characters. Shorthand option -A is for those who get used to mysql client.")
+        ("wait_for_suggestions_to_load", "Load suggestion data synchonously.")
+        ("time,t", "print query execution time to stderr in non-interactive mode (for benchmarks)")
+        ("memory-usage", po::value<std::string>()->implicit_value("default")->default_value("none"), "print memory usage to stderr in non-interactive mode (for benchmarks). Values: 'none', 'default', 'readable'")
+
+        ("echo", "in batch mode, print query before execution")
+
+        ("log-level", po::value<std::string>(), "log level")
+        ("server_logs_file", po::value<std::string>(), "put server logs into specified file")
+
+        ("suggestion_limit", po::value<int>()->default_value(10000), "Suggestion limit for how many databases, tables and columns to fetch.")
+
+        ("format,f", po::value<std::string>(), "default output format (and input format for clickhouse-local)")
+        ("output-format", po::value<std::string>(), "default output format (this option has preference over --format)")
+
+        ("vertical,E", "vertical output format, same as --format=Vertical or FORMAT Vertical or \\G at end of command")
+        ("highlight", po::value<bool>()->default_value(true), "enable or disable basic syntax highlight in interactive command line")
+
+        ("ignore-error", "do not stop processing when an error occurs")
+        ("stacktrace", "print stack traces of exceptions")
+        ("hardware-utilization", "print hardware utilization information in progress bar")
+        ("print-profile-events", po::value(&profile_events.print)->zero_tokens(), "Printing ProfileEvents packets")
+        ("profile-events-delay-ms", po::value<UInt64>()->default_value(profile_events.delay_ms), "Delay between printing `ProfileEvents` packets (-1 - print only totals, 0 - print every single packet)")
+        ("processed-rows", "print the number of locally processed rows")
+
+        ("interactive", "Process queries-file or --query query and start interactive mode")
+        ("pager", po::value<std::string>(), "Pipe all output into this command (less or similar)")
+        ("max_memory_usage_in_client", po::value<std::string>(), "Set memory limit in client/local server")
+
+        ("fuzzer-args", po::value<std::string>(), "Command line arguments for the LLVM's libFuzzer driver. Only relevant if the application is compiled with libFuzzer.")
+
+        ("client_logs_file", po::value<std::string>(), "Path to a file for writing client logs. Currently we only have fatal logs (when the client crashes)")
+    ;
+
+    addOptions(options_description);
+
+    OptionsDescription options_description_non_verbose = options_description;
+
+    auto getter = [](const auto & op)
+    {
+        String op_long_name = op->long_name();
+        return "--" + String(op_long_name);
+    };
+
+    if (options_description.main_description)
+    {
+        const auto & main_options = options_description.main_description->options();
+        std::transform(main_options.begin(), main_options.end(), std::back_inserter(cmd_options), getter);
+    }
+
+    if (options_description.external_description)
+    {
+        const auto & external_options = options_description.external_description->options();
+        std::transform(external_options.begin(), external_options.end(), std::back_inserter(cmd_options), getter);
+    }
+
+    po::variables_map options;
+    parseAndCheckOptions(options_description, options, common_arguments);
+    po::notify(options);
+
+    if (options.count("version") || options.count("V"))
+    {
+        showClientVersion();
+        exit(0); // NOLINT(concurrency-mt-unsafe)
+    }
+
+    if (options.count("version-clean"))
+    {
+        output_stream << VERSION_STRING;
+        exit(0); // NOLINT(concurrency-mt-unsafe)
+    }
+
+    if (options.count("verbose"))
+        getClientConfiguration().setBool("verbose", true);
+
+    /// Output of help message.
+    if (options.count("help")
+        || (options.count("host") && options["host"].as<std::string>() == "elp")) /// If user writes -help instead of --help.
+    {
+        if (getClientConfiguration().getBool("verbose", false))
+            printHelpMessage(options_description, true);
+        else
+            printHelpMessage(options_description_non_verbose, false);
+        exit(0); // NOLINT(concurrency-mt-unsafe)
+    }
+
+    /// Common options for clickhouse-client and clickhouse-local.
+
+    /// Output execution time to stderr in batch mode.
+    if (options.count("time"))
+        getClientConfiguration().setBool("print-time-to-stderr", true);
+    if (options.count("memory-usage"))
+    {
+        const auto & memory_usage_mode = options["memory-usage"].as<std::string>();
+        if (memory_usage_mode != "none" && memory_usage_mode != "default" && memory_usage_mode != "readable")
+            throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unknown memory-usage mode: {}", memory_usage_mode);
+        getClientConfiguration().setString("print-memory-to-stderr", memory_usage_mode);
+    }
+
+    if (options.count("query"))
+        queries = options["query"].as<std::vector<std::string>>();
+    if (options.count("query_id"))
+        getClientConfiguration().setString("query_id", options["query_id"].as<std::string>());
+    if (options.count("database"))
+        getClientConfiguration().setString("database", options["database"].as<std::string>());
+    if (options.count("config-file"))
+        getClientConfiguration().setString("config-file", options["config-file"].as<std::string>());
+    if (options.count("queries-file"))
+        queries_files = options["queries-file"].as<std::vector<std::string>>();
+    if (options.count("multiline"))
+        getClientConfiguration().setBool("multiline", true);
+    if (options.count("ignore-error"))
+        getClientConfiguration().setBool("ignore-error", true);
+    if (options.count("format"))
+        getClientConfiguration().setString("format", options["format"].as<std::string>());
+    if (options.count("output-format"))
+        getClientConfiguration().setString("output-format", options["output-format"].as<std::string>());
+    if (options.count("vertical"))
+        getClientConfiguration().setBool("vertical", true);
+    if (options.count("stacktrace"))
+        getClientConfiguration().setBool("stacktrace", true);
+    if (options.count("print-profile-events"))
+        getClientConfiguration().setBool("print-profile-events", true);
+    if (options.count("profile-events-delay-ms"))
+        getClientConfiguration().setUInt64("profile-events-delay-ms", options["profile-events-delay-ms"].as<UInt64>());
+    /// Whether to print the number of processed rows at
+    if (options.count("processed-rows"))
+        getClientConfiguration().setBool("print-num-processed-rows", true);
+    if (options.count("progress"))
+    {
+        switch (options["progress"].as<ProgressOption>())
+        {
+            case DEFAULT:
+                getClientConfiguration().setString("progress", "default");
+                break;
+            case OFF:
+                getClientConfiguration().setString("progress", "off");
+                break;
+            case TTY:
+                getClientConfiguration().setString("progress", "tty");
+                break;
+            case ERR:
+                getClientConfiguration().setString("progress", "err");
+                break;
+        }
+    }
+    if (options.count("echo"))
+        getClientConfiguration().setBool("echo", true);
+    if (options.count("disable_suggestion"))
+        getClientConfiguration().setBool("disable_suggestion", true);
+    if (options.count("wait_for_suggestions_to_load"))
+        getClientConfiguration().setBool("wait_for_suggestions_to_load", true);
+    if (options.count("suggestion_limit"))
+        getClientConfiguration().setInt("suggestion_limit", options["suggestion_limit"].as<int>());
+    if (options.count("highlight"))
+        getClientConfiguration().setBool("highlight", options["highlight"].as<bool>());
+    if (options.count("history_file"))
+        getClientConfiguration().setString("history_file", options["history_file"].as<std::string>());
+    if (options.count("interactive"))
+        getClientConfiguration().setBool("interactive", true);
+    if (options.count("pager"))
+        getClientConfiguration().setString("pager", options["pager"].as<std::string>());
+
+    if (options.count("log-level"))
+        Poco::Logger::root().setLevel(options["log-level"].as<std::string>());
+    if (options.count("server_logs_file"))
+        server_logs_file = options["server_logs_file"].as<std::string>();
+
+    query_processing_stage = QueryProcessingStage::fromString(options["stage"].as<std::string>());
+    query_kind = parseQueryKind(options["query_kind"].as<std::string>());
+    profile_events.print = options.count("print-profile-events");
+    profile_events.delay_ms = options["profile-events-delay-ms"].as<UInt64>();
+
+    processOptions(options_description, options, external_tables_arguments, hosts_and_ports_arguments);
+    {
+        std::unordered_set<std::string> alias_names;
+        alias_names.reserve(options_description.main_description->options().size());
+        for (const auto& option : options_description.main_description->options())
+            alias_names.insert(option->long_name());
+        argsToConfig(common_arguments, getClientConfiguration(), 100, &alias_names);
+    }
+
+    clearPasswordFromCommandLine(argc, argv);
+
+    /// Limit on total memory usage
+    std::string max_client_memory_usage = getClientConfiguration().getString("max_memory_usage_in_client", "0" /*default value*/);
+    if (max_client_memory_usage != "0")
+    {
+        UInt64 max_client_memory_usage_int = parseWithSizeSuffix<UInt64>(max_client_memory_usage.c_str(), max_client_memory_usage.length());
+
+        total_memory_tracker.setHardLimit(max_client_memory_usage_int);
+        total_memory_tracker.setDescription("(total)");
+        total_memory_tracker.setMetric(CurrentMetrics::MemoryTracking);
+    }
+
+    /// Print stacktrace in case of crash
+    HandledSignals::instance().setupTerminateHandler();
+    HandledSignals::instance().setupCommonDeadlySignalHandlers();
+    /// We don't setup signal handlers for SIGINT, SIGQUIT, SIGTERM because we don't
+    /// have an option for client to shutdown gracefully.
+
+    fatal_channel_ptr = new Poco::SplitterChannel;
+    fatal_console_channel_ptr = new Poco::ConsoleChannel;
+    fatal_channel_ptr->addChannel(fatal_console_channel_ptr);
+    if (options.count("client_logs_file"))
+    {
+        fatal_file_channel_ptr = new Poco::SimpleFileChannel(options["client_logs_file"].as<std::string>());
+        fatal_channel_ptr->addChannel(fatal_file_channel_ptr);
+    }
+
+    fatal_log = createLogger("ClientBase", fatal_channel_ptr.get(), Poco::Message::PRIO_FATAL);
+    signal_listener = std::make_unique<SignalListener>(nullptr, fatal_log);
+    signal_listener_thread.start(*signal_listener);
+
+#if USE_GWP_ASAN
+    GWPAsan::initFinished();
+#endif
+
+}
+
+
+}

src/Client/ClientApplicationBase.h

@@ -0,0 +1,64 @@
+#pragma once
+
+
+#include <Poco/Util/Application.h>
+#include <Client/ClientBase.h>
+#include <Client/Suggest.h>
+#include <Common/NamePrompter.h>
+#include <Poco/ConsoleChannel.h>
+#include <Poco/SimpleFileChannel.h>
+#include <Poco/SplitterChannel.h>
+
+#include <boost/program_options.hpp>
+
+#include <vector>
+
+namespace po = boost::program_options;
+
+namespace DB
+{
+
+void interruptSignalHandler(int signum);
+
+/**
+ * The base class for client appliucations such as
+ * clickhouse-client or clickhouse-local.
+ * The main purpose and responsibility of it is dealing with
+ * application-specific stuff such as command line arguments parsing
+ * and setting up signal handlers, so queries will be cancelled after
+ * Ctrl+C is pressed.
+ */
+class ClientApplicationBase : public ClientBase, public Poco::Util::Application, public IHints<2>
+{
+public:
+    using ClientBase::processOptions;
+    using Arguments = ClientBase::Arguments;
+
+    static ClientApplicationBase & getInstance();
+
+    ClientApplicationBase();
+    ~ClientApplicationBase() override;
+
+    void init(int argc, char ** argv);
+    std::vector<String> getAllRegisteredNames() const override { return cmd_options; }
+
+protected:
+    Poco::Util::LayeredConfiguration & getClientConfiguration() override;
+    void setupSignalHandler() override;
+    void addMultiquery(std::string_view query, Arguments & common_arguments) const;
+
+private:
+    void parseAndCheckOptions(OptionsDescription & options_description, po::variables_map & options, Arguments & arguments);
+
+    std::vector<String> cmd_options;
+
+    LoggerPtr fatal_log;
+    Poco::AutoPtr<Poco::SplitterChannel> fatal_channel_ptr;
+    Poco::AutoPtr<Poco::Channel> fatal_console_channel_ptr;
+    Poco::AutoPtr<Poco::Channel> fatal_file_channel_ptr;
+    Poco::Thread signal_listener_thread;
+    std::unique_ptr<Poco::Runnable> signal_listener;
+};
+
+
+}

src/Client/ClientBase.cpp

@@ -5,7 +5,6 @@
 #include <Client/InternalTextLogs.h>
 #include <Client/TestTags.h>
 
-#include <base/argsToConfig.h>
 #include <base/safeExit.h>
 #include <Core/Block.h>
 #include <Core/BaseSettingsProgramOptions.h>
@@ -17,7 +16,6 @@
 #include <Common/getNumberOfPhysicalCPUCores.h>
 #include <Common/typeid_cast.h>
 #include <Common/TerminalSize.h>
-#include <Common/clearPasswordFromCommandLine.h>
 #include <Common/StringUtils.h>
 #include <Common/filesystemHelpers.h>
 #include <Common/NetException.h>
@@ -70,7 +68,6 @@
 
 #include <boost/algorithm/string/case_conv.hpp>
 #include <boost/algorithm/string/replace.hpp>
-#include <boost/algorithm/string/split.hpp>
 #include <iostream>
 #include <filesystem>
 #include <limits>
@@ -80,6 +77,8 @@
 
 #include <Common/config_version.h>
 #include "config.h"
+#include <IO/ReadHelpers.h>
+#include <Processors/Formats/Impl/ValuesBlockInputFormat.h>
 
 #if USE_GWP_ASAN
 #    include <Common/GWPAsan.h>
@@ -89,12 +88,6 @@
 namespace fs = std::filesystem;
 using namespace std::literals;
 
-
-namespace CurrentMetrics
-{
-    extern const Metric MemoryTracking;
-}
-
 namespace DB
 {
 
@@ -157,17 +150,6 @@ std::istream& operator>> (std::istream & in, ProgressOption & progress)
     return in;
 }
 
-static ClientInfo::QueryKind parseQueryKind(const String & query_kind)
-{
-    if (query_kind == "initial_query")
-        return ClientInfo::QueryKind::INITIAL_QUERY;
-    if (query_kind == "secondary_query")
-        return ClientInfo::QueryKind::SECONDARY_QUERY;
-    if (query_kind == "no_query")
-        return ClientInfo::QueryKind::NO_QUERY;
-    throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unknown query kind {}", query_kind);
-}
-
 static void incrementProfileEventsBlock(Block & dst, const Block & src)
 {
     if (!dst)
@@ -268,36 +250,6 @@ static void incrementProfileEventsBlock(Block & dst, const Block & src)
     dst.setColumns(std::move(mutable_columns));
 }
 
-
-std::atomic<Int32> exit_after_signals = 0;
-
-class QueryInterruptHandler : private boost::noncopyable
-{
-public:
-    /// Store how much interrupt signals can be before stopping the query
-    /// by default stop after the first interrupt signal.
-    static void start(Int32 signals_before_stop = 1) { exit_after_signals.store(signals_before_stop); }
-
-    /// Set value not greater then 0 to mark the query as stopped.
-    static void stop() { exit_after_signals.store(0); }
-
-    /// Return true if the query was stopped.
-    /// Query was stopped if it received at least "signals_before_stop" interrupt signals.
-    static bool try_stop() { return exit_after_signals.fetch_sub(1) <= 0; }
-    static bool cancelled() { return exit_after_signals.load() <= 0; }
-
-    /// Return how much interrupt signals remain before stop.
-    static Int32 cancelled_status() { return exit_after_signals.load(); }
-};
-
-/// This signal handler is set for SIGINT and SIGQUIT.
-void interruptSignalHandler(int signum)
-{
-    if (QueryInterruptHandler::try_stop())
-        safeExit(128 + signum);
-}
-
-
 /// To cancel the query on local format error.
 class LocalFormatError : public DB::Exception
 {
@@ -306,19 +258,7 @@ public:
 };
 
 
-ClientBase::~ClientBase()
+ClientBase::~ClientBase() = default;
-{
-    try
-    {
-        writeSignalIDtoSignalPipe(SignalListener::StopThread);
-        signal_listener_thread.join();
-        HandledSignals::instance().reset();
-    }
-    catch (...)
-    {
-        tryLogCurrentException(__PRETTY_FUNCTION__);
-    }
-}
 
 ClientBase::ClientBase(
     int in_fd_,
@@ -344,31 +284,6 @@ ClientBase::ClientBase(
     terminal_width = getTerminalWidth(in_fd, err_fd);
 }
 
-void ClientBase::setupSignalHandler()
-{
-    QueryInterruptHandler::stop();
-
-    struct sigaction new_act;
-    memset(&new_act, 0, sizeof(new_act));
-
-    new_act.sa_handler = interruptSignalHandler;
-    new_act.sa_flags = 0;
-
-#if defined(OS_DARWIN)
-    sigemptyset(&new_act.sa_mask);
-#else
-    if (sigemptyset(&new_act.sa_mask))
-        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
-#endif
-
-    if (sigaction(SIGINT, &new_act, nullptr))
-        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
-
-    if (sigaction(SIGQUIT, &new_act, nullptr))
-        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
-}
-
-
 ASTPtr ClientBase::parseQuery(const char *& pos, const char * end, const Settings & settings, bool allow_multi_statements)
 {
     std::unique_ptr<IParserBase> parser;
@@ -741,18 +656,10 @@ void ClientBase::initLogsOutputStream()
 
 void ClientBase::adjustSettings()
 {
-    Settings settings = global_context->getSettings();
+    Settings settings = global_context->getSettingsCopy();
 
