diff --git a/README.md b/README.md index ea9f365a3c6..bad00d8280f 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ 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-nwwakmk4-xOJ6cdy0sJC3It8j348~IA) 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-qfort0u8-TWqK4wIP0YSdoDE0btKa1w) 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. * [Contacts](https://clickhouse.tech/#contacts) can help to get your questions answered if there are any. diff --git a/base/daemon/BaseDaemon.cpp b/base/daemon/BaseDaemon.cpp index 83384038b7c..01e700ebba3 100644 --- a/base/daemon/BaseDaemon.cpp +++ b/base/daemon/BaseDaemon.cpp @@ -468,7 +468,7 @@ void BaseDaemon::reloadConfiguration() * instead of using files specified in config.xml. * (It's convenient to log in console when you start server without any command line parameters.) */ - config_path = config().getString("config-file", "config.xml"); + config_path = config().getString("config-file", getDefaultConfigFileName()); DB::ConfigProcessor config_processor(config_path, false, true); config_processor.setConfigPath(Poco::Path(config_path).makeParent().toString()); loaded_config = config_processor.loadConfig(/* allow_zk_includes = */ true); @@ -516,6 +516,11 @@ std::string BaseDaemon::getDefaultCorePath() const return "/opt/cores/"; } +std::string BaseDaemon::getDefaultConfigFileName() const +{ + return "config.xml"; +} + void BaseDaemon::closeFDs() { #if defined(OS_FREEBSD) || defined(OS_DARWIN) diff --git a/base/daemon/BaseDaemon.h b/base/daemon/BaseDaemon.h index 8b9d765cf2e..3d47d85a9f5 100644 --- a/base/daemon/BaseDaemon.h +++ b/base/daemon/BaseDaemon.h @@ -149,6 +149,8 @@ protected: virtual std::string getDefaultCorePath() const; + virtual std::string getDefaultConfigFileName() const; + std::optional pid_file; std::atomic_bool is_cancelled{false}; diff --git a/contrib/grpc b/contrib/grpc index 5b79aae85c5..60c986e15ca 160000 --- a/contrib/grpc +++ b/contrib/grpc @@ -1 +1 @@ -Subproject commit 5b79aae85c515e0df4abfb7b1e07975fdc7cecc1 +Subproject commit 60c986e15cae70aade721d26badabab1f822fdd6 diff --git a/contrib/re2 b/contrib/re2 index 7cf8b88e8f7..13ebb377c6a 160000 --- a/contrib/re2 +++ b/contrib/re2 @@ -1 +1 @@ -Subproject commit 7cf8b88e8f70f97fd4926b56aa87e7f53b2717e0 +Subproject commit 13ebb377c6ad763ca61d12dd6f88b1126bd0b911 diff --git a/contrib/re2_st/re2_transform.cmake b/contrib/re2_st/re2_transform.cmake index 2d50d9e8c2a..56a96f45630 100644 --- a/contrib/re2_st/re2_transform.cmake +++ b/contrib/re2_st/re2_transform.cmake @@ -1,7 +1,7 @@ file (READ ${SOURCE_FILENAME} CONTENT) string (REGEX REPLACE "using re2::RE2;" "" CONTENT "${CONTENT}") string (REGEX REPLACE "using re2::LazyRE2;" "" CONTENT "${CONTENT}") -string (REGEX REPLACE "namespace re2" "namespace re2_st" CONTENT "${CONTENT}") +string (REGEX REPLACE "namespace re2 {" "namespace re2_st {" CONTENT "${CONTENT}") string (REGEX REPLACE "re2::" "re2_st::" CONTENT "${CONTENT}") string (REGEX REPLACE "\"re2/" "\"re2_st/" CONTENT "${CONTENT}") string (REGEX REPLACE "(.\\*?_H)" "\\1_ST" CONTENT "${CONTENT}") diff --git a/docker/test/fasttest/run.sh b/docker/test/fasttest/run.sh index 42c720a7e63..3a19a249f8e 100755 --- a/docker/test/fasttest/run.sh +++ b/docker/test/fasttest/run.sh @@ -73,7 +73,7 @@ function start_server --path "$FASTTEST_DATA" --user_files_path "$FASTTEST_DATA/user_files" --top_level_domains_path "$FASTTEST_DATA/top_level_domains" - --keeper_server.log_storage_path "$FASTTEST_DATA/coordination" + --keeper_server.storage_path "$FASTTEST_DATA/coordination" ) clickhouse-server "${opts[@]}" &>> "$FASTTEST_OUTPUT/server.log" & server_pid=$! @@ -376,35 +376,14 @@ function run_tests # Depends on LLVM JIT 01852_jit_if 01865_jit_comparison_constant_result + 01871_merge_tree_compile_expressions ) - (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 "$FASTTEST_OUTPUT/failed-parallel-tests.txt") - - # We will rerun sequentially any tests that have failed during parallel run. - # They might have failed because there was some interference from other tests - # running concurrently. If they fail even in seqential mode, we will report them. - # FIXME All tests that require exclusive access to the server must be - # explicitly marked as `sequential`, and `clickhouse-test` must detect them and - # run them in a separate group after all other tests. This is faster and also - # explicit instead of guessing. - if [[ -n "${FAILED_TESTS[*]}" ]] - then - stop_server ||: - - # Clean the data so that there is no interference from the previous test run. - rm -rf "$FASTTEST_DATA"/{{meta,}data,user_files,coordination} ||: - - start_server - - echo "Going to run again: ${FAILED_TESTS[*]}" - - clickhouse-test --hung-check --order=random --no-long --testname --shard --zookeeper "${FAILED_TESTS[@]}" 2>&1 | ts '%Y-%m-%d %H:%M:%S' | tee -a "$FASTTEST_OUTPUT/test_log.txt" - else - echo "No failed tests" - fi + time clickhouse-test --hung-check -j 8 --order=random --use-skip-list \ + --no-long --testname --shard --zookeeper --skip "${TESTS_TO_SKIP[@]}" \ + -- "$FASTTEST_FOCUS" 2>&1 \ + | ts '%Y-%m-%d %H:%M:%S' \ + | tee "$FASTTEST_OUTPUT/test_log.txt" } case "$stage" in diff --git a/docker/test/integration/runner/compose/docker_compose_keeper.yml b/docker/test/integration/runner/compose/docker_compose_keeper.yml new file mode 100644 index 00000000000..e11a13e6eab --- /dev/null +++ b/docker/test/integration/runner/compose/docker_compose_keeper.yml @@ -0,0 +1,92 @@ +version: '2.3' +services: + zoo1: + image: ${image:-yandex/clickhouse-integration-test} + restart: always + user: ${user:-} + volumes: + - type: bind + source: ${keeper_binary:-} + target: /usr/bin/clickhouse + - type: bind + source: ${keeper_config_dir1:-} + target: /etc/clickhouse-keeper + - type: bind + source: ${keeper_logs_dir1:-} + target: /var/log/clickhouse-keeper + - type: ${keeper_fs:-tmpfs} + source: ${keeper_db_dir1:-} + target: /var/lib/clickhouse-keeper + entrypoint: "clickhouse keeper --config=/etc/clickhouse-keeper/keeper_config1.xml --log-file=/var/log/clickhouse-keeper/clickhouse-keeper.log --errorlog-file=/var/log/clickhouse-keeper/clickhouse-keeper.err.log" + cap_add: + - SYS_PTRACE + - NET_ADMIN + - IPC_LOCK + - SYS_NICE + security_opt: + - label:disable + dns_opt: + - attempts:2 + - timeout:1 + - inet6 + - rotate + zoo2: + image: ${image:-yandex/clickhouse-integration-test} + restart: always + user: ${user:-} + volumes: + - type: bind + source: ${keeper_binary:-} + target: /usr/bin/clickhouse + - type: bind + source: ${keeper_config_dir2:-} + target: /etc/clickhouse-keeper + - type: bind + source: ${keeper_logs_dir2:-} + target: /var/log/clickhouse-keeper + - type: ${keeper_fs:-tmpfs} + source: ${keeper_db_dir2:-} + target: /var/lib/clickhouse-keeper + entrypoint: "clickhouse keeper --config=/etc/clickhouse-keeper/keeper_config2.xml --log-file=/var/log/clickhouse-keeper/clickhouse-keeper.log --errorlog-file=/var/log/clickhouse-keeper/clickhouse-keeper.err.log" + cap_add: + - SYS_PTRACE + - NET_ADMIN + - IPC_LOCK + - SYS_NICE + security_opt: + - label:disable + dns_opt: + - attempts:2 + - timeout:1 + - inet6 + - rotate + zoo3: + image: ${image:-yandex/clickhouse-integration-test} + restart: always + user: ${user:-} + volumes: + - type: bind + source: ${keeper_binary:-} + target: /usr/bin/clickhouse + - type: bind + source: ${keeper_config_dir3:-} + target: /etc/clickhouse-keeper + - type: bind + source: ${keeper_logs_dir3:-} + target: /var/log/clickhouse-keeper + - type: ${keeper_fs:-tmpfs} + source: ${keeper_db_dir3:-} + target: /var/lib/clickhouse-keeper + entrypoint: "clickhouse keeper --config=/etc/clickhouse-keeper/keeper_config3.xml --log-file=/var/log/clickhouse-keeper/clickhouse-keeper.log --errorlog-file=/var/log/clickhouse-keeper/clickhouse-keeper.err.log" + cap_add: + - SYS_PTRACE + - NET_ADMIN + - IPC_LOCK + - SYS_NICE + security_opt: + - label:disable + dns_opt: + - attempts:2 + - timeout:1 + - inet6 + - rotate diff --git a/docs/en/operations/external-authenticators/ldap.md b/docs/en/operations/external-authenticators/ldap.md index 1b65ecc968b..805d45e1b38 100644 --- a/docs/en/operations/external-authenticators/ldap.md +++ b/docs/en/operations/external-authenticators/ldap.md @@ -17,6 +17,7 @@ To define LDAP server you must add `ldap_servers` section to the `config.xml`. + localhost 636 @@ -31,6 +32,18 @@ To define LDAP server you must add `ldap_servers` section to the `config.xml`. /path/to/tls_ca_cert_dir ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:AES256-GCM-SHA384 + + + + localhost + 389 + EXAMPLE\{user_name} + + CN=Users,DC=example,DC=com + (&(objectClass=user)(sAMAccountName={user_name})) + + no + ``` @@ -43,6 +56,15 @@ Note, that you can define multiple LDAP servers inside the `ldap_servers` sectio - `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. +- `user_dn_detection` - Section with LDAP search parameters for detecting the actual user DN of the bound user. + - This is mainly used in search filters for further role mapping when the server is Active Directory. The resulting user DN will be used when replacing `{user_dn}` substrings wherever they are allowed. By default, user DN is set equal to bind DN, but once search is performed, it will be updated with to the actual detected user DN value. + - `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 the 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 the LDAP search. + - Note, that the special characters must be escaped properly in XML. - `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` — A flag to trigger the use of the secure connection to the LDAP server. @@ -107,7 +129,7 @@ Goes into `config.xml`. - + my_ldap_server @@ -122,6 +144,18 @@ Goes into `config.xml`. clickhouse_ + + + + my_ad_server + + CN=Users,DC=example,DC=com + CN + subtree + (&(objectClass=group)(member={user_dn})) + clickhouse_ + + ``` @@ -137,13 +171,13 @@ Note that `my_ldap_server` referred in the `ldap` section inside the `user_direc - 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. + - The resulting DN will be constructed by replacing all `{user_name}`, `{bind_dn}`, and `{user_dn}` substrings of the template with the actual user name, bind DN, and user 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. + - The resulting filter will be constructed by replacing all `{user_name}`, `{bind_dn}`, `{user_dn}`, and `{base_dn}` substrings of the template with the actual user name, bind DN, user 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. + - `attribute` — Attribute name whose values will be returned by the LDAP search. `cn`, by default. - `prefix` — Prefix, that will be expected to be in front of each string in the original list of strings returned by the LDAP search. The prefix will be removed from the original strings and the resulting strings will be treated as local role names. Empty by default. [Original article](https://clickhouse.tech/docs/en/operations/external-authenticators/ldap/) diff --git a/docs/en/operations/settings/merge-tree-settings.md b/docs/en/operations/settings/merge-tree-settings.md index b2470207dcc..6e3d0bc0fde 100644 --- a/docs/en/operations/settings/merge-tree-settings.md +++ b/docs/en/operations/settings/merge-tree-settings.md @@ -135,6 +135,39 @@ Default value: 604800 (1 week). Similar to [replicated_deduplication_window](#replicated-deduplication-window), `replicated_deduplication_window_seconds` specifies how long to store hash sums of blocks for insert deduplication. Hash sums older than `replicated_deduplication_window_seconds` are removed from Zookeeper, even if they are less than ` replicated_deduplication_window`. +## replicated_fetches_http_connection_timeout {#replicated_fetches_http_connection_timeout} + +HTTP connection timeout (in seconds) for part fetch requests. Inherited from default profile [http_connection_timeout](./settings.md#http_connection_timeout) if not set explicitly. + +Possible values: + +- Any positive integer. +- 0 - Use value of `http_connection_timeout`. + +Default value: 0. + +## replicated_fetches_http_send_timeout {#replicated_fetches_http_send_timeout} + +HTTP send timeout (in seconds) for part fetch requests. Inherited from default profile [http_send_timeout](./settings.md#http_send_timeout) if not set explicitly. + +Possible values: + +- Any positive integer. +- 0 - Use value of `http_send_timeout`. + +Default value: 0. + +## replicated_fetches_http_receive_timeout {#replicated_fetches_http_receive_timeout} + +HTTP receive timeout (in seconds) for fetch part requests. Inherited from default profile [http_receive_timeout](./settings.md#http_receive_timeout) if not set explicitly. + +Possible values: + +- Any positive integer. +- 0 - Use value of `http_receive_timeout`. + +Default value: 0. + ## old_parts_lifetime {#old-parts-lifetime} The time (in seconds) of storing inactive parts to protect against data loss during spontaneous server reboots. diff --git a/docs/en/operations/settings/settings.md b/docs/en/operations/settings/settings.md index b0c879af931..3c5efd79863 100644 --- a/docs/en/operations/settings/settings.md +++ b/docs/en/operations/settings/settings.md @@ -1520,8 +1520,8 @@ Do not merge aggregation states from different servers for distributed query pro Possible values: - 0 — Disabled (final query processing is done on the initiator node). -- 1 - Do not merge aggregation states from different servers for distributed query processing (query completelly processed on the shard, initiator only proxy the data). -- 2 - Same as 1 but apply `ORDER BY` and `LIMIT` on the initiator (can be used for queries with `ORDER BY` and/or `LIMIT`). +- 1 - Do not merge aggregation states from different servers for distributed query processing (query completelly processed on the shard, initiator only proxy the data), can be used in case it is for certain that there are different keys on different shards. +- 2 - Same as `1` but applies `ORDER BY` and `LIMIT` (it is not possilbe when the query processed completelly on the remote node, like for `distributed_group_by_no_merge=1`) on the initiator (can be used for queries with `ORDER BY` and/or `LIMIT`). **Example** @@ -2863,6 +2863,39 @@ Sets the interval in seconds after which periodically refreshed [live view](../. Default value: `60`. +## http_connection_timeout {#http_connection_timeout} + +HTTP connection timeout (in seconds). + +Possible values: + +- Any positive integer. +- 0 - Disabled (infinite timeout). + +Default value: 1. + +## http_send_timeout {#http_send_timeout} + +HTTP send timeout (in seconds). + +Possible values: + +- Any positive integer. +- 0 - Disabled (infinite timeout). + +Default value: 1800. + +## http_receive_timeout {#http_receive_timeout} + +HTTP receive timeout (in seconds). + +Possible values: + +- Any positive integer. +- 0 - Disabled (infinite timeout). + +Default value: 1800. + ## check_query_single_value_result {#check_query_single_value_result} Defines the level of detail for the [CHECK TABLE](../../sql-reference/statements/check-table.md#checking-mergetree-tables) query result for `MergeTree` family engines . diff --git a/docs/en/sql-reference/aggregate-functions/parametric-functions.md b/docs/en/sql-reference/aggregate-functions/parametric-functions.md index b9d504241db..0edb1601023 100644 --- a/docs/en/sql-reference/aggregate-functions/parametric-functions.md +++ b/docs/en/sql-reference/aggregate-functions/parametric-functions.md @@ -253,7 +253,7 @@ windowFunnel(window, [mode, [mode, ... ]])(timestamp, cond1, cond2, ..., condN) **Parameters** -- `window` — Length of the sliding window, it is the time interval between first condition and last condition. The unit of `window` depends on the `timestamp` itself and varies. Determined using the expression `timestamp of cond1 <= timestamp of cond2 <= ... <= timestamp of condN <= timestamp of cond1 + window`. +- `window` — Length of the sliding window, it is the time interval between the first and the last condition. The unit of `window` depends on the `timestamp` itself and varies. Determined using the expression `timestamp of cond1 <= timestamp of cond2 <= ... <= timestamp of condN <= timestamp of cond1 + window`. - `mode` — It is an optional argument. One or more modes can be set. - `'strict'` — If same condition holds for sequence of events then such non-unique events would be skipped. - `'strict_order'` — Don't allow interventions of other events. E.g. in the case of `A->B->D->C`, it stops finding `A->B->C` at the `D` and the max event level is 2. @@ -312,7 +312,7 @@ FROM GROUP BY user_id ) GROUP BY level -ORDER BY level ASC +ORDER BY level ASC; ``` Result: diff --git a/docs/en/sql-reference/functions/ip-address-functions.md b/docs/en/sql-reference/functions/ip-address-functions.md index 0b5dd7160b8..d37ef2e8f1a 100644 --- a/docs/en/sql-reference/functions/ip-address-functions.md +++ b/docs/en/sql-reference/functions/ip-address-functions.md @@ -422,7 +422,7 @@ Type: [UInt8](../../sql-reference/data-types/int-uint.md). Query: ``` sql -SELECT isIPAddressInRange('127.0.0.1', '127.0.0.0/8') +SELECT isIPAddressInRange('127.0.0.1', '127.0.0.0/8'); ``` Result: @@ -436,7 +436,7 @@ Result: Query: ``` sql -SELECT isIPAddressInRange('127.0.0.1', 'ffff::/16') +SELECT isIPAddressInRange('127.0.0.1', 'ffff::/16'); ``` Result: diff --git a/docs/en/sql-reference/functions/type-conversion-functions.md b/docs/en/sql-reference/functions/type-conversion-functions.md index d8d13d81d97..661469e6901 100644 --- a/docs/en/sql-reference/functions/type-conversion-functions.md +++ b/docs/en/sql-reference/functions/type-conversion-functions.md @@ -373,7 +373,7 @@ This function accepts a number or date or date with time, and returns a FixedStr ## reinterpretAsUUID {#reinterpretasuuid} -This function accepts 16 bytes string, and returns UUID containing bytes representing the corresponding value in network byte order (big-endian). If the string isn't long enough, the functions work as if the string is padded with the necessary number of null bytes to the end. If the string longer than 16 bytes, the extra bytes at the end are ignored. +Accepts 16 bytes string and returns UUID containing bytes representing the corresponding value in network byte order (big-endian). If the string isn't long enough, the function works as if the string is padded with the necessary number of null bytes to the end. If the string longer than 16 bytes, the extra bytes at the end are ignored. **Syntax** @@ -429,7 +429,24 @@ Result: ## reinterpret(x, T) {#type_conversion_function-reinterpret} -Use the same source in-memory bytes sequence for `x` value and reinterpret it to destination type +Uses the same source in-memory bytes sequence for `x` value and reinterprets it to destination type. + +**Syntax** + +``` sql +reinterpret(x, type) +``` + +**Arguments** + +- `x` — Any type. +- `type` — Destination type. [String](../../sql-reference/data-types/string.md). + +**Returned value** + +- Destination type value. + +**Examples** Query: ```sql @@ -448,11 +465,27 @@ Result: ## CAST(x, T) {#type_conversion_function-cast} -Converts input value `x` to the `T` data type. Unlike to `reinterpret` function use external representation of `x` value. +Converts input value `x` to the `T` data type. Unlike to `reinterpret` function, type conversion is performed in a natural way. The syntax `CAST(x AS t)` is also supported. -Note, that if value `x` does not fit the bounds of type T, the function overflows. For example, CAST(-1, 'UInt8') returns 255. +!!! note "Note" + If value `x` does not fit the bounds of type `T`, the function overflows. For example, `CAST(-1, 'UInt8')` returns `255`. + +**Syntax** + +``` sql +CAST(x, T) +``` + +**Arguments** + +- `x` — Any type. +- `T` — Destination type. [String](../../sql-reference/data-types/string.md). + +**Returned value** + +- Destination type value. **Examples** @@ -460,9 +493,9 @@ Query: ```sql SELECT - cast(toInt8(-1), 'UInt8') AS cast_int_to_uint, - cast(toInt8(1), 'Float32') AS cast_int_to_float, - cast('1', 'UInt32') AS cast_string_to_int + CAST(toInt8(-1), 'UInt8') AS cast_int_to_uint, + CAST(toInt8(1), 'Float32') AS cast_int_to_float, + CAST('1', 'UInt32') AS cast_string_to_int; ``` Result: @@ -492,7 +525,7 @@ Result: └─────────────────────┴─────────────────────┴────────────┴─────────────────────┴───────────────────────────┘ ``` -Conversion to FixedString(N) only works for arguments of type String or FixedString(N). +Conversion to FixedString(N) only works for arguments of type [String](../../sql-reference/data-types/string.md) or [FixedString](../../sql-reference/data-types/fixedstring.md). Type conversion to [Nullable](../../sql-reference/data-types/nullable.md) and back is supported. @@ -1038,7 +1071,7 @@ Result: ## parseDateTime64BestEffort {#parsedatetime64besteffort} -Same as [parseDateTimeBestEffort](#parsedatetimebesteffort) function but also parse milliseconds and microseconds and return `DateTime64(3)` or `DateTime64(6)` data types. +Same as [parseDateTimeBestEffort](#parsedatetimebesteffort) function but also parse milliseconds and microseconds and returns [DateTime](../../sql-reference/functions/type-conversion-functions.md#data_type-datetime) data type. **Syntax** @@ -1049,9 +1082,13 @@ parseDateTime64BestEffort(time_string [, precision [, time_zone]]) **Parameters** - `time_string` — String containing a date or date with time to convert. [String](../../sql-reference/data-types/string.md). -- `precision` — `3` for milliseconds, `6` for microseconds. Default `3`. Optional [UInt8](../../sql-reference/data-types/int-uint.md). +- `precision` — Required precision. `3` — for milliseconds, `6` — for microseconds. Default — `3`. Optional. [UInt8](../../sql-reference/data-types/int-uint.md). - `time_zone` — [Timezone](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](../../sql-reference/data-types/string.md). +**Returned value** + +- `time_string` converted to the [DateTime](../../sql-reference/data-types/datetime.md) data type. + **Examples** Query: @@ -1064,7 +1101,7 @@ UNION ALL SELECT parseDateTime64BestEffort('2021-01-01 01:01:00.12346',6) AS a, toTypeName(a) AS t UNION ALL SELECT parseDateTime64BestEffort('2021-01-01 01:01:00.12346',3,'Europe/Moscow') AS a, toTypeName(a) AS t -FORMAT PrettyCompactMonoBlcok +FORMAT PrettyCompactMonoBlock; ``` Result: @@ -1131,12 +1168,14 @@ Result: ## toUnixTimestamp64Nano {#tounixtimestamp64nano} -Converts a `DateTime64` to a `Int64` value with fixed sub-second precision. -Input value is scaled up or down appropriately depending on it precision. Please note that output value is a timestamp in UTC, not in timezone of `DateTime64`. +Converts a `DateTime64` to a `Int64` value with fixed sub-second precision. Input value is scaled up or down appropriately depending on it precision. + +!!! info "Note" + The output value is a timestamp in UTC, not in the timezone of `DateTime64`. **Syntax** -``` sql +```sql toUnixTimestamp64Milli(value) ``` @@ -1152,7 +1191,7 @@ toUnixTimestamp64Milli(value) Query: -``` sql +```sql WITH toDateTime64('2019-09-16 19:20:12.345678910', 6) AS dt64 SELECT toUnixTimestamp64Milli(dt64); ``` @@ -1298,4 +1337,3 @@ Result: │ 2,"good" │ └───────────────────────────────────────────┘ ``` - diff --git a/docs/en/sql-reference/statements/grant.md b/docs/en/sql-reference/statements/grant.md index 89f35b5f701..068eac1d083 100644 --- a/docs/en/sql-reference/statements/grant.md +++ b/docs/en/sql-reference/statements/grant.md @@ -316,7 +316,7 @@ Allows executing [CREATE](../../sql-reference/statements/create/index.md) and [A Allows executing [DROP](../../sql-reference/statements/misc.md#drop) and [DETACH](../../sql-reference/statements/misc.md#detach) queries according to the following hierarchy of privileges: -- `DROP`. Level: +- `DROP`. Level: `GROUP` - `DROP DATABASE`. Level: `DATABASE` - `DROP TABLE`. Level: `TABLE` - `DROP VIEW`. Level: `VIEW` diff --git a/docs/ru/engines/table-engines/integrations/hdfs.md b/docs/ru/engines/table-engines/integrations/hdfs.md index b56bbfc0788..c96ac12cd2a 100644 --- a/docs/ru/engines/table-engines/integrations/hdfs.md +++ b/docs/ru/engines/table-engines/integrations/hdfs.md @@ -183,7 +183,7 @@ CREATE TABLE big_table (name String, value UInt32) ENGINE = HDFS('hdfs://hdfs1:9 #### Ограничения {#limitations} * hadoop\_security\_kerberos\_ticket\_cache\_path могут быть определены только на глобальном уровне -## Поддержика Kerberos {#kerberos-support} +## Поддержка Kerberos {#kerberos-support} Если hadoop\_security\_authentication параметр имеет значение 'kerberos', ClickHouse аутентифицируется с помощью Kerberos. [Расширенные параметры](#clickhouse-extras) и hadoop\_security\_kerberos\_ticket\_cache\_path помогают сделать это. diff --git a/docs/ru/operations/settings/merge-tree-settings.md b/docs/ru/operations/settings/merge-tree-settings.md index f9093d379e3..e58948b0148 100644 --- a/docs/ru/operations/settings/merge-tree-settings.md +++ b/docs/ru/operations/settings/merge-tree-settings.md @@ -149,6 +149,39 @@ Eсли суммарное число активных кусков во все Стандартное значение Linux dirty_expire_centisecs - 30 секунд (максимальное время, которое записанные данные хранятся только в оперативной памяти), но при больших нагрузках на дисковую систему, данные могут быть записаны намного позже. Экспериментально было найдено время - 480 секунд, за которое гарантированно новый кусок будет записан на диск. +## replicated_fetches_http_connection_timeout {#replicated_fetches_http_connection_timeout} + +Тайм-аут HTTP-соединения (в секундах) для запросов на скачивание кусков. Наследуется из профиля по умолчанию [http_connection_timeout](./settings.md#http_connection_timeout), если не задан явно. + +Возможные значения: + +- 0 - используется значение `http_connection_timeout`. +- Любое положительное целое число. + +Значение по умолчанию: `0`. + +## replicated_fetches_http_send_timeout {#replicated_fetches_http_send_timeout} + +Тайм-аут (в секундах) для отправки HTTP-запросов на скачивание кусков. Наследуется из профиля по умолчанию [http_send_timeout](./settings.md#http_send_timeout), если не задан явно. + +Возможные значения: + +- 0 - используется значение `http_send_timeout`. +- Любое положительное целое число. + +Значение по умолчанию: `0`. + +## replicated_fetches_http_receive_timeout {#replicated_fetches_http_receive_timeout} + +Тайм-аут (в секундах) для получения HTTP-запросов на скачивание кусков. Наследуется из профиля по умолчанию [http_receive_timeout](./settings.md#http_receive_timeout), если не задан явно. + +Возможные значения: + +- 0 - используется значение `http_receive_timeout`. +- Любое положительное целое число. + +Значение по умолчанию: `0`. + ## max_bytes_to_merge_at_max_space_in_pool {#max-bytes-to-merge-at-max-space-in-pool} Максимальный суммарный размер кусков (в байтах) в одном слиянии, при наличии свободных ресурсов в фоновом пуле. diff --git a/docs/ru/operations/settings/settings.md b/docs/ru/operations/settings/settings.md index 3c72a8c9f54..45def8c4b50 100644 --- a/docs/ru/operations/settings/settings.md +++ b/docs/ru/operations/settings/settings.md @@ -2857,5 +2857,37 @@ SELECT * FROM test LIMIT 10 OFFSET 100; │ 109 │ └─────┘ ``` +## http_connection_timeout {#http_connection_timeout} + +Тайм-аут для HTTP-соединения (в секундах). + +Возможные значения: + +- 0 - бесконечный тайм-аут. +- Любое положительное целое число. + +Значение по умолчанию: `1`. + +## http_send_timeout {#http_send_timeout} + +Тайм-аут для отправки данных через HTTP-интерфейс (в секундах). + +Возможные значения: + +- 0 - бесконечный тайм-аут. +- Любое положительное целое число. + +Значение по умолчанию: `1800`. + +## http_receive_timeout {#http_receive_timeout} + +Тайм-аут для получения данных через HTTP-интерфейс (в секундах). + +Возможные значения: + +- 0 - бесконечный тайм-аут. +- Любое положительное целое число. + +Значение по умолчанию: `1800`. [Оригинальная статья](https://clickhouse.tech/docs/ru/operations/settings/settings/) diff --git a/docs/ru/sql-reference/aggregate-functions/parametric-functions.md b/docs/ru/sql-reference/aggregate-functions/parametric-functions.md index e5162b63b88..508c8de2a58 100644 --- a/docs/ru/sql-reference/aggregate-functions/parametric-functions.md +++ b/docs/ru/sql-reference/aggregate-functions/parametric-functions.md @@ -253,7 +253,7 @@ windowFunnel(window, [mode, [mode, ... ]])(timestamp, cond1, cond2, ..., condN) **Параметры** -- `window` — ширина скользящего окна по времени. Единица измерения зависит от `timestamp` и может варьироваться. Должно соблюдаться условие `timestamp события cond2 <= timestamp события cond1 + window`. +- `window` — ширина скользящего окна по времени. Это время между первым и последним условием. Единица измерения зависит от `timestamp` и может варьироваться. Должно соблюдаться условие `timestamp события cond1 <= timestamp события cond2 <= ... <= timestamp события condN <= timestamp события cond1 + window`. - `mode` — необязательный параметр. Может быть установленно несколько значений одновременно. - `'strict'` — не учитывать подряд идущие повторяющиеся события. - `'strict_order'` — запрещает посторонние события в искомой последовательности. Например, при поиске цепочки `A->B->C` в `A->B->D->C` поиск будет остановлен на `D` и функция вернет 2. @@ -311,7 +311,7 @@ FROM GROUP BY user_id ) GROUP BY level -ORDER BY level ASC +ORDER BY level ASC; ``` ## retention {#retention} diff --git a/docs/ru/sql-reference/functions/ip-address-functions.md b/docs/ru/sql-reference/functions/ip-address-functions.md index d7f6d2f7618..b02d45d7667 100644 --- a/docs/ru/sql-reference/functions/ip-address-functions.md +++ b/docs/ru/sql-reference/functions/ip-address-functions.md @@ -397,9 +397,9 @@ SELECT addr, isIPv6String(addr) FROM ( SELECT ['::', '1111::ffff', '::ffff:127.0 ## isIPAddressInRange {#isipaddressinrange} -Проверяет попадает ли IP адрес в интервал, заданный в [CIDR](https://en.wikipedia.org/wiki/Classless_Inter-Domain_Routing) нотации. +Проверяет, попадает ли IP адрес в интервал, заданный в нотации [CIDR](https://en.wikipedia.org/wiki/Classless_Inter-Domain_Routing). -**Syntax** +**Синтаксис** ``` sql isIPAddressInRange(address, prefix) @@ -409,7 +409,7 @@ isIPAddressInRange(address, prefix) **Аргументы** - `address` — IPv4 или IPv6 адрес. [String](../../sql-reference/data-types/string.md). -- `prefix` — IPv4 или IPv6 подсеть, заданная в CIDR нотации. [String](../../sql-reference/data-types/string.md). +- `prefix` — IPv4 или IPv6 подсеть, заданная в нотации CIDR. [String](../../sql-reference/data-types/string.md). **Возвращаемое значение** @@ -422,7 +422,7 @@ isIPAddressInRange(address, prefix) Запрос: ``` sql -SELECT isIPAddressInRange('127.0.0.1', '127.0.0.0/8') +SELECT isIPAddressInRange('127.0.0.1', '127.0.0.0/8'); ``` Результат: @@ -436,7 +436,7 @@ SELECT isIPAddressInRange('127.0.0.1', '127.0.0.0/8') Запрос: ``` sql -SELECT isIPAddressInRange('127.0.0.1', 'ffff::/16') +SELECT isIPAddressInRange('127.0.0.1', 'ffff::/16'); ``` Результат: diff --git a/docs/ru/sql-reference/functions/type-conversion-functions.md b/docs/ru/sql-reference/functions/type-conversion-functions.md index fc1dd15f8e3..2226c90525d 100644 --- a/docs/ru/sql-reference/functions/type-conversion-functions.md +++ b/docs/ru/sql-reference/functions/type-conversion-functions.md @@ -369,7 +369,7 @@ SELECT toFixedString('foo\0bar', 8) AS s, toStringCutToZero(s) AS s_cut; ## reinterpretAsUUID {#reinterpretasuuid} -Функция принимает шестнадцатибайтную строку и интерпретирует ее байты в network order (big-endian). Если строка имеет недостаточную длину, то функция работает так, как будто строка дополнена необходимым количетсвом нулевых байт с конца. Если строка длиннее, чем шестнадцать байт, то игнорируются лишние байты с конца. +Функция принимает строку из 16 байт и интерпретирует ее байты в порядок от старшего к младшему. Если строка имеет недостаточную длину, то функция работает так, как будто строка дополнена необходимым количеством нулевых байтов с конца. Если строка длиннее, чем 16 байтов, то лишние байты с конца игнорируются. **Синтаксис** @@ -425,9 +425,27 @@ SELECT uuid = uuid2; ## reinterpret(x, T) {#type_conversion_function-reinterpret} -Использует туже самую исходную последовательность байт в памяти для значения `x` и переинтерпретирует ее как конечный тип данных +Использует ту же самую исходную последовательность байтов в памяти для значения `x` и интерпретирует ее как конечный тип данных `T`. + +**Синтаксис** + +``` sql +reinterpret(x, type) +``` + +**Аргументы** + +- `x` — любой тип данных. +- `type` — конечный тип данных. [String](../../sql-reference/data-types/string.md). + +**Возвращаемое значение** + +- Значение конечного типа данных. + +**Примеры** Запрос: + ```sql SELECT reinterpret(toInt8(-1), 'UInt8') as int_to_uint, reinterpret(toInt8(1), 'Float32') as int_to_float, @@ -448,7 +466,23 @@ SELECT reinterpret(toInt8(-1), 'UInt8') as int_to_uint, Поддерживается также синтаксис `CAST(x AS t)`. -Обратите внимание, что если значение `x` не может быть преобразовано к типу `T`, возникает переполнение. Например, `CAST(-1, 'UInt8')` возвращает 255. +!!! warning "Предупреждение" + Если значение `x` не может быть преобразовано к типу `T`, возникает переполнение. Например, `CAST(-1, 'UInt8')` возвращает 255. + +**Синтаксис** + +``` sql +CAST(x, T) +``` + +**Аргументы** + +- `x` — любой тип данных. +- `T` — конечный тип данных. [String](../../sql-reference/data-types/string.md). + +**Возвращаемое значение** + +- Значение конечного типа данных. **Примеры** @@ -456,9 +490,9 @@ SELECT reinterpret(toInt8(-1), 'UInt8') as int_to_uint, ```sql SELECT - cast(toInt8(-1), 'UInt8') AS cast_int_to_uint, - cast(toInt8(1), 'Float32') AS cast_int_to_float, - cast('1', 'UInt32') AS cast_string_to_int + CAST(toInt8(-1), 'UInt8') AS cast_int_to_uint, + CAST(toInt8(1), 'Float32') AS cast_int_to_float, + CAST('1', 'UInt32') AS cast_string_to_int ``` Результат: @@ -488,9 +522,9 @@ SELECT └─────────────────────┴─────────────────────┴────────────┴─────────────────────┴───────────────────────────┘ ``` -Преобразование в FixedString(N) работает только для аргументов типа String или FixedString(N). +Преобразование в FixedString(N) работает только для аргументов типа [String](../../sql-reference/data-types/string.md) или [FixedString](../../sql-reference/data-types/fixedstring.md). -Поддержано преобразование к типу [Nullable](../../sql-reference/functions/type-conversion-functions.md) и обратно. +Поддерживается преобразование к типу [Nullable](../../sql-reference/functions/type-conversion-functions.md) и обратно. **Примеры** @@ -860,7 +894,7 @@ AS parseDateTimeBestEffortUS; ## parseDateTimeBestEffortOrZero {#parsedatetimebesteffortorzero} ## parseDateTime32BestEffortOrZero {#parsedatetime32besteffortorzero} -Работает также как [parseDateTimeBestEffort](#parsedatetimebesteffort), но возвращает нулевую дату или нулевую дату и время когда получает формат даты который не может быть обработан. +Работает аналогично функции [parseDateTimeBestEffort](#parsedatetimebesteffort), но возвращает нулевое значение, если формат даты не может быть обработан. ## parseDateTimeBestEffortUSOrNull {#parsedatetimebesteffortusornull} @@ -1036,19 +1070,23 @@ SELECT parseDateTimeBestEffortUSOrZero('02.2021') AS parseDateTimeBestEffortUSOr ## parseDateTime64BestEffort {#parsedatetime64besteffort} -Работает также как функция [parseDateTimeBestEffort](#parsedatetimebesteffort) но также понимамет милисекунды и микросекунды и возвращает `DateTime64(3)` или `DateTime64(6)` типы данных в зависимости от заданной точности. +Работает аналогично функции [parseDateTimeBestEffort](#parsedatetimebesteffort), но также принимает миллисекунды и микросекунды. Возвращает тип данных [DateTime](../../sql-reference/functions/type-conversion-functions.md#data_type-datetime). -**Syntax** +**Синтаксис** ``` sql parseDateTime64BestEffort(time_string [, precision [, time_zone]]) ``` -**Parameters** +**Аргументы** -- `time_string` — String containing a date or date with time to convert. [String](../../sql-reference/data-types/string.md). -- `precision` — `3` for milliseconds, `6` for microseconds. Default `3`. Optional [UInt8](../../sql-reference/data-types/int-uint.md). -- `time_zone` — [Timezone](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone). The function parses `time_string` according to the timezone. Optional. [String](../../sql-reference/data-types/string.md). +- `time_string` — строка, содержащая дату или дату со временем, которые нужно преобразовать. [String](../../sql-reference/data-types/string.md). +- `precision` — требуемая точность: `3` — для миллисекунд, `6` — для микросекунд. По умолчанию — `3`. Необязательный. [UInt8](../../sql-reference/data-types/int-uint.md). +- `time_zone` — [Timezone](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone). Разбирает значение `time_string` в зависимости от часового пояса. Необязательный. [String](../../sql-reference/data-types/string.md). + +**Возвращаемое значение** + +- `time_string`, преобразованная в тип данных [DateTime](../../sql-reference/data-types/datetime.md). **Примеры** @@ -1062,7 +1100,7 @@ UNION ALL SELECT parseDateTime64BestEffort('2021-01-01 01:01:00.12346',6) AS a, toTypeName(a) AS t UNION ALL SELECT parseDateTime64BestEffort('2021-01-01 01:01:00.12346',3,'Europe/Moscow') AS a, toTypeName(a) AS t -FORMAT PrettyCompactMonoBlcok +FORMAT PrettyCompactMonoBlock; ``` Результат: @@ -1078,12 +1116,11 @@ FORMAT PrettyCompactMonoBlcok ## parseDateTime64BestEffortOrNull {#parsedatetime32besteffortornull} -Работает также как функция [parseDateTime64BestEffort](#parsedatetime64besteffort) но возвращает `NULL` когда встречает формат даты который не может обработать. +Работает аналогично функции [parseDateTime64BestEffort](#parsedatetime64besteffort), но возвращает `NULL`, если формат даты не может быть обработан. ## parseDateTime64BestEffortOrZero {#parsedatetime64besteffortorzero} -Работает также как функция [parseDateTime64BestEffort](#parsedatetimebesteffort) но возвращает "нулевую" дату и время когда встречает формат даты который не может обработать. - +Работает аналогично функции [parseDateTime64BestEffort](#parsedatetimebesteffort), но возвращает нулевую дату и время, если формат даты не может быть обработан. ## toLowCardinality {#tolowcardinality} @@ -1130,11 +1167,14 @@ SELECT toLowCardinality('1'); ## toUnixTimestamp64Nano {#tounixtimestamp64nano} Преобразует значение `DateTime64` в значение `Int64` с фиксированной точностью менее одной секунды. -Входное значение округляется соответствующим образом вверх или вниз в зависимости от его точности. Обратите внимание, что возвращаемое значение - это временная метка в UTC, а не в часовом поясе `DateTime64`. +Входное значение округляется соответствующим образом вверх или вниз в зависимости от его точности. + +!!! info "Примечание" + Возвращаемое значение — это временная метка в UTC, а не в часовом поясе `DateTime64`. **Синтаксис** -``` sql +```sql toUnixTimestamp64Milli(value) ``` @@ -1150,7 +1190,7 @@ toUnixTimestamp64Milli(value) Запрос: -``` sql +```sql WITH toDateTime64('2019-09-16 19:20:12.345678910', 6) AS dt64 SELECT toUnixTimestamp64Milli(dt64); ``` @@ -1296,4 +1336,3 @@ FROM numbers(3); │ 2,"good" │ └───────────────────────────────────────────┘ ``` - diff --git a/docs/tools/README.md b/docs/tools/README.md index 0a6c41d8089..4340561fa57 100644 --- a/docs/tools/README.md +++ b/docs/tools/README.md @@ -51,5 +51,5 @@ The easiest way to see the result is to use `--livereload=8888` argument of buil At the moment there’s no easy way to do just that, but you can consider: -- To hit the “Watch” button on top of GitHub web interface to know as early as possible, even during pull request. Alternative to this is `#github-activity` channel of [public ClickHouse Slack](https://join.slack.com/t/clickhousedb/shared_invite/zt-nwwakmk4-xOJ6cdy0sJC3It8j348~IA). +- To hit the “Watch” button on top of GitHub web interface to know as early as possible, even during pull request. Alternative to this is `#github-activity` channel of [public ClickHouse Slack](https://join.slack.com/t/clickhousedb/shared_invite/zt-qfort0u8-TWqK4wIP0YSdoDE0btKa1w). - Some search engines allow to subscribe on specific website changes via email and you can opt-in for that for https://clickhouse.tech. diff --git a/docs/tools/website.py b/docs/tools/website.py index 6927fbd87bb..f0346de5c94 100644 --- a/docs/tools/website.py +++ b/docs/tools/website.py @@ -155,10 +155,6 @@ def build_website(args): os.path.join(args.src_dir, 'utils', 'list-versions', 'version_date.tsv'), os.path.join(args.output_dir, 'data', 'version_date.tsv')) - shutil.copy2( - os.path.join(args.website_dir, 'js', 'embedd.min.js'), - os.path.join(args.output_dir, 'js', 'embedd.min.js')) - for root, _, filenames in os.walk(args.output_dir): for filename in filenames: if filename == 'main.html': diff --git a/docs/zh/engines/table-engines/integrations/odbc.md b/docs/zh/engines/table-engines/integrations/odbc.md index 1264efeaa41..767c32cc438 100644 --- a/docs/zh/engines/table-engines/integrations/odbc.md +++ b/docs/zh/engines/table-engines/integrations/odbc.md @@ -7,11 +7,11 @@ toc_title: ODBC # ODBC {#table-engine-odbc} -允许ClickHouse通过以下方式连接到外部数据库 [ODBC](https://en.wikipedia.org/wiki/Open_Database_Connectivity). +允许ClickHouse通过[ODBC](https://en.wikipedia.org/wiki/Open_Database_Connectivity)方式连接到外部数据库. -为了安全地实现ODBC连接，ClickHouse使用单独的程序 `clickhouse-odbc-bridge`. 如果直接从ODBC驱动程序加载 `clickhouse-server`，驱动程序问题可能会导致ClickHouse服务器崩溃。 ClickHouse自动启动 `clickhouse-odbc-bridge` 当它是必需的。 ODBC桥程序是从相同的软件包作为安装 `clickhouse-server`. +为了安全地实现ODBC连接，ClickHouse使用了一个独立程序 `clickhouse-odbc-bridge`. 如果ODBC驱动程序是直接从 `clickhouse-server`中加载的，那么驱动问题可能会导致ClickHouse服务崩溃。 当有需要时，ClickHouse会自动启动 `clickhouse-odbc-bridge`。 ODBC桥梁程序与`clickhouse-server`来自相同的安装包. -该引擎支持 [可为空](../../../sql-reference/data-types/nullable.md) 数据类型。 +该引擎支持 [可为空](../../../sql-reference/data-types/nullable.md) 的数据类型。 ## 创建表 {#creating-a-table} @@ -25,14 +25,14 @@ CREATE TABLE [IF NOT EXISTS] [db.]table_name [ON CLUSTER cluster] ENGINE = ODBC(connection_settings, external_database, external_table) ``` -请参阅的详细说明 [CREATE TABLE](../../../sql-reference/statements/create.md#create-table-query) 查询。 +详情请见 [CREATE TABLE](../../../sql-reference/statements/create.md#create-table-query) 查询。 表结构可以与源表结构不同: - 列名应与源表中的列名相同，但您可以按任何顺序使用其中的一些列。 -- 列类型可能与源表中的列类型不同。 ClickHouse尝试 [投](../../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast) ClickHouse数据类型的值。 +- 列类型可能与源表中的列类型不同。 ClickHouse尝试将数值[映射](../../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast) 到ClickHouse的数据类型。 -**发动机参数** +**引擎参数** - `connection_settings` — Name of the section with connection settings in the `odbc.ini` 文件 - `external_database` — Name of a database in an external DBMS. @@ -40,13 +40,13 @@ ENGINE = ODBC(connection_settings, external_database, external_table) ## 用法示例 {#usage-example} -**通过ODBC从本地MySQL安装中检索数据** +**通过ODBC从本地安装的MySQL中检索数据** -此示例检查Ubuntu Linux18.04和MySQL服务器5.7。 +本示例针对Ubuntu Linux18.04和MySQL服务器5.7进行检查。 -确保安装了unixODBC和MySQL连接器。 +请确保安装了unixODBC和MySQL连接器。 -默认情况下（如果从软件包安装），ClickHouse以用户身份启动 `clickhouse`. 因此，您需要在MySQL服务器中创建和配置此用户。 +默认情况下（如果从软件包安装），ClickHouse以用户`clickhouse`的身份启动 . 因此，您需要在MySQL服务器中创建和配置此用户。 ``` bash $ sudo mysql @@ -57,7 +57,7 @@ mysql> CREATE USER 'clickhouse'@'localhost' IDENTIFIED BY 'clickhouse'; mysql> GRANT ALL PRIVILEGES ON *.* TO 'clickhouse'@'clickhouse' WITH GRANT OPTION; ``` -然后配置连接 `/etc/odbc.ini`. +然后在`/etc/odbc.ini`中配置连接 . ``` bash $ cat /etc/odbc.ini @@ -70,7 +70,7 @@ USERNAME = clickhouse PASSWORD = clickhouse ``` -您可以使用 `isql` unixodbc安装中的实用程序。 +您可以从安装的unixodbc中使用 `isql` 实用程序来检查连接情况。 ``` bash $ isql -v mysqlconn diff --git a/docs/zh/operations/backup.md b/docs/zh/operations/backup.md index 1b1993e3ae6..6d517e6ccb3 100644 --- a/docs/zh/operations/backup.md +++ b/docs/zh/operations/backup.md @@ -7,37 +7,37 @@ toc_title: "\u6570\u636E\u5907\u4EFD" # 数据备份 {#data-backup} -尽管[副本](../engines/table-engines/mergetree-family/replication.md) 可以预防硬件错误带来的数据丢失, 但是它不能防止人为操作的错误: 意外删除数据, 删除错误的 table 或者删除错误 cluster 上的 table, 可以导致错误数据处理错误或者数据损坏的 bugs. 这类意外可能会影响所有的副本. ClickHouse 有内建的保障措施可以预防一些错误 — 例如, 默认情况下[您不能使用类似MergeTree的引擎删除包含超过50Gb数据的表](server-configuration-parameters/settings.md#max-table-size-to-drop). 但是，这些保障措施不能涵盖所有可能的情况，并且可以规避。 +尽管 [副本] (../engines/table-engines/mergetree-family/replication.md) 可以提供针对硬件的错误防护, 但是它不能预防人为操作失误: 数据的意外删除, 错误表的删除或者错误集群上表的删除, 以及导致错误数据处理或者数据损坏的软件bug. 在很多案例中，这类意外可能会影响所有的副本. ClickHouse 有内置的保护措施可以预防一些错误 — 例如, 默认情况下 [不能人工删除使用带有MergeTree引擎且包含超过50Gb数据的表] (server-configuration-parameters/settings.md#max-table-size-to-drop). 但是，这些保护措施不能覆盖所有可能情况，并且这些措施可以被绕过。 -为了有效地减少可能的人为错误，您应该 **提前**准备备份和还原数据的策略. +为了有效地减少可能的人为错误，您应该 **提前** 仔细的准备备份和数据还原的策略. -不同公司有不同的可用资源和业务需求，因此没有适合各种情况的ClickHouse备份和恢复通用解决方案。 适用于 1GB 的数据的方案可能并不适用于几十 PB 数据的情况。 有多种可能的并有自己优缺点的方法，这将在下面讨论。 好的主意是同时结合使用多种方法而不是仅使用一种，这样可以弥补不同方法各自的缺点。 +不同公司有不同的可用资源和业务需求，因此不存在一个通用的解决方案可以应对各种情况下的ClickHouse备份和恢复。 适用于 1GB 数据的方案可能并不适用于几十 PB 数据的情况。 有多种具备各自优缺点的可能方法，将在下面对其进行讨论。最好使用几种方法而不是仅仅使用一种方法来弥补它们的各种缺点。。 !!! note "注" - 请记住，如果您备份了某些内容并且从未尝试过还原它，那么当您实际需要它时（或者至少需要比业务能够容忍的时间更长），恢复可能无法正常工作。 因此，无论您选择哪种备份方法，请确保自动还原过程，并定期在备用ClickHouse群集上练习。 + 需要注意的是，如果您备份了某些内容并且从未尝试过还原它，那么当您实际需要它时可能无法正常恢复（或者至少需要的时间比业务能够容忍的时间更长）。 因此，无论您选择哪种备份方法，请确保自动还原过程，并定期在备用ClickHouse群集上演练。 -## 将源数据复制到其他地方 {#duplicating-source-data-somewhere-else} +## 将源数据复制到其它地方 {#duplicating-source-data-somewhere-else} -通常被聚集到ClickHouse的数据是通过某种持久队列传递的，例如 [Apache Kafka](https://kafka.apache.org). 在这种情况下，可以配置一组额外的订阅服务器，这些订阅服务器将在写入ClickHouse时读取相同的数据流，并将其存储在冷存储中。 大多数公司已经有一些默认的推荐冷存储，可能是对象存储或分布式文件系统，如 [HDFS](https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html). +通常摄入到ClickHouse的数据是通过某种持久队列传递的，例如 [Apache Kafka] (https://kafka.apache.org). 在这种情况下，可以配置一组额外的订阅服务器，这些订阅服务器将在写入ClickHouse时读取相同的数据流，并将其存储在冷存储中。 大多数公司已经有一些默认推荐的冷存储，可能是对象存储或分布式文件系统，如 [HDFS] (https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html). ## 文件系统快照 {#filesystem-snapshots} -某些本地文件系统提供快照功能（例如, [ZFS](https://en.wikipedia.org/wiki/ZFS)），但它们可能不是提供实时查询的最佳选择。 一个可能的解决方案是使用这种文件系统创建额外的副本，并将它们从 [分布](../engines/table-engines/special/distributed.md) 用于以下目的的表 `SELECT` 查询。 任何修改数据的查询都无法访问此类副本上的快照。 作为奖励，这些副本可能具有特殊的硬件配置，每个服务器附加更多的磁盘，这将是经济高效的。 +某些本地文件系统提供快照功能（例如, [ZFS] (https://en.wikipedia.org/wiki/ZFS)），但它们可能不是提供实时查询的最佳选择。 一个可能的解决方案是使用这种文件系统创建额外的副本，并将它们与用于`SELECT` 查询的 [分布式] (../engines/table-engines/special/distributed.md) 表分离。 任何修改数据的查询都无法访问此类副本上的快照。 作为回报，这些副本可能具有特殊的硬件配置，每个服务器附加更多的磁盘，这将是经济高效的。 ## clickhouse-copier {#clickhouse-copier} -[clickhouse-copier](utilities/clickhouse-copier.md) 是一个多功能工具，最初创建用于重新分片pb大小的表。 因为它可以在ClickHouse表和集群之间可靠地复制数据，所以它还可用于备份和还原数据。 +[clickhouse-copier] (utilities/clickhouse-copier.md) 是一个多功能工具，最初创建它是为了用于重新切分pb大小的表。 因为它能够在ClickHouse表和集群之间可靠地复制数据，所以它也可用于备份和还原数据。 对于较小的数据量，一个简单的 `INSERT INTO ... SELECT ...` 到远程表也可以工作。 -## 部件操作 {#manipulations-with-parts} +## part操作 {#manipulations-with-parts} -ClickHouse允许使用 `ALTER TABLE ... FREEZE PARTITION ...` 查询以创建表分区的本地副本。 这是利用硬链接(hardlink)到 `/var/lib/clickhouse/shadow/` 文件夹中实现的，所以它通常不会占用旧数据的额外磁盘空间。 创建的文件副本不由ClickHouse服务器处理，所以你可以把它们留在那里：你将有一个简单的备份，不需要任何额外的外部系统，但它仍然会容易出现硬件问题。 出于这个原因，最好将它们远程复制到另一个位置，然后删除本地副本。 分布式文件系统和对象存储仍然是一个不错的选择，但是具有足够大容量的正常附加文件服务器也可以工作（在这种情况下，传输将通过网络文件系统 [rsync](https://en.wikipedia.org/wiki/Rsync)). +ClickHouse允许使用 `ALTER TABLE ... FREEZE PARTITION ...` 查询以创建表分区的本地副本。 这是利用硬链接(hardlink)到 `/var/lib/clickhouse/shadow/` 文件夹中实现的，所以它通常不会因为旧数据而占用额外的磁盘空间。 创建的文件副本不由ClickHouse服务器处理，所以你可以把它们留在那里：你将有一个简单的备份，不需要任何额外的外部系统，但它仍然容易出现硬件问题。 出于这个原因，最好将它们远程复制到另一个位置，然后删除本地副本。 分布式文件系统和对象存储仍然是一个不错的选择，但是具有足够大容量的正常附加文件服务器也可以工作（在这种情况下，传输将通过网络文件系统或者也许是 [rsync] (https://en.wikipedia.org/wiki/Rsync) 来进行). 数据可以使用 `ALTER TABLE ... ATTACH PARTITION ...` 从备份中恢复。 -有关与分区操作相关的查询的详细信息，请参阅 [更改文档](../sql-reference/statements/alter.md#alter_manipulations-with-partitions). +有关与分区操作相关的查询的详细信息，请参阅 [更改文档] (../sql-reference/statements/alter.md#alter_manipulations-with-partitions). -第三方工具可用于自动化此方法: [clickhouse-backup](https://github.com/AlexAkulov/clickhouse-backup). +第三方工具可用于自动化此方法: [clickhouse-backup] (https://github.com/AlexAkulov/clickhouse-backup). -[原始文章](https://clickhouse.tech/docs/en/operations/backup/) +[原始文章] (https://clickhouse.tech/docs/en/operations/backup/) diff --git a/docs/zh/operations/system-tables/data_type_families.md b/docs/zh/operations/system-tables/data_type_families.md index 21eb4785e23..db08ff0371b 100644 --- a/docs/zh/operations/system-tables/data_type_families.md +++ b/docs/zh/operations/system-tables/data_type_families.md @@ -5,13 +5,13 @@ machine_translated_rev: 5decc73b5dc60054f19087d3690c4eb99446a6c3 # 系统。data_type_families {#system_tables-data_type_families} -包含有关受支持的信息 [数据类型](../../sql-reference/data-types/). +包含有关受支持的[数据类型](../../sql-reference/data-types/)的信息. -列: +列字段包括: -- `name` ([字符串](../../sql-reference/data-types/string.md)) — Data type name. -- `case_insensitive` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Property that shows whether you can use a data type name in a query in case insensitive manner or not. For example, `Date` 和 `date` 都是有效的。 -- `alias_to` ([字符串](../../sql-reference/data-types/string.md)) — Data type name for which `name` 是个化名 +- `name` ([String](../../sql-reference/data-types/string.md)) — 数据类型的名称. +- `case_insensitive` ([UInt8](../../sql-reference/data-types/int-uint.md)) — 该属性显示是否可以在查询中以不区分大小写的方式使用数据类型名称。例如 `Date` 和 `date` 都是有效的。 +- `alias_to` ([String](../../sql-reference/data-types/string.md)) — 名称为别名的数据类型名称。 **示例** @@ -36,4 +36,4 @@ SELECT * FROM system.data_type_families WHERE alias_to = 'String' **另请参阅** -- [语法](../../sql-reference/syntax.md) — Information about supported syntax. +- [Syntax](../../sql-reference/syntax.md) — 关于所支持的语法信息. diff --git a/docs/zh/operations/system-tables/index.md b/docs/zh/operations/system-tables/index.md index 56067bc5057..0e5778e3051 100644 --- a/docs/zh/operations/system-tables/index.md +++ b/docs/zh/operations/system-tables/index.md @@ -7,33 +7,33 @@ toc_title: "\u7CFB\u7EDF\u8868" # 系统表 {#system-tables} -## 导言 {#system-tables-introduction} +## 引言 {#system-tables-introduction} -系统表提供以下信息: +系统表提供的信息如下: -- 服务器状态、进程和环境。 +- 服务器的状态、进程以及环境。 - 服务器的内部进程。 系统表: -- 坐落于 `system` 数据库。 -- 仅适用于读取数据。 -- 不能删除或更改，但可以分离。 +- 存储于 `system` 数据库。 +- 仅提供数据读取功能。 +- 不能被删除或更改，但可以对其进行分离(detach)操作。 -大多数系统表将数据存储在RAM中。 ClickHouse服务器在开始时创建此类系统表。 +大多数系统表将其数据存储在RAM中。 一个ClickHouse服务在刚启动时便会创建此类系统表。 -与其他系统表不同，系统日志表 [metric_log](../../operations/system-tables/metric_log.md#system_tables-metric_log), [query_log](../../operations/system-tables/query_log.md#system_tables-query_log), [query_thread_log](../../operations/system-tables/query_thread_log.md#system_tables-query_thread_log), [trace_log](../../operations/system-tables/trace_log.md#system_tables-trace_log), [part_log](../../operations/system-tables/part_log.md#system.part_log), crash_log and text_log 默认采用[MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 引擎并将其数据存储在存储文件系统中。 如果从文件系统中删除表，ClickHouse服务器会在下一次写入数据时再次创建空表。 如果系统表架构在新版本中发生更改，则ClickHouse会重命名当前表并创建一个新表。 +不同于其他系统表，系统日志表 [metric_log](../../operations/system-tables/metric_log.md#system_tables-metric_log), [query_log](../../operations/system-tables/query_log.md#system_tables-query_log), [query_thread_log](../../operations/system-tables/query_thread_log.md#system_tables-query_thread_log), [trace_log](../../operations/system-tables/trace_log.md#system_tables-trace_log), [part_log](../../operations/system-tables/part_log.md#system.part_log), crash_log and text_log 默认采用[MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) 引擎并将其数据存储在文件系统中。 如果人为的从文件系统中删除表，ClickHouse服务器会在下一次进行数据写入时再次创建空表。 如果系统表结构在新版本中发生更改，那么ClickHouse会重命名当前表并创建一个新表。 -用户可以通过在`/etc/clickhouse-server/config.d/`下创建与系统表同名的配置文件, 或者在`/etc/clickhouse-server/config.xml`中设置相应配置项，来自定义系统日志表的结构。可以自定义的配置项如下: +用户可以通过在`/etc/clickhouse-server/config.d/`下创建与系统表同名的配置文件, 或者在`/etc/clickhouse-server/config.xml`中设置相应配置项，来自定义系统日志表的结构。可供自定义的配置项如下: -- `database`: 系统日志表所在的数据库。这个选项目前已经废弃。所有的系统日表都位于`system`库中。 -- `table`: 系统日志表名。 +- `database`: 系统日志表所在的数据库。这个选项目前已经不推荐使用。所有的系统日表都位于`system`库中。 +- `table`: 接收数据写入的系统日志表。 - `partition_by`: 指定[PARTITION BY](../../engines/table-engines/mergetree-family/custom-partitioning-key.md)表达式。 - `ttl`: 指定系统日志表TTL选项。 -- `flush_interval_milliseconds`: 指定系统日志表数据落盘时间。 -- `engine`: 指定完整的表引擎定义。(以`ENGINE = `开始)。 这个选项与`partition_by`以及`ttl`冲突。如果两者一起设置，服务启动时会抛出异常并且退出。 +- `flush_interval_milliseconds`: 指定日志表数据刷新到磁盘的时间间隔。 +- `engine`: 指定完整的表引擎定义。(以`ENGINE = `开头)。 这个选项与`partition_by`以及`ttl`冲突。如果与两者一起设置，服务启动时会抛出异常并且退出。 -一个配置定义的例子如下： +配置定义的示例如下： ``` @@ -50,20 +50,20 @@ toc_title: "\u7CFB\u7EDF\u8868" ``` -默认情况下，表增长是无限的。 要控制表的大小，可以使用 TTL 删除过期日志记录的设置。 你也可以使用分区功能 `MergeTree`-发动机表。 +默认情况下，表增长是无限的。可以通过TTL 删除过期日志记录的设置来控制表的大小。 你也可以使用分区功能 `MergeTree`-引擎表。 ## 系统指标的来源 {#system-tables-sources-of-system-metrics} 用于收集ClickHouse服务器使用的系统指标: - `CAP_NET_ADMIN` 能力。 -- [procfs](https://en.wikipedia.org/wiki/Procfs) （仅在Linux中）。 +- [procfs](https://en.wikipedia.org/wiki/Procfs) （仅限于Linux）。 **procfs** -如果ClickHouse服务器没有 `CAP_NET_ADMIN` 能力，它试图回落到 `ProcfsMetricsProvider`. `ProcfsMetricsProvider` 允许收集每个查询系统指标（用于CPU和I/O）。 +如果ClickHouse服务器没有 `CAP_NET_ADMIN` 能力，那么它将试图退回到 `ProcfsMetricsProvider`. `ProcfsMetricsProvider` 允许收集每个查询系统指标（包括CPU和I/O）。 -如果系统上支持并启用procfs，ClickHouse server将收集这些指标: +如果系统上支持并启用procfs，ClickHouse server将收集如下指标: - `OSCPUVirtualTimeMicroseconds` - `OSCPUWaitMicroseconds` diff --git a/docs/zh/sql-reference/data-types/special-data-types/interval.md b/docs/zh/sql-reference/data-types/special-data-types/interval.md index df2ce097df0..9df25e3f555 100644 --- a/docs/zh/sql-reference/data-types/special-data-types/interval.md +++ b/docs/zh/sql-reference/data-types/special-data-types/interval.md @@ -5,9 +5,9 @@ toc_priority: 61 toc_title: "\u95F4\u9694" --- -# 间隔 {#data-type-interval} +# Interval类型 {#data-type-interval} -表示时间和日期间隔的数据类型族。 由此产生的类型 [INTERVAL](../../../sql-reference/operators/index.md#operator-interval) 接线员 +表示时间和日期间隔的数据类型家族。 [INTERVAL](../../../sql-reference/operators/index.md#operator-interval) 运算的结果类型。 !!! warning "警告" `Interval` 数据类型值不能存储在表中。 @@ -15,7 +15,7 @@ toc_title: "\u95F4\u9694" 结构: - 时间间隔作为无符号整数值。 -- 间隔的类型。 +- 时间间隔的类型。 支持的时间间隔类型: @@ -28,7 +28,7 @@ toc_title: "\u95F4\u9694" - `QUARTER` - `YEAR` -对于每个间隔类型，都有一个单独的数据类型。 例如， `DAY` 间隔对应于 `IntervalDay` 数据类型: +对于每个时间间隔类型，都有一个单独的数据类型。 例如， `DAY` 间隔对应于 `IntervalDay` 数据类型: ``` sql SELECT toTypeName(INTERVAL 4 DAY) @@ -42,7 +42,7 @@ SELECT toTypeName(INTERVAL 4 DAY) ## 使用说明 {#data-type-interval-usage-remarks} -您可以使用 `Interval`-在算术运算类型值 [日期](../../../sql-reference/data-types/date.md) 和 [日期时间](../../../sql-reference/data-types/datetime.md)-类型值。 例如，您可以将4天添加到当前时间: +您可以在与 [日期](../../../sql-reference/data-types/date.md) 和 [日期时间](../../../sql-reference/data-types/datetime.md) 类型值的算术运算中使用 `Interval` 类型值。 例如，您可以将4天添加到当前时间: ``` sql SELECT now() as current_date_time, current_date_time + INTERVAL 4 DAY @@ -54,10 +54,10 @@ SELECT now() as current_date_time, current_date_time + INTERVAL 4 DAY └─────────────────────┴───────────────────────────────┘ ``` -不同类型的间隔不能合并。 你不能使用间隔，如 `4 DAY 1 HOUR`. 以小于或等于间隔的最小单位的单位指定间隔，例如，间隔 `1 day and an hour` 间隔可以表示为 `25 HOUR` 或 `90000 SECOND`. - -你不能执行算术运算 `Interval`-类型值，但你可以添加不同类型的时间间隔，因此值 `Date` 或 `DateTime` 数据类型。 例如: +不同类型的间隔不能合并。 你不能使用诸如 `4 DAY 1 HOUR` 的时间间隔. 以小于或等于时间间隔最小单位的单位来指定间隔，例如，时间间隔 `1 day and an hour` 可以表示为 `25 HOUR` 或 `90000 SECOND`. +你不能对 `Interval` 类型的值执行算术运算，但你可以向 `Date` 或 `DateTime` 数据类型的值添加不同类型的时间间隔，例如: + ``` sql SELECT now() AS current_date_time, current_date_time + INTERVAL 4 DAY + INTERVAL 3 HOUR ``` @@ -81,5 +81,5 @@ Code: 43. DB::Exception: Received from localhost:9000. DB::Exception: Wrong argu ## 另请参阅 {#see-also} -- [INTERVAL](../../../sql-reference/operators/index.md#operator-interval) 接线员 +- [INTERVAL](../../../sql-reference/operators/index.md#operator-interval) 操作 - [toInterval](../../../sql-reference/functions/type-conversion-functions.md#function-tointerval) 类型转换函数 diff --git a/docs/zh/sql-reference/statements/create.md b/docs/zh/sql-reference/statements/create.md index 639af0841dc..46e82bd1733 100644 --- a/docs/zh/sql-reference/statements/create.md +++ b/docs/zh/sql-reference/statements/create.md @@ -238,7 +238,7 @@ SELECT a, b, c FROM (SELECT ...) 当一个`SELECT`子句包含`DISTINCT`, `GROUP BY`, `ORDER BY`, `LIMIT`时，请注意，这些仅会在插入数据时在每个单独的数据块上执行。例如，如果你在其中包含了`GROUP BY`，则只会在查询期间进行聚合，但聚合范围仅限于单个批的写入数据。数据不会进一步被聚合。但是当你使用一些其他数据聚合引擎时这是例外的，如：`SummingMergeTree`。 -目前对物化视图执行`ALTER`是不支持的，因此这可能是不方便的。如果物化视图是使用的`TO [db.]name`的方式进行构建的，你可以使用`DETACH`语句现将视图剥离，然后使用`ALTER`运行在目标表上，然后使用`ATTACH`将之前剥离的表重新加载进来。 +目前对物化视图执行`ALTER`是不支持的，因此这可能是不方便的。如果物化视图是使用的`TO [db.]name`的方式进行构建的，你可以使用`DETACH`语句先将视图剥离，然后使用`ALTER`运行在目标表上，然后使用`ATTACH`将之前剥离的表重新加载进来。 视图看起来和普通的表相同。例如，你可以通过`SHOW TABLES`查看到它们。 diff --git a/docs/zh/sql-reference/syntax.md b/docs/zh/sql-reference/syntax.md index 8c331db1139..c05c5a1a7bf 100644 --- a/docs/zh/sql-reference/syntax.md +++ b/docs/zh/sql-reference/syntax.md @@ -14,7 +14,7 @@ INSERT INTO t VALUES (1, 'Hello, world'), (2, 'abc'), (3, 'def') 含`INSERT INTO t VALUES` 的部分由完整SQL解析器处理，包含数据的部分 `(1, 'Hello, world'), (2, 'abc'), (3, 'def')` 交给快速流式解析器解析。通过设置参数 [input_format_values_interpret_expressions](../operations/settings/settings.md#settings-input_format_values_interpret_expressions)，你也可以对数据部分开启完整SQL解析器。当 `input_format_values_interpret_expressions = 1` 时，CH优先采用快速流式解析器来解析数据。如果失败，CH再尝试用完整SQL解析器来处理，就像处理SQL [expression](#syntax-expressions) 一样。 -数据可以采用任何格式。当CH接受到请求时，服务端先在内存中计算不超过 [max_query_size](../operations/settings/settings.md#settings-max_query_size) 字节的请求数据（默认1 mb），然后剩下部分交给快速流式解析器。 +数据可以采用任何格式。当CH接收到请求时，服务端先在内存中计算不超过 [max_query_size](../operations/settings/settings.md#settings-max_query_size) 字节的请求数据（默认1 mb），然后剩下部分交给快速流式解析器。 这将避免在处理大型的 `INSERT`语句时出现问题。 diff --git a/programs/CMakeLists.txt b/programs/CMakeLists.txt index 09199e83026..6fd4c2050b4 100644 --- a/programs/CMakeLists.txt +++ b/programs/CMakeLists.txt @@ -47,6 +47,9 @@ option (ENABLE_CLICKHOUSE_LIBRARY_BRIDGE "HTTP-server working like a proxy to Li option (ENABLE_CLICKHOUSE_GIT_IMPORT "A tool to analyze Git repositories" ${ENABLE_CLICKHOUSE_ALL}) + +option (ENABLE_CLICKHOUSE_KEEPER "ClickHouse alternative to ZooKeeper" ${ENABLE_CLICKHOUSE_ALL}) + if (CLICKHOUSE_SPLIT_BINARY) option(ENABLE_CLICKHOUSE_INSTALL "Install ClickHouse without .deb/.rpm/.tgz packages (having the binary only)" OFF) else () @@ -134,6 +137,12 @@ else() message(STATUS "ClickHouse git-import: OFF") endif() +if (ENABLE_CLICKHOUSE_KEEPER) + message(STATUS "ClickHouse keeper mode: ON") +else() + message(STATUS "ClickHouse keeper mode: OFF") +endif() + if(NOT (MAKE_STATIC_LIBRARIES OR SPLIT_SHARED_LIBRARIES)) set(CLICKHOUSE_ONE_SHARED ON) endif() @@ -189,6 +198,54 @@ macro(clickhouse_program_add name) clickhouse_program_add_executable(${name}) endmacro() +# Embed default config files as a resource into the binary. +# This is needed for two purposes: +# 1. Allow to run the binary without download of any other files. +# 2. Allow to implement "sudo clickhouse install" tool. +# +# Arguments: target (server, client, keeper, etc.) and list of files +# +# Also dependency on TARGET_FILE is required, look at examples in programs/server and programs/keeper +macro(clickhouse_embed_binaries) + # TODO We actually need this on Mac, FreeBSD. + if (OS_LINUX) + + set(arguments_list "${ARGN}") + list(GET arguments_list 0 target) + + # for some reason cmake iterates loop including + math(EXPR arguments_count "${ARGC}-1") + + foreach(RESOURCE_POS RANGE 1 "${arguments_count}") + list(GET arguments_list "${RESOURCE_POS}" RESOURCE_FILE) + set(RESOURCE_OBJ ${RESOURCE_FILE}.o) + set(RESOURCE_OBJS ${RESOURCE_OBJS} ${RESOURCE_OBJ}) + + # https://stackoverflow.com/questions/14776463/compile-and-add-an-object-file-from-a-binary-with-cmake + # PPC64LE fails to do this with objcopy, use ld or lld instead + if (ARCH_PPC64LE) + add_custom_command(OUTPUT ${RESOURCE_OBJ} + COMMAND cd ${CMAKE_CURRENT_SOURCE_DIR} && ${CMAKE_LINKER} -m elf64lppc -r -b binary -o "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}" ${RESOURCE_FILE}) + else() + add_custom_command(OUTPUT ${RESOURCE_OBJ} + COMMAND cd ${CMAKE_CURRENT_SOURCE_DIR} && ${OBJCOPY_PATH} -I binary ${OBJCOPY_ARCH_OPTIONS} ${RESOURCE_FILE} "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}" + COMMAND ${OBJCOPY_PATH} --rename-section .data=.rodata,alloc,load,readonly,data,contents + "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}" "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}") + endif() + set_source_files_properties(${RESOURCE_OBJ} PROPERTIES EXTERNAL_OBJECT true GENERATED true) + endforeach() + + add_library(clickhouse_${target}_configs STATIC ${RESOURCE_OBJS}) + set_target_properties(clickhouse_${target}_configs PROPERTIES LINKER_LANGUAGE C) + + # whole-archive prevents symbols from being discarded for unknown reason + # CMake can shuffle each of target_link_libraries arguments with other + # libraries in linker command. To avoid this we hardcode whole-archive + # library into single string. + add_dependencies(clickhouse-${target}-lib clickhouse_${target}_configs) + endif () +endmacro() + add_subdirectory (server) add_subdirectory (client) @@ -202,6 +259,7 @@ add_subdirectory (obfuscator) add_subdirectory (install) add_subdirectory (git-import) add_subdirectory (bash-completion) +add_subdirectory (keeper) if (ENABLE_CLICKHOUSE_ODBC_BRIDGE) add_subdirectory (odbc-bridge) @@ -212,15 +270,15 @@ if (ENABLE_CLICKHOUSE_LIBRARY_BRIDGE) endif () if (CLICKHOUSE_ONE_SHARED) - add_library(clickhouse-lib SHARED ${CLICKHOUSE_SERVER_SOURCES} ${CLICKHOUSE_CLIENT_SOURCES} ${CLICKHOUSE_LOCAL_SOURCES} ${CLICKHOUSE_BENCHMARK_SOURCES} ${CLICKHOUSE_COPIER_SOURCES} ${CLICKHOUSE_EXTRACT_FROM_CONFIG_SOURCES} ${CLICKHOUSE_COMPRESSOR_SOURCES} ${CLICKHOUSE_FORMAT_SOURCES} ${CLICKHOUSE_OBFUSCATOR_SOURCES} ${CLICKHOUSE_GIT_IMPORT_SOURCES} ${CLICKHOUSE_ODBC_BRIDGE_SOURCES}) - target_link_libraries(clickhouse-lib ${CLICKHOUSE_SERVER_LINK} ${CLICKHOUSE_CLIENT_LINK} ${CLICKHOUSE_LOCAL_LINK} ${CLICKHOUSE_BENCHMARK_LINK} ${CLICKHOUSE_COPIER_LINK} ${CLICKHOUSE_EXTRACT_FROM_CONFIG_LINK} ${CLICKHOUSE_COMPRESSOR_LINK} ${CLICKHOUSE_FORMAT_LINK} ${CLICKHOUSE_OBFUSCATOR_LINK} ${CLICKHOUSE_GIT_IMPORT_LINK} ${CLICKHOUSE_ODBC_BRIDGE_LINK}) - target_include_directories(clickhouse-lib ${CLICKHOUSE_SERVER_INCLUDE} ${CLICKHOUSE_CLIENT_INCLUDE} ${CLICKHOUSE_LOCAL_INCLUDE} ${CLICKHOUSE_BENCHMARK_INCLUDE} ${CLICKHOUSE_COPIER_INCLUDE} ${CLICKHOUSE_EXTRACT_FROM_CONFIG_INCLUDE} ${CLICKHOUSE_COMPRESSOR_INCLUDE} ${CLICKHOUSE_FORMAT_INCLUDE} ${CLICKHOUSE_OBFUSCATOR_INCLUDE} ${CLICKHOUSE_GIT_IMPORT_INCLUDE} ${CLICKHOUSE_ODBC_BRIDGE_INCLUDE}) + add_library(clickhouse-lib SHARED ${CLICKHOUSE_SERVER_SOURCES} ${CLICKHOUSE_CLIENT_SOURCES} ${CLICKHOUSE_LOCAL_SOURCES} ${CLICKHOUSE_BENCHMARK_SOURCES} ${CLICKHOUSE_COPIER_SOURCES} ${CLICKHOUSE_EXTRACT_FROM_CONFIG_SOURCES} ${CLICKHOUSE_COMPRESSOR_SOURCES} ${CLICKHOUSE_FORMAT_SOURCES} ${CLICKHOUSE_OBFUSCATOR_SOURCES} ${CLICKHOUSE_GIT_IMPORT_SOURCES} ${CLICKHOUSE_ODBC_BRIDGE_SOURCES} ${CLICKHOUSE_KEEPER_SOURCES}) + target_link_libraries(clickhouse-lib ${CLICKHOUSE_SERVER_LINK} ${CLICKHOUSE_CLIENT_LINK} ${CLICKHOUSE_LOCAL_LINK} ${CLICKHOUSE_BENCHMARK_LINK} ${CLICKHOUSE_COPIER_LINK} ${CLICKHOUSE_EXTRACT_FROM_CONFIG_LINK} ${CLICKHOUSE_COMPRESSOR_LINK} ${CLICKHOUSE_FORMAT_LINK} ${CLICKHOUSE_OBFUSCATOR_LINK} ${CLICKHOUSE_GIT_IMPORT_LINK} ${CLICKHOUSE_ODBC_BRIDGE_LINK} ${CLICKHOUSE_KEEPER_LINK}) + target_include_directories(clickhouse-lib ${CLICKHOUSE_SERVER_INCLUDE} ${CLICKHOUSE_CLIENT_INCLUDE} ${CLICKHOUSE_LOCAL_INCLUDE} ${CLICKHOUSE_BENCHMARK_INCLUDE} ${CLICKHOUSE_COPIER_INCLUDE} ${CLICKHOUSE_EXTRACT_FROM_CONFIG_INCLUDE} ${CLICKHOUSE_COMPRESSOR_INCLUDE} ${CLICKHOUSE_FORMAT_INCLUDE} ${CLICKHOUSE_OBFUSCATOR_INCLUDE} ${CLICKHOUSE_GIT_IMPORT_INCLUDE} ${CLICKHOUSE_ODBC_BRIDGE_INCLUDE} ${CLICKHOUSE_KEEPER_INCLUDE}) set_target_properties(clickhouse-lib PROPERTIES SOVERSION ${VERSION_MAJOR}.