Merge branch 'master' into fffix

.github/codecov.yml

@@ -1,5 +1,5 @@
 codecov:
-  max_report_age: off
+  max_report_age: "off"
   strict_yaml_branch: "master"
 
 ignore:

.github/workflows/anchore-analysis.yml

@@ -8,7 +8,7 @@
 
 name: Docker Container Scan (clickhouse-server)
 
-on:
+"on":
   pull_request:
     paths:
       - docker/server/Dockerfile
@@ -20,20 +20,20 @@ jobs:
   Anchore-Build-Scan:
     runs-on: ubuntu-latest
     steps:
-    - name: Checkout the code
-      uses: actions/checkout@v2
-    - name: Build the Docker image
-      run: |
-        cd docker/server
-        perl -pi -e 's|=\$version||g' Dockerfile
-        docker build . --file Dockerfile --tag localbuild/testimage:latest      
-    - name: Run the local Anchore scan action itself with GitHub Advanced Security code scanning integration enabled
-      uses: anchore/scan-action@v2
-      id: scan
-      with:
-        image: "localbuild/testimage:latest"
-        acs-report-enable: true
-    - name: Upload Anchore Scan Report
-      uses: github/codeql-action/upload-sarif@v1
-      with:
-        sarif_file: ${{ steps.scan.outputs.sarif }}
+      - name: Checkout the code
+        uses: actions/checkout@v2
+      - name: Build the Docker image
+        run: |
+          cd docker/server
+          perl -pi -e 's|=\$version||g' Dockerfile
+          docker build . --file Dockerfile --tag localbuild/testimage:latest
+      - name: Run the local Anchore scan action itself with GitHub Advanced Security code scanning integration enabled
+        uses: anchore/scan-action@v2
+        id: scan
+        with:
+          image: "localbuild/testimage:latest"
+          acs-report-enable: true
+      - name: Upload Anchore Scan Report
+        uses: github/codeql-action/upload-sarif@v1
+        with:
+          sarif_file: ${{ steps.scan.outputs.sarif }}

.github/workflows/codeql-analysis.yml

@@ -1,32 +0,0 @@
-# See the example here: https://github.com/github/codeql-action
-
-name: "CodeQL Scanning"
-
-on:
-  schedule:
-    - cron: '0 19 * * *'
-jobs:
-  CodeQL-Build:
-
-    runs-on: self-hosted
-    timeout-minutes: 1440
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v2
-      with:
-        fetch-depth: 2
-        submodules: 'recursive'
-
-    - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
-
-      with:
-        languages: cpp
-
-    - run: sudo apt-get update && sudo apt-get install -y git cmake python ninja-build gcc-10 g++-10 && mkdir build
-    - run: cd build && CC=gcc-10 CXX=g++-10 cmake ..
-    - run: cd build && ninja
-
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1

.gitignore

@@ -137,3 +137,9 @@ website/package-lock.json
 /prof
 
 *.iml
+
+# data store
+/programs/server/data
+/programs/server/metadata
+/programs/server/store
+

.gitmodules

@@ -184,7 +184,7 @@
 	url = https://github.com/ClickHouse-Extras/krb5
 [submodule "contrib/cyrus-sasl"]
 	path = contrib/cyrus-sasl
-	url = https://github.com/cyrusimap/cyrus-sasl
+	url = https://github.com/ClickHouse-Extras/cyrus-sasl
 	branch = cyrus-sasl-2.1
 [submodule "contrib/croaring"]
 	path = contrib/croaring
@@ -220,4 +220,4 @@
 	url = https://github.com/ClickHouse-Extras/boringssl.git
 [submodule "contrib/NuRaft"]
 	path = contrib/NuRaft
-	url = https://github.com/eBay/NuRaft.git
+	url = https://github.com/ClickHouse-Extras/NuRaft.git

.potato.yml

@@ -14,14 +14,14 @@ handlers:
         # The trigger for creating the Yandex.Tracker issue. When the specified event occurs, it transfers PR data to Yandex.Tracker.
         github:pullRequest:labeled:
           data:
-              # The Yandex.Tracker queue to create the issue in. Each issue in Tracker belongs to one of the project queues.
-          	queue: CLICKHOUSEDOCS
-              # The issue title.
-          	summary: '[Potato] Pull Request #{{pullRequest.number}}'
-              # The issue description.
-          	description: >
+          # The Yandex.Tracker queue to create the issue in. Each issue in Tracker belongs to one of the project queues.
+          queue: CLICKHOUSEDOCS
+          # The issue title.
+          summary: '[Potato] Pull Request #{{pullRequest.number}}'
+          # The issue description.
+          description: >
                 {{pullRequest.description}}
 
                 Ссылка на Pull Request: {{pullRequest.webUrl}}
-            # The condition for creating the Yandex.Tracker issue.
-        	condition: eventPayload.labels.filter(label => ['pr-feature'].includes(label.name)).length
+          # The condition for creating the Yandex.Tracker issue.
+          condition: eventPayload.labels.filter(label => ['pr-feature'].includes(label.name)).length

.yamllint

@@ -0,0 +1,15 @@
+# vi: ft=yaml
+extends: default
+
+rules:
+    indentation:
+        level: warning
+        indent-sequences: consistent
+    line-length:
+        # there are some bash -c "", so this is OK
+        max: 300
+        level: warning
+    comments:
+        min-spaces-from-content: 1
+    document-start:
+        present: false

CHANGELOG.md

@@ -1,5 +1,180 @@
+## ClickHouse release 21.2
+
+### ClickHouse release v21.2.2.8-stable, 2021-02-07
+
+#### Backward Incompatible Change
+
+* Bitwise functions (`bitAnd`, `bitOr`, etc) are forbidden for floating point arguments. Now you have to do explicit cast to integer. [#19853](https://github.com/ClickHouse/ClickHouse/pull/19853) ([Azat Khuzhin](https://github.com/azat)).
+* Forbid `lcm`/`gcd` for floats. [#19532](https://github.com/ClickHouse/ClickHouse/pull/19532) ([Azat Khuzhin](https://github.com/azat)).
+* Fix memory tracking for `OPTIMIZE TABLE`/merges; account query memory limits and sampling for `OPTIMIZE TABLE`/merges. [#18772](https://github.com/ClickHouse/ClickHouse/pull/18772) ([Azat Khuzhin](https://github.com/azat)).
+* Disallow floating point column as partition key, see [#18421](https://github.com/ClickHouse/ClickHouse/issues/18421#event-4147046255). [#18464](https://github.com/ClickHouse/ClickHouse/pull/18464) ([hexiaoting](https://github.com/hexiaoting)).
+* Excessive parenthesis in type definitions no longer supported, example: `Array((UInt8))`.
+
+#### New Feature
+
+* Added `PostgreSQL` table engine (both select/insert, with support for multidimensional arrays), also as table function. Added `PostgreSQL` dictionary source. Added `PostgreSQL` database engine. [#18554](https://github.com/ClickHouse/ClickHouse/pull/18554) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Data type `Nested` now supports arbitrary levels of nesting. Introduced subcolumns of complex types, such as `size0` in `Array`, `null` in `Nullable`, names of `Tuple` elements, which can be read without reading of whole column. [#17310](https://github.com/ClickHouse/ClickHouse/pull/17310) ([Anton Popov](https://github.com/CurtizJ)).
+* Added `Nullable` support for `FlatDictionary`, `HashedDictionary`, `ComplexKeyHashedDictionary`, `DirectDictionary`, `ComplexKeyDirectDictionary`, `RangeHashedDictionary`. [#18236](https://github.com/ClickHouse/ClickHouse/pull/18236) ([Maksim Kita](https://github.com/kitaisreal)).
+* Adds a new table called `system.distributed_ddl_queue` that displays the queries in the DDL worker queue. [#17656](https://github.com/ClickHouse/ClickHouse/pull/17656) ([Bharat Nallan](https://github.com/bharatnc)).
+* Added support of mapping LDAP group names, and attribute values in general, to local roles for users from ldap user directories. [#17211](https://github.com/ClickHouse/ClickHouse/pull/17211) ([Denis Glazachev](https://github.com/traceon)).
+* Support insert into table function `cluster`, and for both table functions `remote` and `cluster`, support distributing data across nodes by specify sharding key. Close [#16752](https://github.com/ClickHouse/ClickHouse/issues/16752). [#18264](https://github.com/ClickHouse/ClickHouse/pull/18264) ([flynn](https://github.com/ucasFL)).
+* Add function `decodeXMLComponent` to decode characters for XML. Example: `SELECT decodeXMLComponent('Hello,"world"!')` [#17659](https://github.com/ClickHouse/ClickHouse/issues/17659). [#18542](https://github.com/ClickHouse/ClickHouse/pull/18542) ([nauta](https://github.com/nautaa)).
+* Added functions `parseDateTimeBestEffortUSOrZero`, `parseDateTimeBestEffortUSOrNull`. [#19712](https://github.com/ClickHouse/ClickHouse/pull/19712) ([Maksim Kita](https://github.com/kitaisreal)).
+* Add `sign` math function. [#19527](https://github.com/ClickHouse/ClickHouse/pull/19527) ([flynn](https://github.com/ucasFL)).
+* Add information about used features (functions, table engines, etc) into system.query_log. [#18495](https://github.com/ClickHouse/ClickHouse/issues/18495). [#19371](https://github.com/ClickHouse/ClickHouse/pull/19371) ([Kseniia Sumarokova](https://github.com/kssenii)).
+* Function `formatDateTime` support the `%Q` modification to format date to quarter. [#19224](https://github.com/ClickHouse/ClickHouse/pull/19224) ([Jianmei Zhang](https://github.com/zhangjmruc)).
+* Support MetaKey+Enter hotkey binding in play UI. [#19012](https://github.com/ClickHouse/ClickHouse/pull/19012) ([sundyli](https://github.com/sundy-li)).
+* Add three functions for map data type: 1. `mapContains(map, key)` to check weather map.keys include the second parameter key. 2. `mapKeys(map)` return all the keys in Array format 3. `mapValues(map)` return all the values in Array format. [#18788](https://github.com/ClickHouse/ClickHouse/pull/18788) ([hexiaoting](https://github.com/hexiaoting)).
+* Add `log_comment` setting related to [#18494](https://github.com/ClickHouse/ClickHouse/issues/18494). [#18549](https://github.com/ClickHouse/ClickHouse/pull/18549) ([Zijie Lu](https://github.com/TszKitLo40)).
+* Add support of tuple argument to `argMin` and `argMax` functions. [#17359](https://github.com/ClickHouse/ClickHouse/pull/17359) ([Ildus Kurbangaliev](https://github.com/ildus)).
+* Support `EXISTS VIEW` syntax. [#18552](https://github.com/ClickHouse/ClickHouse/pull/18552) ([Du Chuan](https://github.com/spongedu)).
+* Add `SELECT ALL` syntax. closes [#18706](https://github.com/ClickHouse/ClickHouse/issues/18706). [#18723](https://github.com/ClickHouse/ClickHouse/pull/18723) ([flynn](https://github.com/ucasFL)).
+
+#### Performance Improvement
+
+* Faster parts removal by lowering the number of `stat` syscalls. This returns the optimization that existed while ago. More safe interface of `IDisk`. This closes [#19065](https://github.com/ClickHouse/ClickHouse/issues/19065). [#19086](https://github.com/ClickHouse/ClickHouse/pull/19086) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Aliases declared in `WITH` statement are properly used in index analysis. Queries like `WITH column AS alias SELECT ... WHERE alias = ...` may use index now. [#18896](https://github.com/ClickHouse/ClickHouse/pull/18896) ([Amos Bird](https://github.com/amosbird)).
+* Add `optimize_alias_column_prediction` (on by default), that will: - Respect aliased columns in WHERE during partition pruning and skipping data using secondary indexes; - Respect aliased columns in WHERE for trivial count queries for optimize_trivial_count; - Respect aliased columns in GROUP BY/ORDER BY for optimize_aggregation_in_order/optimize_read_in_order. [#16995](https://github.com/ClickHouse/ClickHouse/pull/16995) ([sundyli](https://github.com/sundy-li)).
+* Speed up aggregate function `sum`. Improvement only visible on synthetic benchmarks and not very practical. [#19216](https://github.com/ClickHouse/ClickHouse/pull/19216) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Update libc++ and use another ABI to provide better performance. [#18914](https://github.com/ClickHouse/ClickHouse/pull/18914) ([Danila Kutenin](https://github.com/danlark1)).
+* Rewrite `sumIf()` and `sum(if())` function to `countIf()` function when logically equivalent. [#17041](https://github.com/ClickHouse/ClickHouse/pull/17041) ([flynn](https://github.com/ucasFL)).
+* Use a connection pool for S3 connections, controlled by the `s3_max_connections` settings. [#13405](https://github.com/ClickHouse/ClickHouse/pull/13405) ([Vladimir Chebotarev](https://github.com/excitoon)).
+* Add support for zstd long option for better compression of string columns to save space. [#17184](https://github.com/ClickHouse/ClickHouse/pull/17184) ([ygrek](https://github.com/ygrek)).
+* Slightly improve server latency by removing access to configuration on every connection. [#19863](https://github.com/ClickHouse/ClickHouse/pull/19863) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Reduce lock contention for multiple layers of the `Buffer` engine. [#19379](https://github.com/ClickHouse/ClickHouse/pull/19379) ([Azat Khuzhin](https://github.com/azat)).
+* Support splitting `Filter` step of query plan into `Expression + Filter` pair. Together with `Expression + Expression` merging optimization ([#17458](https://github.com/ClickHouse/ClickHouse/issues/17458)) it may delay execution for some expressions after `Filter` step. [#19253](https://github.com/ClickHouse/ClickHouse/pull/19253) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+
+#### Improvement
+
+* `SELECT count() FROM table` now can be executed if only one any column can be selected from the `table`. This PR fixes [#10639](https://github.com/ClickHouse/ClickHouse/issues/10639). [#18233](https://github.com/ClickHouse/ClickHouse/pull/18233) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Set charset to `utf8mb4` when interacting with remote MySQL servers. Fixes [#19795](https://github.com/ClickHouse/ClickHouse/issues/19795). [#19800](https://github.com/ClickHouse/ClickHouse/pull/19800) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* `S3` table function now supports `auto` compression mode (autodetect). This closes [#18754](https://github.com/ClickHouse/ClickHouse/issues/18754). [#19793](https://github.com/ClickHouse/ClickHouse/pull/19793) ([Vladimir Chebotarev](https://github.com/excitoon)).
+* Correctly output infinite arguments for `formatReadableTimeDelta` function. In previous versions, there was implicit conversion to implementation specific integer value. [#19791](https://github.com/ClickHouse/ClickHouse/pull/19791) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Table function `S3` will use global region if the region can't be determined exactly. This closes [#10998](https://github.com/ClickHouse/ClickHouse/issues/10998). [#19750](https://github.com/ClickHouse/ClickHouse/pull/19750) ([Vladimir Chebotarev](https://github.com/excitoon)).
+* In distributed queries if the setting `async_socket_for_remote` is enabled, it was possible to get stack overflow at least in debug build configuration if very deeply nested data type is used in table (e.g. `Array(Array(Array(...more...)))`). This fixes [#19108](https://github.com/ClickHouse/ClickHouse/issues/19108). This change introduces minor backward incompatibility: excessive parenthesis in type definitions no longer supported, example: `Array((UInt8))`. [#19736](https://github.com/ClickHouse/ClickHouse/pull/19736) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Add separate pool for message brokers (RabbitMQ and Kafka). [#19722](https://github.com/ClickHouse/ClickHouse/pull/19722) ([Azat Khuzhin](https://github.com/azat)).
+* Fix rare `max_number_of_merges_with_ttl_in_pool` limit overrun (more merges with TTL can be assigned) for non-replicated MergeTree. [#19708](https://github.com/ClickHouse/ClickHouse/pull/19708) ([alesapin](https://github.com/alesapin)).
+* Dictionary: better error message during attribute parsing. [#19678](https://github.com/ClickHouse/ClickHouse/pull/19678) ([Maksim Kita](https://github.com/kitaisreal)).
+* Add an option to disable validation of checksums on reading. Should never be used in production. Please do not expect any benefits in disabling it. It may only be used for experiments and benchmarks. The setting only applicable for tables of MergeTree family. Checksums are always validated for other table engines and when receiving data over network. In my observations there is no performance difference or it is less than 0.5%. [#19588](https://github.com/ClickHouse/ClickHouse/pull/19588) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Support constant result in function `multiIf`. [#19533](https://github.com/ClickHouse/ClickHouse/pull/19533) ([Maksim Kita](https://github.com/kitaisreal)).
+* Enable function length/empty/notEmpty for datatype Map, which returns keys number in Map. [#19530](https://github.com/ClickHouse/ClickHouse/pull/19530) ([taiyang-li](https://github.com/taiyang-li)).
+* Add `--reconnect` option to `clickhouse-benchmark`. When this option is specified, it will reconnect before every request. This is needed for testing. [#19872](https://github.com/ClickHouse/ClickHouse/pull/19872) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Support using the new location of `.debug` file. This fixes [#19348](https://github.com/ClickHouse/ClickHouse/issues/19348). [#19520](https://github.com/ClickHouse/ClickHouse/pull/19520) ([Amos Bird](https://github.com/amosbird)).
+* `toIPv6` function parses `IPv4` addresses. [#19518](https://github.com/ClickHouse/ClickHouse/pull/19518) ([Bharat Nallan](https://github.com/bharatnc)).
+* Add `http_referer` field to `system.query_log`, `system.processes`, etc. This closes [#19389](https://github.com/ClickHouse/ClickHouse/issues/19389). [#19390](https://github.com/ClickHouse/ClickHouse/pull/19390) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Improve MySQL compatibility by making more functions case insensitive and adding aliases. [#19387](https://github.com/ClickHouse/ClickHouse/pull/19387) ([Daniil Kondratyev](https://github.com/dankondr)).
+* Add metrics for MergeTree parts (Wide/Compact/InMemory) types. [#19381](https://github.com/ClickHouse/ClickHouse/pull/19381) ([Azat Khuzhin](https://github.com/azat)).
+* Allow docker to be executed with arbitrary uid. [#19374](https://github.com/ClickHouse/ClickHouse/pull/19374) ([filimonov](https://github.com/filimonov)).
+* Fix wrong alignment of values of `IPv4` data type in Pretty formats. They were aligned to the right, not to the left. This closes [#19184](https://github.com/ClickHouse/ClickHouse/issues/19184). [#19339](https://github.com/ClickHouse/ClickHouse/pull/19339) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Allow change `max_server_memory_usage` without restart. This closes [#18154](https://github.com/ClickHouse/ClickHouse/issues/18154). [#19186](https://github.com/ClickHouse/ClickHouse/pull/19186) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* The exception when function `bar` is called with certain NaN argument may be slightly misleading in previous versions. This fixes [#19088](https://github.com/ClickHouse/ClickHouse/issues/19088). [#19107](https://github.com/ClickHouse/ClickHouse/pull/19107) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Explicitly set uid / gid of clickhouse user & group to the fixed values (101) in clickhouse-server images. [#19096](https://github.com/ClickHouse/ClickHouse/pull/19096) ([filimonov](https://github.com/filimonov)).
+* Fixed `PeekableReadBuffer: Memory limit exceed` error when inserting data with huge strings. Fixes [#18690](https://github.com/ClickHouse/ClickHouse/issues/18690). [#18979](https://github.com/ClickHouse/ClickHouse/pull/18979) ([tavplubix](https://github.com/tavplubix)).
+* Docker image: several improvements for clickhouse-server entrypoint. [#18954](https://github.com/ClickHouse/ClickHouse/pull/18954) ([filimonov](https://github.com/filimonov)).
+* Add `normalizeQueryKeepNames` and `normalizedQueryHashKeepNames` to normalize queries without masking long names with `?`. This helps better analyze complex query logs. [#18910](https://github.com/ClickHouse/ClickHouse/pull/18910) ([Amos Bird](https://github.com/amosbird)).
+* Check per-block checksum of the distributed batch on the sender before sending (without reading the file twice, the checksums will be verified while reading), this will avoid stuck of the INSERT on the receiver (on truncated .bin file on the sender). Avoid reading .bin files twice for batched INSERT (it was required to calculate rows/bytes to take squashing into account, now this information included into the header, backward compatible is preserved). [#18853](https://github.com/ClickHouse/ClickHouse/pull/18853) ([Azat Khuzhin](https://github.com/azat)).
+* Fix issues with RIGHT and FULL JOIN of tables with aggregate function states. In previous versions exception about `cloneResized` method was thrown. [#18818](https://github.com/ClickHouse/ClickHouse/pull/18818) ([templarzq](https://github.com/templarzq)).
+* Added prefix-based S3 endpoint settings. [#18812](https://github.com/ClickHouse/ClickHouse/pull/18812) ([Vladimir Chebotarev](https://github.com/excitoon)).
+* Add [UInt8, UInt16, UInt32, UInt64] arguments types support for bitmapTransform, bitmapSubsetInRange, bitmapSubsetLimit, bitmapContains functions. This closes [#18713](https://github.com/ClickHouse/ClickHouse/issues/18713). [#18791](https://github.com/ClickHouse/ClickHouse/pull/18791) ([sundyli](https://github.com/sundy-li)).
+* Allow CTE (Common Table Expressions) to be further aliased. Propagate CSE (Common Subexpressions Elimination) to subqueries in the same level when `enable_global_with_statement = 1`. This fixes [#17378](https://github.com/ClickHouse/ClickHouse/issues/17378) . This fixes https://github.com/ClickHouse/ClickHouse/pull/16575#issuecomment-753416235 . [#18684](https://github.com/ClickHouse/ClickHouse/pull/18684) ([Amos Bird](https://github.com/amosbird)).
+* Update librdkafka to v1.6.0-RC2. Fixes [#18668](https://github.com/ClickHouse/ClickHouse/issues/18668). [#18671](https://github.com/ClickHouse/ClickHouse/pull/18671) ([filimonov](https://github.com/filimonov)).
+* In case of unexpected exceptions automatically restart background thread which is responsible for execution of distributed DDL queries. Fixes [#17991](https://github.com/ClickHouse/ClickHouse/issues/17991). [#18285](https://github.com/ClickHouse/ClickHouse/pull/18285) ([徐炘](https://github.com/weeds085490)).
+* Updated AWS C++ SDK in order to utilize global regions in S3. [#17870](https://github.com/ClickHouse/ClickHouse/pull/17870) ([Vladimir Chebotarev](https://github.com/excitoon)).
+* Added support for `WITH ... [AND] [PERIODIC] REFRESH [interval_in_sec]` clause when creating `LIVE VIEW` tables. [#14822](https://github.com/ClickHouse/ClickHouse/pull/14822) ([vzakaznikov](https://github.com/vzakaznikov)).
+* Restrict `MODIFY TTL` queries for `MergeTree` tables created in old syntax. Previously the query succeeded, but actually it had no effect. [#19064](https://github.com/ClickHouse/ClickHouse/pull/19064) ([Anton Popov](https://github.com/CurtizJ)).
+
+#### Bug Fix
+
+* Fix index analysis of binary functions with constant argument which leads to wrong query results. This fixes [#18364](https://github.com/ClickHouse/ClickHouse/issues/18364). [#18373](https://github.com/ClickHouse/ClickHouse/pull/18373) ([Amos Bird](https://github.com/amosbird)).
+* Fix starting the server with tables having default expressions containing dictGet(). Allow getting return type of dictGet() without loading dictionary. [#19805](https://github.com/ClickHouse/ClickHouse/pull/19805) ([Vitaly Baranov](https://github.com/vitlibar)).
+* Fix server crash after query with `if` function with `Tuple` type of then/else branches result. `Tuple` type must contain `Array` or another complex type. Fixes [#18356](https://github.com/ClickHouse/ClickHouse/issues/18356). [#20133](https://github.com/ClickHouse/ClickHouse/pull/20133) ([alesapin](https://github.com/alesapin)).
+* `MaterializeMySQL` (experimental feature): Fix replication for statements that update several tables. [#20066](https://github.com/ClickHouse/ClickHouse/pull/20066) ([Håvard Kvålen](https://github.com/havardk)).
+* Prevent "Connection refused" in docker during initialization script execution. [#20012](https://github.com/ClickHouse/ClickHouse/pull/20012) ([filimonov](https://github.com/filimonov)).
+* `EmbeddedRocksDB` is an experimental storage. Fix the issue with lack of proper type checking. Simplified code. This closes [#19967](https://github.com/ClickHouse/ClickHouse/issues/19967). [#19972](https://github.com/ClickHouse/ClickHouse/pull/19972) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fix a segfault in function `fromModifiedJulianDay` when the argument type is `Nullable(T)` for any integral types other than Int32. [#19959](https://github.com/ClickHouse/ClickHouse/pull/19959) ([PHO](https://github.com/depressed-pho)).
+* The function `greatCircleAngle` returned inaccurate results in previous versions. This closes [#19769](https://github.com/ClickHouse/ClickHouse/issues/19769). [#19789](https://github.com/ClickHouse/ClickHouse/pull/19789) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fix rare bug when some replicated operations (like mutation) cannot process some parts after data corruption. Fixes [#19593](https://github.com/ClickHouse/ClickHouse/issues/19593). [#19702](https://github.com/ClickHouse/ClickHouse/pull/19702) ([alesapin](https://github.com/alesapin)).
+* Background thread which executes `ON CLUSTER` queries might hang waiting for dropped replicated table to do something. It's fixed. [#19684](https://github.com/ClickHouse/ClickHouse/pull/19684) ([yiguolei](https://github.com/yiguolei)).
+* Fix wrong deserialization of columns description. It makes INSERT into a table with a column named `\` impossible. [#19479](https://github.com/ClickHouse/ClickHouse/pull/19479) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Mark distributed batch as broken in case of empty data block in one of files. [#19449](https://github.com/ClickHouse/ClickHouse/pull/19449) ([Azat Khuzhin](https://github.com/azat)).
+* Fixed very rare bug that might cause mutation to hang after `DROP/DETACH/REPLACE/MOVE PARTITION`. It was partially fixed by [#15537](https://github.com/ClickHouse/ClickHouse/issues/15537) for the most cases. [#19443](https://github.com/ClickHouse/ClickHouse/pull/19443) ([tavplubix](https://github.com/tavplubix)).
+* Fix possible error `Extremes transform was already added to pipeline`. Fixes [#14100](https://github.com/ClickHouse/ClickHouse/issues/14100). [#19430](https://github.com/ClickHouse/ClickHouse/pull/19430) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix default value in join types with non-zero default (e.g. some Enums). Closes [#18197](https://github.com/ClickHouse/ClickHouse/issues/18197). [#19360](https://github.com/ClickHouse/ClickHouse/pull/19360) ([vdimir](https://github.com/vdimir)).
+* Do not mark file for distributed send as broken on EOF. [#19290](https://github.com/ClickHouse/ClickHouse/pull/19290) ([Azat Khuzhin](https://github.com/azat)).
+* Fix leaking of pipe fd for `async_socket_for_remote`. [#19153](https://github.com/ClickHouse/ClickHouse/pull/19153) ([Azat Khuzhin](https://github.com/azat)).
+* Fix infinite reading from file in `ORC` format (was introduced in [#10580](https://github.com/ClickHouse/ClickHouse/issues/10580)). Fixes [#19095](https://github.com/ClickHouse/ClickHouse/issues/19095). [#19134](https://github.com/ClickHouse/ClickHouse/pull/19134) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix issue in merge tree data writer which can lead to marks with bigger size than fixed granularity size. Fixes [#18913](https://github.com/ClickHouse/ClickHouse/issues/18913). [#19123](https://github.com/ClickHouse/ClickHouse/pull/19123) ([alesapin](https://github.com/alesapin)).
+* Fix startup bug when clickhouse was not able to read compression codec from `LowCardinality(Nullable(...))` and throws exception `Attempt to read after EOF`. Fixes [#18340](https://github.com/ClickHouse/ClickHouse/issues/18340). [#19101](https://github.com/ClickHouse/ClickHouse/pull/19101) ([alesapin](https://github.com/alesapin)).
+* Simplify the implementation of `tupleHammingDistance`. Support for tuples of any equal length. Fixes [#19029](https://github.com/ClickHouse/ClickHouse/issues/19029). [#19084](https://github.com/ClickHouse/ClickHouse/pull/19084) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Make sure `groupUniqArray` returns correct type for argument of Enum type. This closes [#17875](https://github.com/ClickHouse/ClickHouse/issues/17875). [#19019](https://github.com/ClickHouse/ClickHouse/pull/19019) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fix possible error `Expected single dictionary argument for function` if use function `ignore` with `LowCardinality` argument. Fixes [#14275](https://github.com/ClickHouse/ClickHouse/issues/14275). [#19016](https://github.com/ClickHouse/ClickHouse/pull/19016) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix inserting of `LowCardinality` column to table with `TinyLog` engine. Fixes [#18629](https://github.com/ClickHouse/ClickHouse/issues/18629). [#19010](https://github.com/ClickHouse/ClickHouse/pull/19010) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix minor issue in JOIN: Join tries to materialize const columns, but our code waits for them in other places. [#18982](https://github.com/ClickHouse/ClickHouse/pull/18982) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
+* Disable `optimize_move_functions_out_of_any` because optimization is not always correct. This closes [#18051](https://github.com/ClickHouse/ClickHouse/issues/18051). This closes [#18973](https://github.com/ClickHouse/ClickHouse/issues/18973). [#18981](https://github.com/ClickHouse/ClickHouse/pull/18981) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fix possible exception `QueryPipeline stream: different number of columns` caused by merging of query plan's `Expression` steps. Fixes [#18190](https://github.com/ClickHouse/ClickHouse/issues/18190). [#18980](https://github.com/ClickHouse/ClickHouse/pull/18980) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fixed very rare deadlock at shutdown. [#18977](https://github.com/ClickHouse/ClickHouse/pull/18977) ([tavplubix](https://github.com/tavplubix)).
+* Fixed rare crashes when server run out of memory. [#18976](https://github.com/ClickHouse/ClickHouse/pull/18976) ([tavplubix](https://github.com/tavplubix)).
+* Fix incorrect behavior when `ALTER TABLE ... DROP PART 'part_name'` query removes all deduplication blocks for the whole partition. Fixes [#18874](https://github.com/ClickHouse/ClickHouse/issues/18874). [#18969](https://github.com/ClickHouse/ClickHouse/pull/18969) ([alesapin](https://github.com/alesapin)).
+* Fixed issue [#18894](https://github.com/ClickHouse/ClickHouse/issues/18894) Add a check to avoid exception when long column alias('table.column' style, usually auto-generated by BI tools like Looker) equals to long table name. [#18968](https://github.com/ClickHouse/ClickHouse/pull/18968) ([Daniel Qin](https://github.com/mathfool)).
+* Fix error `Task was not found in task queue` (possible only for remote queries, with `async_socket_for_remote = 1`). [#18964](https://github.com/ClickHouse/ClickHouse/pull/18964) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix bug when mutation with some escaped text (like `ALTER ... UPDATE e = CAST('foo', 'Enum8(\'foo\' = 1')` serialized incorrectly. Fixes [#18878](https://github.com/ClickHouse/ClickHouse/issues/18878). [#18944](https://github.com/ClickHouse/ClickHouse/pull/18944) ([alesapin](https://github.com/alesapin)).
+* ATTACH PARTITION will reset mutations. [#18804](https://github.com/ClickHouse/ClickHouse/issues/18804). [#18935](https://github.com/ClickHouse/ClickHouse/pull/18935) ([fastio](https://github.com/fastio)).
+* Fix issue with `bitmapOrCardinality` that may lead to nullptr dereference. This closes [#18911](https://github.com/ClickHouse/ClickHouse/issues/18911). [#18912](https://github.com/ClickHouse/ClickHouse/pull/18912) ([sundyli](https://github.com/sundy-li)).
+* Fixed `Attempt to read after eof` error when trying to `CAST` `NULL` from `Nullable(String)` to `Nullable(Decimal(P, S))`. Now function `CAST` returns `NULL` when it cannot parse decimal from nullable string. Fixes [#7690](https://github.com/ClickHouse/ClickHouse/issues/7690). [#18718](https://github.com/ClickHouse/ClickHouse/pull/18718) ([Winter Zhang](https://github.com/zhang2014)).
+* Fix data type convert issue for MySQL engine. [#18124](https://github.com/ClickHouse/ClickHouse/pull/18124) ([bo zeng](https://github.com/mis98zb)).
+* Fix clickhouse-client abort exception while executing only `select`. [#19790](https://github.com/ClickHouse/ClickHouse/pull/19790) ([taiyang-li](https://github.com/taiyang-li)).
+
+
+#### Build/Testing/Packaging Improvement
+
+* Run [SQLancer](https://twitter.com/RiggerManuel/status/1352345625480884228) (logical SQL fuzzer) in CI. [#19006](https://github.com/ClickHouse/ClickHouse/pull/19006) ([Ilya Yatsishin](https://github.com/qoega)).
+* Query Fuzzer will fuzz newly added tests more extensively. This closes [#18916](https://github.com/ClickHouse/ClickHouse/issues/18916). [#19185](https://github.com/ClickHouse/ClickHouse/pull/19185) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Integrate with [Big List of Naughty Strings](https://github.com/minimaxir/big-list-of-naughty-strings/) for better fuzzing. [#19480](https://github.com/ClickHouse/ClickHouse/pull/19480) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Add integration tests run with MSan. [#18974](https://github.com/ClickHouse/ClickHouse/pull/18974) ([alesapin](https://github.com/alesapin)).
+* Fixed MemorySanitizer errors in cyrus-sasl and musl. [#19821](https://github.com/ClickHouse/ClickHouse/pull/19821) ([Ilya Yatsishin](https://github.com/qoega)).
+* Insuffiient arguments check in `positionCaseInsensitiveUTF8` function triggered address sanitizer. [#19720](https://github.com/ClickHouse/ClickHouse/pull/19720) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Remove --project-directory for docker-compose in integration test. Fix logs formatting from docker container. [#19706](https://github.com/ClickHouse/ClickHouse/pull/19706) ([Ilya Yatsishin](https://github.com/qoega)).
+* Made generation of macros.xml easier for integration tests. No more excessive logging from dicttoxml. dicttoxml project is not active for 5+ years. [#19697](https://github.com/ClickHouse/ClickHouse/pull/19697) ([Ilya Yatsishin](https://github.com/qoega)).
+* Allow to explicitly enable or disable watchdog via environment variable `CLICKHOUSE_WATCHDOG_ENABLE`. By default it is enabled if server is not attached to terminal. [#19522](https://github.com/ClickHouse/ClickHouse/pull/19522) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Allow building ClickHouse with Kafka support on arm64. [#19369](https://github.com/ClickHouse/ClickHouse/pull/19369) ([filimonov](https://github.com/filimonov)).
+* Allow building librdkafka without ssl. [#19337](https://github.com/ClickHouse/ClickHouse/pull/19337) ([filimonov](https://github.com/filimonov)).
+* Restore Kafka input in FreeBSD builds. [#18924](https://github.com/ClickHouse/ClickHouse/pull/18924) ([Alexandre Snarskii](https://github.com/snar)).
+* Fix potential nullptr dereference in table function `VALUES`. [#19357](https://github.com/ClickHouse/ClickHouse/pull/19357) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Avoid UBSan reports in `arrayElement` function, `substring` and `arraySum`. Fixes [#19305](https://github.com/ClickHouse/ClickHouse/issues/19305). Fixes [#19287](https://github.com/ClickHouse/ClickHouse/issues/19287). This closes [#19336](https://github.com/ClickHouse/ClickHouse/issues/19336). [#19347](https://github.com/ClickHouse/ClickHouse/pull/19347) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+
+
 ## ClickHouse release 21.1
 