     /// NOTE: Do not forget to set changed=false to avoid sending it to the server (to avoid breakage read only profiles)
 
-    /// In case of multi-query we allow data after semicolon since it will be
-    /// parsed by the client and interpreted as new query
-    if (is_multiquery && !global_context->getSettingsRef().input_format_values_allow_data_after_semicolon.changed)
-    {
-        settings.input_format_values_allow_data_after_semicolon = true;
-        settings.input_format_values_allow_data_after_semicolon.changed = false;
-    }
-
     /// Do not limit pretty format output in case of --pager specified or in case of stdout is not a tty.
     if (!pager.empty() || !stdout_is_a_tty)
     {
@@ -958,7 +865,7 @@ bool ClientBase::isSyncInsertWithData(const ASTInsertQuery & insert_query, const
     if (!insert_query.data)
         return false;
 
-    auto settings = context->getSettings();
+    auto settings = context->getSettingsCopy();
     if (insert_query.settings_ast)
         settings.applyChanges(insert_query.settings_ast->as<ASTSetQuery>()->changes);
 
@@ -1120,8 +1027,8 @@ void ClientBase::processOrdinaryQuery(const String & query_to_execute, ASTPtr pa
     {
         try
         {
-            QueryInterruptHandler::start(signals_before_stop);
+            query_interrupt_handler.start(signals_before_stop);
-            SCOPE_EXIT({ QueryInterruptHandler::stop(); });
+            SCOPE_EXIT({ query_interrupt_handler.stop(); });
 
             connection->sendQuery(
                 connection_parameters.timeouts,
@@ -1185,13 +1092,13 @@ void ClientBase::receiveResult(ASTPtr parsed_query, Int32 signals_before_stop, b
             /// to avoid losing sync.
             if (!cancelled)
             {
-                if (partial_result_on_first_cancel && QueryInterruptHandler::cancelled_status() == signals_before_stop - 1)
+                if (partial_result_on_first_cancel && query_interrupt_handler.cancelled_status() == signals_before_stop - 1)
                 {
                     connection->sendCancel();
                     /// First cancel reading request was sent. Next requests will only be with a full cancel
                     partial_result_on_first_cancel = false;
                 }
-                else if (QueryInterruptHandler::cancelled())
+                else if (query_interrupt_handler.cancelled())
                 {
                     cancelQuery();
                 }
@@ -1525,13 +1432,6 @@ void ClientBase::setInsertionTable(const ASTInsertQuery & insert_query)
 }
 
 
-void ClientBase::addMultiquery(std::string_view query, Arguments & common_arguments) const
-{
-    common_arguments.emplace_back("--multiquery");
-    common_arguments.emplace_back("-q");
-    common_arguments.emplace_back(query);
-}
-
 namespace
 {
 bool isStdinNotEmptyAndValid(ReadBufferFromFileDescriptor & std_in)
@@ -1577,8 +1477,8 @@ void ClientBase::processInsertQuery(const String & query_to_execute, ASTPtr pars
             return;
     }
 
-    QueryInterruptHandler::start();
+    query_interrupt_handler.start();
-    SCOPE_EXIT({ QueryInterruptHandler::stop(); });
+    SCOPE_EXIT({ query_interrupt_handler.stop(); });
 
     connection->sendQuery(
         connection_parameters.timeouts,
@@ -1789,7 +1689,7 @@ try
     Block block;
     while (executor.pull(block))
     {
-        if (!cancelled && QueryInterruptHandler::cancelled())
+        if (!cancelled && query_interrupt_handler.cancelled())
         {
             cancelQuery();
             executor.cancel();
@@ -2186,23 +2086,48 @@ MultiQueryProcessingStage ClientBase::analyzeMultiQueryText(
         return MultiQueryProcessingStage::PARSING_FAILED;
     }
 
-    // INSERT queries may have the inserted data in the query text
+    // INSERT queries may have the inserted data in the query text that follow the query itself, e.g. "insert into t format CSV 1,2". They
-    // that follow the query itself, e.g. "insert into t format CSV 1;2".
+    // need special handling.
-    // They need special handling. First of all, here we find where the
+    // - If the INSERT statement FORMAT is VALUES, we use the VALUES format parser to skip the inserted data until we reach the trailing single semicolon.
-    // inserted data ends. In multi-query mode, it is delimited by a
+    // - Other formats (e.g. FORMAT CSV) are arbitrarily more complex and tricky to parse. For example, we may be unable to distinguish if the semicolon
-    // newline.
+    //   is part of the data or ends the statement. In this case, we simply assume that the end of the INSERT statement is determined by \n\n (two newlines).
-    // The VALUES format needs even more handling - we also allow the
-    // data to be delimited by semicolon. This case is handled later by
-    // the format parser itself.
-    // We can't do multiline INSERTs with inline data, because most
-    // row input formats (e.g. TSV) can't tell when the input stops,
-    // unlike VALUES.
     auto * insert_ast = parsed_query->as<ASTInsertQuery>();
     const char * query_to_execute_end = this_query_end;
-
     if (insert_ast && insert_ast->data)
     {
-        this_query_end = find_first_symbols<'\n'>(insert_ast->data, all_queries_end);
+        if (insert_ast->format == "Values")
+        {
+            // Invoke the VALUES format parser to skip the inserted data
+            ReadBufferFromMemory data_in(insert_ast->data, all_queries_end - insert_ast->data);
+            skipBOMIfExists(data_in);
+            do
+            {
+                skipWhitespaceIfAny(data_in);
+                if (data_in.eof() || *data_in.position() == ';')
+                    break;
+            }
+            while (ValuesBlockInputFormat::skipToNextRow(&data_in, 1, 0));
+            // Handle the case of a comment followed by a semicolon
+            //   Example: INSERT INTO tab VALUES xx; -- {serverError xx}
+            // If we use this error hint, the next query should not be placed on the same line
+            this_query_end = insert_ast->data + data_in.count();
+            const auto * pos_newline = find_first_symbols<'\n'>(this_query_end, all_queries_end);
+            if (pos_newline != this_query_end)
+            {
+                TestHint hint(String(this_query_end, pos_newline - this_query_end));
+                if (hint.hasClientErrors() || hint.hasServerErrors())
+                    this_query_end = pos_newline;
+            }
+        }
+        else
+        {
+            // Handling of generic formats
+            auto pos_newline = String(insert_ast->data, all_queries_end).find("\n\n");
+            if (pos_newline != std::string::npos)
+                this_query_end = insert_ast->data + pos_newline;
+            else
+                this_query_end = all_queries_end;
+        }
         insert_ast->end = this_query_end;
         query_to_execute_end = isSyncInsertWithData(*insert_ast, client_context) ? insert_ast->data : this_query_end;
     }
@@ -2237,7 +2162,10 @@ bool ClientBase::executeMultiQuery(const String & all_queries_text)
     size_t test_tags_length = getTestTagsLength(all_queries_text);
 
     /// Several queries separated by ';'.
-    /// INSERT data is ended by the end of line, not ';'.
+    /// INSERT data is ended by the empty line (\n\n), not ';'.
+    /// Unnecessary semicolons may cause data to be parsed containing ';'
+    /// e.g. 'insert into xx format csv val;' will insert "val;" instead of "val"
+    ///      'insert into xx format csv val\n;' will insert "val" and ";"
     /// An exception is VALUES format where we also support semicolon in
     /// addition to end of line.
     const char * this_query_begin = all_queries_text.data() + test_tags_length;
@@ -2248,8 +2176,8 @@ bool ClientBase::executeMultiQuery(const String & all_queries_text)
     String query_to_execute;
     ASTPtr parsed_query;
     std::unique_ptr<Exception> current_exception;
-
     size_t retries_count = 0;
+    bool is_first = true;
 
     while (true)
     {
@@ -2258,16 +2186,24 @@ bool ClientBase::executeMultiQuery(const String & all_queries_text)
         switch (stage)
         {
             case MultiQueryProcessingStage::QUERIES_END:
+            {
+                /// Compatible with old version when run interactive, e.g. "", "\ld"
+                if (is_first && is_interactive)
+                    processTextAsSingleQuery(all_queries_text);
+                return true;
+            }
             case MultiQueryProcessingStage::PARSING_FAILED:
             {
                 return true;
             }
             case MultiQueryProcessingStage::CONTINUE_PARSING:
             {
+                is_first = false;
                 continue;
             }
             case MultiQueryProcessingStage::PARSING_EXCEPTION:
             {
+                is_first = false;
                 this_query_end = find_first_symbols<'\n'>(this_query_end, all_queries_end);
 
                 // Try to find test hint for syntax error. We don't know where
@@ -2297,6 +2233,7 @@ bool ClientBase::executeMultiQuery(const String & all_queries_text)
             }
             case MultiQueryProcessingStage::EXECUTE_QUERY:
             {
+                is_first = false;
                 full_query = all_queries_text.substr(this_query_begin - all_queries_text.data(), this_query_end - this_query_begin);
                 if (query_fuzzer_runs)
                 {
@@ -2306,6 +2243,8 @@ bool ClientBase::executeMultiQuery(const String & all_queries_text)
                     this_query_begin = this_query_end;
                     continue;
                 }
+                if (suggest)
+                    updateSuggest(parsed_query);
 
                 // Now we know for sure where the query ends.
                 // Look for the hint in the text of query + insert data + trailing
@@ -2456,14 +2395,6 @@ bool ClientBase::processQueryText(const String & text)
         return processMultiQueryFromFile(file_name);
     }
 
-    if (!is_multiquery)
-    {
-        assert(!query_fuzzer_runs);
-        processTextAsSingleQuery(text);
-
-        return true;
-    }
-
     if (query_fuzzer_runs)
     {
         processWithFuzzing(text);
@@ -2740,7 +2671,7 @@ bool ClientBase::processMultiQueryFromFile(const String & file_name)
 
     if (!getClientConfiguration().has("log_comment"))
     {
-        Settings settings = client_context->getSettings();
+        Settings settings = client_context->getSettingsCopy();
         /// NOTE: cannot use even weakly_canonical() since it fails for /dev/stdin due to resolving of "pipe:[X]"
         settings.log_comment = fs::absolute(fs::path(file_name));
         client_context->setSettings(settings);
@@ -2840,7 +2771,6 @@ void ClientBase::runLibFuzzer()
 void ClientBase::runLibFuzzer() {}
 #endif
 
-
 void ClientBase::clearTerminal()
 {
     /// Clear from cursor until end of screen.
@@ -2850,290 +2780,9 @@ void ClientBase::clearTerminal()
     output_stream << "\033[0J" "\033[?25h";
 }
 
-
 void ClientBase::showClientVersion()
 {
     output_stream << VERSION_NAME << " " + getName() + " version " << VERSION_STRING << VERSION_OFFICIAL << "." << std::endl;
 }
 