${VERSION_MINOR} VERSION ${VERSION_SO} OUTPUT_NAME clickhouse DEBUG_POSTFIX "") install (TARGETS clickhouse-lib LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR} COMPONENT clickhouse) endif() if (CLICKHOUSE_SPLIT_BINARY) - set (CLICKHOUSE_ALL_TARGETS clickhouse-server clickhouse-client clickhouse-local clickhouse-benchmark clickhouse-extract-from-config clickhouse-compressor clickhouse-format clickhouse-obfuscator clickhouse-git-import clickhouse-copier) + set (CLICKHOUSE_ALL_TARGETS clickhouse-server clickhouse-client clickhouse-local clickhouse-benchmark clickhouse-extract-from-config clickhouse-compressor clickhouse-format clickhouse-obfuscator clickhouse-git-import clickhouse-copier clickhouse-keeper) if (ENABLE_CLICKHOUSE_ODBC_BRIDGE) list (APPEND CLICKHOUSE_ALL_TARGETS clickhouse-odbc-bridge) @@ -277,6 +335,9 @@ else () if (ENABLE_CLICKHOUSE_GIT_IMPORT) clickhouse_target_link_split_lib(clickhouse git-import) endif () + if (ENABLE_CLICKHOUSE_KEEPER) + clickhouse_target_link_split_lib(clickhouse keeper) + endif() if (ENABLE_CLICKHOUSE_INSTALL) clickhouse_target_link_split_lib(clickhouse install) endif () @@ -332,6 +393,11 @@ else () install (FILES "${CMAKE_CURRENT_BINARY_DIR}/clickhouse-git-import" DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse) list(APPEND CLICKHOUSE_BUNDLE clickhouse-git-import) endif () + if (ENABLE_CLICKHOUSE_KEEPER) + add_custom_target (clickhouse-keeper ALL COMMAND ${CMAKE_COMMAND} -E create_symlink clickhouse clickhouse-keeper DEPENDS clickhouse) + install (FILES "${CMAKE_CURRENT_BINARY_DIR}/clickhouse-keeper" DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse) + list(APPEND CLICKHOUSE_BUNDLE clickhouse-keeper) + endif () install (TARGETS clickhouse RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT clickhouse) diff --git a/programs/config_tools.h.in b/programs/config_tools.h.in index abe9ef8c562..50ba0c16a83 100644 --- a/programs/config_tools.h.in +++ b/programs/config_tools.h.in @@ -16,3 +16,4 @@ #cmakedefine01 ENABLE_CLICKHOUSE_INSTALL #cmakedefine01 ENABLE_CLICKHOUSE_ODBC_BRIDGE #cmakedefine01 ENABLE_CLICKHOUSE_LIBRARY_BRIDGE +#cmakedefine01 ENABLE_CLICKHOUSE_KEEPER diff --git a/programs/keeper/CMakeLists.txt b/programs/keeper/CMakeLists.txt new file mode 100644 index 00000000000..e604d0e304e --- /dev/null +++ b/programs/keeper/CMakeLists.txt @@ -0,0 +1,24 @@ +set(CLICKHOUSE_KEEPER_SOURCES + Keeper.cpp +) + +if (OS_LINUX) + set (LINK_RESOURCE_LIB INTERFACE "-Wl,${WHOLE_ARCHIVE} $ -Wl,${NO_WHOLE_ARCHIVE}") +endif () + +set (CLICKHOUSE_KEEPER_LINK + PRIVATE + clickhouse_common_config + clickhouse_common_io + clickhouse_common_zookeeper + daemon + dbms + + ${LINK_RESOURCE_LIB} +) + +clickhouse_program_add(keeper) + +install (FILES keeper_config.xml DESTINATION "${CLICKHOUSE_ETC_DIR}/clickhouse-keeper" COMPONENT clickhouse-keeper) + +clickhouse_embed_binaries(keeper keeper_config.xml keeper_embedded.xml) diff --git a/programs/keeper/Keeper.cpp b/programs/keeper/Keeper.cpp new file mode 100644 index 00000000000..b9d87ba7fdb --- /dev/null +++ b/programs/keeper/Keeper.cpp @@ -0,0 +1,474 @@ +#include "Keeper.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if !defined(ARCADIA_BUILD) +# include "config_core.h" +# include "Common/config_version.h" +#endif + +#if USE_SSL +# include +# include +#endif + +#if USE_NURAFT +# include +#endif + +#if defined(OS_LINUX) +# include +# include +#endif + + +int mainEntryClickHouseKeeper(int argc, char ** argv) +{ + DB::Keeper app; + + try + { + return app.run(argc, argv); + } + catch (...) + { + std::cerr << DB::getCurrentExceptionMessage(true) << "\n"; + auto code = DB::getCurrentExceptionCode(); + return code ? code : 1; + } +} + +namespace DB +{ + +namespace ErrorCodes +{ + extern const int NO_ELEMENTS_IN_CONFIG; + extern const int SUPPORT_IS_DISABLED; + extern const int NETWORK_ERROR; + extern const int MISMATCHING_USERS_FOR_PROCESS_AND_DATA; + extern const int FAILED_TO_GETPWUID; +} + +namespace +{ + +int waitServersToFinish(std::vector & servers, size_t seconds_to_wait) +{ + const int sleep_max_ms = 1000 * seconds_to_wait; + const int sleep_one_ms = 100; + int sleep_current_ms = 0; + int current_connections = 0; + for (;;) + { + current_connections = 0; + + for (auto & server : servers) + { + server.stop(); + current_connections += server.currentConnections(); + } + + if (!current_connections) + break; + + sleep_current_ms += sleep_one_ms; + if (sleep_current_ms < sleep_max_ms) + std::this_thread::sleep_for(std::chrono::milliseconds(sleep_one_ms)); + else + break; + } + return current_connections; +} + +Poco::Net::SocketAddress makeSocketAddress(const std::string & host, UInt16 port, Poco::Logger * log) +{ + Poco::Net::SocketAddress socket_address; + try + { + socket_address = Poco::Net::SocketAddress(host, port); + } + catch (const Poco::Net::DNSException & e) + { + const auto code = e.code(); + if (code == EAI_FAMILY +#if defined(EAI_ADDRFAMILY) + || code == EAI_ADDRFAMILY +#endif + ) + { + LOG_ERROR(log, "Cannot resolve listen_host ({}), error {}: {}. " + "If it is an IPv6 address and your host has disabled IPv6, then consider to " + "specify IPv4 address to listen in element of configuration " + "file. Example: 0.0.0.0", + host, e.code(), e.message()); + } + + throw; + } + return socket_address; +} + +[[noreturn]] void forceShutdown() +{ +#if defined(THREAD_SANITIZER) && defined(OS_LINUX) + /// Thread sanitizer tries to do something on exit that we don't need if we want to exit immediately, + /// while connection handling threads are still run. + (void)syscall(SYS_exit_group, 0); + __builtin_unreachable(); +#else + _exit(0); +#endif +} + +std::string getUserName(uid_t user_id) +{ + /// Try to convert user id into user name. + auto buffer_size = sysconf(_SC_GETPW_R_SIZE_MAX); + if (buffer_size <= 0) + buffer_size = 1024; + std::string buffer; + buffer.reserve(buffer_size); + + struct passwd passwd_entry; + struct passwd * result = nullptr; + const auto error = getpwuid_r(user_id, &passwd_entry, buffer.data(), buffer_size, &result); + + if (error) + throwFromErrno("Failed to find user name for " + toString(user_id), ErrorCodes::FAILED_TO_GETPWUID, error); + else if (result) + return result->pw_name; + return toString(user_id); +} + +} + +Poco::Net::SocketAddress Keeper::socketBindListen(Poco::Net::ServerSocket & socket, const std::string & host, UInt16 port, [[maybe_unused]] bool secure) const +{ + auto address = makeSocketAddress(host, port, &logger()); +#if !defined(POCO_CLICKHOUSE_PATCH) || POCO_VERSION < 0x01090100 + if (secure) + /// Bug in old (<1.9.1) poco, listen() after bind() with reusePort param will fail because have no implementation in SecureServerSocketImpl + /// https://github.com/pocoproject/poco/pull/2257 + socket.bind(address, /* reuseAddress = */ true); + else +#endif +#if POCO_VERSION < 0x01080000 + socket.bind(address, /* reuseAddress = */ true); +#else + socket.bind(address, /* reuseAddress = */ true, /* reusePort = */ config().getBool("listen_reuse_port", false)); +#endif + + socket.listen(/* backlog = */ config().getUInt("listen_backlog", 64)); + + return address; +} + +void Keeper::createServer(const std::string & listen_host, const char * port_name, bool listen_try, CreateServerFunc && func) const +{ + /// For testing purposes, user may omit tcp_port or http_port or https_port in configuration file. + if (!config().has(port_name)) + return; + + auto port = config().getInt(port_name); + try + { + func(port); + } + catch (const Poco::Exception &) + { + std::string message = "Listen [" + listen_host + "]:" + std::to_string(port) + " failed: " + getCurrentExceptionMessage(false); + + if (listen_try) + { + LOG_WARNING(&logger(), "{}. If it is an IPv6 or IPv4 address and your host has disabled IPv6 or IPv4, then consider to " + "specify not disabled IPv4 or IPv6 address to listen in element of configuration " + "file. Example for disabled IPv6: 0.0.0.0 ." + " Example for disabled IPv4: ::", + message); + } + else + { + throw Exception{message, ErrorCodes::NETWORK_ERROR}; + } + } +} + +void Keeper::uninitialize() +{ + logger().information("shutting down"); + BaseDaemon::uninitialize(); +} + +int Keeper::run() +{ + if (config().hasOption("help")) + { + Poco::Util::HelpFormatter help_formatter(Keeper::options()); + auto header_str = fmt::format("{} [OPTION] [-- [ARG]...]\n" + "positional arguments can be used to rewrite config.xml properties, for example, --http_port=8010", + commandName()); + help_formatter.setHeader(header_str); + help_formatter.format(std::cout); + return 0; + } + if (config().hasOption("version")) + { + std::cout << DBMS_NAME << " keeper version " << VERSION_STRING << VERSION_OFFICIAL << "." << std::endl; + return 0; + } + + return Application::run(); // NOLINT +} + +void Keeper::initialize(Poco::Util::Application & self) +{ + BaseDaemon::initialize(self); + logger().information("starting up"); + + LOG_INFO(&logger(), "OS Name = {}, OS Version = {}, OS Architecture = {}", + Poco::Environment::osName(), + Poco::Environment::osVersion(), + Poco::Environment::osArchitecture()); +} + +std::string Keeper::getDefaultConfigFileName() const +{ + return "keeper_config.xml"; +} + +void Keeper::defineOptions(Poco::Util::OptionSet & options) +{ + options.addOption( + Poco::Util::Option("help", "h", "show help and exit") + .required(false) + .repeatable(false) + .binding("help")); + options.addOption( + Poco::Util::Option("version", "V", "show version and exit") + .required(false) + .repeatable(false) + .binding("version")); + BaseDaemon::defineOptions(options); +} + +int Keeper::main(const std::vector & /*args*/) +{ + Poco::Logger * log = &logger(); + + UseSSL use_ssl; + + MainThreadStatus::getInstance(); + +#if !defined(NDEBUG) || !defined(__OPTIMIZE__) + LOG_WARNING(log, "Keeper was built in debug mode. It will work slowly."); +#endif + +#if defined(SANITIZER) + LOG_WARNING(log, "Keeper was built with sanitizer. It will work slowly."); +#endif + + auto shared_context = Context::createShared(); + global_context = Context::createGlobal(shared_context.get()); + + global_context->makeGlobalContext(); + global_context->setApplicationType(Context::ApplicationType::KEEPER); + + if (!config().has("keeper_server")) + throw Exception(ErrorCodes::NO_ELEMENTS_IN_CONFIG, "Keeper configuration ( section) not found in config"); + + + std::string path; + + if (config().has("keeper_server.storage_path")) + path = config().getString("keeper_server.storage_path"); + else if (config().has("keeper_server.log_storage_path")) + path = config().getString("keeper_server.log_storage_path"); + else if (config().has("keeper_server.snapshot_storage_path")) + path = config().getString("keeper_server.snapshot_storage_path"); + else + path = std::filesystem::path{KEEPER_DEFAULT_PATH}; + + + /// Check that the process user id matches the owner of the data. + const auto effective_user_id = geteuid(); + struct stat statbuf; + if (stat(path.c_str(), &statbuf) == 0 && effective_user_id != statbuf.st_uid) + { + const auto effective_user = getUserName(effective_user_id); + const auto data_owner = getUserName(statbuf.st_uid); + std::string message = "Effective user of the process (" + effective_user + + ") does not match the owner of the data (" + data_owner + ")."; + if (effective_user_id == 0) + { + message += " Run under 'sudo -u " + data_owner + "'."; + throw Exception(message, ErrorCodes::MISMATCHING_USERS_FOR_PROCESS_AND_DATA); + } + else + { + LOG_WARNING(log, message); + } + } + + const Settings & settings = global_context->getSettingsRef(); + + GlobalThreadPool::initialize(config().getUInt("max_thread_pool_size", 100)); + + static ServerErrorHandler error_handler; + Poco::ErrorHandler::set(&error_handler); + + /// Initialize DateLUT early, to not interfere with running time of first query. + LOG_DEBUG(log, "Initializing DateLUT."); + DateLUT::instance(); + LOG_TRACE(log, "Initialized DateLUT with time zone '{}'.", DateLUT::instance().getTimeZone()); + + /// Don't want to use DNS cache + DNSResolver::instance().setDisableCacheFlag(); + + Poco::ThreadPool server_pool(3, config().getUInt("max_connections", 1024)); + + std::vector listen_hosts = DB::getMultipleValuesFromConfig(config(), "", "listen_host"); + + bool listen_try = config().getBool("listen_try", false); + if (listen_hosts.empty()) + { + listen_hosts.emplace_back("::1"); + listen_hosts.emplace_back("127.0.0.1"); + listen_try = true; + } + + auto servers = std::make_shared>(); + +#if USE_NURAFT + /// Initialize test keeper RAFT. Do nothing if no nu_keeper_server in config. + global_context->initializeKeeperStorageDispatcher(); + for (const auto & listen_host : listen_hosts) + { + /// TCP Keeper + const char * port_name = "keeper_server.tcp_port"; + createServer(listen_host, port_name, listen_try, [&](UInt16 port) + { + Poco::Net::ServerSocket socket; + auto address = socketBindListen(socket, listen_host, port); + socket.setReceiveTimeout(settings.receive_timeout); + socket.setSendTimeout(settings.send_timeout); + servers->emplace_back( + port_name, + std::make_unique( + new KeeperTCPHandlerFactory(*this, false), server_pool, socket, new Poco::Net::TCPServerParams)); + + LOG_INFO(log, "Listening for connections to Keeper (tcp): {}", address.toString()); + }); + + const char * secure_port_name = "keeper_server.tcp_port_secure"; + createServer(listen_host, secure_port_name, listen_try, [&](UInt16 port) + { +#if USE_SSL + Poco::Net::SecureServerSocket socket; + auto address = socketBindListen(socket, listen_host, port, /* secure = */ true); + socket.setReceiveTimeout(settings.receive_timeout); + socket.setSendTimeout(settings.send_timeout); + servers->emplace_back( + secure_port_name, + std::make_unique( + new KeeperTCPHandlerFactory(*this, true), server_pool, socket, new Poco::Net::TCPServerParams)); + LOG_INFO(log, "Listening for connections to Keeper with secure protocol (tcp_secure): {}", address.toString()); +#else + UNUSED(port); + throw Exception{"SSL support for TCP protocol is disabled because Poco library was built without NetSSL support.", + ErrorCodes::SUPPORT_IS_DISABLED}; +#endif + }); + } +#else + throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "ClickHouse keeper built without NuRaft library. Cannot use coordination."); +#endif + + for (auto & server : *servers) + server.start(); + + SCOPE_EXIT({ + LOG_INFO(log, "Shutting down."); + + global_context->shutdown(); + + LOG_DEBUG(log, "Waiting for current connections to Keeper to finish."); + int current_connections = 0; + for (auto & server : *servers) + { + server.stop(); + current_connections += server.currentConnections(); + } + + if (current_connections) + LOG_INFO(log, "Closed all listening sockets. Waiting for {} outstanding connections.", current_connections); + else + LOG_INFO(log, "Closed all listening sockets."); + + if (current_connections > 0) + current_connections = waitServersToFinish(*servers, config().getInt("shutdown_wait_unfinished", 5)); + + if (current_connections) + LOG_INFO(log, "Closed connections to Keeper. But {} remain. Probably some users cannot finish their connections after context shutdown.", current_connections); + else + LOG_INFO(log, "Closed connections to Keeper."); + + global_context->shutdownKeeperStorageDispatcher(); + + /// Wait server pool to avoid use-after-free of destroyed context in the handlers + server_pool.joinAll(); + + /** Explicitly destroy Context. It is more convenient than in destructor of Server, because logger is still available. + * At this moment, no one could own shared part of Context. + */ + global_context.reset(); + shared_context.reset(); + + LOG_DEBUG(log, "Destroyed global context."); + + if (current_connections) + { + LOG_INFO(log, "Will shutdown forcefully."); + forceShutdown(); + } + }); + + + buildLoggers(config(), logger()); + + LOG_INFO(log, "Ready for connections."); + + waitForTerminationRequest(); + + return Application::EXIT_OK; +} + + +void Keeper::logRevision() const +{ + Poco::Logger::root().information("Starting ClickHouse Keeper " + std::string{VERSION_STRING} + + " with revision " + std::to_string(ClickHouseRevision::getVersionRevision()) + + ", " + build_id_info + + ", PID " + std::to_string(getpid())); +} + + +} diff --git a/programs/keeper/Keeper.h b/programs/keeper/Keeper.h new file mode 100644 index 00000000000..e80fe10b61c --- /dev/null +++ b/programs/keeper/Keeper.h @@ -0,0 +1,69 @@ +#pragma once + +#include +#include + +namespace Poco +{ + namespace Net + { + class ServerSocket; + } +} + +namespace DB +{ + +/// standalone clickhouse-keeper server (replacement for ZooKeeper). Uses the same +/// config as clickhouse-server. Serves requests on TCP ports with or without +/// SSL using ZooKeeper protocol. +class Keeper : public BaseDaemon, public IServer +{ +public: + using ServerApplication::run; + + Poco::Util::LayeredConfiguration & config() const override + { + return BaseDaemon::config(); + } + + Poco::Logger & logger() const override + { + return BaseDaemon::logger(); + } + + ContextPtr context() const override + { + return global_context; + } + + bool isCancelled() const override + { + return BaseDaemon::isCancelled(); + } + + void defineOptions(Poco::Util::OptionSet & _options) override; + +protected: + void logRevision() const override; + + int run() override; + + void initialize(Application & self) override; + + void uninitialize() override; + + int main(const std::vector & args) override; + + std::string getDefaultConfigFileName() const override; + +private: + ContextPtr global_context; + + Poco::Net::SocketAddress socketBindListen(Poco::Net::ServerSocket & socket, const std::string & host, UInt16 port, [[maybe_unused]] bool secure = false) const; + + using CreateServerFunc = std::function; + void createServer(const std::string & listen_host, const char * port_name, bool listen_try, CreateServerFunc && func) const; +}; + +} diff --git a/programs/keeper/clickhouse-keeper.cpp b/programs/keeper/clickhouse-keeper.cpp new file mode 100644 index 00000000000..baa673f79ee --- /dev/null +++ b/programs/keeper/clickhouse-keeper.cpp @@ -0,0 +1,6 @@ +int mainEntryClickHouseKeeper(int argc, char ** argv); + +int main(int argc_, char ** argv_) +{ + return mainEntryClickHouseKeeper(argc_, argv_); +} diff --git a/programs/keeper/keeper_config.xml b/programs/keeper/keeper_config.xml new file mode 100644 index 00000000000..ef218c9f2d7 --- /dev/null +++ b/programs/keeper/keeper_config.xml @@ -0,0 +1,81 @@ + + + + trace + /var/log/clickhouse-keeper/clickhouse-keeper.log + /var/log/clickhouse-keeper/clickhouse-keeper.err.log + + 1000M + 10 + + + + 4096 + + + 9181 + + + 1 + + /var/lib/clickhouse/coordination/logs + /var/lib/clickhouse/coordination/snapshots + + + 10000 + 30000 + information + + + + + + 1 + + + localhost + 44444 + + + + + + + + + + + + + /etc/clickhouse-keeper/server.crt + /etc/clickhouse-keeper/server.key + + /etc/clickhouse-keeper/dhparam.pem + none + true + true + sslv2,sslv3 + true + + + + diff --git a/programs/keeper/keeper_embedded.xml b/programs/keeper/keeper_embedded.xml new file mode 100644 index 00000000000..37edaedba80 --- /dev/null +++ b/programs/keeper/keeper_embedded.xml @@ -0,0 +1,21 @@ + + + trace + true + + + + 9181 + 1 + ./keeper_log + ./keeper_snapshot + + + + 1 + localhost + 44444 + + + + diff --git a/programs/main.cpp b/programs/main.cpp index cbb22b7a87b..ccdf4d50fb4 100644 --- a/programs/main.cpp +++ b/programs/main.cpp @@ -55,6 +55,9 @@ int mainEntryClickHouseObfuscator(int argc, char ** argv); #if ENABLE_CLICKHOUSE_GIT_IMPORT int mainEntryClickHouseGitImport(int argc, char ** argv); #endif +#if ENABLE_CLICKHOUSE_KEEPER +int mainEntryClickHouseKeeper(int argc, char ** argv); +#endif #if ENABLE_CLICKHOUSE_INSTALL int mainEntryClickHouseInstall(int argc, char ** argv); int mainEntryClickHouseStart(int argc, char ** argv); @@ -112,6 +115,9 @@ std::pair clickhouse_applications[] = #if ENABLE_CLICKHOUSE_GIT_IMPORT {"git-import", mainEntryClickHouseGitImport}, #endif +#if ENABLE_CLICKHOUSE_KEEPER + {"keeper", mainEntryClickHouseKeeper}, +#endif #if ENABLE_CLICKHOUSE_INSTALL {"install", mainEntryClickHouseInstall}, {"start", mainEntryClickHouseStart}, diff --git a/programs/server/CMakeLists.txt b/programs/server/CMakeLists.txt index 0dcfbce1c30..f7f76fdb450 100644 --- a/programs/server/CMakeLists.txt +++ b/programs/server/CMakeLists.txt @@ -31,37 +31,4 @@ clickhouse_program_add(server) install(FILES config.xml users.xml DESTINATION "${CLICKHOUSE_ETC_DIR}/clickhouse-server" COMPONENT clickhouse) -# TODO We actually need this on Mac, FreeBSD. -if (OS_LINUX) - # Embed default config files as a resource into the binary. - # This is needed for two purposes: - # 1. Allow to run the binary without download of any other files. - # 2. Allow to implement "sudo clickhouse install" tool. - - foreach(RESOURCE_FILE config.xml users.xml embedded.xml play.html) - set(RESOURCE_OBJ ${RESOURCE_FILE}.o) - set(RESOURCE_OBJS ${RESOURCE_OBJS} ${RESOURCE_OBJ}) - - # https://stackoverflow.com/questions/14776463/compile-and-add-an-object-file-from-a-binary-with-cmake - # PPC64LE fails to do this with objcopy, use ld or lld instead - if (ARCH_PPC64LE) - add_custom_command(OUTPUT ${RESOURCE_OBJ} - COMMAND cd ${CMAKE_CURRENT_SOURCE_DIR} && ${CMAKE_LINKER} -m elf64lppc -r -b binary -o "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}" ${RESOURCE_FILE}) - else() - add_custom_command(OUTPUT ${RESOURCE_OBJ} - COMMAND cd ${CMAKE_CURRENT_SOURCE_DIR} && ${OBJCOPY_PATH} -I binary ${OBJCOPY_ARCH_OPTIONS} ${RESOURCE_FILE} "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}" - COMMAND ${OBJCOPY_PATH} --rename-section .data=.rodata,alloc,load,readonly,data,contents - "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}" "${CMAKE_CURRENT_BINARY_DIR}/${RESOURCE_OBJ}") - endif() - set_source_files_properties(${RESOURCE_OBJ} PROPERTIES EXTERNAL_OBJECT true GENERATED true) - endforeach(RESOURCE_FILE) - - add_library(clickhouse_server_configs STATIC ${RESOURCE_OBJS}) - set_target_properties(clickhouse_server_configs PROPERTIES LINKER_LANGUAGE C) - - # whole-archive prevents symbols from being discarded for unknown reason - # CMake can shuffle each of target_link_libraries arguments with other - # libraries in linker command. To avoid this we hardcode whole-archive - # library into single string. - add_dependencies(clickhouse-server-lib clickhouse_server_configs) -endif () +clickhouse_embed_binaries(server config.xml users.xml embedded.xml play.html) diff --git a/programs/server/config.xml b/programs/server/config.xml index df8a5266c39..75647b10416 100644 --- a/programs/server/config.xml +++ b/programs/server/config.xml @@ -362,6 +362,20 @@ 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. + user_dn_detection - section with LDAP search parameters for detecting the actual user DN of the bound user. + This is mainly used in search filters for further role mapping when the server is Active Directory. The + resulting user DN will be used when replacing '{user_dn}' substrings wherever they are allowed. By default, + user DN is set equal to bind DN, but once search is performed, it will be updated with to the actual detected + user DN value. + 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 the 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 the LDAP search. + Note, that the special characters must be escaped properly in XML. verification_cooldown - a period of time, in seconds, after a successful bind attempt, during which a 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. @@ -393,6 +407,17 @@ /path/to/tls_ca_cert_dir ECDHE-ECDSA-AES256-GCM-SHA384:ECDHE-RSA-AES256-GCM-SHA384:AES256-GCM-SHA384 + Example (typical Active Directory with configured user DN detection for further role mapping): + + localhost + 389 + EXAMPLE\{user_name} + + CN=Users,DC=example,DC=com + (&(objectClass=user)(sAMAccountName={user_name})) + + no + --> @@ -444,15 +469,16 @@ 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. + The resulting DN will be constructed by replacing all '{user_name}', '{bind_dn}', and '{user_dn}' + substrings of the template with the actual user name, bind DN, and user 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. + The resulting filter will be constructed by replacing all '{user_name}', '{bind_dn}', '{user_dn}', and + '{base_dn}' substrings of the template with the actual user name, bind DN, user 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. + attribute - attribute name whose values will be returned by the LDAP search. 'cn', by default. 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. @@ -471,6 +497,17 @@ clickhouse_ + Example (typical Active Directory with role mapping that relies on the detected user DN): + + my_ad_server + + CN=Users,DC=example,DC=com + CN + subtree + (&(objectClass=group)(member={user_dn})) + clickhouse_ + + --> diff --git a/src/Access/ContextAccess.cpp b/src/Access/ContextAccess.cpp index 0bcaef1e441..90495a83dfc 100644 --- a/src/Access/ContextAccess.cpp +++ b/src/Access/ContextAccess.cpp @@ -143,11 +143,13 @@ ContextAccess::ContextAccess(const AccessControlManager & manager_, const Params : manager(&manager_) , params(params_) { + std::lock_guard lock{mutex}; + subscription_for_user_change = manager->subscribeForChanges( *params.user_id, [this](const UUID &, const AccessEntityPtr & entity) { UserPtr changed_user = entity ? typeid_cast(entity) : nullptr; - std::lock_guard lock{mutex}; + std::lock_guard lock2{mutex}; setUser(changed_user); }); @@ -189,7 +191,7 @@ void ContextAccess::setUser(const UserPtr & user_) const current_roles_with_admin_option = user->granted_roles.findGrantedWithAdminOption(params.current_roles); } - subscription_for_roles_changes = {}; + subscription_for_roles_changes.reset(); enabled_roles = manager->getEnabledRoles(current_roles, current_roles_with_admin_option); subscription_for_roles_changes = enabled_roles->subscribeForChanges([this](const std::shared_ptr & roles_info_) { diff --git a/src/Access/ExternalAuthenticators.cpp b/src/Access/ExternalAuthenticators.cpp index 0c4d2f417c9..d4100c4e520 100644 --- a/src/Access/ExternalAuthenticators.cpp +++ b/src/Access/ExternalAuthenticators.cpp @@ -20,13 +20,42 @@ namespace ErrorCodes namespace { -auto parseLDAPServer(const Poco::Util::AbstractConfiguration & config, const String & name) +void parseLDAPSearchParams(LDAPClient::SearchParams & params, const Poco::Util::AbstractConfiguration & config, const String & prefix) +{ + const bool has_base_dn = config.has(prefix + ".base_dn"); + const bool has_search_filter = config.has(prefix + ".search_filter"); + const bool has_attribute = config.has(prefix + ".attribute"); + const bool has_scope = config.has(prefix + ".scope"); + + if (has_base_dn) + params.base_dn = config.getString(prefix + ".base_dn"); + + if (has_search_filter) + params.search_filter = config.getString(prefix + ".search_filter"); + + if (has_attribute) + params.attribute = config.getString(prefix + ".attribute"); + + if (has_scope) + { + auto scope = config.getString(prefix + ".scope"); + boost::algorithm::to_lower(scope); + + if (scope == "base") params.scope = LDAPClient::SearchParams::Scope::BASE; + else if (scope == "one_level") params.scope = LDAPClient::SearchParams::Scope::ONE_LEVEL; + else if (scope == "subtree") params.scope = LDAPClient::SearchParams::Scope::SUBTREE; + else if (scope == "children") params.scope = LDAPClient::SearchParams::Scope::CHILDREN; + else + throw Exception("Invalid value for 'scope' field of LDAP search parameters in '" + prefix + + "' section, must be one of 'base', 'one_level', 'subtree', or 'children'", ErrorCodes::BAD_ARGUMENTS); + } +} + +void parseLDAPServer(LDAPClient::Params & params, const Poco::Util::AbstractConfiguration & config, const String & name) { if (name.empty()) throw Exception("LDAP server name cannot be empty", ErrorCodes::BAD_ARGUMENTS); - LDAPClient::Params params; - const String ldap_server_config = "ldap_servers." + name; const bool has_host = config.has(ldap_server_config + ".host"); @@ -34,6 +63,7 @@ auto parseLDAPServer(const Poco::Util::AbstractConfiguration & config, const Str const bool has_bind_dn = config.has(ldap_server_config + ".bind_dn"); const bool has_auth_dn_prefix = config.has(ldap_server_config + ".auth_dn_prefix"); const bool has_auth_dn_suffix = config.has(ldap_server_config + ".auth_dn_suffix"); + const bool has_user_dn_detection = config.has(ldap_server_config + ".user_dn_detection"); const bool has_verification_cooldown = config.has(ldap_server_config + ".verification_cooldown"); const bool has_enable_tls = config.has(ldap_server_config + ".enable_tls"); const bool has_tls_minimum_protocol_version = config.has(ldap_server_config + ".tls_minimum_protocol_version"); @@ -66,6 +96,17 @@ auto parseLDAPServer(const Poco::Util::AbstractConfiguration & config, const Str params.bind_dn = auth_dn_prefix + "{user_name}" + auth_dn_suffix; } + if (has_user_dn_detection) + { + if (!params.user_dn_detection) + { + params.user_dn_detection.emplace(); + params.user_dn_detection->attribute = "dn"; + } + + parseLDAPSearchParams(*params.user_dn_detection, config, ldap_server_config + ".user_dn_detection"); + } + if (has_verification_cooldown) params.verification_cooldown = std::chrono::seconds{config.getUInt64(ldap_server_config + ".verification_cooldown")}; @@ -143,14 +184,10 @@ auto parseLDAPServer(const Poco::Util::AbstractConfiguration & config, const Str } else params.port = (params.enable_tls == LDAPClient::Params::TLSEnable::YES ? 