+### ClickHouse release v21.1.3.32-stable, 2021-02-03
+
+#### Bug Fix
+
+* BloomFilter index crash fix. Fixes [#19757](https://github.com/ClickHouse/ClickHouse/issues/19757). [#19884](https://github.com/ClickHouse/ClickHouse/pull/19884) ([Maksim Kita](https://github.com/kitaisreal)).
+* Fix crash when pushing down predicates to union distinct subquery. This fixes [#19855](https://github.com/ClickHouse/ClickHouse/issues/19855). [#19861](https://github.com/ClickHouse/ClickHouse/pull/19861) ([Amos Bird](https://github.com/amosbird)).
+* Fix filtering by UInt8 greater than 127. [#19799](https://github.com/ClickHouse/ClickHouse/pull/19799) ([Anton Popov](https://github.com/CurtizJ)).
+* In previous versions, unusual arguments for function arrayEnumerateUniq may cause crash or infinite loop. This closes [#19787](https://github.com/ClickHouse/ClickHouse/issues/19787). [#19788](https://github.com/ClickHouse/ClickHouse/pull/19788) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fixed stack overflow when using accurate comparison of arithmetic type with string type. [#19773](https://github.com/ClickHouse/ClickHouse/pull/19773) ([tavplubix](https://github.com/tavplubix)).
+* Fix crash when nested column name was used in `WHERE` or `PREWHERE`. Fixes [#19755](https://github.com/ClickHouse/ClickHouse/issues/19755). [#19763](https://github.com/ClickHouse/ClickHouse/pull/19763) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix a segmentation fault in `bitmapAndnot` function. Fixes [#19668](https://github.com/ClickHouse/ClickHouse/issues/19668). [#19713](https://github.com/ClickHouse/ClickHouse/pull/19713) ([Maksim Kita](https://github.com/kitaisreal)).
+* Some functions with big integers may cause segfault. Big integers is experimental feature. This closes [#19667](https://github.com/ClickHouse/ClickHouse/issues/19667). [#19672](https://github.com/ClickHouse/ClickHouse/pull/19672) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fix wrong result of function `neighbor` for `LowCardinality` argument. Fixes [#10333](https://github.com/ClickHouse/ClickHouse/issues/10333). [#19617](https://github.com/ClickHouse/ClickHouse/pull/19617) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix use-after-free of the CompressedWriteBuffer in Connection after disconnect. [#19599](https://github.com/ClickHouse/ClickHouse/pull/19599) ([Azat Khuzhin](https://github.com/azat)).
+* `DROP/DETACH TABLE table ON CLUSTER cluster SYNC` query might hang, it's fixed. Fixes [#19568](https://github.com/ClickHouse/ClickHouse/issues/19568). [#19572](https://github.com/ClickHouse/ClickHouse/pull/19572) ([tavplubix](https://github.com/tavplubix)).
+* Query CREATE DICTIONARY id expression fix. [#19571](https://github.com/ClickHouse/ClickHouse/pull/19571) ([Maksim Kita](https://github.com/kitaisreal)).
+* Fix SIGSEGV with merge_tree_min_rows_for_concurrent_read/merge_tree_min_bytes_for_concurrent_read=0/UINT64_MAX. [#19528](https://github.com/ClickHouse/ClickHouse/pull/19528) ([Azat Khuzhin](https://github.com/azat)).
+* Buffer overflow (on memory read) was possible if `addMonth` function was called with specifically crafted arguments. This fixes [#19441](https://github.com/ClickHouse/ClickHouse/issues/19441). This fixes [#19413](https://github.com/ClickHouse/ClickHouse/issues/19413). [#19472](https://github.com/ClickHouse/ClickHouse/pull/19472) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Uninitialized memory read was possible in encrypt/decrypt functions if empty string was passed as IV. This closes [#19391](https://github.com/ClickHouse/ClickHouse/issues/19391). [#19397](https://github.com/ClickHouse/ClickHouse/pull/19397) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fix possible buffer overflow in Uber H3 library. See https://github.com/uber/h3/issues/392. This closes [#19219](https://github.com/ClickHouse/ClickHouse/issues/19219). [#19383](https://github.com/ClickHouse/ClickHouse/pull/19383) ([alexey-milovidov](https://github.com/alexey-milovidov)).
+* Fix system.parts _state column (LOGICAL_ERROR when querying this column, due to incorrect order). [#19346](https://github.com/ClickHouse/ClickHouse/pull/19346) ([Azat Khuzhin](https://github.com/azat)).
+* Fixed possible wrong result or segfault on aggregation when Materialized View and its target table have different structure. Fixes [#18063](https://github.com/ClickHouse/ClickHouse/issues/18063). [#19322](https://github.com/ClickHouse/ClickHouse/pull/19322) ([tavplubix](https://github.com/tavplubix)).
+* Fix error `Cannot convert column now64() because it is constant but values of constants are different in source and result`. Continuation of [#7156](https://github.com/ClickHouse/ClickHouse/issues/7156). [#19316](https://github.com/ClickHouse/ClickHouse/pull/19316) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
+* Fix bug when concurrent `ALTER` and `DROP` queries may hang while processing ReplicatedMergeTree table. [#19237](https://github.com/ClickHouse/ClickHouse/pull/19237) ([alesapin](https://github.com/alesapin)).
+* Fixed `There is no checkpoint` error when inserting data through http interface using `Template` or `CustomSeparated` format. Fixes [#19021](https://github.com/ClickHouse/ClickHouse/issues/19021). [#19072](https://github.com/ClickHouse/ClickHouse/pull/19072) ([tavplubix](https://github.com/tavplubix)).
+* Disable constant folding for subqueries on the analysis stage, when the result cannot be calculated. [#18446](https://github.com/ClickHouse/ClickHouse/pull/18446) ([Azat Khuzhin](https://github.com/azat)).
+* Mutation might hang waiting for some non-existent part after `MOVE` or `REPLACE PARTITION` or, in rare cases, after `DETACH` or `DROP PARTITION`. It's fixed. [#15537](https://github.com/ClickHouse/ClickHouse/pull/15537) ([tavplubix](https://github.com/tavplubix)).
+
+
+
 ### ClickHouse release v21.1.2.15-stable 2021-01-18
 
 #### Backward Incompatible Change

README.md

@@ -8,12 +8,8 @@ ClickHouse® is an open-source column-oriented database management system that a
 * [Tutorial](https://clickhouse.tech/docs/en/getting_started/tutorial/) shows how to set up and query small ClickHouse cluster.
 * [Documentation](https://clickhouse.tech/docs/en/) provides more in-depth information.
 * [YouTube channel](https://www.youtube.com/c/ClickHouseDB) has a lot of content about ClickHouse in video format.
-* [Slack](https://join.slack.com/t/clickhousedb/shared_invite/zt-d2zxkf9e-XyxDa_ucfPxzuH4SJIm~Ng) and [Telegram](https://telegram.me/clickhouse_en) allow to chat with ClickHouse users in real-time.
+* [Slack](https://join.slack.com/t/clickhousedb/shared_invite/zt-ly9m4w1x-6j7x5Ts_pQZqrctAbRZ3cg) and [Telegram](https://telegram.me/clickhouse_en) allow to chat with ClickHouse users in real-time.
 * [Blog](https://clickhouse.yandex/blog/en/) contains various ClickHouse-related articles, as well as announcements and reports about events.
 * [Code Browser](https://clickhouse.tech/codebrowser/html_report/ClickHouse/index.html) with syntax highlight and navigation.
-* [Yandex.Messenger channel](https://yandex.ru/chat/#/join/20e380d9-c7be-4123-ab06-e95fb946975e) shares announcements and useful links in Russian.
 * [Contacts](https://clickhouse.tech/#contacts) can help to get your questions answered if there are any.
 * You can also [fill this form](https://clickhouse.tech/#meet) to meet Yandex ClickHouse team in person.
-
-## Upcoming Events
-* [Chinese ClickHouse Meetup (online)](http://hdxu.cn/8KxZE) on 6 February 2021.

base/common/DateLUTImpl.h

@@ -7,6 +7,7 @@
 #include <ctime>
 #include <string>
 
+
 #define DATE_LUT_MAX (0xFFFFFFFFU - 86400)
 #define DATE_LUT_MAX_DAY_NUM (0xFFFFFFFFU / 86400)
 /// Table size is bigger than DATE_LUT_MAX_DAY_NUM to fill all indices within UInt16 range: this allows to remove extra check.
@@ -249,7 +250,7 @@ public:
     {
         DayNum index = findIndex(t);
 
-        if (unlikely(index == 0))
+        if (unlikely(index == 0 || index > DATE_LUT_MAX_DAY_NUM))
             return t + offset_at_start_of_epoch;
 
         time_t res = t - lut[index].date;
@@ -264,18 +265,43 @@ public:
     {
         DayNum index = findIndex(t);
 
-        /// If it is not 1970 year (findIndex found nothing appropriate),
-        ///  than limit number of hours to avoid insane results like 1970-01-01 89:28:15
-        if (unlikely(index == 0))
+        /// If it is overflow case,
+        ///  then limit number of hours to avoid insane results like 1970-01-01 89:28:15
+        if (unlikely(index == 0 || index > DATE_LUT_MAX_DAY_NUM))
             return static_cast<unsigned>((t + offset_at_start_of_epoch) / 3600) % 24;
 
-        time_t res = t - lut[index].date;
+        time_t time = t - lut[index].date;
 
-        /// Data is cleaned to avoid possibility of underflow.
-        if (res >= lut[index].time_at_offset_change)
+        if (time >= lut[index].time_at_offset_change)
+            time += lut[index].amount_of_offset_change;
+
+        unsigned res = time / 3600;
+        return res <= 23 ? res : 0;
+    }
+
+    /** Calculating offset from UTC in seconds.
+     * which means Using the same literal time of "t" to get the corresponding timestamp in UTC,
+     * then subtract the former from the latter to get the offset result.
+     * The boundaries when meets DST(daylight saving time) change should be handled very carefully.
+     */
+    inline time_t timezoneOffset(time_t t) const
+    {
+        DayNum index = findIndex(t);
+
+        /// Calculate daylight saving offset first.
+        /// Because the "amount_of_offset_change" in LUT entry only exists in the change day, it's costly to scan it from the very begin.
+        /// but we can figure out all the accumulated offsets from 1970-01-01 to that day just by get the whole difference between lut[].date,
+        /// and then, we can directly subtract multiple 86400s to get the real DST offsets for the leap seconds is not considered now.
+        time_t res = (lut[index].date - lut[0].date) % 86400;
+        /// As so far to know, the maximal DST offset couldn't be more than 2 hours, so after the modulo operation the remainder
+        /// will sits between [-offset --> 0 --> offset] which respectively corresponds to moving clock forward or backward.
+        res = res > 43200 ? (86400 - res) : (0 - res);
+
+        /// Check if has a offset change during this day. Add the change when cross the line
+        if (lut[index].amount_of_offset_change != 0 && t >= lut[index].date + lut[index].time_at_offset_change)
             res += lut[index].amount_of_offset_change;
 
-        return res / 3600;
+        return res + offset_at_start_of_epoch;
     }
 
     /** Only for time zones with/when offset from UTC is multiple of five minutes.
@@ -289,12 +315,12 @@ public:
       *  each minute, with added or subtracted leap second, spans exactly 60 unix timestamps.
       */
 
-    inline unsigned toSecond(time_t t) const { return t % 60; }
+    inline unsigned toSecond(time_t t) const { return UInt32(t) % 60; }
 
     inline unsigned toMinute(time_t t) const
     {
         if (offset_is_whole_number_of_hours_everytime)
-            return (t / 60) % 60;
+            return (UInt32(t) / 60) % 60;
 
         UInt32 date = find(t).date;
         return (UInt32(t) - date) / 60 % 60;
@@ -530,9 +556,7 @@ public:
         }
     }
 
-    /*
-     * check and change mode to effective
-     */
+    /// Check and change mode to effective.
     inline UInt8 check_week_mode(UInt8 mode) const
     {
         UInt8 week_format = (mode & 7);
@@ -541,10 +565,9 @@ public:
         return week_format;
     }
 
-    /*
-     * Calc weekday from d
-     * Returns 0 for monday, 1 for tuesday ...
-     */
+    /** Calculate weekday from d.
+      * Returns 0 for monday, 1 for tuesday...
+      */
     inline unsigned calc_weekday(DayNum d, bool sunday_first_day_of_week) const
     {
         if (!sunday_first_day_of_week)
@@ -553,7 +576,7 @@ public:
             return toDayOfWeek(DayNum(d + 1)) - 1;
     }
 
-    /* Calc days in one year. */
+    /// Calculate days in one year.
     inline unsigned calc_days_in_year(UInt16 year) const
     {
         return ((year & 3) == 0 && (year % 100 || (year % 400 == 0 && year)) ? 366 : 365);

base/common/LocalDate.h

@@ -168,14 +168,6 @@ public:
 static_assert(sizeof(LocalDate) == 4);
 
 
-inline std::ostream & operator<< (std::ostream & ostr, const LocalDate & date)
-{
-    return ostr << date.year()
-        << '-' << (date.month() / 10) << (date.month() % 10)
-        << '-' << (date.day() / 10) << (date.day() % 10);
-}
-
-
 namespace std
 {
 inline string to_string(const LocalDate & date)

base/common/LocalDateTime.h

@@ -169,20 +169,6 @@ public:
 static_assert(sizeof(LocalDateTime) == 8);
 
 
-inline std::ostream & operator<< (std::ostream & ostr, const LocalDateTime & datetime)
-{
-    ostr << std::setfill('0') << std::setw(4) << datetime.year();
-
-    ostr << '-' << (datetime.month() / 10) << (datetime.month() % 10)
-        << '-' << (datetime.day() / 10) << (datetime.day() % 10)
-        << ' ' << (datetime.hour() / 10) << (datetime.hour() % 10)
-        << ':' << (datetime.minute() / 10) << (datetime.minute() % 10)
-        << ':' << (datetime.second() / 10) << (datetime.second() % 10);
-
-    return ostr;
-}
-
-
 namespace std
 {
 inline string to_string(const LocalDateTime & datetime)

base/common/ReplxxLineReader.cpp

@@ -12,6 +12,8 @@
 #include <dlfcn.h>
 #include <fcntl.h>
 #include <fstream>
+#include <fmt/format.h>
+
 
 namespace
 {
@@ -189,8 +191,8 @@ void ReplxxLineReader::openEditor()
         return;
     }
 
-    String editor = std::getenv("EDITOR");
-    if (editor.empty())
+    const char * editor = std::getenv("EDITOR");
+    if (!editor || !*editor)
         editor = "vim";
 
     replxx::Replxx::State state(rx.get_state());
@@ -204,7 +206,7 @@ void ReplxxLineReader::openEditor()
         if ((-1 == res || 0 == res) && errno != EINTR)
         {
             rx.print("Cannot write to temporary query file %s: %s\n", filename, errnoToString(errno).c_str());
-            return;
+            break;
         }
         bytes_written += res;
     }
@@ -215,7 +217,7 @@ void ReplxxLineReader::openEditor()
         return;
     }
 
-    if (0 == execute(editor + " " + filename))
+    if (0 == execute(fmt::format("{} {}", editor, filename)))
     {
         try
         {

base/common/arithmeticOverflow.h

@@ -1,9 +1,30 @@
 #pragma once
 
 #include <common/extended_types.h>
+#include <common/defines.h>
+
 
 namespace common
 {
+    /// Multiply and ignore overflow.
+    template <typename T1, typename T2>
+    inline auto NO_SANITIZE_UNDEFINED mulIgnoreOverflow(T1 x, T2 y)
+    {
+        return x * y;
+    }
+
+    template <typename T1, typename T2>
+    inline auto NO_SANITIZE_UNDEFINED addIgnoreOverflow(T1 x, T2 y)
+    {
+        return x + y;
+    }
+
+    template <typename T1, typename T2>
+    inline auto NO_SANITIZE_UNDEFINED subIgnoreOverflow(T1 x, T2 y)
+    {
+        return x - y;
+    }
+
     template <typename T>
     inline bool addOverflow(T x, T y, T & res)
     {
@@ -33,14 +54,14 @@ namespace common
     {
         static constexpr __int128 min_int128 = minInt128();
         static constexpr __int128 max_int128 = maxInt128();
-        res = x + y;
+        res = addIgnoreOverflow(x, y);
         return (y > 0 && x > max_int128 - y) || (y < 0 && x < min_int128 - y);
     }
 
     template <>
     inline bool addOverflow(wInt256 x, wInt256 y, wInt256 & res)
     {
-        res = x + y;
+        res = addIgnoreOverflow(x, y);
         return (y > 0 && x > std::numeric_limits<wInt256>::max() - y) ||
             (y < 0 && x < std::numeric_limits<wInt256>::min() - y);
     }
@@ -48,7 +69,7 @@ namespace common
     template <>
     inline bool addOverflow(wUInt256 x, wUInt256 y, wUInt256 & res)
     {
-        res = x + y;
+        res = addIgnoreOverflow(x, y);
         return x > std::numeric_limits<wUInt256>::max() - y;
     }
 
@@ -81,14 +102,14 @@ namespace common
     {
         static constexpr __int128 min_int128 = minInt128();
         static constexpr __int128 max_int128 = maxInt128();
-        res = x - y;
+        res = subIgnoreOverflow(x, y);
         return (y < 0 && x > max_int128 + y) || (y > 0 && x < min_int128 + y);
     }
 
     template <>
     inline bool subOverflow(wInt256 x, wInt256 y, wInt256 & res)
     {
-        res = x - y;
+        res = subIgnoreOverflow(x, y);
         return (y < 0 && x > std::numeric_limits<wInt256>::max() + y) ||
             (y > 0 && x < std::numeric_limits<wInt256>::min() + y);
     }
@@ -96,7 +117,7 @@ namespace common
     template <>
     inline bool subOverflow(wUInt256 x, wUInt256 y, wUInt256 & res)
     {
-        res = x - y;
+        res = subIgnoreOverflow(x, y);
         return x < y;
     }
 
@@ -127,33 +148,33 @@ namespace common
     template <>
     inline bool mulOverflow(__int128 x, __int128 y, __int128 & res)
     {
-        res = static_cast<unsigned __int128>(x) * static_cast<unsigned __int128>(y);    /// Avoid signed integer overflow.
+        res = mulIgnoreOverflow(x, y);
         if (!x || !y)
             return false;
 
         unsigned __int128 a = (x > 0) ? x : -x;
         unsigned __int128 b = (y > 0) ? y : -y;
-        return (a * b) / b != a;
+        return mulIgnoreOverflow(a, b) / b != a;
     }
 
     template <>
     inline bool mulOverflow(wInt256 x, wInt256 y, wInt256 & res)
     {
-        res = x * y;
+        res = mulIgnoreOverflow(x, y);
         if (!x || !y)
             return false;
 
         wInt256 a = (x > 0) ? x : -x;
         wInt256 b = (y > 0) ? y : -y;
-        return (a * b) / b != a;
+        return mulIgnoreOverflow(a, b) / b != a;
     }
 
     template <>
     inline bool mulOverflow(wUInt256 x, wUInt256 y, wUInt256 & res)
     {
-        res = x * y;
+        res = mulIgnoreOverflow(x, y);
         if (!x || !y)
             return false;
-        return (x * y) / y != x;
+        return res / y != x;
     }
 }

base/common/defines.h

@@ -84,10 +84,12 @@
 #    define NO_SANITIZE_UNDEFINED __attribute__((__no_sanitize__("undefined")))
 #    define NO_SANITIZE_ADDRESS __attribute__((__no_sanitize__("address")))
 #    define NO_SANITIZE_THREAD __attribute__((__no_sanitize__("thread")))
+#    define ALWAYS_INLINE_NO_SANITIZE_UNDEFINED __attribute__((__always_inline__, __no_sanitize__("undefined")))
 #else  /// It does not work in GCC. GCC 7 cannot recognize this attribute and GCC 8 simply ignores it.
 #    define NO_SANITIZE_UNDEFINED
 #    define NO_SANITIZE_ADDRESS
 #    define NO_SANITIZE_THREAD
+#    define ALWAYS_INLINE_NO_SANITIZE_UNDEFINED ALWAYS_INLINE
 #endif
 
 /// A template function for suppressing warnings about unused variables or function results.

base/daemon/BaseDaemon.cpp

@@ -152,7 +152,7 @@ static void signalHandler(int sig, siginfo_t * info, void * context)
     if (sig != SIGTSTP) /// This signal is used for debugging.
     {
         /// The time that is usually enough for separate thread to print info into log.
-        sleepForSeconds(10);
+        sleepForSeconds(20);  /// FIXME: use some feedback from threads that process stacktrace
         call_default_signal_handler(sig);
     }
 
@@ -230,10 +230,10 @@ public:
             }
             else
             {
-                siginfo_t info;
-                ucontext_t context;
+                siginfo_t info{};
+                ucontext_t context{};
                 StackTrace stack_trace(NoCapture{});
-                UInt32 thread_num;
+                UInt32 thread_num{};
                 std::string query_id;
                 DB::ThreadStatus * thread_ptr{};
 
@@ -311,7 +311,8 @@ private:
         if (stack_trace.getSize())
         {
             /// Write bare stack trace (addresses) just in case if we will fail to print symbolized stack trace.
-            /// NOTE This still require memory allocations and mutex lock inside logger. BTW we can also print it to stderr using write syscalls.
+            /// NOTE: This still require memory allocations and mutex lock inside logger.
+            ///       BTW we can also print it to stderr using write syscalls.
 
             std::stringstream bare_stacktrace;
             bare_stacktrace << "Stack trace:";
@@ -324,7 +325,7 @@ private:
         /// Write symbolized stack trace line by line for better grep-ability.
         stack_trace.toStringEveryLine([&](const std::string & s) { LOG_FATAL(log, s); });
 
-#if defined(__linux__)
+#if defined(OS_LINUX)
         /// Write information about binary checksum. It can be difficult to calculate, so do it only after printing stack trace.
         String calculated_binary_hash = getHashOfLoadedBinaryHex();
         if (daemon.stored_binary_hash.empty())
@@ -415,7 +416,9 @@ static void sanitizerDeathCallback()
     else
         log_message = "Terminate called without an active exception";
 
-    static const size_t buf_size = 1024;
+    /// POSIX.1 says that write(2)s of less than PIPE_BUF bytes must be atomic - man 7 pipe
+    /// And the buffer should not be too small because our exception messages can be large.
+    static constexpr size_t buf_size = PIPE_BUF;
 
     if (log_message.size() > buf_size - 16)
         log_message.resize(buf_size - 16);
@@ -561,6 +564,7 @@ void debugIncreaseOOMScore()
     {
         DB::WriteBufferFromFile buf("/proc/self/oom_score_adj");
         buf.write(new_score.c_str(), new_score.size());
+        buf.close();
     }
     catch (const Poco::Exception & e)
     {
@@ -783,7 +787,7 @@ void BaseDaemon::initializeTerminationAndSignalProcessing()
     /// Setup signal handlers.
     /// SIGTSTP is added for debugging purposes. To output a stack trace of any running thread at anytime.
 