-void ClientBase::init(int argc, char ** argv)
-{
-    namespace po = boost::program_options;
-
-    /// Don't parse options with Poco library, we prefer neat boost::program_options.
-    stopOptionsProcessing();
-
-    stdin_is_a_tty = isatty(STDIN_FILENO);
-    stdout_is_a_tty = isatty(STDOUT_FILENO);
-    stderr_is_a_tty = isatty(STDERR_FILENO);
-    terminal_width = getTerminalWidth();
-
-    std::vector<Arguments> external_tables_arguments;
-    Arguments common_arguments = {""}; /// 0th argument is ignored.
-    std::vector<Arguments> hosts_and_ports_arguments;
-
-    if (argc)
-        argv0 = argv[0];
-    readArguments(argc, argv, common_arguments, external_tables_arguments, hosts_and_ports_arguments);
-
-    /// Support for Unicode dashes
-    /// Interpret Unicode dashes as default double-hyphen
-    for (auto & arg : common_arguments)
-    {
-        // replace em-dash(U+2014)
-        boost::replace_all(arg, "—", "--");
-        // replace en-dash(U+2013)
-        boost::replace_all(arg, "–", "--");
-        // replace mathematical minus(U+2212)
-        boost::replace_all(arg, "−", "--");
-    }
-
-
-    OptionsDescription options_description;
-    options_description.main_description.emplace(createOptionsDescription("Main options", terminal_width));
-
-    /// Common options for clickhouse-client and clickhouse-local.
-    options_description.main_description->add_options()
-        ("help", "print usage summary, combine with --verbose to display all options")
-        ("verbose", "print query and other debugging info")
-        ("version,V", "print version information and exit")
-        ("version-clean", "print version in machine-readable format and exit")
-
-        ("config-file,C", po::value<std::string>(), "config-file path")
-
-        ("query,q", po::value<std::vector<std::string>>()->multitoken(), R"(query; can be specified multiple times (--query "SELECT 1" --query "SELECT 2"...))")
-        ("queries-file", po::value<std::vector<std::string>>()->multitoken(), "file path with queries to execute; multiple files can be specified (--queries-file file1 file2...)")
-        ("multiquery,n", "If specified, multiple queries separated by semicolons can be listed after --query. For convenience, it is also possible to omit --query and pass the queries directly after --multiquery.")
-        ("multiline,m", "If specified, allow multiline queries (do not send the query on Enter)")
-        ("database,d", po::value<std::string>(), "database")
-        ("query_kind", po::value<std::string>()->default_value("initial_query"), "One of initial_query/secondary_query/no_query")
-        ("query_id", po::value<std::string>(), "query_id")
-
-        ("history_file", po::value<std::string>(), "path to history file")
-
-        ("stage", po::value<std::string>()->default_value("complete"), "Request query processing up to specified stage: complete,fetch_columns,with_mergeable_state,with_mergeable_state_after_aggregation,with_mergeable_state_after_aggregation_and_limit")
-        ("progress", po::value<ProgressOption>()->implicit_value(ProgressOption::TTY, "tty")->default_value(ProgressOption::DEFAULT, "default"), "Print progress of queries execution - to TTY: tty|on|1|true|yes; to STDERR non-interactive mode: err; OFF: off|0|false|no; DEFAULT - interactive to TTY, non-interactive is off")
-
-        ("disable_suggestion,A", "Disable loading suggestion data. Note that suggestion data is loaded asynchronously through a second connection to ClickHouse server. Also it is reasonable to disable suggestion if you want to paste a query with TAB characters. Shorthand option -A is for those who get used to mysql client.")
-        ("wait_for_suggestions_to_load", "Load suggestion data synchonously.")
-        ("time,t", "print query execution time to stderr in non-interactive mode (for benchmarks)")
-        ("memory-usage", po::value<std::string>()->implicit_value("default")->default_value("none"), "print memory usage to stderr in non-interactive mode (for benchmarks). Values: 'none', 'default', 'readable'")
-
-        ("echo", "in batch mode, print query before execution")
-
-        ("log-level", po::value<std::string>(), "log level")
-        ("server_logs_file", po::value<std::string>(), "put server logs into specified file")
-
-        ("suggestion_limit", po::value<int>()->default_value(10000), "Suggestion limit for how many databases, tables and columns to fetch.")
-
-        ("format,f", po::value<std::string>(), "default output format (and input format for clickhouse-local)")
-        ("output-format", po::value<std::string>(), "default output format (this option has preference over --format)")
-
-        ("vertical,E", "vertical output format, same as --format=Vertical or FORMAT Vertical or \\G at end of command")
-        ("highlight", po::value<bool>()->default_value(true), "enable or disable basic syntax highlight in interactive command line")
-
-        ("ignore-error", "do not stop processing in multiquery mode")
-        ("stacktrace", "print stack traces of exceptions")
-        ("hardware-utilization", "print hardware utilization information in progress bar")
-        ("print-profile-events", po::value(&profile_events.print)->zero_tokens(), "Printing ProfileEvents packets")
-        ("profile-events-delay-ms", po::value<UInt64>()->default_value(profile_events.delay_ms), "Delay between printing `ProfileEvents` packets (-1 - print only totals, 0 - print every single packet)")
-        ("processed-rows", "print the number of locally processed rows")
-
-        ("interactive", "Process queries-file or --query query and start interactive mode")
-        ("pager", po::value<std::string>(), "Pipe all output into this command (less or similar)")
-        ("max_memory_usage_in_client", po::value<std::string>(), "Set memory limit in client/local server")
-
-        ("fuzzer-args", po::value<std::string>(), "Command line arguments for the LLVM's libFuzzer driver. Only relevant if the application is compiled with libFuzzer.")
-
-        ("client_logs_file", po::value<std::string>(), "Path to a file for writing client logs. Currently we only have fatal logs (when the client crashes)")
-    ;
-
-    addOptions(options_description);
-
-    OptionsDescription options_description_non_verbose = options_description;
-
-    auto getter = [](const auto & op)
-    {
-        String op_long_name = op->long_name();
-        return "--" + String(op_long_name);
-    };
-
-    if (options_description.main_description)
-    {
-        const auto & main_options = options_description.main_description->options();
-        std::transform(main_options.begin(), main_options.end(), std::back_inserter(cmd_options), getter);
-    }
-
-    if (options_description.external_description)
-    {
-        const auto & external_options = options_description.external_description->options();
-        std::transform(external_options.begin(), external_options.end(), std::back_inserter(cmd_options), getter);
-    }
-
-    po::variables_map options;
-    parseAndCheckOptions(options_description, options, common_arguments);
-    po::notify(options);
-
-    if (options.count("version") || options.count("V"))
-    {
-        showClientVersion();
-        exit(0); // NOLINT(concurrency-mt-unsafe)
-    }
-
-    if (options.count("version-clean"))
-    {
-        output_stream << VERSION_STRING;
-        exit(0); // NOLINT(concurrency-mt-unsafe)
-    }
-
-    if (options.count("verbose"))
-        getClientConfiguration().setBool("verbose", true);
-
-    /// Output of help message.
-    if (options.count("help")
-        || (options.count("host") && options["host"].as<std::string>() == "elp")) /// If user writes -help instead of --help.
-    {
-        if (getClientConfiguration().getBool("verbose", false))
-            printHelpMessage(options_description, true);
-        else
-            printHelpMessage(options_description_non_verbose, false);
-        exit(0); // NOLINT(concurrency-mt-unsafe)
-    }
-
-    /// Common options for clickhouse-client and clickhouse-local.
-
-    /// Output execution time to stderr in batch mode.
-    if (options.count("time"))
-        getClientConfiguration().setBool("print-time-to-stderr", true);
-    if (options.count("memory-usage"))
-    {
-        const auto & memory_usage_mode = options["memory-usage"].as<std::string>();
-        if (memory_usage_mode != "none" && memory_usage_mode != "default" && memory_usage_mode != "readable")
-            throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unknown memory-usage mode: {}", memory_usage_mode);
-        getClientConfiguration().setString("print-memory-to-stderr", memory_usage_mode);
-    }
-
-    if (options.count("query"))
-        queries = options["query"].as<std::vector<std::string>>();
-    if (options.count("query_id"))
-        getClientConfiguration().setString("query_id", options["query_id"].as<std::string>());
-    if (options.count("database"))
-        getClientConfiguration().setString("database", options["database"].as<std::string>());
-    if (options.count("config-file"))
-        getClientConfiguration().setString("config-file", options["config-file"].as<std::string>());
-    if (options.count("queries-file"))
-        queries_files = options["queries-file"].as<std::vector<std::string>>();
-    if (options.count("multiline"))
-        getClientConfiguration().setBool("multiline", true);
-    if (options.count("multiquery"))
-        getClientConfiguration().setBool("multiquery", true);
-    if (options.count("ignore-error"))
-        getClientConfiguration().setBool("ignore-error", true);
-    if (options.count("format"))
-        getClientConfiguration().setString("format", options["format"].as<std::string>());
-    if (options.count("output-format"))
-        getClientConfiguration().setString("output-format", options["output-format"].as<std::string>());
-    if (options.count("vertical"))
-        getClientConfiguration().setBool("vertical", true);
-    if (options.count("stacktrace"))
-        getClientConfiguration().setBool("stacktrace", true);
-    if (options.count("print-profile-events"))
-        getClientConfiguration().setBool("print-profile-events", true);
-    if (options.count("profile-events-delay-ms"))
-        getClientConfiguration().setUInt64("profile-events-delay-ms", options["profile-events-delay-ms"].as<UInt64>());
-    /// Whether to print the number of processed rows at
-    if (options.count("processed-rows"))
-        getClientConfiguration().setBool("print-num-processed-rows", true);
-    if (options.count("progress"))
-    {
-        switch (options["progress"].as<ProgressOption>())
-        {
-            case DEFAULT:
-                getClientConfiguration().setString("progress", "default");
-                break;
-            case OFF:
-                getClientConfiguration().setString("progress", "off");
-                break;
-            case TTY:
-                getClientConfiguration().setString("progress", "tty");
-                break;
-            case ERR:
-                getClientConfiguration().setString("progress", "err");
-                break;
-        }
-    }
-    if (options.count("echo"))
-        getClientConfiguration().setBool("echo", true);
-    if (options.count("disable_suggestion"))
-        getClientConfiguration().setBool("disable_suggestion", true);
-    if (options.count("wait_for_suggestions_to_load"))
-        getClientConfiguration().setBool("wait_for_suggestions_to_load", true);
-    if (options.count("suggestion_limit"))
-        getClientConfiguration().setInt("suggestion_limit", options["suggestion_limit"].as<int>());
-    if (options.count("highlight"))
-        getClientConfiguration().setBool("highlight", options["highlight"].as<bool>());
-    if (options.count("history_file"))
-        getClientConfiguration().setString("history_file", options["history_file"].as<std::string>());
-    if (options.count("interactive"))
-        getClientConfiguration().setBool("interactive", true);
-    if (options.count("pager"))
-        getClientConfiguration().setString("pager", options["pager"].as<std::string>());
-
-    if (options.count("log-level"))
-        Poco::Logger::root().setLevel(options["log-level"].as<std::string>());
-    if (options.count("server_logs_file"))
-        server_logs_file = options["server_logs_file"].as<std::string>();
-
-    query_processing_stage = QueryProcessingStage::fromString(options["stage"].as<std::string>());
-    query_kind = parseQueryKind(options["query_kind"].as<std::string>());
-    profile_events.print = options.count("print-profile-events");
-    profile_events.delay_ms = options["profile-events-delay-ms"].as<UInt64>();
-
-    processOptions(options_description, options, external_tables_arguments, hosts_and_ports_arguments);
-    {
-        std::unordered_set<std::string> alias_names;
-        alias_names.reserve(options_description.main_description->options().size());
-        for (const auto& option : options_description.main_description->options())
-            alias_names.insert(option->long_name());
-        argsToConfig(common_arguments, getClientConfiguration(), 100, &alias_names);
-    }
-
-    clearPasswordFromCommandLine(argc, argv);
-
-    /// Limit on total memory usage
-    std::string max_client_memory_usage = getClientConfiguration().getString("max_memory_usage_in_client", "0" /*default value*/);
-    if (max_client_memory_usage != "0")
-    {
-        UInt64 max_client_memory_usage_int = parseWithSizeSuffix<UInt64>(max_client_memory_usage.c_str(), max_client_memory_usage.length());
-
-        total_memory_tracker.setHardLimit(max_client_memory_usage_int);
-        total_memory_tracker.setDescription("(total)");
-        total_memory_tracker.setMetric(CurrentMetrics::MemoryTracking);
-    }
-
-    /// Print stacktrace in case of crash
-    HandledSignals::instance().setupTerminateHandler();
-    HandledSignals::instance().setupCommonDeadlySignalHandlers();
-    /// We don't setup signal handlers for SIGINT, SIGQUIT, SIGTERM because we don't
-    /// have an option for client to shutdown gracefully.
-
-    fatal_channel_ptr = new Poco::SplitterChannel;
-    fatal_console_channel_ptr = new Poco::ConsoleChannel;
-    fatal_channel_ptr->addChannel(fatal_console_channel_ptr);
-    if (options.count("client_logs_file"))
-    {
-        fatal_file_channel_ptr = new Poco::SimpleFileChannel(options["client_logs_file"].as<std::string>());
-        fatal_channel_ptr->addChannel(fatal_file_channel_ptr);
-    }
-
-    fatal_log = createLogger("ClientBase", fatal_channel_ptr.get(), Poco::Message::PRIO_FATAL);
-    signal_listener = std::make_unique<SignalListener>(nullptr, fatal_log);
-    signal_listener_thread.start(*signal_listener);
-
-#if USE_GWP_ASAN
-    GWPAsan::initFinished();
-#endif
-
-}
-
 }

src/Client/ClientBase.h

@@ -1,26 +1,32 @@
 #pragma once
 
-#include <string_view>
+
-#include "Common/NamePrompter.h"
+#include <Client/Suggest.h>
-#include <Parsers/ASTCreateQuery.h>
+#include <Client/QueryFuzzer.h>
-#include <Common/ProgressIndication.h>
+#include <Common/DNSResolver.h>
 #include <Common/InterruptListener.h>
+#include <Common/ProgressIndication.h>
 #include <Common/ShellCommand.h>
 #include <Common/Stopwatch.h>
-#include <Common/DNSResolver.h>
 #include <Core/ExternalTable.h>
 #include <Core/Settings.h>
-#include <Poco/Util/Application.h>
 #include <Poco/ConsoleChannel.h>
 #include <Poco/SimpleFileChannel.h>
 #include <Poco/SplitterChannel.h>
 #include <Interpreters/Context.h>
-#include <Client/Suggest.h>
+#include <Parsers/ASTCreateQuery.h>
-#include <Client/QueryFuzzer.h>
+#include <Poco/Util/Application.h>
-#include <boost/program_options.hpp>
+
-#include <Storages/StorageFile.h>
-#include <Storages/SelectQueryInfo.h>
 #include <Storages/MergeTree/MergeTreeSettings.h>
+#include <Storages/SelectQueryInfo.h>
+#include <Storages/StorageFile.h>
+
+#include <boost/program_options.hpp>
+
+#include <atomic>
+#include <optional>
+#include <string_view>
+#include <string>
 
 namespace po = boost::program_options;
 
@@ -64,9 +70,16 @@ std::istream& operator>> (std::istream & in, ProgressOption & progress);
 class InternalTextLogs;
 class WriteBufferFromFileDescriptor;
 
-class ClientBase : public Poco::Util::Application, public IHints<2>
+/**
+ * The base class which encapsulates the core functionality of a client.
+ * Can be used in a standalone application (clickhouse-client or clickhouse-local),
+ * or be embedded into server.
+ * Always keep in mind that there can be several instances of this class within
+ * a process. Thus, it cannot keep its state in global shared variables or even use them.
+ * The best example - std::cin, std::cout and std::cerr.
+ */
+class ClientBase
 {
-
 public:
     using Arguments = std::vector<String>;
 
@@ -79,12 +92,11 @@ public:
         std::ostream & output_stream_ = std::cout,
         std::ostream & error_stream_ = std::cerr
     );
+    virtual ~ClientBase();
 
-    ~ClientBase() override;
+    bool tryStopQuery() { return query_interrupt_handler.tryStop(); }
+    void stopQuery() { query_interrupt_handler.stop(); }
 
-    void init(int argc, char ** argv);
-
-    std::vector<String> getAllRegisteredNames() const override { return cmd_options; }
     ASTPtr parseQuery(const char *& pos, const char * end, const Settings & settings, bool allow_multi_statements);
 
 protected:
@@ -114,7 +126,7 @@ protected:
         ASTPtr parsed_query, std::optional<bool> echo_query_ = {}, bool report_error = false);
 
     static void adjustQueryEnd(const char *& this_query_end, const char * all_queries_end, uint32_t max_parser_depth, uint32_t max_parser_backtracks);
-    static void setupSignalHandler();
+    virtual void setupSignalHandler() = 0;
 
     bool executeMultiQuery(const String & all_queries_text);
     MultiQueryProcessingStage analyzeMultiQueryText(
@@ -156,8 +168,6 @@ protected:
 
     void setInsertionTable(const ASTInsertQuery & insert_query);
 
-    void addMultiquery(std::string_view query, Arguments & common_arguments) const;
-
 private:
     void receiveResult(ASTPtr parsed_query, Int32 signals_before_stop, bool partial_result_on_first_cancel);
     bool receiveAndProcessPacket(ASTPtr parsed_query, bool cancelled_);
@@ -190,7 +200,6 @@ private:
     String prompt() const;
 
     void resetOutput();
-    void parseAndCheckOptions(OptionsDescription & options_description, po::variables_map & options, Arguments & arguments);
 
     void updateSuggest(const ASTPtr & ast);
 
@@ -198,6 +207,31 @@ private:
     bool addMergeTreeSettings(ASTCreateQuery & ast_create);
 
 protected:
+
+    class QueryInterruptHandler : private boost::noncopyable
+    {
+    public:
+        /// Store how much interrupt signals can be before stopping the query
+        /// by default stop after the first interrupt signal.
+        void start(Int32 signals_before_stop = 1) { exit_after_signals.store(signals_before_stop); }
+
+        /// Set value not greater then 0 to mark the query as stopped.
+        void stop() { exit_after_signals.store(0); }
+
+        /// Return true if the query was stopped.
+        /// Query was stopped if it received at least "signals_before_stop" interrupt signals.
+        bool tryStop() { return exit_after_signals.fetch_sub(1) <= 0; }
+        bool cancelled() { return exit_after_signals.load() <= 0; }
+
+        /// Return how much interrupt signals remain before stop.
+        Int32 cancelled_status() { return exit_after_signals.load(); }
+
+    private:
+        std::atomic<Int32> exit_after_signals = 0;
+    };
+
+    QueryInterruptHandler query_interrupt_handler;
+
     static bool isSyncInsertWithData(const ASTInsertQuery & insert_query, const ContextPtr & context);
     bool processMultiQueryFromFile(const String & file_name);
 
@@ -221,15 +255,7 @@ protected:
     /// Client context is a context used only by the client to parse queries, process query parameters and to connect to clickhouse-server.
     ContextMutablePtr client_context;
 
-    LoggerPtr fatal_log;
-    Poco::AutoPtr<Poco::SplitterChannel> fatal_channel_ptr;
-    Poco::AutoPtr<Poco::Channel> fatal_console_channel_ptr;
-    Poco::AutoPtr<Poco::Channel> fatal_file_channel_ptr;
-    Poco::Thread signal_listener_thread;
-    std::unique_ptr<Poco::Runnable> signal_listener;
-
     bool is_interactive = false; /// Use either interactive line editing interface or batch mode.
-    bool is_multiquery = false;
     bool delayed_interactive = false;
 
     bool echo_queries = false; /// Print queries before execution in batch mode.
@@ -242,7 +268,6 @@ protected:
     std::vector<String> queries; /// Queries passed via '--query'
     std::vector<String> queries_files; /// If not empty, queries will be read from these files
     std::vector<String> interleave_queries_files; /// If not empty, run queries from these files before processing every file from 'queries_files'.
-    std::vector<String> cmd_options;
 
     bool stdin_is_a_tty = false; /// stdin is a terminal.
     bool stdout_is_a_tty = false; /// stdout is a terminal.

src/Client/ClientBaseOptimizedParts.cpp

@@ -1,4 +1,4 @@
-#include <Client/ClientBase.h>
+#include <Client/ClientApplicationBase.h>
 #include <Core/BaseSettingsProgramOptions.h>
 
 namespace DB
@@ -80,7 +80,7 @@ private:
 
 }
 
-void ClientBase::parseAndCheckOptions(OptionsDescription & options_description, po::variables_map & options, Arguments & arguments)
+void ClientApplicationBase::parseAndCheckOptions(OptionsDescription & options_description, po::variables_map & options, Arguments & arguments)
 {
     if (allow_repeated_settings)
         addProgramOptionsAsMultitokens(cmd_settings, options_description.main_description.value());

src/Client/ConnectionPoolWithFailover.h

@@ -42,6 +42,7 @@ public:
             size_t max_error_cap = DBMS_CONNECTION_POOL_WITH_FAILOVER_MAX_ERROR_COUNT);
 
     using Entry = IConnectionPool::Entry;
+    using PoolWithFailoverBase<IConnectionPool>::isTryResultInvalid;
 
     /** Allocates connection to work. */
     Entry get(const ConnectionTimeouts & timeouts) override;

src/Columns/ColumnFunction.cpp

@@ -296,11 +296,22 @@ ColumnWithTypeAndName ColumnFunction::reduce() const
                         function->getName(), toString(args), toString(captured));
 
     ColumnsWithTypeAndName columns = captured_columns;
-    IFunction::ShortCircuitSettings settings;
     /// Arguments of lazy executed function can also be lazy executed.
-    /// But we shouldn't execute arguments if this function is short circuit,
+    if (is_short_circuit_argument)
+    {
+        IFunction::ShortCircuitSettings settings;
+        /// We shouldn't execute all arguments if this function is short circuit,
         /// because it will handle lazy executed arguments by itself.
-    if (is_short_circuit_argument && !function->isShortCircuit(settings, args))
+        /// Execute only arguments with disabled lazy execution.
+        if (function->isShortCircuit(settings, args))
+        {
+            for (size_t i : settings.arguments_with_disabled_lazy_execution)
+            {
+                if (const ColumnFunction * arg = checkAndGetShortCircuitArgument(columns[i].column))
+                    columns[i] = arg->reduce();
+            }
+        }
+        else
         {
             for (auto & col : columns)
             {
@@ -308,6 +319,7 @@ ColumnWithTypeAndName ColumnFunction::reduce() const
                     col = arg->reduce();
             }
         }
+    }
 
     ColumnWithTypeAndName res{nullptr, function->getResultType(), ""};
 

src/Common/Dwarf.cpp

@@ -1559,8 +1559,7 @@ bool Dwarf::isAddrInRangeList(const CompilationUnit & cu,
                     auto sp_start = addr_.substr(*cu.addr_base + index_start * sizeof(uint64_t));
                     auto start = read<uint64_t>(sp_start);
 
-                    auto sp_end = addr_.substr(*cu.addr_base + index_start * sizeof(uint64_t) + length);
+                    auto end = start + length;
-                    auto end = read<uint64_t>(sp_end);
                     if (start != end && address >= start && address < end)
                     {
                         return true;

src/Common/PoolWithFailoverBase.h

@@ -116,6 +116,12 @@ public:
             const TryGetEntryFunc & try_get_entry,
             const GetPriorityFunc & get_priority);
 
+    // Returns if the TryResult provided is an invalid one that cannot be used. Used to prevent logical errors.
+    bool isTryResultInvalid(const TryResult & result, bool skip_read_only_replicas) const
+    {
+        return result.entry.isNull() || !result.is_usable || (skip_read_only_replicas && result.is_readonly);
+    }
+
     size_t getPoolSize() const { return nested_pools.size(); }
 
 protected:
@@ -300,7 +306,7 @@ PoolWithFailoverBase<TNestedPool>::getMany(
         throw DB::NetException(DB::ErrorCodes::ALL_CONNECTION_TRIES_FAILED,
                 "All connection tries failed. Log: \n\n{}\n", fail_messages);
 