636 : 389); - - return params; } -auto parseKerberosParams(const Poco::Util::AbstractConfiguration & config) +void parseKerberosParams(GSSAcceptorContext::Params & params, const Poco::Util::AbstractConfiguration & config) { - GSSAcceptorContext::Params params; - Poco::Util::AbstractConfiguration::Keys keys; config.keys("kerberos", keys); @@ -180,12 +217,20 @@ auto parseKerberosParams(const Poco::Util::AbstractConfiguration & config) params.realm = config.getString("kerberos.realm", ""); params.principal = config.getString("kerberos.principal", ""); - - return params; } } +void parseLDAPRoleSearchParams(LDAPClient::RoleSearchParams & params, const Poco::Util::AbstractConfiguration & config, const String & prefix) +{ + parseLDAPSearchParams(params, config, prefix); + + const bool has_prefix = config.has(prefix + ".prefix"); + + if (has_prefix) + params.prefix = config.getString(prefix + ".prefix"); +} + void ExternalAuthenticators::reset() { std::scoped_lock lock(mutex); @@ -229,7 +274,8 @@ void ExternalAuthenticators::setConfiguration(const Poco::Util::AbstractConfigur { try { - ldap_client_params_blueprint.insert_or_assign(ldap_server_name, parseLDAPServer(config, ldap_server_name)); + ldap_client_params_blueprint.erase(ldap_server_name); + parseLDAPServer(ldap_client_params_blueprint.emplace(ldap_server_name, LDAPClient::Params{}).first->second, config, ldap_server_name); } catch (...) { @@ -240,7 +286,7 @@ void ExternalAuthenticators::setConfiguration(const Poco::Util::AbstractConfigur try { if (kerberos_keys_count > 0) - kerberos_params = parseKerberosParams(config); + parseKerberosParams(kerberos_params.emplace(), config); } catch (...) { @@ -249,7 +295,7 @@ void ExternalAuthenticators::setConfiguration(const Poco::Util::AbstractConfigur } bool ExternalAuthenticators::checkLDAPCredentials(const String & server, const BasicCredentials & credentials, - const LDAPClient::SearchParamsList * search_params, LDAPClient::SearchResultsList * search_results) const + const LDAPClient::RoleSearchParamsList * role_search_params, LDAPClient::SearchResultsList * role_search_results) const { std::optional params; std::size_t params_hash = 0; @@ -267,9 +313,9 @@ bool ExternalAuthenticators::checkLDAPCredentials(const String & server, const B params->password = credentials.getPassword(); params->combineCoreHash(params_hash); - if (search_params) + if (role_search_params) { - for (const auto & params_instance : *search_params) + for (const auto & params_instance : *role_search_params) { params_instance.combineHash(params_hash); } @@ -301,14 +347,14 @@ bool ExternalAuthenticators::checkLDAPCredentials(const String & server, const B // Ensure that search_params are compatible. ( - search_params == nullptr ? - entry.last_successful_search_results.empty() : - search_params->size() == entry.last_successful_search_results.size() + role_search_params == nullptr ? + entry.last_successful_role_search_results.empty() : + role_search_params->size() == entry.last_successful_role_search_results.size() ) ) { - if (search_results) - *search_results = entry.last_successful_search_results; + if (role_search_results) + *role_search_results = entry.last_successful_role_search_results; return true; } @@ -326,7 +372,7 @@ bool ExternalAuthenticators::checkLDAPCredentials(const String & server, const B } LDAPSimpleAuthClient client(params.value()); - const auto result = client.authenticate(search_params, search_results); + const auto result = client.authenticate(role_search_params, role_search_results); const auto current_check_timestamp = std::chrono::steady_clock::now(); // Update the cache, but only if this is the latest check and the server is still configured in a compatible way. @@ -345,9 +391,9 @@ bool ExternalAuthenticators::checkLDAPCredentials(const String & server, const B std::size_t new_params_hash = 0; new_params.combineCoreHash(new_params_hash); - if (search_params) + if (role_search_params) { - for (const auto & params_instance : *search_params) + for (const auto & params_instance : *role_search_params) { params_instance.combineHash(new_params_hash); } @@ -363,17 +409,17 @@ bool ExternalAuthenticators::checkLDAPCredentials(const String & server, const B entry.last_successful_params_hash = params_hash; entry.last_successful_authentication_timestamp = current_check_timestamp; - if (search_results) - entry.last_successful_search_results = *search_results; + if (role_search_results) + entry.last_successful_role_search_results = *role_search_results; else - entry.last_successful_search_results.clear(); + entry.last_successful_role_search_results.clear(); } else if ( entry.last_successful_params_hash != params_hash || ( - search_params == nullptr ? - !entry.last_successful_search_results.empty() : - search_params->size() != entry.last_successful_search_results.size() + role_search_params == nullptr ? + !entry.last_successful_role_search_results.empty() : + role_search_params->size() != entry.last_successful_role_search_results.size() ) ) { diff --git a/src/Access/ExternalAuthenticators.h b/src/Access/ExternalAuthenticators.h index c8feea7eada..24f1f7b6528 100644 --- a/src/Access/ExternalAuthenticators.h +++ b/src/Access/ExternalAuthenticators.h @@ -34,7 +34,7 @@ public: // The name and readiness of the credentials must be verified before calling these. bool checkLDAPCredentials(const String & server, const BasicCredentials & credentials, - const LDAPClient::SearchParamsList * search_params = nullptr, LDAPClient::SearchResultsList * search_results = nullptr) const; + const LDAPClient::RoleSearchParamsList * role_search_params = nullptr, LDAPClient::SearchResultsList * role_search_results = nullptr) const; bool checkKerberosCredentials(const String & realm, const GSSAcceptorContext & credentials) const; GSSAcceptorContext::Params getKerberosParams() const; @@ -44,7 +44,7 @@ private: { std::size_t last_successful_params_hash = 0; std::chrono::steady_clock::time_point last_successful_authentication_timestamp; - LDAPClient::SearchResultsList last_successful_search_results; + LDAPClient::SearchResultsList last_successful_role_search_results; }; using LDAPCache = std::unordered_map; // user name -> cache entry @@ -58,4 +58,6 @@ private: std::optional kerberos_params; }; +void parseLDAPRoleSearchParams(LDAPClient::RoleSearchParams & params, const Poco::Util::AbstractConfiguration & config, const String & prefix); + } diff --git a/src/Access/LDAPAccessStorage.cpp b/src/Access/LDAPAccessStorage.cpp index b47a9b3e041..c1d54e8c9aa 100644 --- a/src/Access/LDAPAccessStorage.cpp +++ b/src/Access/LDAPAccessStorage.cpp @@ -68,34 +68,15 @@ void LDAPAccessStorage::setConfiguration(AccessControlManager * access_control_m common_roles_cfg.insert(role_names.begin(), role_names.end()); } - LDAPClient::SearchParamsList role_search_params_cfg; + LDAPClient::RoleSearchParamsList role_search_params_cfg; if (has_role_mapping) { Poco::Util::AbstractConfiguration::Keys all_keys; config.keys(prefix, all_keys); for (const auto & key : all_keys) { - if (key != "role_mapping" && key.find("role_mapping[") != 0) - continue; - - const String rm_prefix = prefix_str + key; - const String rm_prefix_str = rm_prefix + '.'; - role_search_params_cfg.emplace_back(); - auto & rm_params = role_search_params_cfg.back(); - - rm_params.base_dn = config.getString(rm_prefix_str + "base_dn", ""); - rm_params.search_filter = config.getString(rm_prefix_str + "search_filter", ""); - rm_params.attribute = config.getString(rm_prefix_str + "attribute", "cn"); - rm_params.prefix = config.getString(rm_prefix_str + "prefix", ""); - - auto scope = config.getString(rm_prefix_str + "scope", "subtree"); - boost::algorithm::to_lower(scope); - if (scope == "base") rm_params.scope = LDAPClient::SearchParams::Scope::BASE; - else if (scope == "one_level") rm_params.scope = LDAPClient::SearchParams::Scope::ONE_LEVEL; - else if (scope == "subtree") rm_params.scope = LDAPClient::SearchParams::Scope::SUBTREE; - else if (scope == "children") rm_params.scope = LDAPClient::SearchParams::Scope::CHILDREN; - else - throw Exception("Invalid value of 'scope' field in '" + key + "' section of LDAP user directory, must be one of 'base', 'one_level', 'subtree', or 'children'", ErrorCodes::BAD_ARGUMENTS); + if (key == "role_mapping" || key.find("role_mapping[") == 0) + parseLDAPRoleSearchParams(role_search_params_cfg.emplace_back(), config, prefix_str + key); } } @@ -364,7 +345,7 @@ std::set LDAPAccessStorage::mapExternalRolesNoLock(const LDAPClient::Sea bool LDAPAccessStorage::areLDAPCredentialsValidNoLock(const User & user, const Credentials & credentials, - const ExternalAuthenticators & external_authenticators, LDAPClient::SearchResultsList & search_results) const + const ExternalAuthenticators & external_authenticators, LDAPClient::SearchResultsList & role_search_results) const { if (!credentials.isReady()) return false; @@ -373,7 +354,7 @@ bool LDAPAccessStorage::areLDAPCredentialsValidNoLock(const User & user, const C return false; if (const auto * basic_credentials = dynamic_cast(&credentials)) - return external_authenticators.checkLDAPCredentials(ldap_server_name, *basic_credentials, &role_search_params, &search_results); + return external_authenticators.checkLDAPCredentials(ldap_server_name, *basic_credentials, &role_search_params, &role_search_results); return false; } diff --git a/src/Access/LDAPAccessStorage.h b/src/Access/LDAPAccessStorage.h index ea0ab47c225..33ac9f0a914 100644 --- a/src/Access/LDAPAccessStorage.h +++ b/src/Access/LDAPAccessStorage.h @@ -68,12 +68,12 @@ private: void updateAssignedRolesNoLock(const UUID & id, const String & user_name, const LDAPClient::SearchResultsList & external_roles) const; std::set mapExternalRolesNoLock(const LDAPClient::SearchResultsList & external_roles) const; bool areLDAPCredentialsValidNoLock(const User & user, const Credentials & credentials, - const ExternalAuthenticators & external_authenticators, LDAPClient::SearchResultsList & search_results) const; + const ExternalAuthenticators & external_authenticators, LDAPClient::SearchResultsList & role_search_results) const; mutable std::recursive_mutex mutex; AccessControlManager * access_control_manager = nullptr; String ldap_server_name; - LDAPClient::SearchParamsList role_search_params; + LDAPClient::RoleSearchParamsList role_search_params; std::set common_role_names; // role name that should be granted to all users at all times mutable std::map external_role_hashes; // user name -> LDAPClient::SearchResultsList hash (most recently retrieved and processed) mutable std::map> users_per_roles; // role name -> user names (...it should be granted to; may but don't have to exist for common roles) diff --git a/src/Access/LDAPClient.cpp b/src/Access/LDAPClient.cpp index 5c4b7dd8d99..a8f9675774b 100644 --- a/src/Access/LDAPClient.cpp +++ b/src/Access/LDAPClient.cpp @@ -32,6 +32,11 @@ void LDAPClient::SearchParams::combineHash(std::size_t & seed) const boost::hash_combine(seed, static_cast(scope)); boost::hash_combine(seed, search_filter); boost::hash_combine(seed, attribute); +} + +void LDAPClient::RoleSearchParams::combineHash(std::size_t & seed) const +{ + SearchParams::combineHash(seed); boost::hash_combine(seed, prefix); } @@ -42,6 +47,9 @@ void LDAPClient::Params::combineCoreHash(std::size_t & seed) const boost::hash_combine(seed, bind_dn); boost::hash_combine(seed, user); boost::hash_combine(seed, password); + + if (user_dn_detection) + user_dn_detection->combineHash(seed); } LDAPClient::LDAPClient(const Params & params_) @@ -286,18 +294,33 @@ void LDAPClient::openConnection() if (params.enable_tls == LDAPClient::Params::TLSEnable::YES_STARTTLS) diag(ldap_start_tls_s(handle, nullptr, nullptr)); + final_user_name = escapeForLDAP(params.user); + final_bind_dn = replacePlaceholders(params.bind_dn, { {"{user_name}", final_user_name} }); + final_user_dn = final_bind_dn; // The default value... may be updated right after a successful bind. + switch (params.sasl_mechanism) { case LDAPClient::Params::SASLMechanism::SIMPLE: { - const auto escaped_user_name = escapeForLDAP(params.user); - const auto bind_dn = replacePlaceholders(params.bind_dn, { {"{user_name}", escaped_user_name} }); - ::berval cred; cred.bv_val = const_cast(params.password.c_str()); cred.bv_len = params.password.size(); - diag(ldap_sasl_bind_s(handle, bind_dn.c_str(), LDAP_SASL_SIMPLE, &cred, nullptr, nullptr, nullptr)); + diag(ldap_sasl_bind_s(handle, final_bind_dn.c_str(), LDAP_SASL_SIMPLE, &cred, nullptr, nullptr, nullptr)); + + // Once bound, run the user DN search query and update the default value, if asked. + if (params.user_dn_detection) + { + const auto user_dn_search_results = search(*params.user_dn_detection); + + if (user_dn_search_results.empty()) + throw Exception("Failed to detect user DN: empty search results", ErrorCodes::LDAP_ERROR); + + if (user_dn_search_results.size() > 1) + throw Exception("Failed to detect user DN: more than one entry in the search results", ErrorCodes::LDAP_ERROR); + + final_user_dn = *user_dn_search_results.begin(); + } break; } @@ -316,6 +339,9 @@ void LDAPClient::closeConnection() noexcept ldap_unbind_ext_s(handle, nullptr, nullptr); handle = nullptr; + final_user_name.clear(); + final_bind_dn.clear(); + final_user_dn.clear(); } LDAPClient::SearchResults LDAPClient::search(const SearchParams & search_params) @@ -333,10 +359,19 @@ LDAPClient::SearchResults LDAPClient::search(const SearchParams & search_params) case SearchParams::Scope::CHILDREN: scope = LDAP_SCOPE_CHILDREN; break; } - const auto escaped_user_name = escapeForLDAP(params.user); - const auto bind_dn = replacePlaceholders(params.bind_dn, { {"{user_name}", escaped_user_name} }); - const auto base_dn = replacePlaceholders(search_params.base_dn, { {"{user_name}", escaped_user_name}, {"{bind_dn}", bind_dn} }); - const auto search_filter = replacePlaceholders(search_params.search_filter, { {"{user_name}", escaped_user_name}, {"{bind_dn}", bind_dn}, {"{base_dn}", base_dn} }); + const auto final_base_dn = replacePlaceholders(search_params.base_dn, { + {"{user_name}", final_user_name}, + {"{bind_dn}", final_bind_dn}, + {"{user_dn}", final_user_dn} + }); + + const auto final_search_filter = replacePlaceholders(search_params.search_filter, { + {"{user_name}", final_user_name}, + {"{bind_dn}", final_bind_dn}, + {"{user_dn}", final_user_dn}, + {"{base_dn}", final_base_dn} + }); + char * attrs[] = { const_cast(search_params.attribute.c_str()), nullptr }; ::timeval timeout = { params.search_timeout.count(), 0 }; LDAPMessage* msgs = nullptr; @@ -349,7 +384,7 @@ LDAPClient::SearchResults LDAPClient::search(const SearchParams & search_params) } }); - diag(ldap_search_ext_s(handle, base_dn.c_str(), scope, search_filter.c_str(), attrs, 0, nullptr, nullptr, &timeout, params.search_limit, &msgs)); + diag(ldap_search_ext_s(handle, final_base_dn.c_str(), scope, final_search_filter.c_str(), attrs, 0, nullptr, nullptr, &timeout, params.search_limit, &msgs)); for ( auto * msg = ldap_first_message(handle, msgs); @@ -361,6 +396,27 @@ LDAPClient::SearchResults LDAPClient::search(const