-    addSignalHandler({SIGABRT, SIGSEGV, SIGILL, SIGBUS, SIGSYS, SIGFPE, SIGPIPE, SIGTSTP}, signalHandler, &handled_signals);
+    addSignalHandler({SIGABRT, SIGSEGV, SIGILL, SIGBUS, SIGSYS, SIGFPE, SIGPIPE, SIGTSTP, SIGTRAP}, signalHandler, &handled_signals);
     addSignalHandler({SIGHUP, SIGUSR1}, closeLogsSignalHandler, &handled_signals);
     addSignalHandler({SIGINT, SIGQUIT, SIGTERM}, terminateRequestedSignalHandler, &handled_signals);
 
@@ -986,7 +990,7 @@ void BaseDaemon::setupWatchdog()
         if (errno == ECHILD)
         {
             logger().information("Child process no longer exists.");
-            _exit(status);
+            _exit(WEXITSTATUS(status));
         }
 
         if (WIFEXITED(status))
@@ -1020,7 +1024,7 @@ void BaseDaemon::setupWatchdog()
 
         /// Automatic restart is not enabled but you can play with it.
 #if 1
-        _exit(status);
+        _exit(WEXITSTATUS(status));
 #else
         logger().information("Will restart.");
         if (argv0)

base/daemon/BaseDaemon.h

@@ -83,7 +83,7 @@ public:
     template <class T>
     void writeToGraphite(const std::string & key, const T & value, const std::string & config_name = DEFAULT_GRAPHITE_CONFIG_NAME, time_t timestamp = 0, const std::string & custom_root_path = "")
     {
-        auto writer = getGraphiteWriter(config_name);
+        auto *writer = getGraphiteWriter(config_name);
         if (writer)
             writer->write(key, value, timestamp, custom_root_path);
     }
@@ -91,7 +91,7 @@ public:
     template <class T>
     void writeToGraphite(const GraphiteWriter::KeyValueVector<T> & key_vals, const std::string & config_name = DEFAULT_GRAPHITE_CONFIG_NAME, time_t timestamp = 0, const std::string & custom_root_path = "")
     {
-        auto writer = getGraphiteWriter(config_name);
+        auto *writer = getGraphiteWriter(config_name);
         if (writer)
             writer->write(key_vals, timestamp, custom_root_path);
     }
@@ -99,7 +99,7 @@ public:
     template <class T>
     void writeToGraphite(const GraphiteWriter::KeyValueVector<T> & key_vals, const std::chrono::system_clock::time_point & current_time, const std::string & custom_root_path)
     {
-        auto writer = getGraphiteWriter();
+        auto *writer = getGraphiteWriter();
         if (writer)
             writer->write(key_vals, std::chrono::system_clock::to_time_t(current_time), custom_root_path);
     }

base/glibc-compatibility/musl/sched_getcpu.c

@@ -31,7 +31,7 @@ static void *volatile vdso_func = (void *)getcpu_init;
 int sched_getcpu(void)
 {
 	int r;
-	unsigned cpu;
+	unsigned cpu = 0;
 
 #ifdef VDSO_GETCPU_SYM
 	getcpu_f f = (getcpu_f)vdso_func;

base/mysqlxx/CMakeLists.txt

@@ -3,7 +3,6 @@ add_library (mysqlxx
     Exception.cpp
     Query.cpp
     ResultBase.cpp
-    StoreQueryResult.cpp
     UseQueryResult.cpp
     Row.cpp
     Value.cpp

base/mysqlxx/Connection.cpp

@@ -116,8 +116,8 @@ void Connection::connect(const char* db,
     if (!mysql_real_connect(driver.get(), server, user, password, db, port, ifNotEmpty(socket), driver->client_flag))
         throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
 
-    /// Sets UTF-8 as default encoding.
-    if (mysql_set_character_set(driver.get(), "UTF8"))
+    /// Sets UTF-8 as default encoding. See https://mariadb.com/kb/en/mysql_set_character_set/
+    if (mysql_set_character_set(driver.get(), "utf8mb4"))
         throw ConnectionFailed(errorMessage(driver.get()), mysql_errno(driver.get()));
 
     is_connected = true;

base/mysqlxx/Connection.h

@@ -39,7 +39,6 @@ private:
 /** MySQL connection.
   * Usage:
   *        mysqlxx::Connection connection("Test", "127.0.0.1", "root", "qwerty", 3306);
-  *        std::cout << connection.query("SELECT 'Hello, World!'").store().at(0).at(0).getString() << std::endl;
   *
   * Or with Poco library configuration:
   *        mysqlxx::Connection connection("mysql_params");

base/mysqlxx/Query.cpp

@@ -71,16 +71,6 @@ UseQueryResult Query::use()
     return UseQueryResult(res, conn, this);
 }
 
-StoreQueryResult Query::store()
-{
-    executeImpl();
-    MYSQL_RES * res = mysql_store_result(conn->getDriver());
-    if (!res)
-        checkError(conn->getDriver());
-
-    return StoreQueryResult(res, conn, this);
-}
-
 void Query::execute()
 {
     executeImpl();

base/mysqlxx/Query.h

@@ -3,7 +3,6 @@
 #include <sstream>
 
 #include <mysqlxx/UseQueryResult.h>
-#include <mysqlxx/StoreQueryResult.h>
 
 
 namespace mysqlxx
@@ -46,11 +45,6 @@ public:
       */
     UseQueryResult use();
 
-    /** Выполнить запрос с загрузкой на клиента всех строк.
-      * Требуется оперативка, чтобы вместить весь результат, зато к строкам можно обращаться в произвольном порядке.
-      */
-    StoreQueryResult store();
-
     /// Значение auto increment после последнего INSERT-а.
     UInt64 insertID();
 

base/mysqlxx/ResultBase.h

@@ -9,7 +9,7 @@ class Connection;
 class Query;
 
 
-/** Базовый класс для UseQueryResult и StoreQueryResult.
+/** Базовый класс для UseQueryResult.
   * Содержит общую часть реализации,
   * Ссылается на Connection. Если уничтожить Connection, то пользоваться ResultBase и любым результатом нельзя.
   * Использовать объект можно только для результата одного запроса!

base/mysqlxx/Row.h

@@ -35,7 +35,7 @@ public:
     {
     }
 
-    /** Для того, чтобы создать Row, используйте соответствующие методы UseQueryResult или StoreQueryResult. */
+    /** Для того, чтобы создать Row, используйте соответствующие методы UseQueryResult. */
     Row(MYSQL_ROW row_, ResultBase * res_, MYSQL_LENGTHS lengths_)
         : row(row_), res(res_), lengths(lengths_)
     {

base/mysqlxx/StoreQueryResult.cpp

@@ -1,30 +0,0 @@
-#if __has_include(<mysql.h>)
-#include <mysql.h>
-#else
-#include <mysql/mysql.h>
-#endif
-
-#include <mysqlxx/Connection.h>
-#include <mysqlxx/StoreQueryResult.h>
-
-
-namespace mysqlxx
-{
-
-StoreQueryResult::StoreQueryResult(MYSQL_RES * res_, Connection * conn_, const Query * query_) : ResultBase(res_, conn_, query_)
-{
-    UInt64 rows = mysql_num_rows(res);
-    reserve(rows);
-    lengths.resize(rows * num_fields);
-
-    for (UInt64 i = 0; MYSQL_ROW row = mysql_fetch_row(res); ++i)
-    {
-        MYSQL_LENGTHS lengths_for_row = mysql_fetch_lengths(res);
-        memcpy(&lengths[i * num_fields], lengths_for_row, sizeof(lengths[0]) * num_fields);
-
-        push_back(Row(row, this, &lengths[i * num_fields]));
-    }
-    checkError(conn->getDriver());
-}
-
-}

base/mysqlxx/StoreQueryResult.h

@@ -1,45 +0,0 @@
-#pragma once
-
-#include <vector>
-
-#include <mysqlxx/ResultBase.h>
-#include <mysqlxx/Row.h>
-
-
-namespace mysqlxx
-{
-
-class Connection;
-
-
-/** Результат выполнения запроса, загруженный полностью на клиента.
-  * Это требует оперативку, чтобы вместить весь результат,
-  *  но зато реализует произвольный доступ к строкам по индексу.
-  * Если размер результата большой - используйте лучше UseQueryResult.
-  * Объект содержит ссылку на Connection.
-  * Если уничтожить Connection, то объект становится некорректным и все строки результата - тоже.
-  * Если задать следующий запрос в соединении, то объект и все строки тоже становятся некорректными.
-  * Использовать объект можно только для результата одного запроса!
-  * (При попытке присвоить объекту результат следующего запроса - UB.)
-  */
-class StoreQueryResult : public std::vector<Row>, public ResultBase
-{
-public:
-    StoreQueryResult(MYSQL_RES * res_, Connection * conn_, const Query * query_);
-
-    size_t num_rows() const { return size(); }
-
-private:
-
-    /** Не смотря на то, что весь результат выполнения запроса загружается на клиента,
-      *  и все указатели MYSQL_ROW на отдельные строки различные,
-      *  при этом функция mysql_fetch_lengths() возвращает длины
-      *  для текущей строки по одному и тому же адресу.
-      * То есть, чтобы можно было пользоваться несколькими Row одновременно,
-      *  необходимо заранее куда-то сложить все длины.
-      */
-    using Lengths = std::vector<MYSQL_LENGTH>;
-    Lengths lengths;
-};
-
-}

base/mysqlxx/UseQueryResult.h

@@ -12,8 +12,7 @@ class Connection;
 
 /** Результат выполнения запроса, предназначенный для чтения строк, одна за другой.
   * В памяти при этом хранится только одна, текущая строка.
-  * В отличие от StoreQueryResult, произвольный доступ к строкам невозможен,
-  *  а также, при чтении следующей строки, предыдущая становится некорректной.
+  * При чтении следующей строки, предыдущая становится некорректной.
   * Вы обязаны прочитать все строки из результата
   *  (вызывать функцию fetch(), пока она не вернёт значение, преобразующееся к false),
   *  иначе при следующем запросе будет выкинуто исключение с текстом "Commands out of sync".

base/mysqlxx/Value.h

@@ -25,7 +25,7 @@ class ResultBase;
 
 /** Represents a single value read from MySQL.
   * It doesn't owns the value. It's just a wrapper of a pair (const char *, size_t).
-  * If the UseQueryResult/StoreQueryResult or Connection is destroyed,
+  * If the UseQueryResult or Connection is destroyed,
   *  or you have read the next Row while using UseQueryResult, then the object is invalidated.
   * Allows to transform (parse) the value to various data types:
   * - with getUInt(), getString(), ... (recommended);

base/mysqlxx/tests/mysqlxx_test.cpp

@@ -38,15 +38,6 @@ int main(int, char **)
             }
         }
 
-        {
-            mysqlxx::Query query = connection.query();
-            query << "SELECT 1234567890 abc, 12345.67890 def UNION ALL SELECT 9876543210, 98765.43210";
-            mysqlxx::StoreQueryResult result = query.store();
-
-            std::cerr << result.at(0)["abc"].getUInt() << ", " << result.at(0)["def"].getDouble() << std::endl
-                << result.at(1)["abc"].getUInt() << ", " << result.at(1)["def"].getDouble() << std::endl;
-        }
-
         {
             mysqlxx::UseQueryResult result = connection.query("SELECT 'abc\\\\def' x").use();
             mysqlxx::Row row = result.fetch();
@@ -54,27 +45,6 @@ int main(int, char **)
             std::cerr << row << std::endl;
         }
 
-        {
-            mysqlxx::Query query = connection.query("SEL");
-            query << "ECT 1";
-
-            std::cerr << query.store().at(0).at(0) << std::endl;
-        }
-
-        {
-            /// Копирование Query
-            mysqlxx::Query query = connection.query("SELECT 'Ok' x");
-            using Queries = std::vector<mysqlxx::Query>;
-            Queries queries;
-            queries.push_back(query);
-
-            for (auto & q : queries)
-            {
-                std::cerr << q.str() << std::endl;
-                std::cerr << q.store().at(0) << std::endl;
-            }
-        }
-
         {
             /// Копирование Query
             mysqlxx::Query query1 = connection.query("SELECT");
@@ -84,62 +54,6 @@ int main(int, char **)
             std::cerr << query1.str() << ", " << query2.str() << std::endl;
         }
 
-        {
-            /// Копирование Query
-            using Queries = std::list<mysqlxx::Query>;
-            Queries queries;
-            queries.push_back(connection.query("SELECT"));
-            mysqlxx::Query & qref = queries.back();
-            qref << " 1";
-
-            for (auto & query : queries)
-            {
-                std::cerr << query.str() << std::endl;
-                std::cerr << query.store().at(0) << std::endl;
-            }
-        }
-
-        {
-            /// Транзакции
-            connection.query("DROP TABLE IF EXISTS tmp").execute();
-            connection.query("CREATE TABLE tmp (x INT, PRIMARY KEY (x)) ENGINE = InnoDB").execute();
-
-            mysqlxx::Transaction trans(connection);
-            connection.query("INSERT INTO tmp VALUES (1)").execute();
-
-            std::cerr << connection.query("SELECT * FROM tmp").store().size() << std::endl;
-
-            trans.rollback();
-
-            std::cerr << connection.query("SELECT * FROM tmp").store().size() << std::endl;
-        }
-
-        {
-            /// Транзакции
-            connection.query("DROP TABLE IF EXISTS tmp").execute();
-            connection.query("CREATE TABLE tmp (x INT, PRIMARY KEY (x)) ENGINE = InnoDB").execute();
-
-            {
-                mysqlxx::Transaction trans(connection);
-                connection.query("INSERT INTO tmp VALUES (1)").execute();
-                std::cerr << connection.query("SELECT * FROM tmp").store().size() << std::endl;
-            }
-
-            std::cerr << connection.query("SELECT * FROM tmp").store().size() << std::endl;
-        }
-
-        {
-            /// Транзакции
-            mysqlxx::Connection connection2("test", "127.0.0.1", "root", "qwerty", 3306);
-            connection2.query("DROP TABLE IF EXISTS tmp").execute();
-            connection2.query("CREATE TABLE tmp (x INT, PRIMARY KEY (x)) ENGINE = InnoDB").execute();
-
-            mysqlxx::Transaction trans(connection2);
-            connection2.query("INSERT INTO tmp VALUES (1)").execute();
-            std::cerr << connection2.query("SELECT * FROM tmp").store().size() << std::endl;
-        }
-        std::cerr << connection.query("SELECT * FROM tmp").store().size() << std::endl;
-
         {
             /// NULL
             mysqlxx::Null<int> x = mysqlxx::null;
@@ -152,59 +66,6 @@ int main(int, char **)
             std::cerr << (x == 1 ? "Ok" : "Fail") << std::endl;
             std::cerr << (x.isNull() ? "Fail" : "Ok") << std::endl;
         }
-
-        {
-            /// Исключения при попытке достать значение не того типа
-            try
-            {
-                connection.query("SELECT -1").store().at(0).at(0).getUInt();
-                std::cerr << "Fail" << std::endl;
-            }
-            catch (const mysqlxx::Exception & e)
-            {
-                std::cerr << "Ok, " << e.message() << std::endl;
-            }
-
-            try
-            {
-                connection.query("SELECT 'xxx'").store().at(0).at(0).getInt();
-                std::cerr << "Fail" << std::endl;
-            }
-            catch (const mysqlxx::Exception & e)
-            {
-                std::cerr << "Ok, " << e.message() << std::endl;
-            }
-
-            try
-            {
-                connection.query("SELECT NULL").store().at(0).at(0).getString();
-                std::cerr << "Fail" << std::endl;
-            }
-            catch (const mysqlxx::Exception & e)
-            {
-                std::cerr << "Ok, " << e.message() << std::endl;
-            }
-
-            try
-            {
-                connection.query("SELECT 123").store().at(0).at(0).getDate();
-                std::cerr << "Fail" << std::endl;
-            }
-            catch (const mysqlxx::Exception & e)
-            {
-                std::cerr << "Ok, " << e.message() << std::endl;
-            }
-
-            try
-            {
-                connection.query("SELECT '2011-01-01'").store().at(0).at(0).getDateTime();
-                std::cerr << "Fail" << std::endl;
-            }
-            catch (const mysqlxx::Exception & e)
-            {
-                std::cerr << "Ok, " << e.message() << std::endl;
-            }
-        }
     }
     catch (const mysqlxx::Exception & e)
     {

cmake/autogenerated_versions.txt

@@ -1,9 +1,9 @@
 # This strings autochanged from release_lib.sh:
-SET(VERSION_REVISION 54447)
+SET(VERSION_REVISION 54448)
 SET(VERSION_MAJOR 21)
-SET(VERSION_MINOR 2)
+SET(VERSION_MINOR 3)
 SET(VERSION_PATCH 1)
-SET(VERSION_GITHASH 53d0c9fa7255aa1dc48991d19f4246ff71cc2fd7)
-SET(VERSION_DESCRIBE v21.2.1.1-prestable)
-SET(VERSION_STRING 21.2.1.1)
+SET(VERSION_GITHASH ef72ba7349f230321750c13ee63b49a11a7c0adc)
+SET(VERSION_DESCRIBE v21.3.1.1-prestable)
+SET(VERSION_STRING 21.3.1.1)
 # end of autochange

cmake/find/ccache.cmake

@@ -37,15 +37,13 @@ if (CCACHE_FOUND AND NOT COMPILER_MATCHES_CCACHE)
       #
       # - 4.0+ ccache always includes this environment variable into the hash
       #   of the manifest, which do not allow to use previous cache,
-      # - 4.2+ ccache ignores SOURCE_DATE_EPOCH under time_macros sloppiness.
+      # - 4.2+ ccache ignores SOURCE_DATE_EPOCH for every file w/o __DATE__/__TIME__
       #
       # So for:
-      # - 4.2+ time_macros sloppiness is used,
+      # - 4.2+ does not require any sloppiness
       # - 4.0+ will ignore SOURCE_DATE_EPOCH environment variable.
       if (CCACHE_VERSION VERSION_GREATER_EQUAL "4.2")
-         message(STATUS "Use time_macros sloppiness for ccache")
-         set_property (GLOBAL PROPERTY RULE_LAUNCH_COMPILE "${CCACHE_FOUND} --set-config=sloppiness=time_macros")
-         set_property (GLOBAL PROPERTY RULE_LAUNCH_LINK "${CCACHE_FOUND} --set-config=sloppiness=time_macros")
+         message(STATUS "ccache is 4.2+ no quirks for SOURCE_DATE_EPOCH required")
       elseif (CCACHE_VERSION VERSION_GREATER_EQUAL "4.0")
          message(STATUS "Ignore SOURCE_DATE_EPOCH for ccache")
          set_property (GLOBAL PROPERTY RULE_LAUNCH_COMPILE "env -u SOURCE_DATE_EPOCH ${CCACHE_FOUND}")

cmake/find/nuraft.cmake

@@ -11,7 +11,7 @@ if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/NuRaft/CMakeLists.txt")
     return()
 endif ()
 
-if (NOT OS_FREEBSD)
+if (NOT OS_FREEBSD AND NOT OS_DARWIN)
     set (USE_NURAFT 1)
     set (NURAFT_LIBRARY nuraft)
 
@@ -20,5 +20,5 @@ if (NOT OS_FREEBSD)
     message (STATUS "Using NuRaft=${USE_NURAFT}: ${NURAFT_INCLUDE_DIR} : ${NURAFT_LIBRARY}")
 else()
     set (USE_NURAFT 0)
-    message (STATUS "Using internal NuRaft library on FreeBSD is not supported")
+    message (STATUS "Using internal NuRaft library on FreeBSD and Darwin is not supported")
 endif()

contrib/NuRaft

@@ -1 +1 @@
-Subproject commit 410bd149da84cdde60b4436b02b738749f4e87e1
+Subproject commit 7adf7ae33e7d5c307342431b577c8ab1025ee793

contrib/base64-cmake/CMakeLists.txt

@@ -11,7 +11,7 @@ endif ()
 target_compile_options(base64_scalar PRIVATE -falign-loops)
 
 if (ARCH_AMD64)
-    target_compile_options(base64_ssse3 PRIVATE -mssse3 -falign-loops)
+    target_compile_options(base64_ssse3 PRIVATE -mno-avx -mno-avx2 -mssse3 -falign-loops)
     target_compile_options(base64_avx PRIVATE -falign-loops -mavx)
     target_compile_options(base64_avx2 PRIVATE -falign-loops -mavx2)
 else ()

contrib/boost

@@ -1 +1 @@
-Subproject commit 8e259cd2a6b60d75dd17e73432f11bb7b9351bb1
+Subproject commit 48f40ebb539220d328958f8823b094c0b07a4e79

contrib/hyperscan

@@ -1 +1 @@
-Subproject commit 3907fd00ee8b2538739768fa9533f8635a276531
+Subproject commit e9f08df0213fc637aac0a5bbde9beeaeba2fe9fa

contrib/hyperscan-cmake/CMakeLists.txt

@@ -252,6 +252,7 @@ if (NOT EXTERNAL_HYPERSCAN_LIBRARY_FOUND)
     target_compile_definitions (hyperscan PUBLIC USE_HYPERSCAN=1)
     target_compile_options (hyperscan
         PRIVATE -g0 # Library has too much debug information
+        -mno-avx -mno-avx2 # The library is using dynamic dispatch and is confused if AVX is enabled globally
         -march=corei7 -O2 -fno-strict-aliasing -fno-omit-frame-pointer -fvisibility=hidden # The options from original build system
         -fno-sanitize=undefined # Assume the library takes care of itself
     )

contrib/nuraft-cmake/CMakeLists.txt

@@ -30,7 +30,12 @@ set(SRCS
 
 add_library(nuraft ${SRCS})
 
-target_compile_definitions(nuraft PRIVATE USE_BOOST_ASIO=1 BOOST_ASIO_STANDALONE=1)
+
+if (NOT OPENSSL_SSL_LIBRARY OR NOT OPENSSL_CRYPTO_LIBRARY)
+    target_compile_definitions(nuraft PRIVATE USE_BOOST_ASIO=1 BOOST_ASIO_STANDALONE=1 SSL_LIBRARY_NOT_FOUND=1)
+else()
+    target_compile_definitions(nuraft PRIVATE USE_BOOST_ASIO=1 BOOST_ASIO_STANDALONE=1)
+endif()
 
 target_include_directories (nuraft SYSTEM PRIVATE ${LIBRARY_DIR}/include/libnuraft)
 # for some reason include "asio.h" directly without "boost/" prefix.

contrib/poco

@@ -1 +1 @@
-Subproject commit 2c32e17c7dfee1f8bf24227b697cdef5fddf0823
+Subproject commit fbaaba4a02e29987b8c584747a496c79528f125f

debian/changelog

@@ -1,5 +1,5 @@
-clickhouse (21.2.1.1) unstable; urgency=low
+clickhouse (21.3.1.1) unstable; urgency=low
 
   * Modified source code
 
- -- clickhouse-release <clickhouse-release@yandex-team.ru>  Mon, 11 Jan 2021 11:12:08 +0300
+ -- clickhouse-release <clickhouse-release@yandex-team.ru>  Mon, 01 Feb 2021 12:50:53 +0300

docker/client/Dockerfile

@@ -1,7 +1,7 @@
 FROM ubuntu:18.04
 
 ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
-ARG version=21.2.1.*
+ARG version=21.3.1.*
 
 RUN apt-get update \
     && apt-get install --yes --no-install-recommends \

docker/server/Dockerfile

@@ -1,7 +1,7 @@
 FROM ubuntu:20.04
 
 ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
-ARG version=21.2.1.*
+ARG version=21.3.1.*
 ARG gosu_ver=1.10
 
 # user/group precreated explicitly with fixed uid/gid on purpose.

docker/server/README.md

@@ -113,10 +113,10 @@ $ docker run --rm -e CLICKHOUSE_UID=0 -e CLICKHOUSE_GID=0 --name clickhouse-serv
 
 ### How to create default database and user on starting
 
-Sometimes you may want to create user (user named `default` is used by default) and database on image starting. You can do it using environment variables `CLICKHOUSE_DB`, `CLICKHOUSE_USER` and `CLICKHOUSE_PASSWORD`:
+Sometimes you may want to create user (user named `default` is used by default) and database on image starting. You can do it using environment variables `CLICKHOUSE_DB`, `CLICKHOUSE_USER`, `CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT` and `CLICKHOUSE_PASSWORD`:
 
 ```
-$ docker run --rm -e CLICKHOUSE_DB=my_database -e CLICKHOUSE_USER=username -e CLICKHOUSE_PASSWORD=password -p 9000:9000/tcp yandex/clickhouse-server
+$ docker run --rm -e CLICKHOUSE_DB=my_database -e CLICKHOUSE_USER=username -e CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT=1 -e CLICKHOUSE_PASSWORD=password -p 9000:9000/tcp yandex/clickhouse-server
 ```
 