-    std::erase_if(try_results, [&](const TryResult & r) { return r.entry.isNull() || !r.is_usable || (skip_read_only_replicas && r.is_readonly); });
+    std::erase_if(try_results, [&](const TryResult & r) { return isTryResultInvalid(r, skip_read_only_replicas); });
 
     /// Sort so that preferred items are near the beginning.
     std::stable_sort(
@@ -321,6 +327,9 @@ PoolWithFailoverBase<TNestedPool>::getMany(
     }
     else if (up_to_date_count >= min_entries)
     {
+        if (try_results.size() < up_to_date_count)
+            throw DB::Exception(DB::ErrorCodes::LOGICAL_ERROR, "Could not find enough connections for up-to-date results. Got: {}, needed: {}", try_results.size(), up_to_date_count);
+
         /// There is enough up-to-date entries.
         try_results.resize(up_to_date_count);
     }

src/Common/SharedMutex.cpp

@@ -1,4 +1,5 @@
 #include <Common/SharedMutex.h>
+#include <base/getThreadId.h>
 
 #ifdef OS_LINUX /// Because of futex
 
@@ -12,6 +13,7 @@ namespace DB
 SharedMutex::SharedMutex()
     : state(0)
     , waiters(0)
+    , writer_thread_id(0)
 {}
 
 void SharedMutex::lock()
@@ -29,6 +31,10 @@ void SharedMutex::lock()
             break;
     }
 
+    /// The first step of acquiring the exclusive ownership is finished.
+    /// Now we just wait until all readers release the shared ownership.
+    writer_thread_id.store(getThreadId());
+
     value |= writers;
     while (value & readers)
         futexWaitLowerFetch(state, value);
@@ -37,11 +43,15 @@ void SharedMutex::lock()
 bool SharedMutex::try_lock()
 {
     UInt64 value = 0;
-    return state.compare_exchange_strong(value, writers);
+    bool success = state.compare_exchange_strong(value, writers);
+    if (success)
+        writer_thread_id.store(getThreadId());
+    return success;
 }
 
 void SharedMutex::unlock()
 {
+    writer_thread_id.store(0);
     state.store(0);
     if (waiters)
         futexWakeUpperAll(state);

src/Common/SharedMutex.h

@@ -19,6 +19,8 @@ public:
     ~SharedMutex() = default;
     SharedMutex(const SharedMutex &) = delete;
     SharedMutex & operator=(const SharedMutex &) = delete;
+    SharedMutex(SharedMutex &&) = delete;
+    SharedMutex & operator=(SharedMutex &&) = delete;
 
     // Exclusive ownership
     void lock() TSA_ACQUIRE();
@@ -36,6 +38,8 @@ private:
 
     alignas(64) std::atomic<UInt64> state;
     std::atomic<UInt32> waiters;
+    /// Is set while the lock is held (or is in the process of being acquired) in exclusive mode only to facilitate debugging
+    std::atomic<UInt64> writer_thread_id;
 };
 
 }

src/Common/TimerDescriptor.cpp

@@ -2,9 +2,11 @@
 
 #include <Common/TimerDescriptor.h>
 #include <Common/Exception.h>
+#include <Common/logger_useful.h>
 
 #include <sys/timerfd.h>
 #include <unistd.h>
+#include <fmt/format.h>
 
 
 namespace DB
@@ -89,9 +91,29 @@ void TimerDescriptor::drain() const
 
             /// A signal happened, need to retry.
             if (errno == EINTR)
-                continue;
+            {
+                /** This is to help with debugging.
+                  *
+                  * Sometimes reading from timer_fd blocks, which should not happen, because we opened it in a non-blocking mode.
+                  * But it could be possible if a rogue 3rd-party library closed our file descriptor by mistake
+                  * (for example by double closing due to the lack of exception safety or if it is a crappy code in plain C)
+                  * and then another file descriptor is opened in its place.
+                  *
+                  * Let's try to get a name of this file descriptor and log it.
+                  */
+                LoggerPtr log = getLogger("TimerDescriptor");
 
-            throw ErrnoException(ErrorCodes::CANNOT_READ_FROM_SOCKET, "Cannot drain timer_fd");
+                static constexpr ssize_t max_link_path_length = 256;
+                char link_path[max_link_path_length];
+                ssize_t link_path_length = readlink(fmt::format("/proc/self/fd/{}", timer_fd).c_str(), link_path, max_link_path_length);
+                if (-1 == link_path_length)
+                    throw ErrnoException(ErrorCodes::CANNOT_READ_FROM_SOCKET, "Cannot readlink for a timer_fd {}", timer_fd);
+
+                LOG_TRACE(log, "Received EINTR while trying to drain a TimerDescriptor, fd {}: {}", timer_fd, std::string_view(link_path, link_path_length));
+                continue;
+            }
+
+            throw ErrnoException(ErrorCodes::CANNOT_READ_FROM_SOCKET, "Cannot drain timer_fd {}", timer_fd);
         }
 
         chassert(res == sizeof(buf));

src/Common/config.h.in

@@ -64,6 +64,7 @@
 #cmakedefine01 USE_LIBARCHIVE
 #cmakedefine01 USE_POCKETFFT
 #cmakedefine01 USE_PROMETHEUS_PROTOBUFS
+#cmakedefine01 USE_NUMACTL
 
 /// This is needed for .incbin in assembly. For some reason, include paths don't work there in presence of LTO.
 /// That's why we use absolute paths.

src/Core/InterpolateDescription.cpp

@@ -13,10 +13,10 @@
 
 namespace DB
 {
-    InterpolateDescription::InterpolateDescription(ActionsDAGPtr actions_, const Aliases & aliases)
+    InterpolateDescription::InterpolateDescription(ActionsDAG actions_, const Aliases & aliases)
-        : actions(actions_)
+        : actions(std::move(actions_))
     {
-        for (const auto & name_type : actions->getRequiredColumns())
+        for (const auto & name_type : actions.getRequiredColumns())
         {
             if (const auto & p = aliases.find(name_type.name); p != aliases.end())
                 required_columns_map[p->second->getColumnName()] = name_type;
@@ -24,7 +24,7 @@ namespace DB
                 required_columns_map[name_type.name] = name_type;
         }
 
-        for (const ColumnWithTypeAndName & column : actions->getResultColumns())
+        for (const ColumnWithTypeAndName & column : actions.getResultColumns())
         {
             std::string name = column.name;
             if (const auto & p = aliases.find(name); p != aliases.end())

src/Core/InterpolateDescription.h

@@ -5,21 +5,20 @@
 #include <string>
 #include <Core/NamesAndTypes.h>
 #include <Parsers/IAST_fwd.h>
+#include <Interpreters/ActionsDAG.h>
 
 
 namespace DB
 {
 
-class ActionsDAG;
-using ActionsDAGPtr = std::shared_ptr<ActionsDAG>;
 using Aliases = std::unordered_map<String, ASTPtr>;
 
 /// Interpolate description
 struct InterpolateDescription
 {
-    explicit InterpolateDescription(ActionsDAGPtr actions, const Aliases & aliases);
+    explicit InterpolateDescription(ActionsDAG actions, const Aliases & aliases);
 
-    ActionsDAGPtr actions;
+    ActionsDAG actions;
 
     std::unordered_map<std::string, NameAndTypePair> required_columns_map; /// input column name -> {alias, type}
     std::unordered_set<std::string> result_columns_set; /// result block columns

src/Core/ServerSettings.cpp

@@ -1,4 +1,4 @@
-#include "ServerSettings.h"
+#include <Core/ServerSettings.h>
 #include <Poco/Util/AbstractConfiguration.h>
 
 namespace DB

src/Core/ServerSettings.h

@@ -66,6 +66,15 @@ namespace DB
     M(Bool, async_insert_queue_flush_on_shutdown, true, "If true queue of asynchronous inserts is flushed on graceful shutdown", 0) \
     M(Bool, ignore_empty_sql_security_in_create_view_query, true, "If true, ClickHouse doesn't write defaults for empty SQL security statement in CREATE VIEW queries. This setting is only necessary for the migration period and will become obsolete in 24.4", 0)  \
     \
+    /* Database Catalog */ \
+    M(UInt64, database_atomic_delay_before_drop_table_sec, 8 * 60, "The delay during which a dropped table can be restored using the UNDROP statement. If DROP TABLE ran with a SYNC modifier, the setting is ignored.", 0) \
+    M(UInt64, database_catalog_unused_dir_hide_timeout_sec, 60 * 60, "Parameter of a task that cleans up garbage from store/ directory. If some subdirectory is not used by clickhouse-server and this directory was not modified for last database_catalog_unused_dir_hide_timeout_sec seconds, the task will 'hide' this directory by removing all access rights. It also works for directories that clickhouse-server does not expect to see inside store/. Zero means 'immediately'.", 0) \
+    M(UInt64, database_catalog_unused_dir_rm_timeout_sec, 30 * 24 * 60 * 60, "Parameter of a task that cleans up garbage from store/ directory. If some subdirectory is not used by clickhouse-server and it was previously 'hidden' (see database_catalog_unused_dir_hide_timeout_sec) and this directory was not modified for last database_catalog_unused_dir_rm_timeout_sec seconds, the task will remove this directory. It also works for directories that clickhouse-server does not expect to see inside store/. Zero means 'never'.", 0) \
+    M(UInt64, database_catalog_unused_dir_cleanup_period_sec, 24 * 60 * 60, "Parameter of a task that cleans up garbage from store/ directory. Sets scheduling period of the task. Zero means 'never'.", 0) \
+    M(UInt64, database_catalog_drop_error_cooldown_sec, 5, "In case if drop table failed, ClickHouse will wait for this timeout before retrying the operation.", 0) \
+    M(UInt64, database_catalog_drop_table_concurrency, 16, "The size of the threadpool used for dropping tables.", 0) \
+    \
+    \
     M(UInt64, max_concurrent_queries, 0, "Maximum number of concurrently executed queries. Zero means unlimited.", 0) \
     M(UInt64, max_concurrent_insert_queries, 0, "Maximum number of concurrently INSERT queries. Zero means unlimited.", 0) \
     M(UInt64, max_concurrent_select_queries, 0, "Maximum number of concurrently SELECT queries. Zero means unlimited.", 0) \

src/Core/Settings.h

@@ -1073,7 +1073,7 @@ class IColumn;
     M(Bool, input_format_orc_allow_missing_columns, true, "Allow missing columns while reading ORC input formats", 0) \
     M(Bool, input_format_orc_use_fast_decoder, true, "Use a faster ORC decoder implementation.", 0) \
     M(Bool, input_format_orc_filter_push_down, true, "When reading ORC files, skip whole stripes or row groups based on the WHERE/PREWHERE expressions, min/max statistics or bloom filter in the ORC metadata.", 0) \
-    M(Bool, input_format_orc_read_use_writer_time_zone, false, "Whether use the writer's time zone in ORC stripe for ORC row reader, the default ORC row reader's time zone is GMT.", 0) \
+    M(String, input_format_orc_reader_time_zone_name, "GMT", "The time zone name for ORC row reader, the default ORC row reader's time zone is GMT.", 0) \
     M(Bool, input_format_parquet_allow_missing_columns, true, "Allow missing columns while reading Parquet input formats", 0) \
     M(UInt64, input_format_parquet_local_file_min_bytes_for_seek, 8192, "Min bytes required for local read (file) to do seek, instead of read with ignore in Parquet input format", 0) \
     M(Bool, input_format_arrow_allow_missing_columns, true, "Allow missing columns while reading Arrow input formats", 0) \
@@ -1156,7 +1156,6 @@ class IColumn;
     M(Bool, input_format_values_interpret_expressions, true, "For Values format: if the field could not be parsed by streaming parser, run SQL parser and try to interpret it as SQL expression.", 0) \
     M(Bool, input_format_values_deduce_templates_of_expressions, true, "For Values format: if the field could not be parsed by streaming parser, run SQL parser, deduce template of the SQL expression, try to parse all rows using template and then interpret expression for all rows.", 0) \
     M(Bool, input_format_values_accurate_types_of_literals, true, "For Values format: when parsing and interpreting expressions using template, check actual type of literal to avoid possible overflow and precision issues.", 0) \
-    M(Bool, input_format_values_allow_data_after_semicolon, false, "For Values format: allow extra data after semicolon (used by client to interpret comments).", 0) \
     M(Bool, input_format_avro_allow_missing_fields, false, "For Avro/AvroConfluent format: when field is not found in schema use default value instead of error", 0) \
     /** This setting is obsolete and do nothing, left for compatibility reasons. */ \
     M(Bool, input_format_avro_null_as_default, false, "For Avro/AvroConfluent format: insert default in case of null and non Nullable column", 0) \

src/Core/SettingsChangesHistory.cpp

@@ -69,7 +69,7 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
               {"dictionary_validate_primary_key_type", false, false, "Validate primary key type for dictionaries. By default id type for simple layouts will be implicitly converted to UInt64."},
               {"collect_hash_table_stats_during_joins", false, true, "New setting."},
               {"max_size_to_preallocate_for_joins", 0, 100'000'000, "New setting."},
-              {"input_format_orc_read_use_writer_time_zone", false, false, "Whether use the writer's time zone in ORC stripe for ORC row reader, the default ORC row reader's time zone is GMT."},
+              {"input_format_orc_reader_time_zone_name", "GMT", "GMT", "The time zone name for ORC row reader, the default ORC row reader's time zone is GMT."},
               {"lightweight_mutation_projection_mode", "throw", "throw", "When lightweight delete happens on a table with projection(s), the possible operations include throw the exception as projection exists, or drop all projection related to this table then do lightweight delete."},
               {"database_replicated_allow_heavy_create", true, false, "Long-running DDL queries (CREATE AS SELECT and POPULATE) for Replicated database engine was forbidden"},
               {"query_plan_merge_filters", false, false, "Allow to merge filters in the query plan"},

src/DataTypes/DataTypeAggregateFunction.cpp

@@ -257,8 +257,8 @@ static DataTypePtr create(const ASTPtr & arguments)
     }
     else
         throw Exception(ErrorCodes::BAD_ARGUMENTS,
-                        "Unexpected AST element passed as aggregate function name for data type AggregateFunction. "
+                        "Unexpected AST element {} passed as aggregate function name for data type AggregateFunction. "
-                        "Must be identifier or function.");
+                        "Must be identifier or function", data_type_ast->getID());
 
     for (size_t i = argument_types_start_idx; i < arguments->children.size(); ++i)
         argument_types.push_back(DataTypeFactory::instance().get(arguments->children[i]));

src/DataTypes/DataTypeFactory.cpp

@@ -2,7 +2,7 @@
 #include <DataTypes/DataTypeCustom.h>
 #include <Parsers/parseQuery.h>
 #include <Parsers/ParserCreateQuery.h>
-#include <Parsers/ASTFunction.h>
+#include <Parsers/ASTDataType.h>
 #include <Parsers/ASTIdentifier.h>
 #include <Parsers/ASTLiteral.h>
 #include <Common/typeid_cast.h>
@@ -22,7 +22,6 @@ namespace ErrorCodes
 {
     extern const int LOGICAL_ERROR;
     extern const int UNKNOWN_TYPE;
-    extern const int ILLEGAL_SYNTAX_FOR_DATA_TYPE;
     extern const int UNEXPECTED_AST_STRUCTURE;
     extern const int DATA_TYPE_CANNOT_HAVE_ARGUMENTS;
 }
@@ -83,15 +82,9 @@ DataTypePtr DataTypeFactory::tryGet(const ASTPtr & ast) const
 template <bool nullptr_on_error>
 DataTypePtr DataTypeFactory::getImpl(const ASTPtr & ast) const
 {
-    if (const auto * func = ast->as<ASTFunction>())
+    if (const auto * type = ast->as<ASTDataType>())
     {
-        if (func->parameters)
+        return getImpl<nullptr_on_error>(type->name, type->arguments);
-        {
-            if constexpr (nullptr_on_error)
-                return nullptr;
-            throw Exception(ErrorCodes::ILLEGAL_SYNTAX_FOR_DATA_TYPE, "Data type cannot have multiple parenthesized parameters.");
-        }
-        return getImpl<nullptr_on_error>(func->name, func->arguments);
     }
 
     if (const auto * ident = ast->as<ASTIdentifier>())
@@ -107,7 +100,7 @@ DataTypePtr DataTypeFactory::getImpl(const ASTPtr & ast) const
 
     if constexpr (nullptr_on_error)
         return nullptr;
-    throw Exception(ErrorCodes::UNEXPECTED_AST_STRUCTURE, "Unexpected AST element for data type.");
+    throw Exception(ErrorCodes::UNEXPECTED_AST_STRUCTURE, "Unexpected AST element for data type: {}.", ast->getID());
 }
 
 DataTypePtr DataTypeFactory::get(const String & family_name_param, const ASTPtr & parameters) const

src/DataTypes/DataTypeObject.cpp

@@ -4,9 +4,10 @@
 
 #include <Parsers/IAST.h>
 #include <Parsers/ASTLiteral.h>
-#include <Parsers/ASTFunction.h>
+#include <Parsers/ASTDataType.h>
 #include <IO/Operators.h>
 
+
 namespace DB
 {
 
@@ -53,13 +54,13 @@ static DataTypePtr create(const ASTPtr & arguments)
     ASTPtr schema_argument = arguments->children[0];
     bool is_nullable = false;
 
-    if (const auto * func = schema_argument->as<ASTFunction>())
+    if (const auto * type = schema_argument->as<ASTDataType>())
     {
-        if (func->name != "Nullable" || func->arguments->children.size() != 1)
+        if (type->name != "Nullable" || type->arguments->children.size() != 1)
             throw Exception(ErrorCodes::UNEXPECTED_AST_STRUCTURE,
-                "Expected 'Nullable(<schema_name>)' as parameter for type Object (function: {})", func->name);
+                "Expected 'Nullable(<schema_name>)' as parameter for type Object (function: {})", type->name);
 
-        schema_argument = func->arguments->children[0];
+        schema_argument = type->arguments->children[0];
         is_nullable = true;
     }
 

src/Databases/DatabaseDictionary.cpp

@@ -111,7 +111,7 @@ ASTPtr DatabaseDictionary::getCreateTableQueryImpl(const String & table_name, Co
         buffer << ") Engine = Dictionary(" << backQuoteIfNeed(table_name) << ")";
     }
 
-    auto settings = getContext()->getSettingsRef();
+    const auto & settings = getContext()->getSettingsRef();
     ParserCreateQuery parser;
     const char * pos = query.data();
     std::string error_message;
@@ -133,7 +133,7 @@ ASTPtr DatabaseDictionary::getCreateDatabaseQuery() const
         if (const auto comment_value = getDatabaseComment(); !comment_value.empty())
             buffer << " COMMENT " << backQuote(comment_value);
     }
-    auto settings = getContext()->getSettingsRef();
+    const auto & settings = getContext()->getSettingsRef();
     ParserCreateQuery parser;
     return parseQuery(parser, query.data(), query.data() + query.size(), "", 0, settings.max_parser_depth, settings.max_parser_backtracks);
 }

src/Databases/DatabaseOnDisk.cpp

@@ -534,7 +534,7 @@ ASTPtr DatabaseOnDisk::getCreateDatabaseQuery() const
 {
     ASTPtr ast;
 
-    auto settings = getContext()->getSettingsRef();
+    const auto & settings = getContext()->getSettingsRef();
     {
         std::lock_guard lock(mutex);
         auto database_metadata_path = getContext()->getPath() + "metadata/" + escapeForFileName(database_name) + ".sql";
@@ -733,7 +733,7 @@ ASTPtr DatabaseOnDisk::parseQueryFromMetadata(
         return nullptr;
     }
 
-    auto settings = local_context->getSettingsRef();
+    const auto & settings = local_context->getSettingsRef();
     ParserCreateQuery parser;
     const char * pos = query.data();
     std::string error_message;

src/Databases/DatabasesCommon.cpp

@@ -149,7 +149,7 @@ ASTPtr getCreateQueryFromStorage(const StoragePtr & storage, const ASTPtr & ast_
             columns = metadata_ptr->columns.getAll();
         for (const auto & column_name_and_type: columns)
         {
-            const auto & ast_column_declaration = std::make_shared<ASTColumnDeclaration>();
+            const auto ast_column_declaration = std::make_shared<ASTColumnDeclaration>();
             ast_column_declaration->name = column_name_and_type.name;
             /// parser typename
             {
@@ -164,7 +164,7 @@ ASTPtr getCreateQueryFromStorage(const StoragePtr & storage, const ASTPtr & ast_
                 if (!parser.parse(pos, ast_type, expected))
                 {
                     if (throw_on_error)
-                        throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot parser metadata of {}.{}",
+                        throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot parse metadata of {}.{}",
                                         backQuote(table_id.database_name), backQuote(table_id.table_name));
                     else
                         return nullptr;

src/Databases/MySQL/MaterializedMySQLSyncThread.cpp

@@ -89,7 +89,7 @@ static constexpr auto MYSQL_BACKGROUND_THREAD_NAME = "MySQLDBSync";
 
 static ContextMutablePtr createQueryContext(ContextPtr context)
 {
-    Settings new_query_settings = context->getSettings();
+    Settings new_query_settings = context->getSettingsCopy();
     new_query_settings.insert_allow_materialized_columns = true;
 
     /// To avoid call AST::format

src/Databases/PostgreSQL/DatabasePostgreSQL.cpp

@@ -12,9 +12,9 @@
 #include <Interpreters/evaluateConstantExpression.h>
 #include <Parsers/ASTCreateQuery.h>
 #include <Parsers/ASTFunction.h>
+#include <Parsers/ASTDataType.h>
 #include <Parsers/ParserCreateQuery.h>
 #include <Parsers/parseQuery.h>
-#include <Parsers/queryToString.h>
 #include <Common/escapeForFileName.h>
 #include <Common/parseRemoteDescription.h>
 #include <Databases/DatabaseFactory.h>
@@ -25,6 +25,7 @@
 #include <Core/Settings.h>
 #include <filesystem>
 
+
 namespace fs = std::filesystem;
 
 namespace DB
@@ -432,7 +433,7 @@ ASTPtr DatabasePostgreSQL::getCreateTableQueryImpl(const String & table_name, Co
     auto metadata_snapshot = storage->getInMemoryMetadataPtr();
     for (const auto & column_type_and_name : metadata_snapshot->getColumns().getOrdinary())
     {
-        const auto & column_declaration = std::make_shared<ASTColumnDeclaration>();
+        const auto column_declaration = std::make_shared<ASTColumnDeclaration>();
         column_declaration->name = column_type_and_name.name;
         column_declaration->type = getColumnDeclaration(column_type_and_name.type);
         columns_expression_list->children.emplace_back(column_declaration);
@@ -470,17 +471,15 @@ ASTPtr DatabasePostgreSQL::getColumnDeclaration(const DataTypePtr & data_type) c
     WhichDataType which(data_type);
 
     if (which.isNullable())
-        return makeASTFunction("Nullable", getColumnDeclaration(typeid_cast<const DataTypeNullable *>(data_type.get())->getNestedType()));
+        return makeASTDataType("Nullable", getColumnDeclaration(typeid_cast<const DataTypeNullable *>(data_type.get())->getNestedType()));
 
     if (which.isArray())
-        return makeASTFunction("Array", getColumnDeclaration(typeid_cast<const DataTypeArray *>(data_type.get())->getNestedType()));
+        return makeASTDataType("Array", getColumnDeclaration(typeid_cast<const DataTypeArray *>(data_type.get())->getNestedType()));
 
     if (which.isDateTime64())
-    {
+        return makeASTDataType("DateTime64", std::make_shared<ASTLiteral>(static_cast<UInt32>(6)));
-        return makeASTFunction("DateTime64", std::make_shared<ASTLiteral>(static_cast<UInt32>(6)));
-    }
 
-    return std::make_shared<ASTIdentifier>(data_type->getName());
+    return makeASTDataType(data_type->getName());
 }
 
 void registerDatabasePostgreSQL(DatabaseFactory & factory)

src/Formats/FormatFactory.cpp

@@ -215,7 +215,6 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
     format_settings.tsv.allow_variable_number_of_columns = settings.input_format_tsv_allow_variable_number_of_columns;
     format_settings.tsv.crlf_end_of_line_input = settings.input_format_tsv_crlf_end_of_line;
     format_settings.values.accurate_types_of_literals = settings.input_format_values_accurate_types_of_literals;
-    format_settings.values.allow_data_after_semicolon = settings.input_format_values_allow_data_after_semicolon;
     format_settings.values.deduce_templates_of_expressions = settings.input_format_values_deduce_templates_of_expressions;
     format_settings.values.interpret_expressions = settings.input_format_values_interpret_expressions;
     format_settings.values.escape_quote_with_quote = settings.output_format_values_escape_quote_with_quote;
@@ -244,7 +243,7 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
     format_settings.orc.output_row_index_stride = settings.output_format_orc_row_index_stride;
     format_settings.orc.use_fast_decoder = settings.input_format_orc_use_fast_decoder;
     format_settings.orc.filter_push_down = settings.input_format_orc_filter_push_down;
-    format_settings.orc.read_use_writer_time_zone = settings.input_format_orc_read_use_writer_time_zone;
+    format_settings.orc.reader_time_zone_name = settings.input_format_orc_reader_time_zone_name;
     format_settings.defaults_for_omitted_fields = settings.input_format_defaults_for_omitted_fields;
     format_settings.capn_proto.enum_comparing_mode = settings.format_capn_proto_enum_comparising_mode;
     format_settings.capn_proto.skip_fields_with_unsupported_types_in_schema_inference = settings.input_format_capn_proto_skip_fields_with_unsupported_types_in_schema_inference;
@@ -253,7 +252,7 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
     format_settings.msgpack.number_of_columns = settings.input_format_msgpack_number_of_columns;
     format_settings.msgpack.output_uuid_representation = settings.output_format_msgpack_uuid_representation;
     format_settings.max_rows_to_read_for_schema_inference = settings.input_format_max_rows_to_read_for_schema_inference;
-    format_settings.max_bytes_to_read_for_schema_inference = settings.input_format_max_rows_to_read_for_schema_inference;
+    format_settings.max_bytes_to_read_for_schema_inference = settings.input_format_max_bytes_to_read_for_schema_inference;
     format_settings.column_names_for_schema_inference = settings.column_names_for_schema_inference;
     format_settings.schema_inference_hints = settings.schema_inference_hints;
     format_settings.schema_inference_make_columns_nullable = settings.schema_inference_make_columns_nullable;

src/Formats/FormatSettings.h

@@ -409,7 +409,7 @@ struct FormatSettings
         bool use_fast_decoder = true;
         bool filter_push_down = true;
         UInt64 output_row_index_stride = 10'000;
-        bool read_use_writer_time_zone = false;
+        String reader_time_zone_name = "GMT";
     } orc{};
 
     /// For capnProto format we should determine how to

src/Functions/CRC.cpp

@@ -81,46 +81,43 @@ struct CRCFunctionWrapper
     static constexpr auto is_fixed_to_constant = true;
     using ReturnType = typename Impl::ReturnType;
 
-    static void vector(const ColumnString::Chars & data, const ColumnString::Offsets & offsets, PaddedPODArray<ReturnType> & res)
+    static void vector(const ColumnString::Chars & data, const ColumnString::Offsets & offsets, PaddedPODArray<ReturnType> & res, size_t input_rows_count)
     {
-        size_t size = offsets.size();
-
         ColumnString::Offset prev_offset = 0;
-        for (size_t i = 0; i < size; ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             res[i] = doCRC(data, prev_offset, offsets[i] - prev_offset - 1);
             prev_offset = offsets[i];
         }
     }
 
-    static void vectorFixedToConstant(const ColumnString::Chars & data, size_t n, ReturnType & res) { res = doCRC(data, 0, n); }
+    static void vectorFixedToConstant(const ColumnString::Chars & data, size_t n, ReturnType & res, size_t)
-
-    static void vectorFixedToVector(const ColumnString::Chars & data, size_t n, PaddedPODArray<ReturnType> & res)
     {
-        size_t size = data.size() / n;
+        res = doCRC(data, 0, n);
+    }
 
-        for (size_t i = 0; i < size; ++i)
+    static void vectorFixedToVector(const ColumnString::Chars & data, size_t n, PaddedPODArray<ReturnType> & res, size_t input_rows_count)
     {
+        for (size_t i = 0; i < input_rows_count; ++i)
             res[i] = doCRC(data, i * n, n);
     }
-    }
 
-    [[noreturn]] static void array(const ColumnString::Offsets & /*offsets*/, PaddedPODArray<ReturnType> & /*res*/)
+    [[noreturn]] static void array(const ColumnString::Offsets &, PaddedPODArray<ReturnType> &, size_t)
     {
         throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Cannot apply function {} to Array argument", std::string(Impl::name));
     }
 
-    [[noreturn]] static void uuid(const ColumnUUID::Container & /*offsets*/, size_t /*n*/, PaddedPODArray<ReturnType> & /*res*/)
+    [[noreturn]] static void uuid(const ColumnUUID::Container &, size_t, PaddedPODArray<ReturnType> &, size_t)
     {
         throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Cannot apply function {} to UUID argument", std::string(Impl::name));
     }
 
-    [[noreturn]] static void ipv6(const ColumnIPv6::Container & /*offsets*/, size_t /*n*/, PaddedPODArray<ReturnType> & /*res*/)
+    [[noreturn]] static void ipv6(const ColumnIPv6::Container &, size_t, PaddedPODArray<ReturnType> &, size_t)
     {
         throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Cannot apply function {} to IPv6 argument", std::string(Impl::name));
     }
 
-    [[noreturn]] static void ipv4(const ColumnIPv4::Container & /*offsets*/, size_t /*n*/, PaddedPODArray<ReturnType> & /*res*/)
+    [[noreturn]] static void ipv4(const ColumnIPv4::Container &, size_t, PaddedPODArray<ReturnType> &, size_t)
     {
         throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Cannot apply function {} to IPv4 argument", std::string(Impl::name));
     }

src/Functions/CustomWeekTransforms.h

@@ -32,13 +32,12 @@ struct WeekTransformer
     {}
 
     template <typename FromVectorType, typename ToVectorType>
-    void vector(const FromVectorType & vec_from, ToVectorType & vec_to, UInt8 week_mode, const DateLUTImpl & time_zone) const
+    void vector(const FromVectorType & vec_from, ToVectorType & vec_to, UInt8 week_mode, const DateLUTImpl & time_zone, size_t input_rows_count) const
     {
         using ValueType = typename ToVectorType::value_type;
-        size_t size = vec_from.size();
+        vec_to.resize(input_rows_count);
-        vec_to.resize(size);
 
-        for (size_t i = 0; i < size; ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             if constexpr (is_extended_result)
                 vec_to[i] = static_cast<ValueType>(transform.executeExtendedResult(vec_from[i], week_mode, time_zone));
@@ -56,7 +55,7 @@ template <typename FromDataType, typename ToDataType, bool is_extended_result =
 struct CustomWeekTransformImpl
 {
     template <typename Transform>
-    static ColumnPtr execute(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/, Transform transform = {})
+    static ColumnPtr execute(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count, Transform transform = {})
     {
         const auto op = WeekTransformer<typename FromDataType::FieldType, typename ToDataType::FieldType, Transform, is_extended_result>{transform};
 
@@ -77,9 +76,9 @@ struct CustomWeekTransformImpl
             const auto * sources = checkAndGetColumn<DataTypeString::ColumnType>(source_col.get());
 
             auto col_to = ToDataType::ColumnType::create();
-            col_to->getData().resize(sources->size());
+            col_to->getData().resize(input_rows_count);
 
-            for (size_t i = 0; i < sources->size(); ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
             {
                 DateTime64 dt64;
                 ReadBufferFromString buf(sources->getDataAt(i).toView());
@@ -92,7 +91,7 @@ struct CustomWeekTransformImpl
         else if (const auto * sources = checkAndGetColumn<typename FromDataType::ColumnType>(source_col.get()))
         {
             auto col_to = ToDataType::ColumnType::create();
-            op.vector(sources->getData(), col_to->getData(), week_mode, time_zone);
+            op.vector(sources->getData(), col_to->getData(), week_mode, time_zone, input_rows_count);
             return col_to;
         }
         else

src/Functions/DateTimeTransforms.h

@@ -2134,13 +2134,12 @@ struct Transformer
 {
     template <typename FromTypeVector, typename ToTypeVector>
     static void vector(const FromTypeVector & vec_from, ToTypeVector & vec_to, const DateLUTImpl & time_zone, const Transform & transform,
-        [[maybe_unused]] ColumnUInt8::Container * vec_null_map_to)
+        [[maybe_unused]] ColumnUInt8::Container * vec_null_map_to, size_t input_rows_count)
     {
         using ValueType = typename ToTypeVector::value_type;
-        size_t size = vec_from.size();
+        vec_to.resize(input_rows_count);
-        vec_to.resize(size);
 
-        for (size_t i = 0; i < size; ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             if constexpr (std::is_same_v<ToType, DataTypeDate> || std::is_same_v<ToType, DataTypeDateTime>)
             {
@@ -2178,7 +2177,7 @@ struct DateTimeTransformImpl
 {
     template <typename Additions = void *>
     static ColumnPtr execute(
-        const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t /*input_rows_count*/, const Transform & transform = {})
+        const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t input_rows_count, const Transform & transform = {})
     {
         using Op = Transformer<FromDataType, ToDataType, Transform, is_extended_result, Additions>;
 
@@ -2200,7 +2199,7 @@ struct DateTimeTransformImpl
             if (result_data_type.isDateTime() || result_data_type.isDateTime64())
             {
                 const auto & time_zone = dynamic_cast<const TimezoneMixin &>(*result_type).getTimeZone();
-                Op::vector(sources->getData(), col_to->getData(), time_zone, transform, vec_null_map_to);
+                Op::vector(sources->getData(), col_to->getData(), time_zone, transform, vec_null_map_to, input_rows_count);
             }
             else
             {
@@ -2209,16 +2208,14 @@ struct DateTimeTransformImpl
                     time_zone_argument_position = 2;
 
                 const DateLUTImpl & time_zone = extractTimeZoneFromFunctionArguments(arguments, time_zone_argument_position, 0);
-                Op::vector(sources->getData(), col_to->getData(), time_zone, transform, vec_null_map_to);
+                Op::vector(sources->getData(), col_to->getData(), time_zone, transform, vec_null_map_to, input_rows_count);
             }
 
             if constexpr (std::is_same_v<Additions, DateTimeAccurateOrNullConvertStrategyAdditions>)
             {
                 if (vec_null_map_to)
-                {
                     return ColumnNullable::create(std::move(mutable_result_col), std::move(col_null_map_to));
             }
-            }
 
             return mutable_result_col;
         }

src/Functions/EmptyImpl.h

@@ -21,11 +21,10 @@ struct EmptyImpl
     /// If the function will return constant value for FixedString data type.
     static constexpr auto is_fixed_to_constant = false;
 