 ## How to extend this image

docker/server/alpine-build.sh

@@ -54,8 +54,10 @@ docker cp -L "${ubuntu20image}":/lib/x86_64-linux-gnu/libm.so.6       "${CONTAIN
 docker cp -L "${ubuntu20image}":/lib/x86_64-linux-gnu/libpthread.so.0 "${CONTAINER_ROOT_FOLDER}/lib"
 docker cp -L "${ubuntu20image}":/lib/x86_64-linux-gnu/librt.so.1      "${CONTAINER_ROOT_FOLDER}/lib"
 docker cp -L "${ubuntu20image}":/lib/x86_64-linux-gnu/libnss_dns.so.2 "${CONTAINER_ROOT_FOLDER}/lib"
+docker cp -L "${ubuntu20image}":/lib/x86_64-linux-gnu/libnss_files.so.2 "${CONTAINER_ROOT_FOLDER}/lib"
 docker cp -L "${ubuntu20image}":/lib/x86_64-linux-gnu/libresolv.so.2  "${CONTAINER_ROOT_FOLDER}/lib"
 docker cp -L "${ubuntu20image}":/lib64/ld-linux-x86-64.so.2           "${CONTAINER_ROOT_FOLDER}/lib64"
+docker cp -L "${ubuntu20image}":/etc/nsswitch.conf                    "${CONTAINER_ROOT_FOLDER}/etc"
 
 docker build "$DOCKER_BUILD_FOLDER" -f Dockerfile.alpine -t "${DOCKER_IMAGE}:${VERSION}-alpine" --pull
 rm -rf "$CONTAINER_ROOT_FOLDER"

docker/server/entrypoint.sh

@@ -54,6 +54,7 @@ FORMAT_SCHEMA_PATH="$(clickhouse extract-from-config --config-file "$CLICKHOUSE_
 CLICKHOUSE_USER="${CLICKHOUSE_USER:-default}"
 CLICKHOUSE_PASSWORD="${CLICKHOUSE_PASSWORD:-}"
 CLICKHOUSE_DB="${CLICKHOUSE_DB:-}"
+CLICKHOUSE_ACCESS_MANAGEMENT="${CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT:-0}"
 
 for dir in "$DATA_DIR" \
   "$ERROR_LOG_DIR" \
@@ -97,6 +98,7 @@ if [ -n "$CLICKHOUSE_USER" ] && [ "$CLICKHOUSE_USER" != "default" ] || [ -n "$CL
           </networks>
           <password>${CLICKHOUSE_PASSWORD}</password>
           <quota>default</quota>
+          <access_management>${CLICKHOUSE_ACCESS_MANAGEMENT}</access_management>
         </${CLICKHOUSE_USER}>
       </users>
     </yandex>
@@ -120,7 +122,7 @@ if [ -n "$(ls /docker-entrypoint-initdb.d/)" ] || [ -n "$CLICKHOUSE_DB" ]; then
         sleep 1
     done
 
-    clickhouseclient=( clickhouse-client --multiquery -u "$CLICKHOUSE_USER" --password "$CLICKHOUSE_PASSWORD" )
+    clickhouseclient=( clickhouse-client --multiquery --host "127.0.0.1" -u "$CLICKHOUSE_USER" --password "$CLICKHOUSE_PASSWORD" )
 
     echo
 

docker/test/Dockerfile

@@ -1,7 +1,7 @@
 FROM ubuntu:18.04
 
 ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
-ARG version=21.2.1.*
+ARG version=21.3.1.*
 
 RUN apt-get update && \
     apt-get install -y apt-transport-https dirmngr && \

docker/test/fasttest/Dockerfile

@@ -47,6 +47,7 @@ RUN apt-get update \
         expect \
         fakeroot \
         git \
+        gdb \
         gperf \
         lld-${LLVM_VERSION} \
         llvm-${LLVM_VERSION} \

docker/test/fasttest/run.sh

@@ -107,6 +107,18 @@ function start_server
     fi
 
     echo "ClickHouse server pid '$server_pid' started and responded"
+
+    echo "
+handle all noprint
+handle SIGSEGV stop print
+handle SIGBUS stop print
+handle SIGABRT stop print
+continue
+thread apply all backtrace
+continue
+" > script.gdb
+
+    gdb -batch -command script.gdb -p "$server_pid" &
 }
 
 function clone_root
@@ -120,7 +132,7 @@ function clone_root
                 git checkout FETCH_HEAD
                 echo 'Clonned merge head'
             else
-                git fetch
+                git fetch origin "+refs/pull/$PULL_REQUEST_NUMBER/head"
                 git checkout "$COMMIT_SHA"
                 echo 'Checked out to commit'
             fi
@@ -163,6 +175,7 @@ function clone_submodules
             contrib/xz
             contrib/dragonbox
             contrib/fast_float
+            contrib/NuRaft
         )
 
         git submodule sync
@@ -182,6 +195,7 @@ function run_cmake
         "-DENABLE_EMBEDDED_COMPILER=0"
         "-DENABLE_THINLTO=0"
         "-DUSE_UNWIND=1"
+        "-DENABLE_NURAFT=1"
     )
 
     # TODO remove this? we don't use ccache anyway. An option would be to download it
@@ -251,8 +265,13 @@ function run_tests
         00701_rollup
         00834_cancel_http_readonly_queries_on_client_close
         00911_tautological_compare
+
+        # Hyperscan
         00926_multimatch
         00929_multi_match_edit_distance
+        01681_hyperscan_debug_assertion
+
+        01176_mysql_client_interactive          # requires mysql client
         01031_mutations_interpreter_and_context
         01053_ssd_dictionary # this test mistakenly requires acces to /var/lib/clickhouse -- can't run this locally, disabled
         01083_expressions_in_engine_arguments
@@ -315,11 +334,12 @@ function run_tests
 
          # In fasttest, ENABLE_LIBRARIES=0, so rocksdb engine is not enabled by default
         01504_rocksdb
+        01686_rocksdb
 
         # Look at DistributedFilesToInsert, so cannot run in parallel.
         01460_DistributedFilesToInsert
 
-        01541_max_memory_usage_for_user
+        01541_max_memory_usage_for_user_long
 
         # Require python libraries like scipy, pandas and numpy
         01322_ttest_scipy
@@ -335,9 +355,10 @@ function run_tests
 
         # JSON functions
         01666_blns
+        01674_htm_xml_coarse_parse
     )
 
-    time clickhouse-test --hung-check -j 8 --order=random --use-skip-list --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" -- "$FASTTEST_FOCUS" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
+    (time clickhouse-test --hung-check -j 8 --order=random --use-skip-list --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" -- "$FASTTEST_FOCUS" 2>&1 ||:) | ts '%Y-%m-%d %H:%M:%S' | tee "$FASTTEST_OUTPUT/test_log.txt"
 
     # substr is to remove semicolon after test name
     readarray -t FAILED_TESTS < <(awk '/\[ FAIL|TIMEOUT|ERROR \]/ { print substr($3, 1, length($3)-1) }' "$FASTTEST_OUTPUT/test_log.txt" | tee "$FASTTEST_OUTPUT/failed-parallel-tests.txt")

docker/test/fuzzer/run-fuzzer.sh

@@ -21,13 +21,16 @@ function clone
 
     git init
     git remote add origin https://github.com/ClickHouse/ClickHouse
-    git fetch --depth=100 origin "$SHA_TO_TEST"
-    git fetch --depth=100 origin master # Used to obtain the list of modified or added tests
+
+    # Network is unreliable. GitHub neither.
+    for _ in {1..100}; do git fetch --depth=100 origin "$SHA_TO_TEST" && break; sleep 1; done
+    # Used to obtain the list of modified or added tests
+    for _ in {1..100}; do git fetch --depth=100 origin master && break; sleep 1; done
 
     # If not master, try to fetch pull/.../{head,merge}
     if [ "$PR_TO_TEST" != "0" ]
     then
-        git fetch --depth=100 origin "refs/pull/$PR_TO_TEST/*:refs/heads/pull/$PR_TO_TEST/*"
+        for _ in {1..100}; do git fetch --depth=100 origin "refs/pull/$PR_TO_TEST/*:refs/heads/pull/$PR_TO_TEST/*" && break; sleep 1; done
     fi
 
     git checkout "$SHA_TO_TEST"
@@ -187,7 +190,7 @@ case "$stage" in
         # Lost connection to the server. This probably means that the server died
         # with abort.
         echo "failure" > status.txt
-        if ! grep -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*\|SUMMARY: MemorySanitizer:.*\|SUMMARY: ThreadSanitizer:.*" server.log > description.txt
+        if ! grep -ao "Received signal.*\|Logical error.*\|Assertion.*failed\|Failed assertion.*\|.*runtime error: .*\|.*is located.*\|SUMMARY: MemorySanitizer:.*\|SUMMARY: ThreadSanitizer:.*\|.*_LIBCPP_ASSERT.*" server.log > description.txt
         then
             echo "Lost connection to server. See the logs." > description.txt
         fi

docker/test/integration/runner/Dockerfile

@@ -58,10 +58,11 @@ RUN dockerd --version; docker --version
 
 RUN python3 -m pip install \
     PyMySQL \
-    aerospike \
+    aerospike==4.0.0 \
     avro \
     cassandra-driver \
-    confluent-kafka \
+    confluent-kafka==1.5.0 \
+    dict2xml \
     dicttoxml \
     docker \
     docker-compose==1.22.0 \

docker/test/integration/runner/compose/docker_compose_cassandra.yml

@@ -4,4 +4,4 @@ services:
         image: cassandra
         restart: always
         ports:
-          - 9043:9042
+            - 9043:9042

docker/test/integration/runner/compose/docker_compose_hdfs.yml

@@ -5,6 +5,6 @@ services:
         hostname: hdfs1
         restart: always
         ports:
-          - 50075:50075
-          - 50070:50070
+            - 50075:50075
+            - 50070:50070
         entrypoint: /etc/bootstrap.sh -d

docker/test/integration/runner/compose/docker_compose_kafka.yml

@@ -5,42 +5,42 @@ services:
     image: zookeeper:3.4.9
     hostname: kafka_zookeeper
     environment:
-        ZOO_MY_ID: 1
-        ZOO_PORT: 2181
-        ZOO_SERVERS: server.1=kafka_zookeeper:2888:3888
+      ZOO_MY_ID: 1
+      ZOO_PORT: 2181
+      ZOO_SERVERS: server.1=kafka_zookeeper:2888:3888
     security_opt:
-        - label:disable
+      - label:disable
 
   kafka1:
     image: confluentinc/cp-kafka:5.2.0
     hostname: kafka1
     ports:
-        - "9092:9092"
+      - "9092:9092"
     environment:
-        KAFKA_ADVERTISED_LISTENERS: INSIDE://localhost:9092,OUTSIDE://kafka1:19092
-        KAFKA_LISTENERS: INSIDE://:9092,OUTSIDE://:19092
-        KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: INSIDE:PLAINTEXT,OUTSIDE:PLAINTEXT
-        KAFKA_INTER_BROKER_LISTENER_NAME: INSIDE
-        KAFKA_BROKER_ID: 1
-        KAFKA_ZOOKEEPER_CONNECT: "kafka_zookeeper:2181"
-        KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
-        KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
+      KAFKA_ADVERTISED_LISTENERS: INSIDE://localhost:9092,OUTSIDE://kafka1:19092
+      KAFKA_LISTENERS: INSIDE://:9092,OUTSIDE://:19092
+      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: INSIDE:PLAINTEXT,OUTSIDE:PLAINTEXT
+      KAFKA_INTER_BROKER_LISTENER_NAME: INSIDE
+      KAFKA_BROKER_ID: 1
+      KAFKA_ZOOKEEPER_CONNECT: "kafka_zookeeper:2181"
+      KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
+      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
     depends_on:
-        - kafka_zookeeper
+      - kafka_zookeeper
     security_opt:
-        - label:disable
+      - label:disable
 
   schema-registry:
     image: confluentinc/cp-schema-registry:5.2.0
     hostname: schema-registry
     ports:
-        - "8081:8081"
+      - "8081:8081"
     environment:
-        SCHEMA_REGISTRY_HOST_NAME: schema-registry
-        SCHEMA_REGISTRY_KAFKASTORE_SECURITY_PROTOCOL: PLAINTEXT
-        SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: PLAINTEXT://kafka1:19092
+      SCHEMA_REGISTRY_HOST_NAME: schema-registry
+      SCHEMA_REGISTRY_KAFKASTORE_SECURITY_PROTOCOL: PLAINTEXT
+      SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS: PLAINTEXT://kafka1:19092
     depends_on:
-        - kafka_zookeeper
-        - kafka1
+      - kafka_zookeeper
+      - kafka1
     security_opt:
-        - label:disable
+      - label:disable

docker/test/integration/runner/compose/docker_compose_kerberized_hdfs.yml

@@ -8,22 +8,22 @@ services:
     hostname: kerberizedhdfs1
     restart: always
     volumes:
-        - ${KERBERIZED_HDFS_DIR}/../../hdfs_configs/bootstrap.sh:/etc/bootstrap.sh:ro
-        - ${KERBERIZED_HDFS_DIR}/secrets:/usr/local/hadoop/etc/hadoop/conf
-        - ${KERBERIZED_HDFS_DIR}/secrets/krb_long.conf:/etc/krb5.conf:ro
+      - ${KERBERIZED_HDFS_DIR}/../../hdfs_configs/bootstrap.sh:/etc/bootstrap.sh:ro
+      - ${KERBERIZED_HDFS_DIR}/secrets:/usr/local/hadoop/etc/hadoop/conf
+      - ${KERBERIZED_HDFS_DIR}/secrets/krb_long.conf:/etc/krb5.conf:ro
     ports:
       - 1006:1006
       - 50070:50070
-      - 9000:9000
+      - 9010:9010
     depends_on:
-        - hdfskerberos
+      - hdfskerberos
     entrypoint: /etc/bootstrap.sh -d
 
   hdfskerberos:
     image: yandex/clickhouse-kerberos-kdc:${DOCKER_KERBEROS_KDC_TAG}
     hostname: hdfskerberos
     volumes:
-        - ${KERBERIZED_HDFS_DIR}/secrets:/tmp/keytab
-        - ${KERBERIZED_HDFS_DIR}/../../kerberos_image_config.sh:/config.sh
-        - /dev/urandom:/dev/random
+      - ${KERBERIZED_HDFS_DIR}/secrets:/tmp/keytab
+      - ${KERBERIZED_HDFS_DIR}/../../kerberos_image_config.sh:/config.sh
+      - /dev/urandom:/dev/random
     ports: [88, 749]

docker/test/integration/runner/compose/docker_compose_kerberized_kafka.yml

@@ -6,54 +6,54 @@ services:
     # restart: always
     hostname: kafka_kerberized_zookeeper
     environment:
-        ZOOKEEPER_SERVER_ID: 1
-        ZOOKEEPER_CLIENT_PORT: 2181
-        ZOOKEEPER_SERVERS: "kafka_kerberized_zookeeper:2888:3888"
-        KAFKA_OPTS: "-Djava.security.auth.login.config=/etc/kafka/secrets/zookeeper_jaas.conf -Djava.security.krb5.conf=/etc/kafka/secrets/krb.conf -Dzookeeper.authProvider.1=org.apache.zookeeper.server.auth.SASLAuthenticationProvider -Dsun.security.krb5.debug=true"
+      ZOOKEEPER_SERVER_ID: 1
+      ZOOKEEPER_CLIENT_PORT: 2181
+      ZOOKEEPER_SERVERS: "kafka_kerberized_zookeeper:2888:3888"
+      KAFKA_OPTS: "-Djava.security.auth.login.config=/etc/kafka/secrets/zookeeper_jaas.conf -Djava.security.krb5.conf=/etc/kafka/secrets/krb.conf -Dzookeeper.authProvider.1=org.apache.zookeeper.server.auth.SASLAuthenticationProvider -Dsun.security.krb5.debug=true"
     volumes:
-        - ${KERBERIZED_KAFKA_DIR}/secrets:/etc/kafka/secrets
-        - /dev/urandom:/dev/random
+      - ${KERBERIZED_KAFKA_DIR}/secrets:/etc/kafka/secrets
+      - /dev/urandom:/dev/random
     depends_on:
-        - kafka_kerberos
+      - kafka_kerberos
     security_opt:
-        - label:disable
+      - label:disable
 
   kerberized_kafka1:
     image: confluentinc/cp-kafka:5.2.0
     # restart: always
     hostname: kerberized_kafka1
     ports:
-        - "9092:9092"
-        - "9093:9093"
+      - "9092:9092"
+      - "9093:9093"
     environment:
-        KAFKA_LISTENERS: OUTSIDE://:19092,UNSECURED_OUTSIDE://:19093,UNSECURED_INSIDE://:9093
-        KAFKA_ADVERTISED_LISTENERS: OUTSIDE://kerberized_kafka1:19092,UNSECURED_OUTSIDE://kerberized_kafka1:19093,UNSECURED_INSIDE://localhost:9093
-        # KAFKA_LISTENERS: INSIDE://kerberized_kafka1:9092,OUTSIDE://kerberized_kafka1:19092
-        # KAFKA_ADVERTISED_LISTENERS: INSIDE://localhost:9092,OUTSIDE://kerberized_kafka1:19092
-        KAFKA_SASL_MECHANISM_INTER_BROKER_PROTOCOL: GSSAPI
-        KAFKA_SASL_ENABLED_MECHANISMS: GSSAPI
-        KAFKA_SASL_KERBEROS_SERVICE_NAME: kafka
-        KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: OUTSIDE:SASL_PLAINTEXT,UNSECURED_OUTSIDE:PLAINTEXT,UNSECURED_INSIDE:PLAINTEXT,
-        KAFKA_INTER_BROKER_LISTENER_NAME: OUTSIDE
-        KAFKA_BROKER_ID: 1
-        KAFKA_ZOOKEEPER_CONNECT: "kafka_kerberized_zookeeper:2181"
-        KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
-        KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
-        KAFKA_OPTS: "-Djava.security.auth.login.config=/etc/kafka/secrets/broker_jaas.conf -Djava.security.krb5.conf=/etc/kafka/secrets/krb.conf -Dsun.security.krb5.debug=true"
+      KAFKA_LISTENERS: OUTSIDE://:19092,UNSECURED_OUTSIDE://:19093,UNSECURED_INSIDE://:9093
+      KAFKA_ADVERTISED_LISTENERS: OUTSIDE://kerberized_kafka1:19092,UNSECURED_OUTSIDE://kerberized_kafka1:19093,UNSECURED_INSIDE://localhost:9093
+      # KAFKA_LISTENERS: INSIDE://kerberized_kafka1:9092,OUTSIDE://kerberized_kafka1:19092
+      # KAFKA_ADVERTISED_LISTENERS: INSIDE://localhost:9092,OUTSIDE://kerberized_kafka1:19092
+      KAFKA_SASL_MECHANISM_INTER_BROKER_PROTOCOL: GSSAPI
+      KAFKA_SASL_ENABLED_MECHANISMS: GSSAPI
+      KAFKA_SASL_KERBEROS_SERVICE_NAME: kafka
+      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: OUTSIDE:SASL_PLAINTEXT,UNSECURED_OUTSIDE:PLAINTEXT,UNSECURED_INSIDE:PLAINTEXT,
+      KAFKA_INTER_BROKER_LISTENER_NAME: OUTSIDE
+      KAFKA_BROKER_ID: 1
+      KAFKA_ZOOKEEPER_CONNECT: "kafka_kerberized_zookeeper:2181"
+      KAFKA_LOG4J_LOGGERS: "kafka.controller=INFO,kafka.producer.async.DefaultEventHandler=INFO,state.change.logger=INFO"
+      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
+      KAFKA_OPTS: "-Djava.security.auth.login.config=/etc/kafka/secrets/broker_jaas.conf -Djava.security.krb5.conf=/etc/kafka/secrets/krb.conf -Dsun.security.krb5.debug=true"
     volumes:
-        - ${KERBERIZED_KAFKA_DIR}/secrets:/etc/kafka/secrets
-        - /dev/urandom:/dev/random
+      - ${KERBERIZED_KAFKA_DIR}/secrets:/etc/kafka/secrets
+      - /dev/urandom:/dev/random
     depends_on:
-        - kafka_kerberized_zookeeper
-        - kafka_kerberos
+      - kafka_kerberized_zookeeper
+      - kafka_kerberos
     security_opt:
-        - label:disable
+      - label:disable
 
   kafka_kerberos:
     image: yandex/clickhouse-kerberos-kdc:${DOCKER_KERBEROS_KDC_TAG:-latest}
     hostname: kafka_kerberos
     volumes:
-        - ${KERBERIZED_KAFKA_DIR}/secrets:/tmp/keytab
-        - ${KERBERIZED_KAFKA_DIR}/../../kerberos_image_config.sh:/config.sh
-        - /dev/urandom:/dev/random
+      - ${KERBERIZED_KAFKA_DIR}/secrets:/tmp/keytab
+      - ${KERBERIZED_KAFKA_DIR}/../../kerberos_image_config.sh:/config.sh
+      - /dev/urandom:/dev/random
     ports: [88, 749]

docker/test/integration/runner/compose/docker_compose_mongo.yml

@@ -7,5 +7,5 @@ services:
             MONGO_INITDB_ROOT_USERNAME: root
             MONGO_INITDB_ROOT_PASSWORD: clickhouse
         ports:
-          - 27018:27017
+            - 27018:27017
         command: --profile=2 --verbose

docker/test/integration/runner/compose/docker_compose_mysql.yml

@@ -6,5 +6,5 @@ services:
         environment:
             MYSQL_ROOT_PASSWORD: clickhouse
         ports:
-          - 3308:3306
+            - 3308:3306
         command: --server_id=100 --log-bin='mysql-bin-1.log' --default-time-zone='+3:00' --gtid-mode="ON" --enforce-gtid-consistency

docker/test/integration/runner/compose/docker_compose_mysql_5_7_for_materialize_mysql.yml

@@ -6,5 +6,9 @@ services:
         environment:
             MYSQL_ROOT_PASSWORD: clickhouse
         ports:
-          - 3308:3306
-        command: --server_id=100 --log-bin='mysql-bin-1.log' --default-time-zone='+3:00' --gtid-mode="ON" --enforce-gtid-consistency
+            - 3308:3306
+        command: --server_id=100 --log-bin='mysql-bin-1.log'
+            --default-time-zone='+3:00'
+            --gtid-mode="ON"
+            --enforce-gtid-consistency
+            --log-error-verbosity=3

docker/test/integration/runner/compose/docker_compose_mysql_8_0_for_materialize_mysql.yml

@@ -6,5 +6,10 @@ services:
         environment:
             MYSQL_ROOT_PASSWORD: clickhouse
         ports:
-          - 33308:3306
-        command: --server_id=100 --log-bin='mysql-bin-1.log' --default_authentication_plugin='mysql_native_password' --default-time-zone='+3:00' --gtid-mode="ON" --enforce-gtid-consistency
+            - 33308:3306
+        command: --server_id=100 --log-bin='mysql-bin-1.log'
+            --default_authentication_plugin='mysql_native_password'
+            --default-time-zone='+3:00'
+            --gtid-mode="ON"
+            --enforce-gtid-consistency
+            --log-error-verbosity=3

docker/test/integration/runner/compose/docker_compose_mysql_client.yml

@@ -7,7 +7,7 @@ services:
       MYSQL_ALLOW_EMPTY_PASSWORD: 1
     command: --federated --socket /var/run/mysqld/mysqld.sock
     healthcheck:
-      test: ["CMD", "mysqladmin" ,"ping", "-h", "localhost"]
+      test: ["CMD", "mysqladmin", "ping", "-h", "localhost"]
       interval: 1s
       timeout: 2s
       retries: 100

docker/test/integration/runner/compose/docker_compose_postgres.yml

@@ -6,8 +6,8 @@ services:
         environment:
             POSTGRES_PASSWORD: mysecretpassword
         ports:
-          - 5432:5432
+            - 5432:5432
         networks:
-          default:
-            aliases:
-              - postgre-sql.local
+            default:
+                aliases:
+                    - postgre-sql.local

docker/test/integration/runner/compose/docker_compose_redis.yml

@@ -4,5 +4,5 @@ services:
         image: redis
         restart: always
         ports:
-          - 6380:6379
+            - 6380:6379
         command: redis-server --requirepass "clickhouse" --databases 32

docker/test/performance-comparison/compare.sh

@@ -97,6 +97,7 @@ function configure
     rm -r right/db ||:
     rm -r db0/preprocessed_configs ||:
     rm -r db0/{data,metadata}/system ||:
+    rm db0/status ||:
     cp -al db0/ left/db/
     cp -al db0/ right/db/
 }

docker/test/performance-comparison/perf.py

@@ -44,6 +44,7 @@ parser.add_argument('--port', nargs='*', default=[9000], help="Space-separated l
 parser.add_argument('--runs', type=int, default=1, help='Number of query runs per server.')
 parser.add_argument('--max-queries', type=int, default=None, help='Test no more than this number of queries, chosen at random.')
 parser.add_argument('--queries-to-run', nargs='*', type=int, default=None, help='Space-separated list of indexes of queries to test.')
+parser.add_argument('--max-query-seconds', type=int, default=10, help='For how many seconds at most a query is allowed to run. The script finishes with error if this time is exceeded.')
 parser.add_argument('--profile-seconds', type=int, default=0, help='For how many seconds to profile a query for which the performance has changed.')
 parser.add_argument('--long', action='store_true', help='Do not skip the tests tagged as long.')
 parser.add_argument('--print-queries', action='store_true', help='Print test queries and exit.')
@@ -323,7 +324,7 @@ for query_index in queries_to_run:
             server_seconds += elapsed
             print(f'query\t{query_index}\t{run_id}\t{conn_index}\t{elapsed}')
 
-            if elapsed > 10:
+            if elapsed > args.max_query_seconds:
                 # Stop processing pathologically slow queries, to avoid timing out
                 # the entire test task. This shouldn't really happen, so we don't
                 # need much handling for this case and can just exit.

docker/test/stateful/run.sh

@@ -60,4 +60,8 @@ fi
 # more idiologically correct.
 read -ra ADDITIONAL_OPTIONS <<< "${ADDITIONAL_OPTIONS:-}"
 
+if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+    ADDITIONAL_OPTIONS+=('--replicated-database')
+fi
+
 clickhouse-test --testname --shard --zookeeper --no-stateless --hung-check --print-time "$SKIP_LIST_OPT" "${ADDITIONAL_OPTIONS[@]}" "$SKIP_TESTS_OPTION" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee test_output/test_result.txt

docker/test/stateless/Dockerfile

@@ -3,6 +3,9 @@ FROM yandex/clickhouse-test-base
 
 ARG odbc_driver_url="https://github.com/ClickHouse/clickhouse-odbc/releases/download/v1.1.4.20200302/clickhouse-odbc-1.1.4-Linux.tar.gz"
 
+RUN echo "deb [trusted=yes] http://repo.mysql.com/apt/ubuntu/ bionic mysql-5.7" >> /etc/apt/sources.list \
+    && apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 8C718D3B5072E1F5
+
 RUN apt-get update -y \
     && env DEBIAN_FRONTEND=noninteractive \
         apt-get install --yes --no-install-recommends \
@@ -13,6 +16,7 @@ RUN apt-get update -y \
             ncdu \
             netcat-openbsd \
             openssl \
+            protobuf-compiler \
             python3 \
             python3-lxml \
             python3-requests \
@@ -23,7 +27,8 @@ RUN apt-get update -y \
             telnet \
             tree \
             unixodbc \
-            wget
+            wget \
+            mysql-client=5.7*
 
 RUN pip3 install numpy scipy pandas
 

docker/test/stateless/run.sh

@@ -53,14 +53,19 @@ function run_tests()
     if [ "$NUM_TRIES" -gt "1" ]; then
         ADDITIONAL_OPTIONS+=('--skip')
         ADDITIONAL_OPTIONS+=('00000_no_tests_to_skip')
+        ADDITIONAL_OPTIONS+=('--jobs')
+        ADDITIONAL_OPTIONS+=('4')
     fi
 
-    for _ in $(seq 1 "$NUM_TRIES"); do
-        clickhouse-test --testname --shard --zookeeper --hung-check --print-time "$SKIP_LIST_OPT" "${ADDITIONAL_OPTIONS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a test_output/test_result.txt
-        if [ "${PIPESTATUS[0]}" -ne "0" ]; then
-            break;
-        fi
-    done
+    if [[ -n "$USE_DATABASE_REPLICATED" ]] && [[ "$USE_DATABASE_REPLICATED" -eq 1 ]]; then
+        ADDITIONAL_OPTIONS+=('--replicated-database')
+    fi
+
+    clickhouse-test --testname --shard --zookeeper --hung-check --print-time \
+            --test-runs "$NUM_TRIES" \
+            "$SKIP_LIST_OPT" "${ADDITIONAL_OPTIONS[@]}" 2>&1 \
+        | ts '%Y-%m-%d %H:%M:%S' \
+        | tee -a test_output/test_result.txt
 }
 
 export -f run_tests

docker/test/stateless_pytest/Dockerfile

@@ -5,7 +5,10 @@ RUN apt-get update -y && \
     apt-get install -y --no-install-recommends \
         python3-pip \
         python3-setuptools \
-        python3-wheel
+        python3-wheel \
+        brotli \
+        netcat-openbsd \
+        zstd
 
 RUN python3 -m pip install \
     wheel \
@@ -15,7 +18,10 @@ RUN python3 -m pip install \
     pytest-randomly \
     pytest-rerunfailures \
     pytest-timeout \
-    pytest-xdist
+    pytest-xdist \
+    pandas \
+    numpy \
+    scipy
 