-    static void vector(const ColumnString::Chars & /*data*/, const ColumnString::Offsets & offsets, PaddedPODArray<UInt8> & res)
+    static void vector(const ColumnString::Chars & /*data*/, const ColumnString::Offsets & offsets, PaddedPODArray<UInt8> & res, size_t input_rows_count)
     {
-        size_t size = offsets.size();
         ColumnString::Offset prev_offset = 1;
-        for (size_t i = 0; i < size; ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             res[i] = negative ^ (offsets[i] == prev_offset);
             prev_offset = offsets[i] + 1;
@@ -33,42 +32,40 @@ struct EmptyImpl
     }
 
     /// Only make sense if is_fixed_to_constant.
-    static void vectorFixedToConstant(const ColumnString::Chars & /*data*/, size_t /*n*/, UInt8 & /*res*/)
+    static void vectorFixedToConstant(const ColumnString::Chars &, size_t, UInt8 &, size_t)
     {
         throw Exception(ErrorCodes::LOGICAL_ERROR, "'vectorFixedToConstant method' is called");
     }
 
-    static void vectorFixedToVector(const ColumnString::Chars & data, size_t n, PaddedPODArray<UInt8> & res)
+    static void vectorFixedToVector(const ColumnString::Chars & data, size_t n, PaddedPODArray<UInt8> & res, size_t input_rows_count)
     {
-        size_t size = data.size() / n;
+        for (size_t i = 0; i < input_rows_count; ++i)
-        for (size_t i = 0; i < size; ++i)
             res[i] = negative ^ memoryIsZeroSmallAllowOverflow15(data.data() + i * n, n);
     }
 
-    static void array(const ColumnString::Offsets & offsets, PaddedPODArray<UInt8> & res)
+    static void array(const ColumnString::Offsets & offsets, PaddedPODArray<UInt8> & res, size_t input_rows_count)
     {
-        size_t size = offsets.size();
         ColumnString::Offset prev_offset = 0;
-        for (size_t i = 0; i < size; ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             res[i] = negative ^ (offsets[i] == prev_offset);
             prev_offset = offsets[i];
         }
     }
 
-    static void uuid(const ColumnUUID::Container & container, size_t n, PaddedPODArray<UInt8> & res)
+    static void uuid(const ColumnUUID::Container & container, size_t n, PaddedPODArray<UInt8> & res, size_t)
     {
         for (size_t i = 0; i < n; ++i)
             res[i] = negative ^ (container[i].toUnderType() == 0);
     }
 
-    static void ipv6(const ColumnIPv6::Container & container, size_t n, PaddedPODArray<UInt8> & res)
+    static void ipv6(const ColumnIPv6::Container & container, size_t n, PaddedPODArray<UInt8> & res, size_t)
     {
         for (size_t i = 0; i < n; ++i)
             res[i] = negative ^ (container[i].toUnderType() == 0);
     }
 
-    static void ipv4(const ColumnIPv4::Container & container, size_t n, PaddedPODArray<UInt8> & res)
+    static void ipv4(const ColumnIPv4::Container & container, size_t n, PaddedPODArray<UInt8> & res, size_t)
     {
         for (size_t i = 0; i < n; ++i)
             res[i] = negative ^ (container[i].toUnderType() == 0);

src/Functions/ExtractString.h

@@ -20,7 +20,7 @@ namespace DB
 // includes extracting ASCII ngram, UTF8 ngram, ASCII word and UTF8 word
 struct ExtractStringImpl
 {
-    static ALWAYS_INLINE inline const UInt8 * readOneWord(const UInt8 *& pos, const UInt8 * end)
+    static const UInt8 * readOneWord(const UInt8 *& pos, const UInt8 * end)
     {
         // jump separators
         while (pos < end && isUTF8Sep(*pos))

src/Functions/FunctionBitTestMany.h

@@ -46,7 +46,7 @@ public:
             throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of first argument of function {}", first_arg->getName(), getName());
 
 
-        for (const auto i : collections::range(1, arguments.size()))
+        for (size_t i = 1; i < arguments.size(); ++i)
         {
             const auto & pos_arg = arguments[i];
 
@@ -57,19 +57,19 @@ public:
         return std::make_shared<DataTypeUInt8>();
     }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t input_rows_count) const override
     {
         const auto * value_col = arguments.front().column.get();
 
         ColumnPtr res;
-        if (!((res = execute<UInt8>(arguments, result_type, value_col))
+        if (!((res = execute<UInt8>(arguments, result_type, value_col, input_rows_count))
-            || (res = execute<UInt16>(arguments, result_type, value_col))
+            || (res = execute<UInt16>(arguments, result_type, value_col, input_rows_count))
-            || (res = execute<UInt32>(arguments, result_type, value_col))
+            || (res = execute<UInt32>(arguments, result_type, value_col, input_rows_count))
-            || (res = execute<UInt64>(arguments, result_type, value_col))
+            || (res = execute<UInt64>(arguments, result_type, value_col, input_rows_count))
-            || (res = execute<Int8>(arguments, result_type, value_col))
+            || (res = execute<Int8>(arguments, result_type, value_col, input_rows_count))
-            || (res = execute<Int16>(arguments, result_type, value_col))
+            || (res = execute<Int16>(arguments, result_type, value_col, input_rows_count))
-            || (res = execute<Int32>(arguments, result_type, value_col))
+            || (res = execute<Int32>(arguments, result_type, value_col, input_rows_count))
-            || (res = execute<Int64>(arguments, result_type, value_col))))
+            || (res = execute<Int64>(arguments, result_type, value_col, input_rows_count))))
             throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of argument of function {}", value_col->getName(), getName());
 
         return res;
@@ -79,28 +79,28 @@ private:
     template <typename T>
     ColumnPtr execute(
             const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type,
-            const IColumn * const value_col_untyped) const
+            const IColumn * const value_col_untyped,
+            size_t input_rows_count) const
     {
         if (const auto value_col = checkAndGetColumn<ColumnVector<T>>(value_col_untyped))
         {
-            const auto size = value_col->size();
             bool is_const;
             const auto const_mask = createConstMaskIfConst<T>(arguments, is_const);
             const auto & val = value_col->getData();
 
-            auto out_col = ColumnVector<UInt8>::create(size);
+            auto out_col = ColumnVector<UInt8>::create(input_rows_count);
             auto & out = out_col->getData();
 
             if (is_const)
             {
-                for (const auto i : collections::range(0, size))
+                for (size_t i = 0; i < input_rows_count; ++i)
                     out[i] = Impl::apply(val[i], const_mask);
             }
             else
             {
-                const auto mask = createMask<T>(size, arguments);
+                const auto mask = createMask<T>(input_rows_count, arguments);
 
-                for (const auto i : collections::range(0, size))
+                for (size_t i = 0; i < input_rows_count; ++i)
                     out[i] = Impl::apply(val[i], mask[i]);
             }
 
@@ -108,23 +108,22 @@ private:
         }
         else if (const auto value_col_const = checkAndGetColumnConst<ColumnVector<T>>(value_col_untyped))
         {
-            const auto size = value_col_const->size();
             bool is_const;
             const auto const_mask = createConstMaskIfConst<T>(arguments, is_const);
             const auto val = value_col_const->template getValue<T>();
 
             if (is_const)
             {
-                return result_type->createColumnConst(size, toField(Impl::apply(val, const_mask)));
+                return result_type->createColumnConst(input_rows_count, toField(Impl::apply(val, const_mask)));
             }
             else
             {
-                const auto mask = createMask<T>(size, arguments);
+                const auto mask = createMask<T>(input_rows_count, arguments);
-                auto out_col = ColumnVector<UInt8>::create(size);
+                auto out_col = ColumnVector<UInt8>::create(input_rows_count);
 
                 auto & out = out_col->getData();
 
-                for (const auto i : collections::range(0, size))
+                for (size_t i = 0; i < input_rows_count; ++i)
                     out[i] = Impl::apply(val, mask[i]);
 
                 return out_col;
@@ -140,7 +139,7 @@ private:
         out_is_const = true;
         ValueType mask = 0;
 
-        for (const auto i : collections::range(1, arguments.size()))
+        for (size_t i = 1; i < arguments.size(); ++i)
         {
             if (auto pos_col_const = checkAndGetColumnConst<ColumnVector<ValueType>>(arguments[i].column.get()))
             {
@@ -166,7 +165,7 @@ private:
     {
         PaddedPODArray<ValueType> mask(size, ValueType{});
 
-        for (const auto i : collections::range(1, arguments.size()))
+        for (size_t i = 1; i < arguments.size(); ++i)
         {
             const auto * pos_col = arguments[i].column.get();
 
@@ -187,7 +186,7 @@ private:
         {
             const auto & pos = pos_col->getData();
 
-            for (const auto i : collections::range(0, mask.size()))
+            for (size_t i = 0; i < mask.size(); ++i)
                 if (pos[i] < 8 * sizeof(ValueType))
                     mask[i] = mask[i] | (ValueType(1) << pos[i]);
                 else
@@ -205,7 +204,7 @@ private:
 
             const auto new_mask = ValueType(1) << pos;
 
-            for (const auto i : collections::range(0, mask.size()))
+            for (size_t i = 0; i < mask.size(); ++i)
                 mask[i] = mask[i] | new_mask;
 
             return true;

src/Functions/FunctionChar.cpp

@@ -103,14 +103,11 @@ private:
         const ColumnVector<T> * src_data_concrete = checkAndGetColumn<ColumnVector<T>>(&src_data);
 
         if (!src_data_concrete)
-        {
             return false;
-        }
 
         for (size_t row = 0; row < rows; ++row)
-        {
             out_vec[row * size_per_row + column_idx] = static_cast<char>(src_data_concrete->getInt(row));
-        }
+
         return true;
     }
 };

src/Functions/FunctionDateOrDateTimeAddInterval.h

@@ -428,19 +428,17 @@ struct Processor
     {}
 
     template <typename FromColumnType, typename ToColumnType>
-    void NO_INLINE vectorConstant(const FromColumnType & col_from, ToColumnType & col_to, Int64 delta, const DateLUTImpl & time_zone, UInt16 scale) const
+    void NO_INLINE vectorConstant(const FromColumnType & col_from, ToColumnType & col_to, Int64 delta, const DateLUTImpl & time_zone, UInt16 scale, size_t input_rows_count) const
     {
         static const DateLUTImpl & utc_time_zone = DateLUT::instance("UTC");
 
         if constexpr (std::is_same_v<FromColumnType, ColumnString>)
         {
-            const auto & offsets_from = col_from.getOffsets();
             auto & vec_to = col_to.getData();
 
-            size_t size = offsets_from.size();
+            vec_to.resize(input_rows_count);
-            vec_to.resize(size);
 
-            for (size_t i = 0 ; i < size; ++i)
+            for (size_t i = 0 ; i < input_rows_count; ++i)
             {
                 std::string_view from = col_from.getDataAt(i).toView();
                 vec_to[i] = transform.execute(from, checkOverflow(delta), time_zone, utc_time_zone, scale);
@@ -451,32 +449,31 @@ struct Processor
             const auto & vec_from = col_from.getData();
             auto & vec_to = col_to.getData();
 
-            size_t size = vec_from.size();
+            vec_to.resize(input_rows_count);
-            vec_to.resize(size);
 
-            for (size_t i = 0; i < size; ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
                 vec_to[i] = transform.execute(vec_from[i], checkOverflow(delta), time_zone, utc_time_zone, scale);
         }
     }
 
     template <typename FromColumnType, typename ToColumnType>
-    void vectorVector(const FromColumnType & col_from, ToColumnType & col_to, const IColumn & delta, const DateLUTImpl & time_zone, UInt16 scale) const
+    void vectorVector(const FromColumnType & col_from, ToColumnType & col_to, const IColumn & delta, const DateLUTImpl & time_zone, UInt16 scale, size_t input_rows_count) const
     {
         castTypeToEither<
             ColumnUInt8, ColumnUInt16, ColumnUInt32, ColumnUInt64,
             ColumnInt8, ColumnInt16, ColumnInt32, ColumnInt64,
             ColumnFloat32, ColumnFloat64>(
-            &delta, [&](const auto & column){ vectorVector(col_from, col_to, column, time_zone, scale); return true; });
+            &delta, [&](const auto & column){ vectorVector(col_from, col_to, column, time_zone, scale, input_rows_count); return true; });
     }
 
     template <typename FromType, typename ToColumnType>
-    void constantVector(const FromType & from, ToColumnType & col_to, const IColumn & delta, const DateLUTImpl & time_zone, UInt16 scale) const
+    void constantVector(const FromType & from, ToColumnType & col_to, const IColumn & delta, const DateLUTImpl & time_zone, UInt16 scale, size_t input_rows_count) const
     {
         castTypeToEither<
             ColumnUInt8, ColumnUInt16, ColumnUInt32, ColumnUInt64,
             ColumnInt8, ColumnInt16, ColumnInt32, ColumnInt64,
             ColumnFloat32, ColumnFloat64>(
-            &delta, [&](const auto & column){ constantVector(from, col_to, column, time_zone, scale); return true; });
+            &delta, [&](const auto & column){ constantVector(from, col_to, column, time_zone, scale, input_rows_count); return true; });
     }
 
 private:
@@ -491,19 +488,17 @@ private:
 
     template <typename FromColumnType, typename ToColumnType, typename DeltaColumnType>
     NO_INLINE NO_SANITIZE_UNDEFINED void vectorVector(
-        const FromColumnType & col_from, ToColumnType & col_to, const DeltaColumnType & delta, const DateLUTImpl & time_zone, UInt16 scale) const
+        const FromColumnType & col_from, ToColumnType & col_to, const DeltaColumnType & delta, const DateLUTImpl & time_zone, UInt16 scale, size_t input_rows_count) const
     {
         static const DateLUTImpl & utc_time_zone = DateLUT::instance("UTC");
 
         if constexpr (std::is_same_v<FromColumnType, ColumnString>)
         {
-            const auto & offsets_from = col_from.getOffsets();
             auto & vec_to = col_to.getData();
 
-            size_t size = offsets_from.size();
+            vec_to.resize(input_rows_count);
-            vec_to.resize(size);
 
-            for (size_t i = 0 ; i < size; ++i)
+            for (size_t i = 0 ; i < input_rows_count; ++i)
             {
                 std::string_view from = col_from.getDataAt(i).toView();
                 vec_to[i] = transform.execute(from, checkOverflow(delta.getData()[i]), time_zone, utc_time_zone, scale);
@@ -514,26 +509,24 @@ private:
             const auto & vec_from = col_from.getData();
             auto & vec_to = col_to.getData();
 
-            size_t size = vec_from.size();
+            vec_to.resize(input_rows_count);
-            vec_to.resize(size);
 
-            for (size_t i = 0; i < size; ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
                 vec_to[i] = transform.execute(vec_from[i], checkOverflow(delta.getData()[i]), time_zone, utc_time_zone, scale);
         }
     }
 
     template <typename FromType, typename ToColumnType, typename DeltaColumnType>
     NO_INLINE NO_SANITIZE_UNDEFINED void constantVector(
-        const FromType & from, ToColumnType & col_to, const DeltaColumnType & delta, const DateLUTImpl & time_zone, UInt16 scale) const
+        const FromType & from, ToColumnType & col_to, const DeltaColumnType & delta, const DateLUTImpl & time_zone, UInt16 scale, size_t input_rows_count) const
     {
         static const DateLUTImpl & utc_time_zone = DateLUT::instance("UTC");
 
         auto & vec_to = col_to.getData();
 
-        size_t size = delta.size();
+        vec_to.resize(input_rows_count);
-        vec_to.resize(size);
 