 CMD dpkg -i package_folder/clickhouse-common-static_*.deb; \
     dpkg -i package_folder/clickhouse-common-static-dbg_*.deb; \

docker/test/stress/run.sh

@@ -8,16 +8,23 @@ dpkg -i package_folder/clickhouse-server_*.deb
 dpkg -i package_folder/clickhouse-client_*.deb
 dpkg -i package_folder/clickhouse-test_*.deb
 
+function configure()
+{
+    # install test configs
+    /usr/share/clickhouse-test/config/install.sh
+
+    # for clickhouse-server (via service)
+    echo "ASAN_OPTIONS='malloc_context_size=10 verbosity=1 allocator_release_to_os_interval_ms=10000'" >> /etc/environment
+    # for clickhouse-client
+    export ASAN_OPTIONS='malloc_context_size=10 allocator_release_to_os_interval_ms=10000'
+
+    # since we run clickhouse from root
+    sudo chown root: /var/lib/clickhouse
+}
+
 function stop()
 {
-    timeout 120 service clickhouse-server stop
-
-    # Wait for process to disappear from processlist and also try to kill zombies.
-    while kill -9 "$(pidof clickhouse-server)"
-    do
-        echo "Killed clickhouse-server"
-        sleep 0.5
-    done
+    clickhouse stop
 }
 
 function start()
@@ -33,19 +40,26 @@ function start()
             tail -n1000 /var/log/clickhouse-server/clickhouse-server.log
             break
         fi
-        timeout 120 service clickhouse-server start
+        # use root to match with current uid
+        clickhouse start --user root >/var/log/clickhouse-server/stdout.log 2>/var/log/clickhouse-server/stderr.log
         sleep 0.5
         counter=$((counter + 1))
     done
+
+    echo "
+handle all noprint
+handle SIGSEGV stop print
+handle SIGBUS stop print
+handle SIGABRT stop print
+continue
+thread apply all backtrace
+continue
+" > script.gdb
+
+    gdb -batch -command script.gdb -p "$(cat /var/run/clickhouse-server/clickhouse-server.pid)" &
 }
 
-# install test configs
-/usr/share/clickhouse-test/config/install.sh
-
-# for clickhouse-server (via service)
-echo "ASAN_OPTIONS='malloc_context_size=10 verbosity=1 allocator_release_to_os_interval_ms=10000'" >> /etc/environment
-# for clickhouse-client
-export ASAN_OPTIONS='malloc_context_size=10 allocator_release_to_os_interval_ms=10000'
+configure
 
 start
 
@@ -64,7 +78,7 @@ clickhouse-client --query "RENAME TABLE datasets.hits_v1 TO test.hits"
 clickhouse-client --query "RENAME TABLE datasets.visits_v1 TO test.visits"
 clickhouse-client --query "SHOW TABLES FROM test"
 
-./stress --output-folder test_output --skip-func-tests "$SKIP_TESTS_OPTION"
+./stress --hung-check --output-folder test_output --skip-func-tests "$SKIP_TESTS_OPTION" && echo "OK" > /test_output/script_exit_code.txt || echo "FAIL" > /test_output/script_exit_code.txt
 
 stop
 start

docker/test/stress/stress

@@ -1,8 +1,9 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 from multiprocessing import cpu_count
-from subprocess import Popen, check_call
+from subprocess import Popen, call, STDOUT
 import os
+import sys
 import shutil
 import argparse
 import logging
@@ -22,12 +23,15 @@ def get_options(i):
     if 0 < i:
         options += " --order=random"
 
-    if i % 2 == 1:
+    if i % 3 == 1:
         options += " --db-engine=Ordinary"
 
+    if i % 3 == 2:
+        options += ''' --db-engine="Replicated('/test/db/test_{}', 's1', 'r1')"'''.format(i)
+
     # If database name is not specified, new database is created for each functional test.
     # Run some threads with one database for all tests.
-    if i % 3 == 1:
+    if i % 2 == 1:
         options += " --database=test_{}".format(i)
 
     if i == 13:
@@ -64,7 +68,8 @@ if __name__ == "__main__":
     parser.add_argument("--server-log-folder", default='/var/log/clickhouse-server')
     parser.add_argument("--output-folder")
     parser.add_argument("--global-time-limit", type=int, default=3600)
-    parser.add_argument("--num-parallel", default=cpu_count());
+    parser.add_argument("--num-parallel", default=cpu_count())
+    parser.add_argument('--hung-check', action='store_true', default=False)
 
     args = parser.parse_args()
     func_pipes = []
@@ -81,4 +86,13 @@ if __name__ == "__main__":
         logging.info("Finished %s from %s processes", len(retcodes), len(func_pipes))
         time.sleep(5)
 
+    logging.info("All processes finished")
+    if args.hung_check:
+        logging.info("Checking if some queries hung")
+        cmd = "{} {} {}".format(args.test_cmd, "--hung-check", "00001_select_1")
+        res = call(cmd, shell=True, stderr=STDOUT)
+        if res != 0:
+            logging.info("Hung check failed with exit code {}".format(res))
+            sys.exit(1)
+
     logging.info("Stress test finished")

docker/test/style/Dockerfile

@@ -1,12 +1,23 @@
 # docker build -t yandex/clickhouse-style-test .
 FROM ubuntu:20.04
 
-RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes shellcheck libxml2-utils git python3-pip python3-pytest && pip3 install codespell
+RUN apt-get update && env DEBIAN_FRONTEND=noninteractive apt-get install --yes \
+    shellcheck \
+    libxml2-utils \
+    git \
+    python3-pip \
+    pylint \
+    yamllint \
+    && pip3 install codespell
 
 
+# For |& syntax
+SHELL ["bash", "-c"]
+
 CMD cd /ClickHouse/utils/check-style && \
-    ./check-style -n | tee /test_output/style_output.txt && \
-    ./check-typos | tee /test_output/typos_output.txt && \
-    ./check-whitespaces -n | tee /test_output/whitespaces_output.txt && \
-    ./check-duplicate-includes.sh | tee /test_output/duplicate_output.txt && \
-    ./shellcheck-run.sh | tee /test_output/shellcheck_output.txt
+    ./check-style -n              |& tee /test_output/style_output.txt && \
+    ./check-typos                 |& tee /test_output/typos_output.txt && \
+    ./check-whitespaces -n        |& tee /test_output/whitespaces_output.txt && \
+    ./check-duplicate-includes.sh |& tee /test_output/duplicate_output.txt && \
+    ./shellcheck-run.sh           |& tee /test_output/shellcheck_output.txt && \
+    true

docs/_description_templates/template-data-type.md

@@ -0,0 +1,29 @@
+---
+toc_priority: 
+toc_title: 
+---
+
+# data_type_name {#data_type-name}
+
+Description.
+
+**Parameters** (Optional)
+
+-   `x` — Description. [Type name](relative/path/to/type/dscr.md#type).
+-   `y` — Description. [Type name](relative/path/to/type/dscr.md#type).
+
+**Examples**
+
+```sql
+
+```
+
+## Additional Info {#additional-info} (Optional)
+
+The name of an additional section can be any, for example, **Usage**.
+
+**See Also** (Optional)
+
+-   [link](#)
+
+[Original article](https://clickhouse.tech/docs/en/data_types/<data-type-name>/) <!--hide-->

docs/_description_templates/template-function.md

@@ -12,16 +12,20 @@ Alias: `<alias name>`. (Optional)
 
 More text (Optional).
 
-**Parameters** (Optional)
+**Arguments** (Optional)
 
 -   `x` — Description. [Type name](relative/path/to/type/dscr.md#type).
 -   `y` — Description. [Type name](relative/path/to/type/dscr.md#type).
 
+**Parameters** (Optional, only for parametric aggregate functions)
+
+-   `z` — Description. [Type name](relative/path/to/type/dscr.md#type).
+
 **Returned value(s)**
 
 -   Returned values list. 
 
-Type: [Type](relative/path/to/type/dscr.md#type).
+Type: [Type name](relative/path/to/type/dscr.md#type).
 
 **Example**
 

docs/_description_templates/template-system-table.md

@@ -8,10 +8,14 @@ Columns:
 
 **Example**
 
+Query:
+
 ``` sql
 SELECT * FROM system.table_name
 ```
 
+Result:
+
 ``` text
 Some output. It shouldn't be too long.
 ```

docs/en/development/build-osx.md

@@ -40,7 +40,7 @@ $ cd ClickHouse
 ``` bash
 $ mkdir build
 $ cd build
-$ cmake ..-DCMAKE_C_COMPILER=`brew --prefix llvm`/bin/clang -DCMAKE_CXX_COMPILER=`brew --prefix llvm`/bin/clang++ -DCMAKE_PREFIX_PATH=`brew --prefix llvm`
+$ cmake .. -DCMAKE_C_COMPILER=`brew --prefix llvm`/bin/clang -DCMAKE_CXX_COMPILER=`brew --prefix llvm`/bin/clang++ -DCMAKE_PREFIX_PATH=`brew --prefix llvm`
 $ ninja
 $ cd ..
 ```

docs/en/engines/database-engines/materialize-mysql.md

@@ -93,6 +93,7 @@ ClickHouse has only one physical order, which is determined by `ORDER BY` clause
 - Cascade `UPDATE/DELETE` queries are not supported by the `MaterializeMySQL` engine.
 - Replication can be easily broken.
 - Manual operations on database and tables are forbidden.
+- `MaterializeMySQL` is influenced by [optimize_on_insert](../../operations/settings/settings.md#optimize-on-insert) setting. The data is merged in the corresponding table in the `MaterializeMySQL` database when a table in the MySQL server changes.
 
 ## Examples of Use {#examples-of-use}
 
@@ -156,4 +157,4 @@ SELECT * FROM mysql.test;
 └───┴─────┴──────┘
 ```
 
-[Original article](https://clickhouse.tech/docs/en/database_engines/materialize-mysql/) <!--hide-->
+[Original article](https://clickhouse.tech/docs/en/engines/database-engines/materialize-mysql/) <!--hide-->

docs/en/engines/table-engines/integrations/embedded-rocksdb.md

@@ -7,8 +7,6 @@ toc_title: EmbeddedRocksDB
 
 This engine allows integrating ClickHouse with [rocksdb](http://rocksdb.org/).
 
-`EmbeddedRocksDB` lets you:
-
 ## Creating a Table {#table_engine-EmbeddedRocksDB-creating-a-table}
 
 ``` sql
@@ -23,6 +21,9 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster]
 Required parameters:
 
 -  `primary_key_name` – any column name in the column list.
+- `primary key` must be specified, it supports only one column in the primary key. The primary key will be serialized in binary as a `rocksdb key`.
+- columns other than the primary key will be serialized in binary as `rocksdb` value in corresponding order.
+- queries with key `equals` or `in` filtering will be optimized to multi keys lookup from `rocksdb`.
 
 Example:
 
@@ -38,8 +39,4 @@ ENGINE = EmbeddedRocksDB
 PRIMARY KEY key
 ```
 
-## Description {#description}
-
-- `primary key` must be specified, it only supports one column in primary key. The primary key will serialized in binary as rocksdb key.
-- columns other than the primary key will be serialized in binary as rocksdb value in corresponding order.
-- queries with key `equals` or `in` filtering will be optimized to multi keys lookup from rocksdb.
+[Original article](https://clickhouse.tech/docs/en/operations/table_engines/embedded-rocksdb/) <!--hide-->

docs/en/engines/table-engines/integrations/index.md

@@ -12,6 +12,9 @@ List of supported integrations:
 -   [ODBC](../../../engines/table-engines/integrations/odbc.md)
 -   [JDBC](../../../engines/table-engines/integrations/jdbc.md)
 -   [MySQL](../../../engines/table-engines/integrations/mysql.md)
+-   [MongoDB](../../../engines/table-engines/integrations/mongodb.md)
 -   [HDFS](../../../engines/table-engines/integrations/hdfs.md)
 -   [S3](../../../engines/table-engines/integrations/s3.md)
 -   [Kafka](../../../engines/table-engines/integrations/kafka.md)
+-   [EmbeddedRocksDB](../../../engines/table-engines/integrations/embedded-rocksdb.md)
+-   [RabbitMQ](../../../engines/table-engines/integrations/rabbitmq.md)

docs/en/engines/table-engines/integrations/mongodb.md

@@ -0,0 +1,57 @@
+---
+toc_priority: 7
+toc_title: MongoDB
+---
+
+# MongoDB {#mongodb}
+
+MongoDB engine is read-only table engine which allows to read data (`SELECT` queries) from remote MongoDB collection. Engine supports only non-nested data types. `INSERT` queries are not supported.
+
+## Creating a Table {#creating-a-table}
+
+``` sql
+CREATE TABLE [IF NOT EXISTS] [db.]table_name
+(
+    name1 [type1],
+    name2 [type2],
+    ...
+) ENGINE = MongoDB(host:port, database, collection, user, password);
+```
+
+**Engine Parameters**
+
+-   `host:port` — MongoDB server address.
+
+-   `database` — Remote database name.
+
+-   `collection` — Remote collection name.
+
+-   `user` — MongoDB user.
+
+-   `password` — User password.
+
+## Usage Example {#usage-example}
+
+Table in ClickHouse which allows to read data from MongoDB collection:
+
+``` text
+CREATE TABLE mongo_table
+(
+    key UInt64, 
+    data String
+) ENGINE = MongoDB('mongo1:27017', 'test', 'simple_table', 'testuser', 'clickhouse');
+```
+
+Query:
+
+``` sql
+SELECT COUNT() FROM mongo_table;
+```
+
+``` text
+┌─count()─┐
+│       4 │
+└─────────┘
+```
+
+[Original article](https://clickhouse.tech/docs/en/operations/table_engines/integrations/mongodb/) <!--hide-->

docs/en/engines/table-engines/integrations/rabbitmq.md

@@ -59,10 +59,26 @@ Optional parameters:
 -   `rabbitmq_max_block_size`
 -   `rabbitmq_flush_interval_ms`
 
-Required configuration:
+Also format settings can be added along with rabbitmq-related settings.
+
+Example:
+
+``` sql
+  CREATE TABLE queue (
+    key UInt64,
+    value UInt64,
+    date DateTime
+  ) ENGINE = RabbitMQ SETTINGS rabbitmq_host_port = 'localhost:5672',
+                            rabbitmq_exchange_name = 'exchange1',
+                            rabbitmq_format = 'JSONEachRow',
+                            rabbitmq_num_consumers = 5,
+                            date_time_input_format = 'best_effort';
+```
 
 The RabbitMQ server configuration should be added using the ClickHouse config file.
 
+Required configuration:
+
 ``` xml
  <rabbitmq>
     <username>root</username>
@@ -70,16 +86,12 @@ The RabbitMQ server configuration should be added using the ClickHouse config fi
  </rabbitmq>
 ```
 
-Example:
+Additional configuration:
 
-``` sql
-  CREATE TABLE queue (
-    key UInt64,
-    value UInt64
-  ) ENGINE = RabbitMQ SETTINGS rabbitmq_host_port = 'localhost:5672',
-                            rabbitmq_exchange_name = 'exchange1',
-                            rabbitmq_format = 'JSONEachRow',
-                            rabbitmq_num_consumers = 5;
+``` xml
+ <rabbitmq>
+    <vhost>clickhouse</vhost>
+ </rabbitmq>
 ```
 
 ## Description {#description}
@@ -105,6 +117,7 @@ Exchange type options:
 -   `consistent_hash` - Data is evenly distributed between all bound tables (where the exchange name is the same). Note that this exchange type must be enabled with RabbitMQ plugin: `rabbitmq-plugins enable rabbitmq_consistent_hash_exchange`.
 
 Setting `rabbitmq_queue_base` may be used for the following cases:
+
 -   to let different tables share queues, so that multiple consumers could be registered for the same queues, which makes a better performance. If using `rabbitmq_num_consumers` and/or `rabbitmq_num_queues` settings, the exact match of queues is achieved in case these parameters are the same.
 -   to be able to restore reading from certain durable queues when not all messages were successfully consumed. To resume consumption from one specific queue - set its name in `rabbitmq_queue_base` setting and do not specify `rabbitmq_num_consumers` and `rabbitmq_num_queues` (defaults to 1). To resume consumption from all queues, which were declared for a specific table - just specify the same settings: `rabbitmq_queue_base`, `rabbitmq_num_consumers`, `rabbitmq_num_queues`. By default, queue names will be unique to tables.
 -   to reuse queues as they are declared durable and not auto-deleted. (Can be deleted via any of RabbitMQ CLI tools.)

docs/en/engines/table-engines/integrations/s3.md

@@ -136,8 +136,7 @@ The following settings can be specified in configuration file for given endpoint
 -   `access_key_id` and `secret_access_key` — Optional. Specifies credentials to use with given endpoint.
 -   `use_environment_credentials` — Optional, default value is `false`. If set to `true`, S3 client will try to obtain credentials from environment variables and Amazon EC2 metadata for given endpoint.
 -   `header` — Optional, can be speficied multiple times. Adds specified HTTP header to a request to given endpoint.
-
-This configuration also applies to S3 disks in `MergeTree` table engine family.
+-   `server_side_encryption_customer_key_base64` — Optional. If specified, required headers for accessing S3 objects with SSE-C encryption will be set.
 
 Example:
 
@@ -149,6 +148,7 @@ Example:
         <!-- <secret_access_key>SECRET_ACCESS_KEY</secret_access_key> -->
         <!-- <use_environment_credentials>false</use_environment_credentials> -->
         <!-- <header>Authorization: Bearer SOME-TOKEN</header> -->
+        <!-- <server_side_encryption_customer_key_base64>BASE64-ENCODED-KEY</server_side_encryption_customer_key_base64> -->
     </endpoint-name>
 </s3>
 ```

docs/en/engines/table-engines/mergetree-family/mergetree.md

@@ -45,7 +45,10 @@ ORDER BY expr
 [PARTITION BY expr]
 [PRIMARY KEY expr]
 [SAMPLE BY expr]
-[TTL expr [DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'], ...]
+[TTL expr 
+    [DELETE|TO DISK 'xxx'|TO VOLUME 'xxx' [, ...] ]
+    [WHERE conditions] 
+    [GROUP BY key_expr [SET v1 = aggr_func(v1) [, v2 = aggr_func(v2) ...]] ] ] 
 [SETTINGS name=value, ...]
 ```
 
@@ -80,7 +83,7 @@ For a description of parameters, see the [CREATE query description](../../../sql
     Expression must have one `Date` or `DateTime` column as a result. Example:
     `TTL date + INTERVAL 1 DAY`
 
-    Type of the rule `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'` specifies an action to be done with the part if the expression is satisfied (reaches current time): removal of expired rows, moving a part (if expression is satisfied for all rows in a part) to specified disk (`TO DISK 'xxx'`) or to volume (`TO VOLUME 'xxx'`). Default type of the rule is removal (`DELETE`). List of multiple rules can specified, but there should be no more than one `DELETE` rule.
+    Type of the rule `DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'|GROUP BY` specifies an action to be done with the part if the expression is satisfied (reaches current time): removal of expired rows, moving a part (if expression is satisfied for all rows in a part) to specified disk (`TO DISK 'xxx'`) or to volume (`TO VOLUME 'xxx'`), or aggregating values in expired rows. Default type of the rule is removal (`DELETE`). List of multiple rules can specified, but there should be no more than one `DELETE` rule.
 
     For more details, see [TTL for columns and tables](#table_engine-mergetree-ttl)
 
@@ -101,6 +104,7 @@ For a description of parameters, see the [CREATE query description](../../../sql
     -   `max_parts_in_total` — Maximum number of parts in all partitions.
 	-   `max_compress_block_size` — Maximum size of blocks of uncompressed data before compressing for writing to a table. You can also specify this setting in the global settings (see [max_compress_block_size](../../../operations/settings/settings.md#max-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
 	-   `min_compress_block_size` — Minimum size of blocks of uncompressed data required for compression when writing the next mark. You can also specify this setting in the global settings (see [min_compress_block_size](../../../operations/settings/settings.md#min-compress-block-size) setting). The value specified when table is created overrides the global value for this setting.
+    -   `max_partitions_to_read` — Limits the maximum number of partitions that can be accessed in one query. You can also specify setting [max_partitions_to_read](../../../operations/settings/merge-tree-settings.md#max-partitions-to-read) in the global setting.
     
 **Example of Sections Setting**
 
@@ -455,18 +459,28 @@ ALTER TABLE example_table
 Table can have an expression for removal of expired rows, and multiple expressions for automatic move of parts between [disks or volumes](#table_engine-mergetree-multiple-volumes). When rows in the table expire, ClickHouse deletes all corresponding rows. For parts moving feature, all rows of a part must satisfy the movement expression criteria.
 
 ``` sql
-TTL expr [DELETE|TO DISK 'aaa'|TO VOLUME 'bbb'], ...
+TTL expr 
+    [DELETE|TO DISK 'xxx'|TO VOLUME 'xxx'][, DELETE|TO DISK 'aaa'|TO VOLUME 'bbb'] ...
+    [WHERE conditions] 
+    [GROUP BY key_expr [SET v1 = aggr_func(v1) [, v2 = aggr_func(v2) ...]] ]   
 ```
 
 Type of TTL rule may follow each TTL expression. It affects an action which is to be done once the expression is satisfied (reaches current time):
 
 -   `DELETE` - delete expired rows (default action);
 -   `TO DISK 'aaa'` - move part to the disk `aaa`;
--   `TO VOLUME 'bbb'` - move part to the disk `bbb`.
+-   `TO VOLUME 'bbb'` - move part to the disk `bbb`;
+-   `GROUP BY` - aggregate expired rows.
 
-Examples:
+With `WHERE` clause you may specify which of the expired rows to delete or aggregate (it cannot be applied to moves).
 
-Creating a table with TTL
+`GROUP BY` expression must be a prefix of the table primary key. 
+
+If a column is not part of the `GROUP BY` expression and is not set explicitely in the `SET` clause, in result row it contains an occasional value from the grouped rows (as if aggregate function `any` is applied to it).
+
+**Examples**
+
+Creating a table with TTL:
 
 ``` sql
 CREATE TABLE example_table
@@ -482,13 +496,43 @@ TTL d + INTERVAL 1 MONTH [DELETE],
     d + INTERVAL 2 WEEK TO DISK 'bbb';
 ```
 
-Altering TTL of the table
+Altering TTL of the table:
 
 ``` sql
 ALTER TABLE example_table
     MODIFY TTL d + INTERVAL 1 DAY;
 ```
 
+Creating a table, where the rows are expired after one month. The expired rows where dates are Mondays are deleted:
+
+``` sql
+CREATE TABLE table_with_where
+(
+    d DateTime, 
+    a Int
+)
+ENGINE = MergeTree
+PARTITION BY toYYYYMM(d)
+ORDER BY d
+TTL d + INTERVAL 1 MONTH DELETE WHERE toDayOfWeek(d) = 1;
+```
+
+Creating a table, where expired rows are aggregated. In result rows `x` contains the maximum value accross the grouped rows, `y` — the minimum value, and `d` — any occasional value from grouped rows.
+
+``` sql
+CREATE TABLE table_for_aggregation
+(
+    d DateTime, 
+    k1 Int, 
+    k2 Int, 
+    x Int, 
+    y Int
+)
+ENGINE = MergeTree
+ORDER BY k1, k2
+TTL d + INTERVAL 1 MONTH GROUP BY k1, k2 SET x = max(x), y = min(y);
+```
+
 **Removing Data**
 
 Data with an expired TTL is removed when ClickHouse merges data parts.
@@ -671,6 +715,7 @@ Configuration markup:
             <endpoint>https://storage.yandexcloud.net/my-bucket/root-path/</endpoint>
             <access_key_id>your_access_key_id</access_key_id>
             <secret_access_key>your_secret_access_key</secret_access_key>
+            <server_side_encryption_customer_key_base64>your_base64_encoded_customer_key</server_side_encryption_customer_key_base64>
             <proxy>
                 <uri>http://proxy1</uri>
                 <uri>http://proxy2</uri>
@@ -706,7 +751,8 @@ Optional parameters:
 -   `metadata_path` — Path on local FS to store metadata files for S3. Default value is `/var/lib/clickhouse/disks/<disk_name>/`. 
 -   `cache_enabled` — Allows to cache mark and index files on local FS. Default value is `true`. 
 -   `cache_path` — Path on local FS where to store cached mark and index files. Default value is `/var/lib/clickhouse/disks/<disk_name>/cache/`. 
--   `skip_access_check` — If true disk access checks will not be performed on disk start-up. Default value is `false`.
+-   `skip_access_check` — If true, disk access checks will not be performed on disk start-up. Default value is `false`.
+-   `server_side_encryption_customer_key_base64` — If specified, required headers for accessing S3 objects with SSE-C encryption will be set.
 
 
 S3 disk can be configured as `main` or `cold` storage:

docs/en/faq/operations/delete-old-data.md

@@ -39,4 +39,4 @@ More details on [manipulating partitions](../../sql-reference/statements/alter/p
 
 It’s rather radical to drop all data from a table, but in some cases it might be exactly what you need.
 
-More details on [table truncation](../../sql-reference/statements/alter/partition.md#alter_drop-partition).
+More details on [table truncation](../../sql-reference/statements/truncate.md).

docs/en/getting-started/tutorial.md

@@ -644,7 +644,7 @@ If there are no replicas at the moment on replicated table creation, a new first
 
 ``` sql
 CREATE TABLE tutorial.hits_replica (...)
-ENGINE = ReplcatedMergeTree(
+ENGINE = ReplicatedMergeTree(
     '/clickhouse_perftest/tables/{shard}/hits',
     '{replica}'
 )

docs/en/interfaces/formats.md

@@ -31,8 +31,8 @@ The supported formats are:
 | [JSONCompactString](#jsoncompactstring)                                                 | ✗     | ✔      |
 | [JSONEachRow](#jsoneachrow)                                                             | ✔     | ✔      |
 | [JSONEachRowWithProgress](#jsoneachrowwithprogress)                                     | ✗     | ✔      |
-| [JSONStringEachRow](#jsonstringeachrow)                                                 | ✔     | ✔      |
-| [JSONStringEachRowWithProgress](#jsonstringeachrowwithprogress)                         | ✗     | ✔      |
+| [JSONStringsEachRow](#jsonstringseachrow)                                               | ✔     | ✔      |
+| [JSONStringsEachRowWithProgress](#jsonstringseachrowwithprogress)                       | ✗     | ✔      |
 | [JSONCompactEachRow](#jsoncompacteachrow)                                               | ✔     | ✔      |
 | [JSONCompactEachRowWithNamesAndTypes](#jsoncompacteachrowwithnamesandtypes)             | ✔     | ✔      |
 | [JSONCompactStringEachRow](#jsoncompactstringeachrow)                                   | ✔     | ✔      |
@@ -612,7 +612,7 @@ Example:
 ```
 
 ## JSONEachRow {#jsoneachrow}
-## JSONStringEachRow {#jsonstringeachrow}
+## JSONStringsEachRow {#jsonstringseachrow}
 ## JSONCompactEachRow {#jsoncompacteachrow}
 ## JSONCompactStringEachRow {#jsoncompactstringeachrow}
 
@@ -627,9 +627,9 @@ When using these formats, ClickHouse outputs rows as separated, newline-delimite
 When inserting the data, you should provide a separate JSON value for each row.
 