-        for (size_t i = 0; i < size; ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
             vec_to[i] = transform.execute(from, checkOverflow(delta.getData()[i]), time_zone, utc_time_zone, scale);
     }
 };
@@ -542,7 +535,7 @@ private:
 template <typename FromDataType, typename ToDataType, typename Transform>
 struct DateTimeAddIntervalImpl
 {
-    static ColumnPtr execute(Transform transform, const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, UInt16 scale)
+    static ColumnPtr execute(Transform transform, const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, UInt16 scale, size_t input_rows_count)
     {
         using FromValueType = typename FromDataType::FieldType;
         using FromColumnType = typename FromDataType::ColumnType;
@@ -561,15 +554,15 @@ struct DateTimeAddIntervalImpl
         if (const auto * sources = checkAndGetColumn<FromColumnType>(&source_column))
         {
             if (const auto * delta_const_column = typeid_cast<const ColumnConst *>(&delta_column))
-                processor.vectorConstant(*sources, *col_to, delta_const_column->getInt(0), time_zone, scale);
+                processor.vectorConstant(*sources, *col_to, delta_const_column->getInt(0), time_zone, scale, input_rows_count);
             else
-                processor.vectorVector(*sources, *col_to, delta_column, time_zone, scale);
+                processor.vectorVector(*sources, *col_to, delta_column, time_zone, scale, input_rows_count);
         }
         else if (const auto * sources_const = checkAndGetColumnConst<FromColumnType>(&source_column))
         {
             processor.constantVector(
                 sources_const->template getValue<FromValueType>(),
-                *col_to, delta_column, time_zone, scale);
+                *col_to, delta_column, time_zone, scale, input_rows_count);
         }
         else
         {
@@ -708,25 +701,25 @@ public:
     bool useDefaultImplementationForConstants() const override { return true; }
     ColumnNumbers getArgumentsThatAreAlwaysConstant() const override { return {2}; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr & result_type, size_t input_rows_count) const override
     {
         const IDataType * from_type = arguments[0].type.get();
         WhichDataType which(from_type);
 
         if (which.isDate())
-            return DateTimeAddIntervalImpl<DataTypeDate, TransformResultDataType<DataTypeDate>, Transform>::execute(Transform{}, arguments, result_type, 0);
+            return DateTimeAddIntervalImpl<DataTypeDate, TransformResultDataType<DataTypeDate>, Transform>::execute(Transform{}, arguments, result_type, 0, input_rows_count);
         else if (which.isDate32())
-            return DateTimeAddIntervalImpl<DataTypeDate32, TransformResultDataType<DataTypeDate32>, Transform>::execute(Transform{}, arguments, result_type, 0);
+            return DateTimeAddIntervalImpl<DataTypeDate32, TransformResultDataType<DataTypeDate32>, Transform>::execute(Transform{}, arguments, result_type, 0, input_rows_count);
         else if (which.isDateTime())
-            return DateTimeAddIntervalImpl<DataTypeDateTime, TransformResultDataType<DataTypeDateTime>, Transform>::execute(Transform{}, arguments, result_type, 0);
+            return DateTimeAddIntervalImpl<DataTypeDateTime, TransformResultDataType<DataTypeDateTime>, Transform>::execute(Transform{}, arguments, result_type, 0, input_rows_count);
         else if (which.isDateTime64())
         {
             const auto * datetime64_type = assert_cast<const DataTypeDateTime64 *>(from_type);
             auto from_scale = datetime64_type->getScale();
-            return DateTimeAddIntervalImpl<DataTypeDateTime64, TransformResultDataType<DataTypeDateTime64>, Transform>::execute(Transform{}, arguments, result_type, from_scale);
+            return DateTimeAddIntervalImpl<DataTypeDateTime64, TransformResultDataType<DataTypeDateTime64>, Transform>::execute(Transform{}, arguments, result_type, from_scale, input_rows_count);
         }
         else if (which.isString())
-            return DateTimeAddIntervalImpl<DataTypeString, DataTypeDateTime64, Transform>::execute(Transform{}, arguments, result_type, 3);
+            return DateTimeAddIntervalImpl<DataTypeString, DataTypeDateTime64, Transform>::execute(Transform{}, arguments, result_type, 3, input_rows_count);
         else
             throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Illegal type {} of first argument of function {}", arguments[0].type->getName(), getName());
     }

src/Functions/FunctionMathBinaryFloat64.h

@@ -54,7 +54,7 @@ private:
     }
 
     template <typename LeftType, typename RightType>
-    static ColumnPtr executeTyped(const ColumnConst * left_arg, const IColumn * right_arg)
+    static ColumnPtr executeTyped(const ColumnConst * left_arg, const IColumn * right_arg, size_t input_rows_count)
     {
         if (const auto right_arg_typed = checkAndGetColumn<ColumnVector<RightType>>(right_arg))
         {
@@ -63,12 +63,11 @@ private:
             LeftType left_src_data[Impl::rows_per_iteration];
             std::fill(std::begin(left_src_data), std::end(left_src_data), left_arg->template getValue<LeftType>());
             const auto & right_src_data = right_arg_typed->getData();
-            const auto src_size = right_src_data.size();
             auto & dst_data = dst->getData();
-            dst_data.resize(src_size);
+            dst_data.resize(input_rows_count);
 
-            const auto rows_remaining = src_size % Impl::rows_per_iteration;
+            const auto rows_remaining = input_rows_count % Impl::rows_per_iteration;
-            const auto rows_size = src_size - rows_remaining;
+            const auto rows_size = input_rows_count - rows_remaining;
 
             for (size_t i = 0; i < rows_size; i += Impl::rows_per_iteration)
                 Impl::execute(left_src_data, &right_src_data[i], &dst_data[i]);
@@ -92,7 +91,7 @@ private:
     }
 
     template <typename LeftType, typename RightType>
-    static ColumnPtr executeTyped(const ColumnVector<LeftType> * left_arg, const IColumn * right_arg)
+    static ColumnPtr executeTyped(const ColumnVector<LeftType> * left_arg, const IColumn * right_arg, size_t input_rows_count)
     {
         if (const auto right_arg_typed = checkAndGetColumn<ColumnVector<RightType>>(right_arg))
         {
@@ -100,12 +99,11 @@ private:
 
             const auto & left_src_data = left_arg->getData();
             const auto & right_src_data = right_arg_typed->getData();
-            const auto src_size = left_src_data.size();
             auto & dst_data = dst->getData();
-            dst_data.resize(src_size);
+            dst_data.resize(input_rows_count);
 
-            const auto rows_remaining = src_size % Impl::rows_per_iteration;
+            const auto rows_remaining = input_rows_count % Impl::rows_per_iteration;
-            const auto rows_size = src_size - rows_remaining;
+            const auto rows_size = input_rows_count - rows_remaining;
 
             for (size_t i = 0; i < rows_size; i += Impl::rows_per_iteration)
                 Impl::execute(&left_src_data[i], &right_src_data[i], &dst_data[i]);
@@ -136,12 +134,11 @@ private:
             const auto & left_src_data = left_arg->getData();
             RightType right_src_data[Impl::rows_per_iteration];
             std::fill(std::begin(right_src_data), std::end(right_src_data), right_arg_typed->template getValue<RightType>());
-            const auto src_size = left_src_data.size();
             auto & dst_data = dst->getData();
-            dst_data.resize(src_size);
+            dst_data.resize(input_rows_count);
 
-            const auto rows_remaining = src_size % Impl::rows_per_iteration;
+            const auto rows_remaining = input_rows_count % Impl::rows_per_iteration;
-            const auto rows_size = src_size - rows_remaining;
+            const auto rows_size = input_rows_count - rows_remaining;
 
             for (size_t i = 0; i < rows_size; i += Impl::rows_per_iteration)
                 Impl::execute(&left_src_data[i], right_src_data, &dst_data[i]);
@@ -165,7 +162,7 @@ private:
         return nullptr;
     }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const ColumnWithTypeAndName & col_left = arguments[0];
         const ColumnWithTypeAndName & col_right = arguments[1];
@@ -202,7 +199,7 @@ private:
 
             if (const auto left_arg_typed = checkAndGetColumn<ColVecLeft>(left_arg))
             {
-                if ((res = executeTyped<LeftType, RightType>(left_arg_typed, right_arg)))
+                if ((res = executeTyped<LeftType, RightType>(left_arg_typed, right_arg, input_rows_count)))
                     return true;
 
                 throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of second argument of function {}",
@@ -210,7 +207,7 @@ private:
             }
             if (const auto left_arg_typed = checkAndGetColumnConst<ColVecLeft>(left_arg))
             {
-                if ((res = executeTyped<LeftType, RightType>(left_arg_typed, right_arg)))
+                if ((res = executeTyped<LeftType, RightType>(left_arg_typed, right_arg, input_rows_count)))
                     return true;
 
                 throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of second argument of function {}",

src/Functions/FunctionMathUnary.h

@@ -106,42 +106,40 @@ private:
     }
 
     template <typename T, typename ReturnType>
-    static ColumnPtr execute(const ColumnVector<T> * col)
+    static ColumnPtr execute(const ColumnVector<T> * col, size_t input_rows_count)
     {
         const auto & src_data = col->getData();
-        const size_t size = src_data.size();
 
         auto dst = ColumnVector<ReturnType>::create();
         auto & dst_data = dst->getData();
-        dst_data.resize(size);
+        dst_data.resize(input_rows_count);
 
-        executeInIterations(src_data.data(), dst_data.data(), size);
+        executeInIterations(src_data.data(), dst_data.data(), input_rows_count);
 
         return dst;
     }
 
     template <typename T, typename ReturnType>
-    static ColumnPtr execute(const ColumnDecimal<T> * col)
+    static ColumnPtr execute(const ColumnDecimal<T> * col, size_t input_rows_count)
     {
         const auto & src_data = col->getData();
-        const size_t size = src_data.size();
         UInt32 scale = col->getScale();
 
         auto dst = ColumnVector<ReturnType>::create();
         auto & dst_data = dst->getData();
-        dst_data.resize(size);
+        dst_data.resize(input_rows_count);
 
-        for (size_t i = 0; i < size; ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
             dst_data[i] = DecimalUtils::convertTo<ReturnType>(src_data[i], scale);
 
-        executeInIterations(dst_data.data(), dst_data.data(), size);
+        executeInIterations(dst_data.data(), dst_data.data(), input_rows_count);
 
         return dst;
     }
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const ColumnWithTypeAndName & col = arguments[0];
         ColumnPtr res;
@@ -156,7 +154,7 @@ private:
             const auto col_vec = checkAndGetColumn<ColVecType>(col.column.get());
             if (col_vec == nullptr)
                 return false;
-            return (res = execute<Type, ReturnType>(col_vec)) != nullptr;
+            return (res = execute<Type, ReturnType>(col_vec, input_rows_count)) != nullptr;
         };
 
         if (!callOnBasicType<void, true, true, true, false>(col.type->getTypeId(), call))

src/Functions/FunctionNumericPredicate.h

@@ -53,39 +53,37 @@ public:
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const auto * in = arguments.front().column.get();
 
         ColumnPtr res;
-        if (!((res = execute<UInt8>(in))
+        if (!((res = execute<UInt8>(in, input_rows_count))
-            || (res = execute<UInt16>(in))
+            || (res = execute<UInt16>(in, input_rows_count))
-            || (res = execute<UInt32>(in))
+            || (res = execute<UInt32>(in, input_rows_count))
-            || (res = execute<UInt64>(in))
+            || (res = execute<UInt64>(in, input_rows_count))
-            || (res = execute<Int8>(in))
+            || (res = execute<Int8>(in, input_rows_count))
-            || (res = execute<Int16>(in))
+            || (res = execute<Int16>(in, input_rows_count))
-            || (res = execute<Int32>(in))
+            || (res = execute<Int32>(in, input_rows_count))
-            || (res = execute<Int64>(in))
+            || (res = execute<Int64>(in, input_rows_count))
-            || (res = execute<Float32>(in))
+            || (res = execute<Float32>(in, input_rows_count))
-            || (res = execute<Float64>(in))))
+            || (res = execute<Float64>(in, input_rows_count))))
             throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of first argument of function {}", in->getName(), getName());
 
         return res;
     }
 
     template <typename T>
-    ColumnPtr execute(const IColumn * in_untyped) const
+    ColumnPtr execute(const IColumn * in_untyped, size_t input_rows_count) const
     {
         if (const auto in = checkAndGetColumn<ColumnVector<T>>(in_untyped))
         {
-            const auto size = in->size();
+            auto out = ColumnUInt8::create(input_rows_count);
-
-            auto out = ColumnUInt8::create(size);
 
             const auto & in_data = in->getData();
             auto & out_data = out->getData();
 
-            for (const auto i : collections::range(0, size))
+            for (size_t i = 0; i < input_rows_count; ++i)
                 out_data[i] = Impl::execute(in_data[i]);
 
             return out;

src/Functions/FunctionSpaceFillingCurve.h

@@ -132,9 +132,7 @@ public:
         }
         DataTypes types(tuple_size);
         for (size_t i = 0; i < tuple_size; i++)
-        {
             types[i] = std::make_shared<DataTypeUInt64>();
-        }
         return std::make_shared<DataTypeTuple>(types);
     }
 };

src/Functions/FunctionStringOrArrayToT.h

@@ -71,7 +71,7 @@ public:
 
             typename ColumnVector<ResultType>::Container & vec_res = col_res->getData();
             vec_res.resize(col->size());
-            Impl::vector(col->getChars(), col->getOffsets(), vec_res);
+            Impl::vector(col->getChars(), col->getOffsets(), vec_res, input_rows_count);
 
             return col_res;
         }
@@ -80,7 +80,7 @@ public:
             if (Impl::is_fixed_to_constant)
             {
                 ResultType res = 0;
-                Impl::vectorFixedToConstant(col_fixed->getChars(), col_fixed->getN(), res);
+                Impl::vectorFixedToConstant(col_fixed->getChars(), col_fixed->getN(), res, input_rows_count);
 
                 return result_type->createColumnConst(col_fixed->size(), toField(res));
             }
@@ -90,7 +90,7 @@ public:
 
                 typename ColumnVector<ResultType>::Container & vec_res = col_res->getData();
                 vec_res.resize(col_fixed->size());
-                Impl::vectorFixedToVector(col_fixed->getChars(), col_fixed->getN(), vec_res);
+                Impl::vectorFixedToVector(col_fixed->getChars(), col_fixed->getN(), vec_res, input_rows_count);
 
                 return col_res;
             }
@@ -101,7 +101,7 @@ public:
 
             typename ColumnVector<ResultType>::Container & vec_res = col_res->getData();
             vec_res.resize(col_arr->size());
-            Impl::array(col_arr->getOffsets(), vec_res);
+            Impl::array(col_arr->getOffsets(), vec_res, input_rows_count);
 
             return col_res;
         }
@@ -112,7 +112,7 @@ public:
             vec_res.resize(col_map->size());
             const auto & col_nested = col_map->getNestedColumn();
 
-            Impl::array(col_nested.getOffsets(), vec_res);
+            Impl::array(col_nested.getOffsets(), vec_res, input_rows_count);
             return col_res;
         }
         else if (const ColumnUUID * col_uuid = checkAndGetColumn<ColumnUUID>(column.get()))
@@ -120,7 +120,7 @@ public:
             auto col_res = ColumnVector<ResultType>::create();
             typename ColumnVector<ResultType>::Container & vec_res = col_res->getData();
             vec_res.resize(col_uuid->size());
-            Impl::uuid(col_uuid->getData(), input_rows_count, vec_res);
+            Impl::uuid(col_uuid->getData(), input_rows_count, vec_res, input_rows_count);
             return col_res;
         }
         else if (const ColumnIPv6 * col_ipv6 = checkAndGetColumn<ColumnIPv6>(column.get()))
@@ -128,7 +128,7 @@ public:
             auto col_res = ColumnVector<ResultType>::create();
             typename ColumnVector<ResultType>::Container & vec_res = col_res->getData();
             vec_res.resize(col_ipv6->size());
-            Impl::ipv6(col_ipv6->getData(), input_rows_count, vec_res);
+            Impl::ipv6(col_ipv6->getData(), input_rows_count, vec_res, input_rows_count);
             return col_res;
         }
         else if (const ColumnIPv4 * col_ipv4 = checkAndGetColumn<ColumnIPv4>(column.get()))
@@ -136,7 +136,7 @@ public:
             auto col_res = ColumnVector<ResultType>::create();
             typename ColumnVector<ResultType>::Container & vec_res = col_res->getData();
             vec_res.resize(col_ipv4->size());
-            Impl::ipv4(col_ipv4->getData(), input_rows_count, vec_res);
+            Impl::ipv4(col_ipv4->getData(), input_rows_count, vec_res, input_rows_count);
             return col_res;
         }
         else

src/Functions/FunctionStringReplace.h

@@ -45,7 +45,7 @@ public:
         return std::make_shared<DataTypeString>();
     }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         ColumnPtr column_haystack = arguments[0].column;
         column_haystack = column_haystack->convertToFullColumnIfConst();
@@ -70,7 +70,8 @@ public:
                 col_haystack->getChars(), col_haystack->getOffsets(),
                 col_needle_const->getValue<String>(),
                 col_replacement_const->getValue<String>(),
-                col_res->getChars(), col_res->getOffsets());
+                col_res->getChars(), col_res->getOffsets(),
+                input_rows_count);
             return col_res;
         }
         else if (col_haystack && col_needle_vector && col_replacement_const)
@@ -79,7 +80,8 @@ public:
                 col_haystack->getChars(), col_haystack->getOffsets(),
                 col_needle_vector->getChars(), col_needle_vector->getOffsets(),
                 col_replacement_const->getValue<String>(),
-                col_res->getChars(), col_res->getOffsets());
+                col_res->getChars(), col_res->getOffsets(),
+                input_rows_count);
             return col_res;
         }
         else if (col_haystack && col_needle_const && col_replacement_vector)
@@ -88,7 +90,8 @@ public:
                 col_haystack->getChars(), col_haystack->getOffsets(),
                 col_needle_const->getValue<String>(),
                 col_replacement_vector->getChars(), col_replacement_vector->getOffsets(),
-                col_res->getChars(), col_res->getOffsets());
+                col_res->getChars(), col_res->getOffsets(),
+                input_rows_count);
             return col_res;
         }
         else if (col_haystack && col_needle_vector && col_replacement_vector)
@@ -97,7 +100,8 @@ public:
                 col_haystack->getChars(), col_haystack->getOffsets(),
                 col_needle_vector->getChars(), col_needle_vector->getOffsets(),
                 col_replacement_vector->getChars(), col_replacement_vector->getOffsets(),
-                col_res->getChars(), col_res->getOffsets());
+                col_res->getChars(), col_res->getOffsets(),
+                input_rows_count);
             return col_res;
         }
         else if (col_haystack_fixed && col_needle_const && col_replacement_const)
@@ -106,7 +110,8 @@ public:
                 col_haystack_fixed->getChars(), col_haystack_fixed->getN(),
                 col_needle_const->getValue<String>(),
                 col_replacement_const->getValue<String>(),
-                col_res->getChars(), col_res->getOffsets());
+                col_res->getChars(), col_res->getOffsets(),
+                input_rows_count);
             return col_res;
         }
         else

src/Functions/FunctionsBinaryRepresentation.cpp

@@ -632,7 +632,7 @@ public:
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const ColumnPtr & column = arguments[0].column;
 