 ## JSONEachRowWithProgress {#jsoneachrowwithprogress}
-## JSONStringEachRowWithProgress {#jsonstringeachrowwithprogress}
+## JSONStringsEachRowWithProgress {#jsonstringseachrowwithprogress}
 
-Differs from `JSONEachRow`/`JSONStringEachRow` in that ClickHouse will also yield progress information as JSON values.
+Differs from `JSONEachRow`/`JSONStringsEachRow` in that ClickHouse will also yield progress information as JSON values.
 
 ```json
 {"row":{"'hello'":"hello","multiply(42, number)":"0","range(5)":[0,1,2,3,4]}}

docs/en/introduction/adopters.md

@@ -8,118 +8,120 @@ toc_title: Adopters
 !!! warning "Disclaimer"
     The following list of companies using ClickHouse and their success stories is assembled from public sources, thus might differ from current reality. We’d appreciate it if you share the story of adopting ClickHouse in your company and [add it to the list](https://github.com/ClickHouse/ClickHouse/edit/master/docs/en/introduction/adopters.md), but please make sure you won’t have any NDA issues by doing so. Providing updates with publications from other companies is also useful.
 
-| Company                                                                                        | Industry                        | Usecase               | Cluster Size                                               | (Un)Compressed Data Size<abbr title="of single replica"><sup>\*</sup></abbr> | Reference                                                                                                                                                                                                               |
-|------------------------------------------------------------------------------------------------|---------------------------------|-----------------------|------------------------------------------------------------|------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| <a href="https://2gis.ru" class="favicon">2gis</a>                                             | Maps                            | Monitoring            | —                                                          | —                                                                            | [Talk in Russian, July 2019](https://youtu.be/58sPkXfq6nw)                                                                                                                                                              |
-| <a href="https://getadmiral.com/" class="favicon">Admiral</a>                                  | Martech                         | Engagement Management | —                                                          | —                                                                            | [Webinar Slides, June 2020](https://altinity.com/presentations/2020/06/16/big-data-in-real-time-how-clickhouse-powers-admirals-visitor-relationships-for-publishers)                                                                                                                                                                                              |
-| <a href="https://cn.aliyun.com/" class="favicon">Alibaba Cloud</a> | Cloud | Managed Service | — | — | [Official Website](https://help.aliyun.com/product/144466.html)                                                                                                                                                              |
-| <a href="https://alohabrowser.com/" class="favicon">Aloha Browser</a>                          | Mobile App                      | Browser backend       | —                                                          | —                                                                            | [Slides in Russian, May 2019](https://presentations.clickhouse.tech/meetup22/aloha.pdf)                                                                                                                                 |
-| <a href="https://amadeus.com/" class="favicon">Amadeus</a>                                     | Travel                          | Analytics             | —                                                          | —                                                                            | [Press Release, April 2018](https://www.altinity.com/blog/2018/4/5/amadeus-technologies-launches-investment-and-insights-tool-based-on-machine-learning-and-strategy-algorithms)                                        |
-| <a href="https://www.appsflyer.com" class="favicon">Appsflyer</a>                              | Mobile analytics                | Main product          | —                                                          | —                                                                            | [Talk in Russian, July 2019](https://www.youtube.com/watch?v=M3wbRlcpBbY)                                                                                                                                               |
-| <a href="https://arenadata.tech/" class="favicon">ArenaData</a>                                | Data Platform                   | Main product          | —                                                          | —                                                                            | [Slides in Russian, December 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup38/indexes.pdf)                                                                                             |
-| <a href="https://avito.ru/" class="favicon">Avito</a>                                | Classifieds                   | Monitoring          | —                                                          | —                                                                            | [Meetup, April 2020](https://www.youtube.com/watch?v=n1tm4j4W8ZQ)                                                                                             |
-| <a href="https://badoo.com" class="favicon">Badoo</a>                                          | Dating                          | Timeseries            | —                                                          | —                                                                            | [Slides in Russian, December 2019](https://presentations.clickhouse.tech/meetup38/forecast.pdf)                                                                                                                         |
-| <a href="https://www.benocs.com/" class="favicon">Benocs</a>                                   | Network Telemetry and Analytics | Main Product          | —                                                          | —                                                                            | [Slides in English, October 2017](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup9/lpm.pdf)                                                                                                   |
+| Company | Industry | Usecase | Cluster Size | (Un)Compressed Data Size<abbr title="of single replica"><sup>\*</sup></abbr> | Reference |
+|---------|----------|---------|--------------|------------------------------------------------------------------------------|-----------|
+| <a href="https://2gis.ru" class="favicon">2gis</a> | Maps | Monitoring | — | — | [Talk in Russian, July 2019](https://youtu.be/58sPkXfq6nw) |
+| <a href="https://getadmiral.com/" class="favicon">Admiral</a> | Martech | Engagement Management | — | — | [Webinar Slides, June 2020](https://altinity.com/presentations/2020/06/16/big-data-in-real-time-how-clickhouse-powers-admirals-visitor-relationships-for-publishers) |
+| <a href="https://cn.aliyun.com/" class="favicon">Alibaba Cloud</a> | Cloud | Managed Service | — | — | [Official Website](https://help.aliyun.com/product/144466.html) |
+| <a href="https://alohabrowser.com/" class="favicon">Aloha Browser</a> | Mobile App | Browser backend | — | — | [Slides in Russian, May 2019](https://presentations.clickhouse.tech/meetup22/aloha.pdf) |
+| <a href="https://amadeus.com/" class="favicon">Amadeus</a> | Travel | Analytics | — | — | [Press Release, April 2018](https://www.altinity.com/blog/2018/4/5/amadeus-technologies-launches-investment-and-insights-tool-based-on-machine-learning-and-strategy-algorithms) |
+| <a href="https://www.appsflyer.com" class="favicon">Appsflyer</a> | Mobile analytics | Main product | — | — | [Talk in Russian, July 2019](https://www.youtube.com/watch?v=M3wbRlcpBbY) |
+| <a href="https://arenadata.tech/" class="favicon">ArenaData</a> | Data Platform | Main product | — | — | [Slides in Russian, December 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup38/indexes.pdf) |
+| <a href="https://avito.ru/" class="favicon">Avito</a> | Classifieds | Monitoring | — | — | [Meetup, April 2020](https://www.youtube.com/watch?v=n1tm4j4W8ZQ) |
+| <a href="https://badoo.com" class="favicon">Badoo</a> | Dating | Timeseries | — | — | [Slides in Russian, December 2019](https://presentations.clickhouse.tech/meetup38/forecast.pdf) |
+| <a href="https://www.benocs.com/" class="favicon">Benocs</a> | Network Telemetry and Analytics | Main Product | — | — | [Slides in English, October 2017](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup9/lpm.pdf) |
 | <a href="https://www.bigo.sg/" class="favicon">BIGO</a> | Video | Computing Platform | — | — | [Blog Article, August 2020](https://www.programmersought.com/article/44544895251/) |
-| <a href="https://www.bloomberg.com/" class="favicon">Bloomberg</a>                             | Finance, Media                  | Monitoring            | 102 servers                                                | —                                                                            | [Slides, May 2018](https://www.slideshare.net/Altinity/http-analytics-for-6m-requests-per-second-using-clickhouse-by-alexander-bocharov)                                                                                |
-| <a href="https://bloxy.info" class="favicon">Bloxy</a>                                         | Blockchain                      | Analytics             | —                                                          | —                                                                            | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/4_bloxy.pptx)                                                                                              |
-| <a href="https://www.bytedance.com" class="favicon">Bytedance</a>                                              | Social platforms                            |  — | —                                                          | —                                                                            | [The ClickHouse Meetup East, October 2020](https://www.youtube.com/watch?v=ckChUkC3Pns)                                                                                                |
+| <a href="https://www.bloomberg.com/" class="favicon">Bloomberg</a> | Finance, Media | Monitoring | 102 servers | — | [Slides, May 2018](https://www.slideshare.net/Altinity/http-analytics-for-6m-requests-per-second-using-clickhouse-by-alexander-bocharov) |
+| <a href="https://bloxy.info" class="favicon">Bloxy</a> | Blockchain | Analytics | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/4_bloxy.pptx) |
+| <a href="https://www.bytedance.com" class="favicon">Bytedance</a> | Social platforms | — | — | — | [The ClickHouse Meetup East, October 2020](https://www.youtube.com/watch?v=ckChUkC3Pns) |
 | <a href="https://cardsmobile.ru/" class="favicon">CardsMobile</a> | Finance | Analytics | — | — | [VC.ru](https://vc.ru/s/cardsmobile/143449-rukovoditel-gruppy-analiza-dannyh) |
-| <a href="https://carto.com/" class="favicon">CARTO</a>                                         | Business Intelligence           | Geo analytics         | —                                                          | —                                                                            | [Geospatial processing with ClickHouse](https://carto.com/blog/geospatial-processing-with-clickhouse/)                                                                                                                  |
-| <a href="http://public.web.cern.ch/public/" class="favicon">CERN</a>                           | Research                        | Experiment            | —                                                          | —                                                                            | [Press release, April 2012](https://www.yandex.com/company/press_center/press_releases/2012/2012-04-10/)                                                                                                                |
-| <a href="http://cisco.com/" class="favicon">Cisco</a>                                          | Networking                      | Traffic analysis      | —                                                          | —                                                                            | [Lightning talk, October 2019](https://youtu.be/-hI1vDR2oPY?t=5057)                                                                                                                                                     |
-| <a href="https://www.citadelsecurities.com/" class="favicon">Citadel Securities</a>            | Finance                         | —                     | —                                                          | —                                                                            | [Contribution, March 2019](https://github.com/ClickHouse/ClickHouse/pull/4774)                                                                                                                                          |
-| <a href="https://city-mobil.ru" class="favicon">Citymobil</a>                                  | Taxi                            | Analytics             | —                                                          | —                                                                            | [Blog Post in Russian, March 2020](https://habr.com/en/company/citymobil/blog/490660/)                                                                                                                                  |
-| <a href="https://cloudflare.com" class="favicon">Cloudflare</a>                                | CDN                             | Traffic analysis      | 36 servers                                                 | —                                                                            | [Blog post, May 2017](https://blog.cloudflare.com/how-cloudflare-analyzes-1m-dns-queries-per-second/), [Blog post, March 2018](https://blog.cloudflare.com/http-analytics-for-6m-requests-per-second-using-clickhouse/) |
-| <a href="https://corporate.comcast.com/" class="favicon">Comcast</a>                           | Media                           | CDN Traffic Analysis  | —                                                          | —                                                                            | [ApacheCon 2019 Talk](https://www.youtube.com/watch?v=e9TZ6gFDjNg)                                                                                                          |
-| <a href="https://contentsquare.com" class="favicon">ContentSquare</a>                          | Web analytics                   | Main product          | —                                                          | —                                                                            | [Blog post in French, November 2018](http://souslecapot.net/2018/11/21/patrick-chatain-vp-engineering-chez-contentsquare-penser-davantage-amelioration-continue-que-revolution-constante/)                              |
-| <a href="https://coru.net/" class="favicon">Corunet</a>                                        | Analytics                       | Main product          | —                                                          | —                                                                            | [Slides in English, April 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup21/predictive_models.pdf)                                                                                      |
-| <a href="https://www.creditx.com" class="favicon">CraiditX 氪信</a>                            | Finance AI                      | Analysis              | —                                                          | —                                                                            | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/udf.pptx)                                                                                                |
-| <a href="https://crazypanda.ru/en/" class="favicon">Crazypanda</a>                             | Games                           |                       | —                                                          | —                                                                            | Live session on ClickHouse meetup                                                                                                                                                                                       |
-| <a href="https://www.criteo.com/" class="favicon">Criteo</a>                                   | Retail                          | Main product          | —                                                          | —                                                                            | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/3_storetail.pptx)                                                                                         |
-| <a href="https://www.chinatelecomglobal.com/" class="favicon">Dataliance for China Telecom</a> | Telecom                         | Analytics             | —                                                          | —                                                                            | [Slides in Chinese, January 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup12/telecom.pdf)                                                                                              |
-| <a href="https://db.com" class="favicon">Deutsche Bank</a>                                     | Finance                         | BI Analytics          | —                                                          | —                                                                            | [Slides in English, October 2019](https://bigdatadays.ru/wp-content/uploads/2019/10/D2-H3-3_Yakunin-Goihburg.pdf)                                                                                                       |
-| <a href="https://deeplay.io/eng/" class="favicon">Deeplay</a> | Gaming Analytics | — | — | — | [Job advertisement, 2020](https://career.habr.com/vacancies/1000062568)                                                                                                       |
-| <a href="https://www.diva-e.com" class="favicon">Diva-e</a>                                    | Digital consulting              | Main Product          | —                                                          | —                                                                            | [Slides in English, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup29/ClickHouse-MeetUp-Unusual-Applications-sd-2019-09-17.pdf)                                               |
-| <a href="https://www.ecwid.com/" class="favicon">Ecwid</a>                                    | E-commerce SaaS | Metrics, Logging      | —                                                          | —                                                                            | [Slides in Russian, April 2019](https://nastachku.ru/var/files/1/presentation/backend/2_Backend_6.pdf)                                                                                                                                                        |
-| <a href="https://www.ebay.com/" class="favicon">eBay</a>                                    | E-commerce | Logs, Metrics and Events | —                                                          | —                                                                            | [Official website, Sep 2020](https://tech.ebayinc.com/engineering/ou-online-analytical-processing/)                                                                                                                                                        |
-| <a href="https://www.exness.com" class="favicon">Exness</a>                                    | Trading                         | Metrics, Logging      | —                                                          | —                                                                            | [Talk in Russian, May 2019](https://youtu.be/_rpU-TvSfZ8?t=3215)                                                                                                                                                        |
-| <a href="https://fastnetmon.com/" class="favicon">FastNetMon</a> | DDoS Protection | Main Product |  | —                                                                            | [Official website](https://fastnetmon.com/docs-fnm-advanced/fastnetmon-advanced-traffic-persistency/) |
-| <a href="https://www.flipkart.com/" class="favicon">Flipkart</a>                               | e-Commerce                      | —                     | —                                                          | —                                                                            | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=239)                                                                                               |
-| <a href="https://fun.co/rp" class="favicon">FunCorp</a>                                        | Games                           |                       | —                                                          | —                                                                            | [Article](https://www.altinity.com/blog/migrating-from-redshift-to-clickhouse)                                                                                                                                          |
-| <a href="https://geniee.co.jp" class="favicon">Geniee</a>                                      | Ad network                      | Main product          | —                                                          | —                                                                            | [Blog post in Japanese, July 2017](https://tech.geniee.co.jp/entry/2017/07/20/160100)                                                                                                                                   |
-| <a href="https://www.genotek.ru/" class="favicon">Genotek</a>                                      | Bioinformatics                      | Main product          | —                                                          | —                                                                            | [Video, August 2020](https://youtu.be/v3KyZbz9lEE)                                                                                                                                   |
-| <a href="https://www.huya.com/" class="favicon">HUYA</a>                                       | Video Streaming                 | Analytics             | —                                                          | —                                                                            | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/7.%20ClickHouse万亿数据分析实践%20李本旺(sundy-li)%20虎牙.pdf)                                            |
-| <a href="https://www.the-ica.com/" class="favicon">ICA</a>                   | FinTech | Risk Management | — | — | [Blog Post in English, Sep 2020](https://altinity.com/blog/clickhouse-vs-redshift-performance-for-fintech-risk-management?utm_campaign=ClickHouse%20vs%20RedShift&utm_content=143520807&utm_medium=social&utm_source=twitter&hss_channel=tw-3894792263)                                                                                                         |
-| <a href="https://www.idealista.com" class="favicon">Idealista</a>                              | Real Estate                     | Analytics             | —                                                          | —                                                                            | [Blog Post in English, April 2019](https://clickhouse.tech/blog/en/clickhouse-meetup-in-madrid-on-april-2-2019)                                                                                                         |
-| <a href="https://www.infovista.com/" class="favicon">Infovista</a>                             | Networks                        | Analytics             | —                                                          | —                                                                            | [Slides in English, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup30/infovista.pdf)                                                                                            |
-| <a href="https://www.innogames.com" class="favicon">InnoGames</a>                              | Games                           | Metrics, Logging      | —                                                          | —                                                                            | [Slides in Russian, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup28/graphite_and_clickHouse.pdf)                                                                            |
-| <a href="https://www.instana.com" class="favicon">Instana</a>                                  | APM Platform                    | Main product          | —                                                          | —                                                                            | [Twitter post](https://twitter.com/mieldonkers/status/1248884119158882304)                                                                                                                                              |
-| <a href="https://integros.com" class="favicon">Integros</a>                                    | Platform for video services     | Analytics             | —                                                          | —                                                                            | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf)                                                                                               |
-| <a href="https://ippon.tech" class="favicon">Ippon Technologies</a>                            | Technology Consulting           | —                     | —                                                          | —                                                                            | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=205)                                                                                               |
-| <a href="https://www.ivi.ru/" class="favicon">Ivi</a> | Online Cinema | Analytics, Monitoring | —                                                          | —                                                                            | [Article in Russian, Jan 2018](https://habr.com/en/company/ivi/blog/347408/) |
-| <a href="https://jinshuju.net" class="favicon">Jinshuju 金数据</a>                             | BI Analytics                    | Main product          | —                                                          | —                                                                            | [Slides in Chinese, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/3.%20金数据数据架构调整方案Public.pdf)                                                                    |
-| <a href="https://www.kodiakdata.com/" class="favicon">Kodiak Data</a>                          | Clouds                          | Main product          | —                                                          | —                                                                            | [Slides in Engish, April 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup13/kodiak_data.pdf)                                                                                             |
-| <a href="https://kontur.ru" class="favicon">Kontur</a>                                         | Software Development            | Metrics               | —                                                          | —                                                                            | [Talk in Russian, November 2018](https://www.youtube.com/watch?v=U4u4Bd0FtrY)                                                                                                                                           |
-| <a href="https://www.kuaishou.com/" class="favicon">Kuaishou</a>                                         | Video            | — | —                                                          | —                                                                            | [ClickHouse Meetup, October 2018](https://clickhouse.tech/blog/en/2018/clickhouse-community-meetup-in-beijing-on-october-28-2018/)                                                                                                                                           |
-| <a href="https://www.lbl.gov" class="favicon">Lawrence Berkeley National Laboratory</a>        | Research                        | Traffic analysis      | 1 server                                                   | 11.8 TiB                                                                     | [Slides in English, April 2019](https://www.smitasin.com/presentations/2019-04-17_DOE-NSM.pdf)                                                                                                                          |
-| <a href="https://lifestreet.com/" class="favicon">LifeStreet</a>                               | Ad network                      | Main product          | 75 servers (3 replicas)                                    | 5.27 PiB                                                                     | [Blog post in Russian, February 2017](https://habr.com/en/post/322620/)                                                                                                                                                 |
-| <a href="https://mcs.mail.ru/" class="favicon">Mail.ru Cloud Solutions</a>                     | Cloud services                  | Main product          | —                                                          | —                                                                            | [Article in Russian](https://mcs.mail.ru/help/db-create/clickhouse#)                                                                                                                                                    |
-| <a href="https://tech.mymarilyn.ru" class="favicon">Marilyn</a>                                | Advertising                     | Statistics            | —                                                          | —                                                                            | [Talk in Russian, June 2017](https://www.youtube.com/watch?v=iXlIgx2khwc)                                                                                                                                               |
-| <a href="https://mellodesign.ru/" class="favicon">Mello</a>                                | Marketing                     | Analytics            | 1 server                                                          | —                                                                            | [Article, Oct 2020](https://vc.ru/marketing/166180-razrabotka-tipovogo-otcheta-skvoznoy-analitiki)                                                                                                                                               |
-| <a href="https://www.messagebird.com" class="favicon">MessageBird</a>                          | Telecommunications              | Statistics            | —                                                          | —                                                                            | [Slides in English, November 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup20/messagebird.pdf)                                                                                         |
-| <a href="https://www.mindsdb.com/" class="favicon">MindsDB</a>                          | Machine Learning              | Main Product            | —                                                          | —                                                                            | [Official Website](https://www.mindsdb.com/blog/machine-learning-models-as-tables-in-ch) |x
-| <a href="https://mux.com/" class="favicon">MUX</a>                                       | Online Video                           | Video Analytics       | —                                                          | —                                                                            | [Talk in English, August 2019](https://altinity.com/presentations/2019/8/13/how-clickhouse-became-the-default-analytics-database-for-mux/)                                                                                                              |
-| <a href="https://www.mgid.com/" class="favicon">MGID</a>                                       | Ad network                      | Web-analytics         | —                                                          | —                                                                            | [Blog post in Russian, April 2020](http://gs-studio.com/news-about-it/32777----clickhouse---c)                                                                                                                          |
-| <a href="https://getnoc.com/" class="favicon">NOC Project</a> | Network Monitoring | Analytics | Main Product | — | [Official Website](https://getnoc.com/features/big-data/)                                                                                               |
-| <a href="https://www.nuna.com/" class="favicon">Nuna Inc.</a>                                  | Health Data Analytics           | —                     | —                                                          | —                                                                            | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=170)                                                                                               |
-| <a href="https://www.oneapm.com/" class="favicon">OneAPM</a>                                   | Monitorings and Data Analysis   | Main product          | —                                                          | —                                                                            | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/8.%20clickhouse在OneAPM的应用%20杜龙.pdf)                                                                 |
-| <a href="https://www.percent.cn/" class="favicon">Percent 百分点</a>                           | Analytics                       | Main Product          | —                                                          | —                                                                            | [Slides in Chinese, June 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/4.%20ClickHouse万亿数据双中心的设计与实践%20.pdf)                                                            |
-| <a href="https://www.percona.com/" class="favicon">Percona</a>               | Performance analysis | Percona Monitoring and Management | — | — | [Official website, Mar 2020](https://www.percona.com/blog/2020/03/30/advanced-query-analysis-in-percona-monitoring-and-management-with-direct-clickhouse-access/)                                                            |
-| <a href="https://plausible.io/" class="favicon">Plausible</a>                                  | Analytics                       | Main Product          | —                                                          | —                                                                            | [Blog post, June 2020](https://twitter.com/PlausibleHQ/status/1273889629087969280)                                                                                                                                      |
-| <a href="https://posthog.com/" class="favicon">PostHog</a>                                 | Product Analytics                        | Main Product                     | —                                                          | —                                                                            | [Release Notes, Oct 2020](https://posthog.com/blog/the-posthog-array-1-15-0)                                                                                               |
-| <a href="https://postmates.com/" class="favicon">Postmates</a>                                 | Delivery                        | —                     | —                                                          | —                                                                            | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=188)                                                                                               |
-| <a href="http://www.pragma-innovation.fr/" class="favicon">Pragma Innovation</a>               | Telemetry and Big Data Analysis | Main product          | —                                                          | —                                                                            | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/4_pragma_innovation.pdf)                                                                                  |
-| <a href="https://www.qingcloud.com/" class="favicon">QINGCLOUD</a>                             | Cloud services                  | Main product          | —                                                          | —                                                                            | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/4.%20Cloud%20%2B%20TSDB%20for%20ClickHouse%20张健%20QingCloud.pdf)                                        |
-| <a href="https://qrator.net" class="favicon">Qrator</a>                                        | DDoS protection                 | Main product          | —                                                          | —                                                                            | [Blog Post, March 2019](https://blog.qrator.net/en/clickhouse-ddos-mitigation_37/)                                                                                                                                      |
-| <a href="https://www.rbinternational.com/" class="favicon">Raiffeisenbank</a>                                       | Banking               | Analytics             | —                                                          | —                                                                            | [Lecture in Russian, December 2020](https://cs.hse.ru/announcements/421965599.html)                                                                                                |
-| <a href="https://rambler.ru" class="favicon">Rambler</a>                                       | Internet services               | Analytics             | —                                                          | —                                                                            | [Talk in Russian, April 2018](https://medium.com/@ramblertop/разработка-api-clickhouse-для-рамблер-топ-100-f4c7e56f3141)                                                                                                |
-| <a href="https://retell.cc/" class="favicon">Retell</a>                                       | Speech synthesis               | Analytics             | —                                                          | —                                                                            | [Blog Article, August 2020](https://vc.ru/services/153732-kak-sozdat-audiostati-na-vashem-sayte-i-zachem-eto-nuzhno)                                                                                                |
-| <a href="https://rspamd.com/" class="favicon">Rspamd</a> | Antispam | Analytics | — | — | [Official Website](https://rspamd.com/doc/modules/clickhouse.html)                                                                                                |
-| <a href="https://rusiem.com/en" class="favicon">RuSIEM</a> | SIEM | Main Product | — | — | [Official Website](https://rusiem.com/en/products/architecture)                                                                                                |
-| <a href="https://www.s7.ru" class="favicon">S7 Airlines</a>                                    | Airlines                        | Metrics, Logging      | —                                                          | —                                                                            | [Talk in Russian, March 2019](https://www.youtube.com/watch?v=nwG68klRpPg&t=15s)                                                                                                                                        |
-| <a href="https://www.scireum.de/" class="favicon">scireum GmbH</a>                             | e-Commerce                      | Main product          | —                                                          | —                                                                            | [Talk in German, February 2020](https://www.youtube.com/watch?v=7QWAn5RbyR4)                                                                                                                                            |
-| <a href="https://segment.com/" class="favicon">Segment</a>                   | Data processing                      | Main product          | 9 * i3en.3xlarge nodes 7.5TB NVME SSDs, 96GB Memory, 12 vCPUs                                                          | —                                                                            | [Slides, 2019](https://slides.com/abraithwaite/segment-clickhouse)                                                                                                                                            |
-| <a href="https://www.semrush.com/" class="favicon">SEMrush</a>                                 | Marketing                       | Main product          | —                                                          | —                                                                            | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/5_semrush.pdf)                                                                                             |
-| <a href="https://sentry.io/" class="favicon">Sentry</a>                                        | Software Development            | Main product          | —                                                          | —                                                                            | [Blog Post in English, May 2019](https://blog.sentry.io/2019/05/16/introducing-snuba-sentrys-new-search-infrastructure)                                                                                                 |
-| <a href="https://seo.do/" class="favicon">seo.do</a>                                           | Analytics                       | Main product          | —                                                          | —                                                                            | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/CH%20Presentation-%20Metehan%20Çetinkaya.pdf)                                                            |
-| <a href="http://www.sgk.gov.tr/wps/portal/sgk/tr" class="favicon">SGK</a>                      | Goverment Social Security       | Analytics             | —                                                          | —                                                                            | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/ClickHouse%20Meetup-Ramazan%20POLAT.pdf)                                                                 |
-| <a href="http://english.sina.com/index.html" class="favicon">Sina</a>                          | News                            | —                     | —                                                          | —                                                                            | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/6.%20ClickHouse最佳实践%20高鹏_新浪.pdf)                                                                  |
-| <a href="https://smi2.ru/" class="favicon">SMI2</a>                                            | News                            | Analytics             | —                                                          | —                                                                            | [Blog Post in Russian, November 2017](https://habr.com/ru/company/smi2/blog/314558/)                                                                                                                                    |
-| <a href="https://www.splunk.com/" class="favicon">Splunk</a>                                   | Business Analytics              | Main product          | —                                                          | —                                                                            | [Slides in English, January 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup12/splunk.pdf)                                                                                               |
-| <a href="https://www.spotify.com" class="favicon">Spotify</a>                                  | Music                           | Experimentation       | —                                                          | —                                                                            | [Slides, July 2018](https://www.slideshare.net/glebus/using-clickhouse-for-experimentation-104247173)                                                                                                                   |
-| <a href="https://www.staffcop.ru/" class="favicon">Staffcop</a>                                | Information Security                      | Main Product | —                                                          | —                                                                            | [Official website, Documentation](https://www.staffcop.ru/sce43) |
-| <a href="https://www.suning.com/" class="favicon">Suning</a>                                | E-Commerce                      | User behaviour analytics | —                                                          | —                                                                            | [Blog article](https://www.sohu.com/a/434152235_411876) |
-| <a href="https://www.teralytics.net/" class="favicon">Teralytics</a>                                | Mobility                      | Analytics | —                                                          | —                                                                            | [Tech blog](https://www.teralytics.net/knowledge-hub/visualizing-mobility-data-the-scalability-challenge) |
-| <a href="https://www.tencent.com" class="favicon">Tencent</a>                                  | Big Data                        | Data processing       | —                                                          | —                                                                            | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/5.%20ClickHouse大数据集群应用_李俊飞腾讯网媒事业部.pdf)                                                   |
-| <a href="https://www.tencent.com" class="favicon">Tencent</a>                                  | Messaging                       | Logging               | —                                                          | —                                                                            | [Talk in Chinese, November 2019](https://youtu.be/T-iVQRuw-QY?t=5050)                                                                                                                                                   |
-| <a href="https://www.tencentmusic.com/" class="favicon">Tencent Music Entertainment (TME)</a>                                  | BigData                       | Data processing               | —                                                          | —                                                                            | [Blog in Chinese, June 2020](https://cloud.tencent.com/developer/article/1637840)                                                                                                                                                   |
-| <a href="https://trafficstars.com/" class="favicon">Traffic Stars</a>                          | AD network                      | —                     | —                                                          | —                                                                            | [Slides in Russian, May 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup15/lightning/ninja.pdf)                                                                                          |
-| <a href="https://www.uber.com" class="favicon">Uber</a>                                        | Taxi                            | Logging               | —                                                          | —                                                                            | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/uber.pdf)                                                                                                                                        |
-| <a href="https://vk.com" class="favicon">VKontakte</a>                                         | Social Network                  | Statistics, Logging   | —                                                          | —                                                                            | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/3_vk.pdf)                                                                                                  |
-| <a href="https://www.walmartlabs.com/" class="favicon">Walmart Labs</a>                        | Internet, Retail                | —                     | —                                                          | —                                                                            | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=144)                                                                                               |
-| <a href="https://wargaming.com/en/" class="favicon">Wargaming</a>                              | Games                           |                       | —                                                          | —                                                                            | [Interview](https://habr.com/en/post/496954/)                                                                                                                                                                           |
-| <a href="https://wisebits.com/" class="favicon">Wisebits</a>                                   | IT Solutions                    | Analytics             | —                                                          | —                                                                            | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf)                                                                                               |
-| <a href="https://www.workato.com/" class="favicon">Workato</a>                                 | Automation Software             | —                     | —                                                          | —                                                                            | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=334)                                                                                               |
-| <a href="http://www.xiaoxintech.cn/" class="favicon">Xiaoxin Tech</a>                          | Education                       | Common purpose        | —                                                          | —                                                                            | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/sync-clickhouse-with-mysql-mongodb.pptx)                                                                 |
-| <a href="https://www.ximalaya.com/" class="favicon">Ximalaya</a>                               | Audio sharing                   | OLAP                  | —                                                          | —                                                                            | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/ximalaya.pdf)                                                                                            |
-| <a href="https://cloud.yandex.ru/services/managed-clickhouse" class="favicon">Yandex Cloud</a> | Public Cloud                    | Main product          | —                                                          | —                                                                            | [Talk in Russian, December 2019](https://www.youtube.com/watch?v=pgnak9e_E0o)                                                                                                                                           |
-| <a href="https://cloud.yandex.ru/services/datalens" class="favicon">Yandex DataLens</a>        | Business Intelligence           | Main product          | —                                                          | —                                                                            | [Slides in Russian, December 2019](https://presentations.clickhouse.tech/meetup38/datalens.pdf)                                                                                                                         |
-| <a href="https://market.yandex.ru/" class="favicon">Yandex Market</a>                          | e-Commerce                      | Metrics, Logging      | —                                                          | —                                                                            | [Talk in Russian, January 2019](https://youtu.be/_l1qP0DyBcA?t=478)                                                                                                                                                     |
-| <a href="https://metrica.yandex.com" class="favicon">Yandex Metrica</a>                        | Web analytics                   | Main product          | 630 servers in one cluster, 360 servers in another cluster, 1862 servers in one department | 133 PiB / 8.31 PiB / 120 trillion records                                                        | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/introduction/#13)                                                                                                                                |
-| <a href="https://htc-cs.ru/" class="favicon">ЦВТ</a>                                           | Software Development            | Metrics, Logging      | —                                                          | —                                                                            | [Blog Post, March 2019, in Russian](https://vc.ru/dev/62715-kak-my-stroili-monitoring-na-prometheus-clickhouse-i-elk)                                                                                                   |
-| <a href="https://mkb.ru/" class="favicon">МКБ</a>                                              | Bank                            | Web-system monitoring | —                                                          | —                                                                            | [Slides in Russian, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup28/mkb.pdf)                                                                                                |
-| <a href="https://cft.ru/" class="favicon">ЦФТ</a>                                              | Banking, Financial products, Payments                            |  — | —                                                          | —                                                                            | [Meetup in Russian, April 2020](https://team.cft.ru/events/162)                                                                                                |
-| <a href="https://www.kakaocorp.com/" class="favicon">kakaocorp</a>                                              | Internet company         |  — | —                                                          | —                                                                            | [if(kakao)2020 conference](https://if.kakao.com/session/117)                                                                                                |
+| <a href="https://carto.com/" class="favicon">CARTO</a> | Business Intelligence | Geo analytics | — | — | [Geospatial processing with ClickHouse](https://carto.com/blog/geospatial-processing-with-clickhouse/) |
+| <a href="http://public.web.cern.ch/public/" class="favicon">CERN</a> | Research | Experiment | — | — | [Press release, April 2012](https://www.yandex.com/company/press_center/press_releases/2012/2012-04-10/) |
+| <a href="http://cisco.com/" class="favicon">Cisco</a> | Networking | Traffic analysis | — | — | [Lightning talk, October 2019](https://youtu.be/-hI1vDR2oPY?t=5057) |
+| <a href="https://www.citadelsecurities.com/" class="favicon">Citadel Securities</a> | Finance | — | — | — | [Contribution, March 2019](https://github.com/ClickHouse/ClickHouse/pull/4774) |
+| <a href="https://city-mobil.ru" class="favicon">Citymobil</a> | Taxi | Analytics | — | — | [Blog Post in Russian, March 2020](https://habr.com/en/company/citymobil/blog/490660/) |
+| <a href="https://cloudflare.com" class="favicon">Cloudflare</a> | CDN | Traffic analysis | 36 servers | — | [Blog post, May 2017](https://blog.cloudflare.com/how-cloudflare-analyzes-1m-dns-queries-per-second/), [Blog post, March 2018](https://blog.cloudflare.com/http-analytics-for-6m-requests-per-second-using-clickhouse/) |
+| <a href="https://corporate.comcast.com/" class="favicon">Comcast</a> | Media | CDN Traffic Analysis | — | — | [ApacheCon 2019 Talk](https://www.youtube.com/watch?v=e9TZ6gFDjNg) |
+| <a href="https://contentsquare.com" class="favicon">ContentSquare</a> | Web analytics | Main product | — | — | [Blog post in French, November 2018](http://souslecapot.net/2018/11/21/patrick-chatain-vp-engineering-chez-contentsquare-penser-davantage-amelioration-continue-que-revolution-constante/) |
+| <a href="https://coru.net/" class="favicon">Corunet</a> | Analytics | Main product | — | — | [Slides in English, April 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup21/predictive_models.pdf) |
+| <a href="https://www.creditx.com" class="favicon">CraiditX 氪信</a> | Finance AI | Analysis | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/udf.pptx) |
+| <a href="https://crazypanda.ru/en/" class="favicon">Crazypanda</a> | Games | | — | — | Live session on ClickHouse meetup |
+| <a href="https://www.criteo.com/" class="favicon">Criteo</a> | Retail | Main product | — | — | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/3_storetail.pptx) |
+| <a href="https://www.chinatelecomglobal.com/" class="favicon">Dataliance for China Telecom</a> | Telecom | Analytics | — | — | [Slides in Chinese, January 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup12/telecom.pdf) |
+| <a href="https://db.com" class="favicon">Deutsche Bank</a> | Finance | BI Analytics | — | — | [Slides in English, October 2019](https://bigdatadays.ru/wp-content/uploads/2019/10/D2-H3-3_Yakunin-Goihburg.pdf) |
+| <a href="https://deeplay.io/eng/" class="favicon">Deeplay</a> | Gaming Analytics | — | — | — | [Job advertisement, 2020](https://career.habr.com/vacancies/1000062568) |
+| <a href="https://www.diva-e.com" class="favicon">Diva-e</a> | Digital consulting | Main Product | — | — | [Slides in English, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup29/ClickHouse-MeetUp-Unusual-Applications-sd-2019-09-17.pdf) |
+| <a href="https://www.ecwid.com/" class="favicon">Ecwid</a> | E-commerce SaaS | Metrics, Logging | — | — | [Slides in Russian, April 2019](https://nastachku.ru/var/files/1/presentation/backend/2_Backend_6.pdf) |
+| <a href="https://www.ebay.com/" class="favicon">eBay</a> | E-commerce | Logs, Metrics and Events | — | — | [Official website, Sep 2020](https://tech.ebayinc.com/engineering/ou-online-analytical-processing/) |
+| <a href="https://www.exness.com" class="favicon">Exness</a> | Trading | Metrics, Logging | — | — | [Talk in Russian, May 2019](https://youtu.be/_rpU-TvSfZ8?t=3215) |
+| <a href="https://fastnetmon.com/" class="favicon">FastNetMon</a> | DDoS Protection | Main Product | | — | [Official website](https://fastnetmon.com/docs-fnm-advanced/fastnetmon-advanced-traffic-persistency/) |
+| <a href="https://www.flipkart.com/" class="favicon">Flipkart</a> | e-Commerce | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=239) |
+| <a href="https://fun.co/rp" class="favicon">FunCorp</a> | Games | | — | 14 bn records/day as of Jan 2021 | [Article](https://www.altinity.com/blog/migrating-from-redshift-to-clickhouse) |
+| <a href="https://geniee.co.jp" class="favicon">Geniee</a> | Ad network | Main product | — | — | [Blog post in Japanese, July 2017](https://tech.geniee.co.jp/entry/2017/07/20/160100) |
+| <a href="https://www.genotek.ru/" class="favicon">Genotek</a> | Bioinformatics | Main product | — | — | [Video, August 2020](https://youtu.be/v3KyZbz9lEE) |
+| <a href="https://www.huya.com/" class="favicon">HUYA</a> | Video Streaming | Analytics | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/7.%20ClickHouse万亿数据分析实践%20李本旺(sundy-li)%20虎牙.pdf) |
+| <a href="https://www.the-ica.com/" class="favicon">ICA</a> | FinTech | Risk Management | — | — | [Blog Post in English, Sep 2020](https://altinity.com/blog/clickhouse-vs-redshift-performance-for-fintech-risk-management?utm_campaign=ClickHouse%20vs%20RedShift&utm_content=143520807&utm_medium=social&utm_source=twitter&hss_channel=tw-3894792263) |
+| <a href="https://www.idealista.com" class="favicon">Idealista</a> | Real Estate | Analytics | — | — | [Blog Post in English, April 2019](https://clickhouse.tech/blog/en/clickhouse-meetup-in-madrid-on-april-2-2019) |
+| <a href="https://www.infovista.com/" class="favicon">Infovista</a> | Networks | Analytics | — | — | [Slides in English, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup30/infovista.pdf) |
+| <a href="https://www.innogames.com" class="favicon">InnoGames</a> | Games | Metrics, Logging | — | — | [Slides in Russian, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup28/graphite_and_clickHouse.pdf) |
+| <a href="https://www.instana.com" class="favicon">Instana</a> | APM Platform | Main product | — | — | [Twitter post](https://twitter.com/mieldonkers/status/1248884119158882304) |
+| <a href="https://integros.com" class="favicon">Integros</a> | Platform for video services | Analytics | — | — | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf) |
+| <a href="https://ippon.tech" class="favicon">Ippon Technologies</a> | Technology Consulting | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=205) |
+| <a href="https://www.ivi.ru/" class="favicon">Ivi</a> | Online Cinema | Analytics, Monitoring | — | — | [Article in Russian, Jan 2018](https://habr.com/en/company/ivi/blog/347408/) |
+| <a href="https://jinshuju.net" class="favicon">Jinshuju 金数据</a> | BI Analytics | Main product | — | — | [Slides in Chinese, October 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/3.%20金数据数据架构调整方案Public.pdf) |
+| <a href="https://www.kodiakdata.com/" class="favicon">Kodiak Data</a> | Clouds | Main product | — | — | [Slides in Engish, April 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup13/kodiak_data.pdf) |
+| <a href="https://kontur.ru" class="favicon">Kontur</a> | Software Development | Metrics | — | — | [Talk in Russian, November 2018](https://www.youtube.com/watch?v=U4u4Bd0FtrY) |
+| <a href="https://www.kuaishou.com/" class="favicon">Kuaishou</a> | Video | — | — | — | [ClickHouse Meetup, October 2018](https://clickhouse.tech/blog/en/2018/clickhouse-community-meetup-in-beijing-on-october-28-2018/) |
+| <a href="https://www.lbl.gov" class="favicon">Lawrence Berkeley National Laboratory</a> | Research | Traffic analysis | 1 server | 11.8 TiB | [Slides in English, April 2019](https://www.smitasin.com/presentations/2019-04-17_DOE-NSM.pdf) |
+| <a href="https://lifestreet.com/" class="favicon">LifeStreet</a> | Ad network | Main product | 75 servers (3 replicas) | 5.27 PiB | [Blog post in Russian, February 2017](https://habr.com/en/post/322620/) |
+| <a href="https://mcs.mail.ru/" class="favicon">Mail.ru Cloud Solutions</a> | Cloud services | Main product | — | — | [Article in Russian](https://mcs.mail.ru/help/db-create/clickhouse#) |
+| <a href="https://tech.mymarilyn.ru" class="favicon">Marilyn</a> | Advertising | Statistics | — | — | [Talk in Russian, June 2017](https://www.youtube.com/watch?v=iXlIgx2khwc) |
+| <a href="https://mellodesign.ru/" class="favicon">Mello</a> | Marketing | Analytics | 1 server | — | [Article, Oct 2020](https://vc.ru/marketing/166180-razrabotka-tipovogo-otcheta-skvoznoy-analitiki) |
+| <a href="https://www.messagebird.com" class="favicon">MessageBird</a> | Telecommunications | Statistics | — | — | [Slides in English, November 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup20/messagebird.pdf) |
+| <a href="https://www.mindsdb.com/" class="favicon">MindsDB</a> | Machine Learning | Main Product | — | — | [Official Website](https://www.mindsdb.com/blog/machine-learning-models-as-tables-in-ch) |x
+| <a href="https://mux.com/" class="favicon">MUX</a> | Online Video | Video Analytics | — | — | [Talk in English, August 2019](https://altinity.com/presentations/2019/8/13/how-clickhouse-became-the-default-analytics-database-for-mux/) |
+| <a href="https://www.mgid.com/" class="favicon">MGID</a> | Ad network | Web-analytics | — | — | [Blog post in Russian, April 2020](http://gs-studio.com/news-about-it/32777----clickhouse---c) |
+| <a href="https://getnoc.com/" class="favicon">NOC Project</a> | Network Monitoring | Analytics | Main Product | — | [Official Website](https://getnoc.com/features/big-data/) |
+| <a href="https://www.nuna.com/" class="favicon">Nuna Inc.</a> | Health Data Analytics | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=170) |
+| <a href="https://www.oneapm.com/" class="favicon">OneAPM</a> | Monitorings and Data Analysis | Main product | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/8.%20clickhouse在OneAPM的应用%20杜龙.pdf) |
+| <a href="https://panelbear.com/" class="favicon">Panelbear | Analytics | Monitoring and Analytics | — | — | [Tech Stack, November 2020](https://panelbear.com/blog/tech-stack/) |
+| <a href="https://www.percent.cn/" class="favicon">Percent 百分点</a> | Analytics | Main Product | — | — | [Slides in Chinese, June 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup24/4.%20ClickHouse万亿数据双中心的设计与实践%20.pdf) |
+| <a href="https://www.percona.com/" class="favicon">Percona</a> | Performance analysis | Percona Monitoring and Management | — | — | [Official website, Mar 2020](https://www.percona.com/blog/2020/03/30/advanced-query-analysis-in-percona-monitoring-and-management-with-direct-clickhouse-access/) |
+| <a href="https://plausible.io/" class="favicon">Plausible</a> | Analytics | Main Product | — | — | [Blog post, June 2020](https://twitter.com/PlausibleHQ/status/1273889629087969280) |
+| <a href="https://posthog.com/" class="favicon">PostHog</a> | Product Analytics | Main Product | — | — | [Release Notes, Oct 2020](https://posthog.com/blog/the-posthog-array-1-15-0) |
+| <a href="https://postmates.com/" class="favicon">Postmates</a> | Delivery | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=188) |
+| <a href="http://www.pragma-innovation.fr/" class="favicon">Pragma Innovation</a> | Telemetry and Big Data Analysis | Main product | — | — | [Slides in English, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup18/4_pragma_innovation.pdf) |
+| <a href="https://prana-system.com/en/" class="favicon">PRANA</a> | Industrial predictive analytics | Main product | — | — | [News (russian), Feb 2021](https://habr.com/en/news/t/541392/) |
+| <a href="https://www.qingcloud.com/" class="favicon">QINGCLOUD</a> | Cloud services | Main product | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/4.%20Cloud%20%2B%20TSDB%20for%20ClickHouse%20张健%20QingCloud.pdf) |
+| <a href="https://qrator.net" class="favicon">Qrator</a> | DDoS protection | Main product | — | — | [Blog Post, March 2019](https://blog.qrator.net/en/clickhouse-ddos-mitigation_37/) |
+| <a href="https://www.rbinternational.com/" class="favicon">Raiffeisenbank</a> | Banking | Analytics | — | — | [Lecture in Russian, December 2020](https://cs.hse.ru/announcements/421965599.html) |
+| <a href="https://rambler.ru" class="favicon">Rambler</a> | Internet services | Analytics | — | — | [Talk in Russian, April 2018](https://medium.com/@ramblertop/разработка-api-clickhouse-для-рамблер-топ-100-f4c7e56f3141) |
+| <a href="https://retell.cc/" class="favicon">Retell</a> | Speech synthesis | Analytics | — | — | [Blog Article, August 2020](https://vc.ru/services/153732-kak-sozdat-audiostati-na-vashem-sayte-i-zachem-eto-nuzhno) |
+| <a href="https://rspamd.com/" class="favicon">Rspamd</a> | Antispam | Analytics | — | — | [Official Website](https://rspamd.com/doc/modules/clickhouse.html) |
+| <a href="https://rusiem.com/en" class="favicon">RuSIEM</a> | SIEM | Main Product | — | — | [Official Website](https://rusiem.com/en/products/architecture) |
+| <a href="https://www.s7.ru" class="favicon">S7 Airlines</a> | Airlines | Metrics, Logging | — | — | [Talk in Russian, March 2019](https://www.youtube.com/watch?v=nwG68klRpPg&t=15s) |
+| <a href="https://www.scireum.de/" class="favicon">scireum GmbH</a> | e-Commerce | Main product | — | — | [Talk in German, February 2020](https://www.youtube.com/watch?v=7QWAn5RbyR4) |
+| <a href="https://segment.com/" class="favicon">Segment</a> | Data processing | Main product | 9 * i3en.3xlarge nodes 7.5TB NVME SSDs, 96GB Memory, 12 vCPUs | — | [Slides, 2019](https://slides.com/abraithwaite/segment-clickhouse) |
+| <a href="https://www.semrush.com/" class="favicon">SEMrush</a> | Marketing | Main product | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/5_semrush.pdf) |
+| <a href="https://sentry.io/" class="favicon">Sentry</a> | Software Development | Main product | — | — | [Blog Post in English, May 2019](https://blog.sentry.io/2019/05/16/introducing-snuba-sentrys-new-search-infrastructure) |
+| <a href="https://seo.do/" class="favicon">seo.do</a> | Analytics | Main product | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/CH%20Presentation-%20Metehan%20Çetinkaya.pdf) |
+| <a href="http://www.sgk.gov.tr/wps/portal/sgk/tr" class="favicon">SGK</a> | Goverment Social Security | Analytics | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup35/ClickHouse%20Meetup-Ramazan%20POLAT.pdf) |
+| <a href="http://english.sina.com/index.html" class="favicon">Sina</a> | News | — | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/6.%20ClickHouse最佳实践%20高鹏_新浪.pdf) |
+| <a href="https://smi2.ru/" class="favicon">SMI2</a> | News | Analytics | — | — | [Blog Post in Russian, November 2017](https://habr.com/ru/company/smi2/blog/314558/) |
+| <a href="https://www.splunk.com/" class="favicon">Splunk</a> | Business Analytics | Main product | — | — | [Slides in English, January 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup12/splunk.pdf) |
+| <a href="https://www.spotify.com" class="favicon">Spotify</a> | Music | Experimentation | — | — | [Slides, July 2018](https://www.slideshare.net/glebus/using-clickhouse-for-experimentation-104247173) |
+| <a href="https://www.staffcop.ru/" class="favicon">Staffcop</a> | Information Security | Main Product | — | — | [Official website, Documentation](https://www.staffcop.ru/sce43) |
+| <a href="https://www.suning.com/" class="favicon">Suning</a> | E-Commerce | User behaviour analytics | — | — | [Blog article](https://www.sohu.com/a/434152235_411876) |
+| <a href="https://www.teralytics.net/" class="favicon">Teralytics</a> | Mobility | Analytics | — | — | [Tech blog](https://www.teralytics.net/knowledge-hub/visualizing-mobility-data-the-scalability-challenge) |
+| <a href="https://www.tencent.com" class="favicon">Tencent</a> | Big Data | Data processing | — | — | [Slides in Chinese, October 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup19/5.%20ClickHouse大数据集群应用_李俊飞腾讯网媒事业部.pdf) |
+| <a href="https://www.tencent.com" class="favicon">Tencent</a> | Messaging | Logging | — | — | [Talk in Chinese, November 2019](https://youtu.be/T-iVQRuw-QY?t=5050) |
+| <a href="https://www.tencentmusic.com/" class="favicon">Tencent Music Entertainment (TME)</a> | BigData | Data processing | — | — | [Blog in Chinese, June 2020](https://cloud.tencent.com/developer/article/1637840) |
+| <a href="https://trafficstars.com/" class="favicon">Traffic Stars</a> | AD network | — | — | — | [Slides in Russian, May 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup15/lightning/ninja.pdf) |
+| <a href="https://www.uber.com" class="favicon">Uber</a> | Taxi | Logging | — | — | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/uber.pdf) |
+| <a href="https://vk.com" class="favicon">VKontakte</a> | Social Network | Statistics, Logging | — | — | [Slides in Russian, August 2018](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup17/3_vk.pdf) |
+| <a href="https://www.walmartlabs.com/" class="favicon">Walmart Labs</a> | Internet, Retail | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=144) |
+| <a href="https://wargaming.com/en/" class="favicon">Wargaming</a> | Games | | — | — | [Interview](https://habr.com/en/post/496954/) |
+| <a href="https://wisebits.com/" class="favicon">Wisebits</a> | IT Solutions | Analytics | — | — | [Slides in Russian, May 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup22/strategies.pdf) |
+| <a href="https://www.workato.com/" class="favicon">Workato</a> | Automation Software | — | — | — | [Talk in English, July 2020](https://youtu.be/GMiXCMFDMow?t=334) |
+| <a href="http://www.xiaoxintech.cn/" class="favicon">Xiaoxin Tech</a> | Education | Common purpose | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/sync-clickhouse-with-mysql-mongodb.pptx) |
+| <a href="https://www.ximalaya.com/" class="favicon">Ximalaya</a> | Audio sharing | OLAP | — | — | [Slides in English, November 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup33/ximalaya.pdf) |
+| <a href="https://cloud.yandex.ru/services/managed-clickhouse" class="favicon">Yandex Cloud</a> | Public Cloud | Main product | — | — | [Talk in Russian, December 2019](https://www.youtube.com/watch?v=pgnak9e_E0o) |
+| <a href="https://cloud.yandex.ru/services/datalens" class="favicon">Yandex DataLens</a> | Business Intelligence | Main product | — | — | [Slides in Russian, December 2019](https://presentations.clickhouse.tech/meetup38/datalens.pdf) |
+| <a href="https://market.yandex.ru/" class="favicon">Yandex Market</a> | e-Commerce | Metrics, Logging | — | — | [Talk in Russian, January 2019](https://youtu.be/_l1qP0DyBcA?t=478) |
+| <a href="https://metrica.yandex.com" class="favicon">Yandex Metrica</a> | Web analytics | Main product | 630 servers in one cluster, 360 servers in another cluster, 1862 servers in one department | 133 PiB / 8.31 PiB / 120 trillion records | [Slides, February 2020](https://presentations.clickhouse.tech/meetup40/introduction/#13) |
+| <a href="https://htc-cs.ru/" class="favicon">ЦВТ</a> | Software Development | Metrics, Logging | — | — | [Blog Post, March 2019, in Russian](https://vc.ru/dev/62715-kak-my-stroili-monitoring-na-prometheus-clickhouse-i-elk) |
+| <a href="https://mkb.ru/" class="favicon">МКБ</a> | Bank | Web-system monitoring | — | — | [Slides in Russian, September 2019](https://github.com/ClickHouse/clickhouse-presentations/blob/master/meetup28/mkb.pdf) |
+| <a href="https://cft.ru/" class="favicon">ЦФТ</a> | Banking, Financial products, Payments | — | — | — | [Meetup in Russian, April 2020](https://team.cft.ru/events/162) |
+| <a href="https://www.kakaocorp.com/" class="favicon">kakaocorp</a> | Internet company | — | — | — | [if(kakao)2020 conference](https://if.kakao.com/session/117) |
 
 [Original article](https://clickhouse.tech/docs/en/introduction/adopters/) <!--hide-->

docs/en/operations/backup.md

@@ -5,7 +5,7 @@ toc_title: Data Backup
 
 # Data Backup {#data-backup}
 
-While [replication](../engines/table-engines/mergetree-family/replication.md) provides protection from hardware failures, it does not protect against human errors: accidental deletion of data, deletion of the wrong table or a table on the wrong cluster, and software bugs that result in incorrect data processing or data corruption. In many cases mistakes like these will affect all replicas. ClickHouse has built-in safeguards to prevent some types of mistakes — for example, by default [you can’t just drop tables with a MergeTree-like engine containing more than 50 Gb of data](https://github.com/ClickHouse/ClickHouse/blob/v18.14.18-stable/programs/server/config.xml#L322-L330). However, these safeguards don’t cover all possible cases and can be circumvented.
+While [replication](../engines/table-engines/mergetree-family/replication.md) provides protection from hardware failures, it does not protect against human errors: accidental deletion of data, deletion of the wrong table or a table on the wrong cluster, and software bugs that result in incorrect data processing or data corruption. In many cases mistakes like these will affect all replicas. ClickHouse has built-in safeguards to prevent some types of mistakes — for example, by default [you can’t just drop tables with a MergeTree-like engine containing more than 50 Gb of data](server-configuration-parameters/settings.md#max-table-size-to-drop). However, these safeguards don’t cover all possible cases and can be circumvented.
 
 In order to effectively mitigate possible human errors, you should carefully prepare a strategy for backing up and restoring your data **in advance**.
 

docs/en/operations/external-authenticators/index.md

@@ -0,0 +1,13 @@
+---
+toc_folder_title: External User Authenticators and Directories
+toc_priority: 48
+toc_title: Introduction
+---
+
+# External User Authenticators and Directories {#external-authenticators}
+
+ClickHouse supports authenticating and managing users using external services.
+
+The following external authenticators and directories are supported:
+
+- [LDAP](./ldap.md#external-authenticators-ldap) [Authenticator](./ldap.md#ldap-external-authenticator) and [Directory](./ldap.md#ldap-external-user-directory)

docs/en/operations/external-authenticators/ldap.md

@@ -0,0 +1,156 @@
+# LDAP {#external-authenticators-ldap} 
+
+LDAP server can be used to authenticate ClickHouse users. There are two different approaches for doing this:
+
+- use LDAP as an external authenticator for existing users, which are defined in `users.xml` or in local access control paths
+- use LDAP as an external user directory and allow locally undefined users to be authenticated if they exist on the LDAP server
+
+For both of these approaches, an internally named LDAP server must be defined in the ClickHouse config so that other parts of config are able to refer to it.
+
+## LDAP Server Definition {#ldap-server-definition}
+
+To define LDAP server you must add `ldap_servers` section to the `config.xml`. For example,
+
+```xml
+<yandex>
+    <!- ... -->
+    <ldap_servers>
+        <my_ldap_server>
+            <host>localhost</host>
+            <port>636</port>
+            <bind_dn>uid={user_name},ou=users,dc=example,dc=com</bind_dn>
+            <verification_cooldown>300</verification_cooldown>
+            <enable_tls>yes</enable_tls>
+            <tls_minimum_protocol_version>tls1.2</tls_minimum_protocol_version>
+            <tls_require_cert>demand</tls_require_cert>
+            <tls_cert_file>/path/to/tls_cert_file</tls_cert_file>
+            <tls_key_file>/path/to/tls_key_file</tls_key_file>
+            <tls_ca_cert_file>/path/to/tls_ca_cert_file</tls_ca_cert_file>
+            <tls_ca_cert_dir>/path/to/tls_ca_cert_dir</tls_ca_cert_dir>
+            <tls_cipher_suite>ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:AES256-GCM-SHA384</tls_cipher_suite>
+        </my_ldap_server>
+    </ldap_servers>
+</yandex>
+```
+
+Note, that you can define multiple LDAP servers inside the `ldap_servers` section using distinct names.
+
+Parameters:
+
+- `host` - LDAP server hostname or IP, this parameter is mandatory and cannot be empty.
+- `port` - LDAP server port, default is `636` if `enable_tls` is set to `true`, `389` otherwise.
+- `bind_dn` - template used to construct the DN to bind to.
+    - The resulting DN will be constructed by replacing all `{user_name}` substrings of the
+      template with the actual user name during each authentication attempt.
+- `verification_cooldown` - a period of time, in seconds, after a successful bind attempt,
+  during which the user will be assumed to be successfully authenticated for all consecutive
+  requests without contacting the LDAP server.
+    - Specify `0` (the default) to disable caching and force contacting the LDAP server for each authentication request.
+- `enable_tls` - flag to trigger use of secure connection to the LDAP server.
+    - Specify `no` for plain text `ldap://` protocol (not recommended).
+    - Specify `yes` for LDAP over SSL/TLS `ldaps://` protocol (recommended, the default).
+    - Specify `starttls` for legacy StartTLS protocol (plain text `ldap://` protocol, upgraded to TLS).
+- `tls_minimum_protocol_version` - the minimum protocol version of SSL/TLS.
+    - Accepted values are: `ssl2`, `ssl3`, `tls1.0`, `tls1.1`, `tls1.2` (the default).
+- `tls_require_cert` - SSL/TLS peer certificate verification behavior.
+    - Accepted values are: `never`, `allow`, `try`, `demand` (the default).
+- `tls_cert_file` - path to certificate file.
+- `tls_key_file` - path to certificate key file.
+- `tls_ca_cert_file` - path to CA certificate file.
+- `tls_ca_cert_dir` - path to the directory containing CA certificates.
+- `tls_cipher_suite` - allowed cipher suite (in OpenSSL notation).
+
+## LDAP External Authenticator {#ldap-external-authenticator}
+
+A remote LDAP server can be used as a method for verifying passwords for locally defined users (users defined in `users.xml` or in local access control paths). In order to achieve this, specify previously defined LDAP server name instead of `password` or similar sections in the user definition.
+
+At each login attempt, ClickHouse will try to "bind" to the specified DN defined by the `bind_dn` parameter in the [LDAP server definition](#ldap-server-definition) using the provided credentials, and if successful, the user will be considered authenticated. This is often called a "simple bind" method.
+
+For example,
+
+```xml
+<yandex>
+    <!- ... -->
+    <users>
+        <!- ... -->
+        <my_user>
+            <!- ... -->
+            <ldap>
+                <server>my_ldap_server</server>
+            </ldap>
+        </my_user>
+    </users>
+</yandex>
+```
+
+Note, that user `my_user` refers to `my_ldap_server`. This LDAP server must be configured in the main `config.xml` file as described previously.
+
+When SQL-driven [Access Control and Account Management](../access-rights.md#access-control) is enabled in ClickHouse, users that are authenticated by LDAP servers can also be created using the [CRATE USER](../../sql-reference/statements/create/user.md#create-user-statement) statement.
+
+
+```sql
+CREATE USER my_user IDENTIFIED WITH ldap_server BY 'my_ldap_server'
+```
+
+## LDAP Exernal User Directory {#ldap-external-user-directory}
+
+In addition to the locally defined users, a remote LDAP server can be used as a source of user definitions. In order to achieve this, specify previously defined LDAP server name (see [LDAP Server Definition](#ldap-server-definition)) in the `ldap` section inside the `users_directories` section of the `config.xml` file.
+
+At each login attempt, ClickHouse will try to find the user definition locally and authenticate it as usual, but if the user is not defined, ClickHouse will assume it exists in the external LDAP directory, and will try to "bind" to the specified DN at the LDAP server using the provided credentials. If successful, the user will be considered existing and authenticated. The user will be assigned roles from the list specified in the `roles` section. Additionally, LDAP "search" can be performed and results can be transformed and treated as role names and then be assigned to the user if the `role_mapping` section is also configured. All this implies that the SQL-driven [Access Control and Account Management](../access-rights.md#access-control) is enabled and roles are created using the [CREATE ROLE](../../sql-reference/statements/create/role.md#create-role-statement) statement.
+
+Example (goes into `config.xml`):
+
+```xml
+<yandex>
+    <!- ... -->
+    <user_directories>
+        <!- ... -->
+        <ldap>
+            <server>my_ldap_server</server>
+            <roles>
+                <my_local_role1 />
+                <my_local_role2 />
+            </roles>
+            <role_mapping>
+                <base_dn>ou=groups,dc=example,dc=com</base_dn>
+                <scope>subtree</scope>
+                <search_filter>(&amp;(objectClass=groupOfNames)(member={bind_dn}))</search_filter>
+                <attribute>cn</attribute>
+                <prefix>clickhouse_</prefix>
+            </role_mapping>
+        </ldap>
+    </user_directories>
+</yandex>
+```
+
+Note that `my_ldap_server` referred in the `ldap` section inside the `user_directories` section must be a previously
+defined LDAP server that is configured in the `config.xml` (see [LDAP Server Definition](#ldap-server-definition)).
+
+Parameters:
+
+- `server` - one of LDAP server names defined in the `ldap_servers` config section above.
+  This parameter is mandatory and cannot be empty.
+- `roles` - section with a list of locally defined roles that will be assigned to each user retrieved from the LDAP server.
+    - If no roles are specified here or assigned during role mapping (below), user will not be able
+      to perform any actions after authentication.
+- `role_mapping` - section with LDAP search parameters and mapping rules.
+    - When a user authenticates, while still bound to LDAP, an LDAP search is performed using `search_filter`
+      and the name of the logged in user. For each entry found during that search, the value of the specified
+      attribute is extracted. For each attribute value that has the specified prefix, the prefix is removed,
+      and the rest of the value becomes the name of a local role defined in ClickHouse,
+      which is expected to be created beforehand by the [CREATE ROLE](../../sql-reference/statements/create/role.md#create-role-statement) statement.
+    - There can be multiple `role_mapping` sections defined inside the same `ldap` section. All of them will be applied.
+        - `base_dn` - template used to construct the base DN for the LDAP search.
+           - The resulting DN will be constructed by replacing all `{user_name}` and `{bind_dn}`
+             substrings of the template with the actual user name and bind DN during each LDAP search.
+        - `scope` - scope of the LDAP search.
+            - Accepted values are: `base`, `one_level`, `children`, `subtree` (the default).
+        - `search_filter` - template used to construct the search filter for the LDAP search.
+            - The resulting filter will be constructed by replacing all `{user_name}`, `{bind_dn}`, and `{base_dn}`
+              substrings of the template with the actual user name, bind DN, and base DN during each LDAP search.
+            - Note, that the special characters must be escaped properly in XML.
+        - `attribute` - attribute name whose values will be returned by the LDAP search.
+        - `prefix` - prefix, that will be expected to be in front of each string in the original
+          list of strings returned by the LDAP search. Prefix will be removed from the original
+          strings and resulting strings will be treated as local role names. Empty, by default.
+

docs/en/operations/quotas.md

@@ -29,6 +29,8 @@ Let’s look at the section of the ‘users.xml’ file that defines quotas.
 
             <!-- Unlimited. Just collect data for the specified time interval. -->
             <queries>0</queries>
+            <query_selects>0</query_selects>
+            <query_inserts>0</query_inserts>
             <errors>0</errors>
             <result_rows>0</result_rows>
             <read_rows>0</read_rows>
@@ -48,6 +50,8 @@ The resource consumption calculated for each interval is output to the server lo
         <duration>3600</duration>
 
         <queries>1000</queries>
+        <query_selects>100</query_selects>
+        <query_inserts>100</query_inserts>
         <errors>100</errors>
         <result_rows>1000000000</result_rows>
         <read_rows>100000000000</read_rows>
@@ -58,6 +62,8 @@ The resource consumption calculated for each interval is output to the server lo
         <duration>86400</duration>
 
         <queries>10000</queries>
+        <query_selects>10000</query_selects>
+        <query_inserts>10000</query_inserts>
         <errors>1000</errors>
         <result_rows>5000000000</result_rows>
         <read_rows>500000000000</read_rows>
@@ -74,6 +80,10 @@ Here are the amounts that can be restricted:
 
 `queries` – The total number of requests.
 
+`query_selects` – The total number of select requests.
+
+`query_inserts` – The total number of insert requests.
+
 `errors` – The number of queries that threw an exception.
 
 `result_rows` – The total number of rows given as a result.

docs/en/operations/server-configuration-parameters/settings.md

@@ -296,11 +296,33 @@ Useful for breaking away from a specific network interface.
 <interserver_http_host>example.yandex.ru</interserver_http_host>
 ```
 