@@ -646,11 +646,10 @@ public:
             const ColumnString::Chars & in_vec = col->getChars();
             const ColumnString::Offsets & in_offsets = col->getOffsets();
 
-            size_t size = in_offsets.size();
+            out_offsets.resize(input_rows_count);
-            out_offsets.resize(size);
 
             size_t max_out_len = 0;
-            for (size_t i = 0; i < in_offsets.size(); ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
             {
                 const size_t len = in_offsets[i] - (i == 0 ? 0 : in_offsets[i - 1])
                     - /* trailing zero symbol that is always added in ColumnString and that is ignored while decoding */ 1;
@@ -662,7 +661,7 @@ public:
             char * pos = begin;
             size_t prev_offset = 0;
 
-            for (size_t i = 0; i < size; ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
             {
                 size_t new_offset = in_offsets[i];
 
@@ -691,15 +690,14 @@ public:
             const ColumnString::Chars & in_vec = col_fix_string->getChars();
             const size_t n = col_fix_string->getN();
 
-            size_t size = col_fix_string->size();
+            out_offsets.resize(input_rows_count);
-            out_offsets.resize(size);
+            out_vec.resize(((n + word_size - 1) / word_size + /* trailing zero symbol that is always added by Impl::decode */ 1) * input_rows_count);
-            out_vec.resize(((n + word_size - 1) / word_size + /* trailing zero symbol that is always added by Impl::decode */ 1) * size);
 
             char * begin = reinterpret_cast<char *>(out_vec.data());
             char * pos = begin;
             size_t prev_offset = 0;
 
-            for (size_t i = 0; i < size; ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
             {
                 size_t new_offset = prev_offset + n;
 

src/Functions/FunctionsBitToArray.cpp

@@ -60,17 +60,17 @@ public:
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         ColumnPtr res;
-        if (!((res = executeType<UInt8>(arguments))
+        if (!((res = executeType<UInt8>(arguments, input_rows_count))
-            || (res = executeType<UInt16>(arguments))
+            || (res = executeType<UInt16>(arguments, input_rows_count))
-            || (res = executeType<UInt32>(arguments))
+            || (res = executeType<UInt32>(arguments, input_rows_count))
-            || (res = executeType<UInt64>(arguments))
+            || (res = executeType<UInt64>(arguments, input_rows_count))
-            || (res = executeType<Int8>(arguments))
+            || (res = executeType<Int8>(arguments, input_rows_count))
-            || (res = executeType<Int16>(arguments))
+            || (res = executeType<Int16>(arguments, input_rows_count))
-            || (res = executeType<Int32>(arguments))
+            || (res = executeType<Int32>(arguments, input_rows_count))
-            || (res = executeType<Int64>(arguments))))
+            || (res = executeType<Int64>(arguments, input_rows_count))))
             throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Illegal column {} of argument of function {}",
                             arguments[0].column->getName(), getName());
 
@@ -98,7 +98,7 @@ private:
     }
 
     template <typename T>
-    ColumnPtr executeType(const ColumnsWithTypeAndName & columns) const
+    ColumnPtr executeType(const ColumnsWithTypeAndName & columns, size_t input_rows_count) const
     {
         if (const ColumnVector<T> * col_from = checkAndGetColumn<ColumnVector<T>>(columns[0].column.get()))
         {
@@ -107,13 +107,12 @@ private:
             const typename ColumnVector<T>::Container & vec_from = col_from->getData();
             ColumnString::Chars & data_to = col_to->getChars();
             ColumnString::Offsets & offsets_to = col_to->getOffsets();
-            size_t size = vec_from.size();
+            data_to.resize(input_rows_count * 2);
-            data_to.resize(size * 2);
+            offsets_to.resize(input_rows_count);
-            offsets_to.resize(size);
 
             WriteBufferFromVector<ColumnString::Chars> buf_to(data_to);
 
-            for (size_t i = 0; i < size; ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
             {
                 writeBitmask<T>(vec_from[i], buf_to);
                 writeChar(0, buf_to);
@@ -244,7 +243,7 @@ public:
     bool useDefaultImplementationForConstants() const override { return true; }
 
     template <typename T>
-    ColumnPtr executeType(const IColumn * column) const
+    ColumnPtr executeType(const IColumn * column, size_t input_rows_count) const
     {
         const ColumnVector<T> * col_from = checkAndGetColumn<ColumnVector<T>>(column);
         if (!col_from)
@@ -257,13 +256,12 @@ public:
         auto & result_array_offsets_data = result_array_offsets->getData();
 
         auto & vec_from = col_from->getData();
-        size_t size = vec_from.size();
+        result_array_offsets_data.resize(input_rows_count);
-        result_array_offsets_data.resize(size);
+        result_array_values_data.reserve(input_rows_count * 2);
-        result_array_values_data.reserve(size * 2);
 
         using UnsignedType = make_unsigned_t<T>;
 
-        for (size_t row = 0; row < size; ++row)
+        for (size_t row = 0; row < input_rows_count; ++row)
         {
             UnsignedType x = static_cast<UnsignedType>(vec_from[row]);
 
@@ -302,24 +300,24 @@ public:
         return result_column;
     }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const IColumn * in_column = arguments[0].column.get();
         ColumnPtr result_column;
 
-        if (!((result_column = executeType<UInt8>(in_column))
+        if (!((result_column = executeType<UInt8>(in_column, input_rows_count))
-              || (result_column = executeType<UInt16>(in_column))
+              || (result_column = executeType<UInt16>(in_column, input_rows_count))
-              || (result_column = executeType<UInt32>(in_column))
+              || (result_column = executeType<UInt32>(in_column, input_rows_count))
-              || (result_column = executeType<UInt32>(in_column))
+              || (result_column = executeType<UInt32>(in_column, input_rows_count))
-              || (result_column = executeType<UInt64>(in_column))
+              || (result_column = executeType<UInt64>(in_column, input_rows_count))
-              || (result_column = executeType<UInt128>(in_column))
+              || (result_column = executeType<UInt128>(in_column, input_rows_count))
-              || (result_column = executeType<UInt256>(in_column))
+              || (result_column = executeType<UInt256>(in_column, input_rows_count))
-              || (result_column = executeType<Int8>(in_column))
+              || (result_column = executeType<Int8>(in_column, input_rows_count))
-              || (result_column = executeType<Int16>(in_column))
+              || (result_column = executeType<Int16>(in_column, input_rows_count))
-              || (result_column = executeType<Int32>(in_column))
+              || (result_column = executeType<Int32>(in_column, input_rows_count))
-              || (result_column = executeType<Int64>(in_column))
+              || (result_column = executeType<Int64>(in_column, input_rows_count))
-              || (result_column = executeType<Int128>(in_column))
+              || (result_column = executeType<Int128>(in_column, input_rows_count))
-              || (result_column = executeType<Int256>(in_column))))
+              || (result_column = executeType<Int256>(in_column, input_rows_count))))
         {
             throw Exception(ErrorCodes::ILLEGAL_COLUMN,
                             "Illegal column {} of first argument of function {}",

src/Functions/FunctionsBitmap.h

@@ -155,7 +155,7 @@ public:
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /* input_rows_count */) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const IDataType * from_type = arguments[0].type.get();
         const auto * array_type = typeid_cast<const DataTypeArray *>(from_type);
@@ -165,21 +165,21 @@ public:
 
         WhichDataType which(nested_type);
         if (which.isUInt8())
-            return executeBitmapData<UInt8>(argument_types, arguments);
+            return executeBitmapData<UInt8>(argument_types, arguments, input_rows_count);
         else if (which.isUInt16())
-            return executeBitmapData<UInt16>(argument_types, arguments);
+            return executeBitmapData<UInt16>(argument_types, arguments, input_rows_count);
         else if (which.isUInt32())
-            return executeBitmapData<UInt32>(argument_types, arguments);
+            return executeBitmapData<UInt32>(argument_types, arguments, input_rows_count);
         else if (which.isUInt64())
-            return executeBitmapData<UInt64>(argument_types, arguments);
+            return executeBitmapData<UInt64>(argument_types, arguments, input_rows_count);
         else if (which.isInt8())
-            return executeBitmapData<Int8>(argument_types, arguments);
+            return executeBitmapData<Int8>(argument_types, arguments, input_rows_count);
         else if (which.isInt16())
-            return executeBitmapData<Int16>(argument_types, arguments);
+            return executeBitmapData<Int16>(argument_types, arguments, input_rows_count);
         else if (which.isInt32())
-            return executeBitmapData<Int32>(argument_types, arguments);
+            return executeBitmapData<Int32>(argument_types, arguments, input_rows_count);
         else if (which.isInt64())
-            return executeBitmapData<Int64>(argument_types, arguments);
+            return executeBitmapData<Int64>(argument_types, arguments, input_rows_count);
         else
             throw Exception(ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT, "Unexpected type {} of argument of function {}",
                 from_type->getName(), getName());
@@ -187,7 +187,7 @@ public:
 
 private:
     template <typename T>
-    ColumnPtr executeBitmapData(DataTypes & argument_types, const ColumnsWithTypeAndName & arguments) const
+    ColumnPtr executeBitmapData(DataTypes & argument_types, const ColumnsWithTypeAndName & arguments, size_t input_rows_count) const
     {
         // input data
         const ColumnArray * array = typeid_cast<const ColumnArray *>(arguments[0].column.get());
@@ -203,10 +203,10 @@ private:
         AggregateFunctionPtr bitmap_function = AggregateFunctionFactory::instance().get(
             AggregateFunctionGroupBitmapData<T>::name(), action, argument_types, params_row, properties);
         auto col_to = ColumnAggregateFunction::create(bitmap_function);
-        col_to->reserve(offsets.size());
+        col_to->reserve(input_rows_count);
 
         size_t pos = 0;
-        for (size_t i = 0; i < offsets.size(); ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             col_to->insertDefault();
             AggregateFunctionGroupBitmapData<T> & bitmap_data

src/Functions/FunctionsCharsetClassification.cpp

@@ -23,7 +23,7 @@ namespace
     constexpr size_t max_string_size = 1UL << 15;
 
     template <typename ModelMap>
-    ALWAYS_INLINE inline Float64 naiveBayes(
+    Float64 naiveBayes(
         const FrequencyHolder::EncodingMap & standard,
         const ModelMap & model,
         Float64 max_result)
@@ -51,7 +51,7 @@ namespace
 
     /// Count how many times each bigram occurs in the text.
     template <typename ModelMap>
-    ALWAYS_INLINE inline void calculateStats(
+    void calculateStats(
         const UInt8 * data,
         const size_t size,
         ModelMap & model)
@@ -77,24 +77,25 @@ struct CharsetClassificationImpl
         const ColumnString::Chars & data,
         const ColumnString::Offsets & offsets,
         ColumnString::Chars & res_data,
-        ColumnString::Offsets & res_offsets)
+        ColumnString::Offsets & res_offsets,
+        size_t input_rows_count)
     {
         const auto & encodings_freq = FrequencyHolder::getInstance().getEncodingsFrequency();
 
         if constexpr (detect_language)
             /// 2 chars for ISO code + 1 zero byte
-            res_data.reserve(offsets.size() * 3);
+            res_data.reserve(input_rows_count * 3);
         else
             /// Mean charset length is 8
-            res_data.reserve(offsets.size() * 8);
+            res_data.reserve(input_rows_count * 8);
 
-        res_offsets.resize(offsets.size());
+        res_offsets.resize(input_rows_count);
 
         size_t current_result_offset = 0;
 
         double zero_frequency_log = log(zero_frequency);
 
-        for (size_t i = 0; i < offsets.size(); ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             const UInt8 * str = data.data() + offsets[i - 1];
             const size_t str_len = offsets[i] - offsets[i - 1] - 1;

src/Functions/FunctionsCodingIP.cpp

@@ -341,7 +341,7 @@ class FunctionIPv4NumToString : public IFunction
 {
 private:
     template <typename ArgType>
-    ColumnPtr executeTyped(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const
+    ColumnPtr executeTyped(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const
     {
         using ColumnType = ColumnVector<ArgType>;
 
@@ -356,12 +356,12 @@ private:
             ColumnString::Chars & vec_res = col_res->getChars();
             ColumnString::Offsets & offsets_res = col_res->getOffsets();
 
-            vec_res.resize(vec_in.size() * (IPV4_MAX_TEXT_LENGTH + 1)); /// the longest value is: 255.255.255.255\0
+            vec_res.resize(input_rows_count * (IPV4_MAX_TEXT_LENGTH + 1)); /// the longest value is: 255.255.255.255\0
-            offsets_res.resize(vec_in.size());
+            offsets_res.resize(input_rows_count);
             char * begin = reinterpret_cast<char *>(vec_res.data());
             char * pos = begin;
 
-            for (size_t i = 0; i < vec_in.size(); ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
             {
                 DB::formatIPv4(reinterpret_cast<const unsigned char*>(&vec_in[i]), sizeof(ArgType), pos, mask_tail_octets, "xxx");
                 offsets_res[i] = pos - begin;
@@ -532,7 +532,7 @@ public:
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const auto & col_type_name = arguments[0];
         const ColumnPtr & column = col_type_name.column;
@@ -542,11 +542,11 @@ public:
             auto col_res = ColumnIPv6::create();
 
             auto & vec_res = col_res->getData();
-            vec_res.resize(col_in->size());
+            vec_res.resize(input_rows_count);
 
             const auto & vec_in = col_in->getData();
 
-            for (size_t i = 0; i < vec_res.size(); ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
                 mapIPv4ToIPv6(vec_in[i], reinterpret_cast<UInt8 *>(&vec_res[i].toUnderType()));
 
             return col_res;
@@ -557,7 +557,7 @@ public:
             auto col_res = ColumnFixedString::create(IPV6_BINARY_LENGTH);
 
             auto & vec_res = col_res->getChars();
-            vec_res.resize(col_in->size() * IPV6_BINARY_LENGTH);
+            vec_res.resize(input_rows_count * IPV6_BINARY_LENGTH);
 
             const auto & vec_in = col_in->getData();
 
@@ -742,7 +742,7 @@ public:
 
     bool useDefaultImplementationForConstants() const override { return true; }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const ColumnPtr & column = arguments[0].column;
 
@@ -751,13 +751,13 @@ public:
             auto col_res = ColumnUInt64::create();
 
             ColumnUInt64::Container & vec_res = col_res->getData();
-            vec_res.resize(col->size());
+            vec_res.resize(input_rows_count);
 
             const ColumnString::Chars & vec_src = col->getChars();
             const ColumnString::Offsets & offsets_src = col->getOffsets();
             size_t prev_offset = 0;
 
-            for (size_t i = 0; i < vec_res.size(); ++i)
+            for (size_t i = 0; i < input_rows_count; ++i)
             {
                 size_t current_offset = offsets_src[i];
                 size_t string_size = current_offset - prev_offset - 1; /// mind the terminating zero byte
@@ -1054,7 +1054,7 @@ public:
         return std::make_shared<DataTypeUInt8>();
     }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const ColumnString * input_column = checkAndGetColumn<ColumnString>(arguments[0].column.get());
 
@@ -1067,14 +1067,14 @@ public:
         auto col_res = ColumnUInt8::create();
 
         ColumnUInt8::Container & vec_res = col_res->getData();
-        vec_res.resize(input_column->size());
+        vec_res.resize(input_rows_count);
 
         const ColumnString::Chars & vec_src = input_column->getChars();
         const ColumnString::Offsets & offsets_src = input_column->getOffsets();
         size_t prev_offset = 0;
         UInt32 result = 0;
 
-        for (size_t i = 0; i < vec_res.size(); ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             vec_res[i] = DB::parseIPv4whole(reinterpret_cast<const char *>(&vec_src[prev_offset]), reinterpret_cast<unsigned char *>(&result));
             prev_offset = offsets_src[i];
@@ -1110,7 +1110,7 @@ public:
         return std::make_shared<DataTypeUInt8>();
     }
 
-    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t /*input_rows_count*/) const override
+    ColumnPtr executeImpl(const ColumnsWithTypeAndName & arguments, const DataTypePtr &, size_t input_rows_count) const override
     {
         const ColumnString * input_column = checkAndGetColumn<ColumnString>(arguments[0].column.get());
         if (!input_column)
@@ -1122,14 +1122,14 @@ public:
         auto col_res = ColumnUInt8::create();
 
         ColumnUInt8::Container & vec_res = col_res->getData();
-        vec_res.resize(input_column->size());
+        vec_res.resize(input_rows_count);
 
         const ColumnString::Chars & vec_src = input_column->getChars();
         const ColumnString::Offsets & offsets_src = input_column->getOffsets();
         size_t prev_offset = 0;
         char buffer[IPV6_BINARY_LENGTH];
 
-        for (size_t i = 0; i < vec_res.size(); ++i)
+        for (size_t i = 0; i < input_rows_count; ++i)
         {
             vec_res[i] = DB::parseIPv6whole(reinterpret_cast<const char *>(&vec_src[prev_offset]),
                                             reinterpret_cast<const char *>(&vec_src[offsets_src[i] - 1]),