+## interserver_https_port {#interserver-https-port}
+
+Port for exchanging data between ClickHouse servers over `HTTPS`.
+
+**Example**
+
+``` xml
+<interserver_https_port>9010</interserver_https_port>
+```
+
+## interserver_https_host {#interserver-https-host}
+
+Similar to `interserver_http_host`, except that this hostname can be used by other servers to access this server over `HTTPS`.
+
+**Example**
+
+``` xml
+<interserver_https_host>example.yandex.ru</interserver_https_host>
+```
+
 ## interserver_http_credentials {#server-settings-interserver-http-credentials}
 
 The username and password used to authenticate during [replication](../../engines/table-engines/mergetree-family/replication.md) with the Replicated\* engines. These credentials are used only for communication between replicas and are unrelated to credentials for ClickHouse clients. The server is checking these credentials for connecting replicas and use the same credentials when connecting to other replicas. So, these credentials should be set the same for all replicas in a cluster.
 By default, the authentication is not used.
 
+**Note:** These credentials are common for replication through `HTTP` and `HTTPS`.
+
 This section contains the following parameters:
 
 -   `user` — username.

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

@@ -186,5 +186,16 @@ Possible values:
 Default value: auto (number of CPU cores).
 
 During startup ClickHouse reads all parts of all tables (reads files with metadata of parts) to build a list of all parts in memory. In some systems with a large number of parts this process can take a long time, and this time might be shortened by increasing `max_part_loading_threads` (if this process is not CPU and disk I/O bound).
+## max_partitions_to_read {#max-partitions-to-read}
+
+Limits the maximum number of partitions that can be accessed in one query.
+
+The setting value specified when the table is created can be overridden via query-level setting.
+
+Possible values:
+
+-   Any positive integer.
+
+Default value: -1 (unlimited).
 
 [Original article](https://clickhouse.tech/docs/en/operations/settings/merge_tree_settings/) <!--hide-->

docs/en/operations/settings/settings-users.md

@@ -139,7 +139,7 @@ You can assign a quotas set for the user. For a detailed description of quotas c
 
 ### user_name/databases {#user-namedatabases}
 
-In this section, you can you can limit rows that are returned by ClickHouse for `SELECT` queries made by the current user, thus implementing basic row-level security.
+In this section, you can limit rows that are returned by ClickHouse for `SELECT` queries made by the current user, thus implementing basic row-level security.
 
 **Example**
 

docs/en/operations/settings/settings.md

@@ -312,7 +312,7 @@ Enables or disables parsing enum values as enum ids for TSV input format.
 Possible values:
 
 -   0 — Enum values are parsed as values.
--   1 — Enum values are parsed as enum IDs
+-   1 — Enum values are parsed as enum IDs.
 
 Default value: 0.
 
@@ -428,7 +428,7 @@ Possible values:
 
 -   `'basic'` — Use basic parser.
 
-    ClickHouse can parse only the basic `YYYY-MM-DD HH:MM:SS` or `YYYY-MM-DD` format. For example, `'2019-08-20 10:18:56'` or `2019-08-20`.
+    ClickHouse can parse only the basic `YYYY-MM-DD HH:MM:SS` or `YYYY-MM-DD` format. For example, `2019-08-20 10:18:56` or `2019-08-20`.
 
 Default value: `'basic'`.
 
@@ -443,19 +443,19 @@ Allows choosing different output formats of the text representation of date and
 
 Possible values:
 
--   `'simple'` - Simple output format.
+-   `simple` - Simple output format.
 
-    Clickhouse output date and time `YYYY-MM-DD hh:mm:ss` format. For example, `'2019-08-20 10:18:56'`. Calculation is performed according to the data type's time zone (if present) or server time zone.
+    Clickhouse output date and time `YYYY-MM-DD hh:mm:ss` format. For example, `2019-08-20 10:18:56`. The calculation is performed according to the data type's time zone (if present) or server time zone.
 
--   `'iso'` - ISO output format.
+-   `iso` - ISO output format.
 
-    Clickhouse output date and time in [ISO 8601](https://en.wikipedia.org/wiki/ISO_8601) `YYYY-MM-DDThh:mm:ssZ` format. For example, `'2019-08-20T10:18:56Z'`. Note that output is in UTC (`Z` means UTC).
+    Clickhouse output date and time in [ISO 8601](https://en.wikipedia.org/wiki/ISO_8601) `YYYY-MM-DDThh:mm:ssZ` format. For example, `2019-08-20T10:18:56Z`. Note that output is in UTC (`Z` means UTC).
 
--   `'unix_timestamp'` - Unix timestamp output format.
+-   `unix_timestamp` - Unix timestamp output format.
 
-    Clickhouse output date and time in [Unix timestamp](https://en.wikipedia.org/wiki/Unix_time) format. For example `'1566285536'`.
+    Clickhouse output date and time in [Unix timestamp](https://en.wikipedia.org/wiki/Unix_time) format. For example `1566285536`.
 
-Default value: `'simple'`.
+Default value: `simple`.
 
 See also:
 
@@ -1944,6 +1944,21 @@ Possible values:
 
 Default value: 16.
 
+## background_message_broker_schedule_pool_size {#background_message_broker_schedule_pool_size}
+
+Sets the number of threads performing background tasks for message streaming. This setting is applied at the ClickHouse server start and can’t be changed in a user session.
+
+Possible values:
+
+-   Any positive integer.
+
+Default value: 16.
+
+**See Also**
+
+-   [Kafka](../../engines/table-engines/integrations/kafka.md#kafka) engine
+-   [RabbitMQ](../../engines/table-engines/integrations/rabbitmq.md#rabbitmq-engine) engine
+
 ## validate_polygons {#validate_polygons}
 
 Enables or disables throwing an exception in the [pointInPolygon](../../sql-reference/functions/geo/index.md#pointinpolygon) function, if the polygon is self-intersecting or self-tangent.
@@ -2577,4 +2592,90 @@ Possible values:
 
 Default value: `16`.
 
+## opentelemetry_start_trace_probability {#opentelemetry-start-trace-probability}
+
+Sets the probability that the ClickHouse can start a trace for executed queries (if no parent [trace context](https://www.w3.org/TR/trace-context/) is supplied).
+
+Possible values:
+
+-   0 — The trace for all executed queries is disabled (if no parent trace context is supplied).
+-   Positive floating-point number in the range [0..1]. For example, if the setting value is `0,5`, ClickHouse can start a trace on average for half of the queries.
+-   1 — The trace for all executed queries is enabled.
+
+Default value: `0`.
+
+## optimize_on_insert {#optimize-on-insert}
+
+Enables or disables data transformation before the insertion, as if merge was done on this block (according to table engine).
+
+Possible values:
+
+-   0 — Disabled.
+-   1 — Enabled.
+
+Default value: 1.
+
+**Example**
+
+The difference between enabled and disabled:
+
+Query:
+
+```sql
+SET optimize_on_insert = 1;
+
+CREATE TABLE test1 (`FirstTable` UInt32) ENGINE = ReplacingMergeTree ORDER BY FirstTable;
+
+INSERT INTO test1 SELECT number % 2 FROM numbers(5);
+
+SELECT * FROM test1;
+
+SET optimize_on_insert = 0;
+
+CREATE TABLE test2 (`SecondTable` UInt32) ENGINE = ReplacingMergeTree ORDER BY SecondTable;
+
+INSERT INTO test2 SELECT number % 2 FROM numbers(5);
+
+SELECT * FROM test2;
+```
+
+Result:
+
+``` text
+┌─FirstTable─┐
+│          0 │
+│          1 │
+└────────────┘
+
+┌─SecondTable─┐
+│           0 │
+│           0 │
+│           0 │
+│           1 │
+│           1 │
+└─────────────┘
+```
+
+Note that this setting influences [Materialized view](../../sql-reference/statements/create/view.md#materialized) and [MaterializeMySQL](../../engines/database-engines/materialize-mysql.md) behaviour.
+
 [Original article](https://clickhouse.tech/docs/en/operations/settings/settings/) <!-- hide -->
+
+## engine_file_empty_if_not_exists {#engine-file-empty_if-not-exists}
+
+Allows to select data from a file engine table without file.
+
+Possible values:
+- 0 — `SELECT` throws exception.
+- 1 — `SELECT` returns empty result.
+
+Default value: `0`.
+
+## engine_file_truncate_on_insert {#engine-file-truncate-on-insert}
+
+Enables or disables truncate before insert in file engine tables.
+
+Possible values:
+- 0 — Disabled.
+- 1 — Enabled.
+
+Default value: `0`.

docs/en/operations/system-tables/distributed_ddl_queue.md

@@ -1,22 +1,21 @@
 # system.distributed_ddl_queue {#system_tables-distributed_ddl_queue}
 
-Contains information about distributed ddl queries (ON CLUSTER queries) that were executed on a cluster.
+Contains information about [distributed ddl queries (ON CLUSTER clause)](../../sql-reference/distributed-ddl.md) that were executed on a cluster.
 
 Columns:
 
--   `entry`  ([String](../../sql-reference/data-types/string.md)) - Query id.
--   `host_name`  ([String](../../sql-reference/data-types/string.md)) - Hostname.
--   `host_address`  ([String](../../sql-reference/data-types/string.md)) - IP address that the Hostname resolves to.
--   `port`  ([UInt16](../../sql-reference/data-types/int-uint.md)) - Host Port.
--   `status`  ([Enum](../../sql-reference/data-types/enum.md)) - Stats of the query.
--   `cluster`  ([String](../../sql-reference/data-types/string.md)) - Cluster name.
--   `query`  ([String](../../sql-reference/data-types/string.md)) - Query executed.
--   `initiator`  ([String](../../sql-reference/data-types/string.md)) - Nod that executed the query.
--   `query_start_time` ([Date](../../sql-reference/data-types/date.md)) — Query start time.
--   `query_finish_time` ([Date](../../sql-reference/data-types/date.md)) — Query finish time.
--   `query_duration_ms` ([UInt64](../../sql-reference/data-types/datetime64.md)) — Duration of query execution in milliseconds.
--   `exception_code`  ([Enum](../../sql-reference/data-types/enum.md)) - Exception code from ZooKeeper.
-
+-   `entry` ([String](../../sql-reference/data-types/string.md)) — Query id.
+-   `host_name` ([String](../../sql-reference/data-types/string.md)) — Hostname.
+-   `host_address` ([String](../../sql-reference/data-types/string.md)) — IP address that the Hostname resolves to.
+-   `port` ([UInt16](../../sql-reference/data-types/int-uint.md)) — Host Port.
+-   `status` ([Enum8](../../sql-reference/data-types/enum.md)) — Status of the query.
+-   `cluster` ([String](../../sql-reference/data-types/string.md)) — Cluster name.
+-   `query` ([String](../../sql-reference/data-types/string.md)) — Query executed.
+-   `initiator` ([String](../../sql-reference/data-types/string.md)) — Node that executed the query.
+-   `query_start_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Query start time.
+-   `query_finish_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Query finish time.
+-   `query_duration_ms` ([UInt64](../../sql-reference/data-types/datetime64.md)) — Duration of query execution (in milliseconds).
+-   `exception_code` ([Enum8](../../sql-reference/data-types/enum.md)) — Exception code from [ZooKeeper](../../operations/tips.md#zookeeper).
 
 **Example**
 
@@ -62,6 +61,5 @@ exception_code:    ZOK
 2 rows in set. Elapsed: 0.025 sec.
 ```
 
-
 [Original article](https://clickhouse.tech/docs/en/operations/system_tables/distributed_ddl_queuedistributed_ddl_queue.md) <!--hide-->
  

docs/en/operations/system-tables/opentelemetry_span_log.md

@@ -0,0 +1,53 @@
+# system.opentelemetry_span_log {#system_tables-opentelemetry_span_log}
+
+Contains information about [trace spans](https://opentracing.io/docs/overview/spans/) for executed queries.
+
+Columns:
+
+-   `trace_id` ([UUID](../../sql-reference/data-types/uuid.md) — ID of the trace for executed query.
+
+-   `span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — ID of the `trace span`.
+
+-   `parent_span_id` ([UInt64](../../sql-reference/data-types/int-uint.md)) — ID of the parent `trace span`.
+
+-   `operation_name` ([String](../../sql-reference/data-types/string.md)) — The name of the operation.
+
+-   `start_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The start time of the `trace span` (in microseconds).
+
+-   `finish_time_us` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The finish time of the `trace span` (in microseconds).
+
+-   `finish_date` ([Date](../../sql-reference/data-types/date.md)) — The finish date of the `trace span`.
+
+-   `attribute.names` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — [Attribute](https://opentelemetry.io/docs/go/instrumentation/#attributes) names depending on the `trace span`. They are filled in according to the recommendations in the [OpenTelemetry](https://opentelemetry.io/) standard.
+
+-   `attribute.values` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) — Attribute values depending on the `trace span`. They are filled in according to the recommendations in the `OpenTelemetry` standard.
+
+**Example**
+
+Query:
+
+``` sql
+SELECT * FROM system.opentelemetry_span_log LIMIT 1 FORMAT Vertical;
+```
+
+Result:
+
+``` text
+Row 1:
+──────
+trace_id:         cdab0847-0d62-61d5-4d38-dd65b19a1914
+span_id:          701487461015578150
+parent_span_id:   2991972114672045096
+operation_name:   DB::Block DB::InterpreterSelectQuery::getSampleBlockImpl()
+start_time_us:    1612374594529090
+finish_time_us:   1612374594529108
+finish_date:      2021-02-03
+attribute.names:  []
+attribute.values: []
+```
+
+**See Also**
+
+-   [OpenTelemetry](../../operations/opentelemetry.md)
+
+[Original article](https://clickhouse.tech/docs/en/operations/system_tables/opentelemetry_span_log) <!--hide-->

docs/en/operations/system-tables/part_log.md

@@ -6,29 +6,65 @@ This table contains information about events that occurred with [data parts](../
 
 The `system.part_log` table contains the following columns:
 
--   `event_type` (Enum) — Type of the event that occurred with the data part. Can have one of the following values:
+-   `query_id` ([String](../../sql-reference/data-types/string.md)) — Identifier of the `INSERT` query that created this data part.
+-   `event_type` ([Enum8](../../sql-reference/data-types/enum.md)) — Type of the event that occurred with the data part. Can have one of the following values:
     -   `NEW_PART` — Inserting of a new data part.
     -   `MERGE_PARTS` — Merging of data parts.
     -   `DOWNLOAD_PART` — Downloading a data part.
     -   `REMOVE_PART` — Removing or detaching a data part using [DETACH PARTITION](../../sql-reference/statements/alter/partition.md#alter_detach-partition).
     -   `MUTATE_PART` — Mutating of a data part.
     -   `MOVE_PART` — Moving the data part from the one disk to another one.
--   `event_date` (Date) — Event date.
--   `event_time` (DateTime) — Event time.
--   `duration_ms` (UInt64) — Duration.
--   `database` (String) — Name of the database the data part is in.
--   `table` (String) — Name of the table the data part is in.
--   `part_name` (String) — Name of the data part.
--   `partition_id` (String) — ID of the partition that the data part was inserted to. The column takes the ‘all’ value if the partitioning is by `tuple()`.
--   `rows` (UInt64) — The number of rows in the data part.
--   `size_in_bytes` (UInt64) — Size of the data part in bytes.
--   `merged_from` (Array(String)) — An array of names of the parts which the current part was made up from (after the merge).
--   `bytes_uncompressed` (UInt64) — Size of uncompressed bytes.
--   `read_rows` (UInt64) — The number of rows was read during the merge.
--   `read_bytes` (UInt64) — The number of bytes was read during the merge.
--   `error` (UInt16) — The code number of the occurred error.
--   `exception` (String) — Text message of the occurred error.
+-   `event_date` ([Date](../../sql-reference/data-types/date.md)) — Event date.
+-   `event_time` ([DateTime](../../sql-reference/data-types/datetime.md)) — Event time.
+-   `event_time_microseconds` ([DateTime64](../../sql-reference/data-types/datetime64.md)) — Event time with microseconds precision.
+
+-   `duration_ms` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Duration.
+-   `database` ([String](../../sql-reference/data-types/string.md)) — Name of the database the data part is in.
+-   `table` ([String](../../sql-reference/data-types/string.md)) — Name of the table the data part is in.
+-   `part_name` ([String](../../sql-reference/data-types/string.md)) — Name of the data part.
+-   `partition_id` ([String](../../sql-reference/data-types/string.md)) — ID of the partition that the data part was inserted to. The column takes the `all` value if the partitioning is by `tuple()`.
+-   `path_on_disk` ([String](../../sql-reference/data-types/string.md)) — Absolute path to the folder with data part files.
+-   `rows` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The number of rows in the data part.
+-   `size_in_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Size of the data part in bytes.
+-   `merged_from` ([Array(String)](../../sql-reference/data-types/array.md)) — An array of names of the parts which the current part was made up from (after the merge).
+-   `bytes_uncompressed` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Size of uncompressed bytes.
+-   `read_rows` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The number of rows was read during the merge.
+-   `read_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The number of bytes was read during the merge.
+-   `peak_memory_usage` ([Int64](../../sql-reference/data-types/int-uint.md)) — The maximum difference between the amount of allocated and freed memory in context of this thread.
+-   `error` ([UInt16](../../sql-reference/data-types/int-uint.md)) — The code number of the occurred error.
+-   `exception` ([String](../../sql-reference/data-types/string.md)) — Text message of the occurred error.
 
 The `system.part_log` table is created after the first inserting data to the `MergeTree` table.
 
+**Example**
+
+``` sql
+SELECT * FROM system.part_log LIMIT 1 FORMAT Vertical;
+```
+
+``` text
+Row 1:
+──────
+query_id:                      983ad9c7-28d5-4ae1-844e-603116b7de31
+event_type:                    NewPart
+event_date:                    2021-02-02
+event_time:                    2021-02-02 11:14:28
+event_time_microseconds:                    2021-02-02 11:14:28.861919
+duration_ms:                   35
+database:                      default
+table:                         log_mt_2
+part_name:                     all_1_1_0
+partition_id:                  all
+path_on_disk:                  db/data/default/log_mt_2/all_1_1_0/
+rows:                          115418
+size_in_bytes:                 1074311
+merged_from:                   []
+bytes_uncompressed:            0
+read_rows:                     0
+read_bytes:                    0
+peak_memory_usage:             0
+error:                         0
+exception:                   
+```
+
 [Original article](https://clickhouse.tech/docs/en/operations/system_tables/part_log) <!--hide-->

docs/en/operations/system-tables/quota_limits.md

@@ -9,6 +9,8 @@ Columns:
 - `0` — Interval is not randomized.
 - `1` — Interval is randomized.
 - `max_queries` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of queries.
+- `max_query_selects` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of select queries.
+- `max_query_inserts` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of insert queries.
 - `max_errors` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of errors.
 - `max_result_rows` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of result rows.
 - `max_result_bytes` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of RAM volume in bytes used to store a queries result.

docs/en/operations/system-tables/quota_usage.md

@@ -9,6 +9,8 @@ Columns:
 - `end_time`([Nullable](../../sql-reference/data-types/nullable.md)([DateTime](../../sql-reference/data-types/datetime.md))) — End time for calculating resource consumption.
 - `duration` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Length of the time interval for calculating resource consumption, in seconds.
 - `queries` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — The total number of requests on this interval.
+- `query_selects` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — The total number of select requests on this interval.
+- `query_inserts` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — The total number of insert requests on this interval.
 - `max_queries` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of requests.
 - `errors` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — The number of queries that threw an exception.
 - `max_errors` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — Maximum number of errors.