SearchParams & search_params) { case LDAP_RES_SEARCH_ENTRY: { + // Extract DN separately, if the requested attribute is DN. + if (boost::iequals("dn", search_params.attribute)) + { + BerElement * ber = nullptr; + + SCOPE_EXIT({ + if (ber) + { + ber_free(ber, 0); + ber = nullptr; + } + }); + + ::berval bv; + + diag(ldap_get_dn_ber(handle, msg, &ber, &bv)); + + if (bv.bv_val && bv.bv_len > 0) + result.emplace(bv.bv_val, bv.bv_len); + } + BerElement * ber = nullptr; SCOPE_EXIT({ @@ -471,12 +527,12 @@ LDAPClient::SearchResults LDAPClient::search(const SearchParams & search_params) return result; } -bool LDAPSimpleAuthClient::authenticate(const SearchParamsList * search_params, SearchResultsList * search_results) +bool LDAPSimpleAuthClient::authenticate(const RoleSearchParamsList * role_search_params, SearchResultsList * role_search_results) { if (params.user.empty()) throw Exception("LDAP authentication of a user with empty name is not allowed", ErrorCodes::BAD_ARGUMENTS); - if (!search_params != !search_results) + if (!role_search_params != !role_search_results) throw Exception("Cannot return LDAP search results", ErrorCodes::BAD_ARGUMENTS); // Silently reject authentication attempt if the password is empty as if it didn't match. @@ -489,21 +545,21 @@ bool LDAPSimpleAuthClient::authenticate(const SearchParamsList * search_params, openConnection(); // While connected, run search queries and save the results, if asked. - if (search_params) + if (role_search_params) { - search_results->clear(); - search_results->reserve(search_params->size()); + role_search_results->clear(); + role_search_results->reserve(role_search_params->size()); try { - for (const auto & single_search_params : *search_params) + for (const auto & params_instance : *role_search_params) { - search_results->emplace_back(search(single_search_params)); + role_search_results->emplace_back(search(params_instance)); } } catch (...) { - search_results->clear(); + role_search_results->clear(); throw; } } @@ -532,7 +588,7 @@ LDAPClient::SearchResults LDAPClient::search(const SearchParams &) throw Exception("ClickHouse was built without LDAP support", ErrorCodes::FEATURE_IS_NOT_ENABLED_AT_BUILD_TIME); } -bool LDAPSimpleAuthClient::authenticate(const SearchParamsList *, SearchResultsList *) +bool LDAPSimpleAuthClient::authenticate(const RoleSearchParamsList *, SearchResultsList *) { throw Exception("ClickHouse was built without LDAP support", ErrorCodes::FEATURE_IS_NOT_ENABLED_AT_BUILD_TIME); } diff --git a/src/Access/LDAPClient.h b/src/Access/LDAPClient.h index 4fc97bb957b..388e7ad0f0d 100644 --- a/src/Access/LDAPClient.h +++ b/src/Access/LDAPClient.h @@ -38,12 +38,20 @@ public: Scope scope = Scope::SUBTREE; String search_filter; String attribute = "cn"; + + void combineHash(std::size_t & seed) const; + }; + + struct RoleSearchParams + : public SearchParams + { String prefix; void combineHash(std::size_t & seed) const; }; - using SearchParamsList = std::vector; + using RoleSearchParamsList = std::vector; + using SearchResults = std::set; using SearchResultsList = std::vector; @@ -105,6 +113,8 @@ public: String user; String password; + std::optional user_dn_detection; + std::chrono::seconds verification_cooldown{0}; std::chrono::seconds operation_timeout{40}; @@ -134,6 +144,9 @@ protected: #if USE_LDAP LDAP * handle = nullptr; #endif + String final_user_name; + String final_bind_dn; + String final_user_dn; }; class LDAPSimpleAuthClient @@ -141,7 +154,7 @@ class LDAPSimpleAuthClient { public: using LDAPClient::LDAPClient; - bool authenticate(const SearchParamsList * search_params, SearchResultsList * search_results); + bool authenticate(const RoleSearchParamsList * role_search_params, SearchResultsList * role_search_results); }; } diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index 292adc0e124..a0f36163d68 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -107,7 +107,7 @@ list (APPEND clickhouse_common_io_sources ${CONFIG_BUILD}) list (APPEND clickhouse_common_io_headers ${CONFIG_VERSION} ${CONFIG_COMMON}) list (APPEND dbms_sources Functions/IFunction.cpp Functions/FunctionFactory.cpp Functions/FunctionHelpers.cpp Functions/extractTimeZoneFromFunctionArguments.cpp Functions/replicate.cpp Functions/FunctionsLogical.cpp) -list (APPEND dbms_headers Functions/IFunctionImpl.h Functions/FunctionFactory.h Functions/FunctionHelpers.h Functions/extractTimeZoneFromFunctionArguments.h Functions/replicate.h Functions/FunctionsLogical.h) +list (APPEND dbms_headers Functions/IFunction.h Functions/FunctionFactory.h Functions/FunctionHelpers.h Functions/extractTimeZoneFromFunctionArguments.h Functions/replicate.h Functions/FunctionsLogical.h) list (APPEND dbms_sources AggregateFunctions/AggregateFunctionFactory.cpp diff --git a/src/Common/Allocator.h b/src/Common/Allocator.h index ebfd654d558..f20f11889ce 100644 --- a/src/Common/Allocator.h +++ b/src/Common/Allocator.h @@ -99,9 +99,17 @@ public: /// Free memory range. void free(void * buf, size_t size) { - checkSize(size); - freeNoTrack(buf, size); - CurrentMemoryTracker::free(size); + try + { + checkSize(size); + freeNoTrack(buf, size); + CurrentMemoryTracker::free(size); + } + catch (...) + { + DB::tryLogCurrentException("Allocator::free"); + throw; + } } /** Enlarge memory range. diff --git a/src/Common/Config/ConfigProcessor.cpp b/src/Common/Config/ConfigProcessor.cpp index 39ab407579d..bc2a8a27943 100644 --- a/src/Common/Config/ConfigProcessor.cpp +++ b/src/Common/Config/ConfigProcessor.cpp @@ -462,10 +462,19 @@ XMLDocumentPtr ConfigProcessor::processConfig( } else { - /// When we can use config embedded in binary. + /// These embedded files added during build with some cmake magic. + /// Look at the end of programs/sever/CMakeLists.txt. + std::string embedded_name; if (path == "config.xml") + embedded_name = "embedded.xml"; + + if (path == "keeper_config.xml") + embedded_name = "keeper_embedded.xml"; + + /// When we can use config embedded in binary. + if (!embedded_name.empty()) { - auto resource = getResource("embedded.xml"); + auto resource = getResource(embedded_name); if (resource.empty()) throw Exception(ErrorCodes::FILE_DOESNT_EXIST, "Configuration file {} doesn't exist and there is no embedded config", path); LOG_DEBUG(log, "There is no file '{}', will use embedded config.", path); diff --git a/src/Common/HashTable/LRUHashMap.h b/src/Common/HashTable/LRUHashMap.h index 870fb219523..bdefee351b1 100644 --- a/src/Common/HashTable/LRUHashMap.h +++ b/src/Common/HashTable/LRUHashMap.h @@ -220,6 +220,12 @@ public: return find(key) != nullptr; } + Value & ALWAYS_INLINE operator[](const Key & key) + { + auto [it, _] = emplace(key); + return it->getMapped(); + } + bool ALWAYS_INLINE erase(const Key & key) { auto key_hash = Base::hash(key); diff --git a/src/Common/NamePrompter.h b/src/Common/NamePrompter.h index 5f7832c4423..bb17f860f29 100644 --- a/src/Common/NamePrompter.h +++ b/src/Common/NamePrompter.h @@ -90,17 +90,16 @@ private: } }; -template + +template class IHints { public: - virtual std::vector getAllRegisteredNames() const = 0; std::vector getHints(const String & name) const { - static const auto registered_names = getAllRegisteredNames(); - return prompter.getHints(name, registered_names); + return prompter.getHints(name, getAllRegisteredNames()); } virtual ~IHints() = default; diff --git a/src/Common/PODArray.h b/src/Common/PODArray.h index 8f6414b3fa9..d90ac0469c5 100644 --- a/src/Common/PODArray.h +++ b/src/Common/PODArray.h @@ -513,7 +513,7 @@ public: insertPrepare(from_begin, from_end); if (unlikely(bytes_to_move)) - memcpy(this->c_end + bytes_to_copy - bytes_to_move, this->c_end - bytes_to_move, bytes_to_move); + memmove(this->c_end + bytes_to_copy - bytes_to_move, this->c_end - bytes_to_move, bytes_to_move); memcpy(this->c_end - bytes_to_move, reinterpret_cast(&*from_begin), bytes_to_copy); diff --git a/src/Common/examples/CMakeLists.txt b/src/Common/examples/CMakeLists.txt index 0395cb32438..c94ce580942 100644 --- a/src/Common/examples/CMakeLists.txt +++ b/src/Common/examples/CMakeLists.txt @@ -36,7 +36,7 @@ add_executable (arena_with_free_lists arena_with_free_lists.cpp) target_link_libraries (arena_with_free_lists PRIVATE dbms) add_executable (lru_hash_map_perf lru_hash_map_perf.cpp) -target_link_libraries (lru_hash_map_perf PRIVATE clickhouse_common_io) +target_link_libraries (lru_hash_map_perf PRIVATE dbms) add_executable (thread_creation_latency thread_creation_latency.cpp) target_link_libraries (thread_creation_latency PRIVATE clickhouse_common_io) diff --git a/src/Common/examples/lru_hash_map_perf.cpp b/src/Common/examples/lru_hash_map_perf.cpp index 14beff3f7da..c40548bea49 100644 --- a/src/Common/examples/lru_hash_map_perf.cpp +++ b/src/Common/examples/lru_hash_map_perf.cpp @@ -7,23 +7,26 @@ #include #include +#include +#include + template class LRUHashMapBasic { public: using key_type = Key; using value_type = Value; - using list_type = std::list; - using node = std::pair; - using map_type = std::unordered_map>; + using list_type = std::list>; + using map_type = std::unordered_map; - LRUHashMapBasic(size_t max_size_, bool preallocated) + LRUHashMapBasic(size_t max_size_, bool preallocated = false) : hash_map(preallocated ? max_size_ : 32) , max_size(max_size_) { } - void insert(const Key &key, const Value &value) + template + std::pair emplace(const Key &key, Args &&... args) { auto it = hash_map.find(key); @@ -33,40 +36,39 @@ public: { auto iterator_to_remove = list.begin(); - hash_map.erase(*iterator_to_remove); + auto & key_to_remove = iterator_to_remove->first; + hash_map.erase(key_to_remove); + list.erase(iterator_to_remove); } - list.push_back(key); - hash_map[key] = std::make_pair(value, --list.end()); + + Value value(std::forward(args)...); + auto node = std::make_pair(key, std::move(value)); + + list.push_back(std::move(node)); + + auto inserted_iterator = --list.end(); + + hash_map[key] = inserted_iterator; + + return std::make_pair(&inserted_iterator->second, true); } else { - auto & [value_to_update, iterator_in_list_to_update] = it->second; + auto & iterator_in_list_to_update = it->second; list.splice(list.end(), list, iterator_in_list_to_update); + iterator_in_list_to_update = --list.end(); - iterator_in_list_to_update = list.end(); - value_to_update = value; + return std::make_pair(&iterator_in_list_to_update->second, false); } } - value_type & get(const key_type &key) + value_type & operator[](const key_type & key) { - auto iterator_in_map = hash_map.find(key); - assert(iterator_in_map != hash_map.end()); - - auto & [value_to_return, iterator_in_list_to_update] = iterator_in_map->second; - - list.splice(list.end(), list, iterator_in_list_to_update); - iterator_in_list_to_update = list.end(); - - return value_to_return; - } - - const value_type & get(const key_type & key) const - { - return const_cast *>(this)->get(key); + auto [it, _] = emplace(key); + return *it; } size_t getMaxSize() const @@ -101,110 +103,45 @@ private: size_t max_size; }; -std::vector generateNumbersToInsert(size_t numbers_to_insert_size) +template +static void NO_INLINE test(const Key * data, size_t size, const std::string & name) { - std::vector numbers; - numbers.reserve(numbers_to_insert_size); - - std::random_device rd; - pcg64 gen(rd()); - - UInt64 min = std::numeric_limits::min(); - UInt64 max = std::numeric_limits::max(); - - auto distribution = std::uniform_int_distribution<>(min, max); - - for (size_t i = 0; i < numbers_to_insert_size; ++i) - { - UInt64 number = distribution(gen); - numbers.emplace_back(number); - } - - return numbers; -} - -void testInsertElementsIntoHashMap(size_t map_size, const std::vector & numbers_to_insert, bool preallocated) -{ - size_t numbers_to_insert_size = numbers_to_insert.size(); - std::cout << "TestInsertElementsIntoHashMap preallocated map size: " << map_size << " numbers to insert size: " << numbers_to_insert_size; - std::cout << std::endl; - - HashMap hash_map(preallocated ? map_size : 32); - + size_t cache_size = size / 10; + Map cache(cache_size); Stopwatch watch; - for (size_t i = 0; i < numbers_to_insert_size; ++i) - hash_map.insert({ numbers_to_insert[i], numbers_to_insert[i] }); + for (size_t i = 0; i < size; ++i) + ++cache[data[i]]; - std::cout << "Inserted in " << watch.elapsedMilliseconds() << " milliseconds" << std::endl; + watch.stop(); - UInt64 summ = 0; - - for (size_t i = 0; i < numbers_to_insert_size; ++i) - { - auto * it = hash_map.find(numbers_to_insert[i]); - - if (it) - summ += it->getMapped(); - } - - std::cout << "Calculated summ: " << summ << " in " << watch.elapsedMilliseconds() << " milliseconds" << std::endl; + std::cerr << name + << ":\nElapsed: " << watch.elapsedSeconds() + << " (" << size / watch.elapsedSeconds() << " elem/sec.)" + << ", map size: " << cache.size() << "\n"; } -void testInsertElementsIntoStandardMap(size_t map_size, const std::vector & numbers_to_insert, bool preallocated) +template +static void NO_INLINE testForType(size_t method, size_t rows_size) { - size_t numbers_to_insert_size = numbers_to_insert.size(); - std::cout << "TestInsertElementsIntoStandardMap map size: " << map_size << " numbers to insert size: " << numbers_to_insert_size; - std::cout << std::endl; + std::cerr << std::fixed << std::setprecision(3); - std::unordered_map hash_map(preallocated ? map_size : 32); + std::vector data(rows_size); - Stopwatch watch; - - for (size_t i = 0; i < numbers_to_insert_size; ++i) - hash_map.insert({ numbers_to_insert[i], numbers_to_insert[i] }); - - std::cout << "Inserted in " << watch.elapsedMilliseconds() << " milliseconds" << std::endl; - - UInt64 summ = 0; - - for (size_t i = 0; i < numbers_to_insert_size; ++i) { - auto it = hash_map.find(numbers_to_insert[i]); - - if (it != hash_map.end()) - summ += it->second; + DB::ReadBufferFromFileDescriptor in1(STDIN_FILENO); + DB::CompressedReadBuffer in2(in1); + in2.readStrict(reinterpret_cast(data.data()), sizeof(data[0]) * rows_size); } - std::cout << "Calculated summ: " << summ << " in " << watch.elapsedMilliseconds() << " milliseconds" << std::endl; -} - -template -UInt64 testInsertIntoEmptyCache(size_t map_size, const std::vector & numbers_to_insert, bool preallocated) -{ - size_t numbers_to_insert_size = numbers_to_insert.size(); - std::cout << "Test testInsertPreallocated preallocated map size: " << map_size << " numbers to insert size: " << numbers_to_insert_size; - std::cout << std::endl; - - LRUCache cache(map_size, preallocated); - Stopwatch watch; - - for (size_t i = 0; i < numbers_to_insert_size; ++i) + if (method == 0) { - cache.insert(numbers_to_insert[i], numbers_to_insert[i]); + test>(data.data(), data.size(), "CH HashMap"); + } + else if (method == 1) + { + test>(data.data(), data.size(), "BasicLRU"); } - - std::cout << "Inserted in " << watch.elapsedMilliseconds() << " milliseconds" << std::endl; - - UInt64 summ = 0; - - for (size_t i = 0; i < numbers_to_insert_size; ++i) - if (cache.contains(numbers_to_insert[i])) - summ += cache.get(numbers_to_insert[i]); - - std::cout << "Calculated summ: " << summ << " in " << watch.elapsedMilliseconds() << " milliseconds" << std::endl; - - return summ; } int main(int argc, char ** argv) @@ -212,33 +149,34 @@ int main(int argc, char ** argv) (void)(argc); (void)(argv); - size_t hash_map_size = 1200000; - size_t numbers_to_insert_size = 12000000; - std::vector numbers = generateNumbersToInsert(numbers_to_insert_size); + if (argc < 4) + { + std::cerr << "Usage: program method column_type_name rows_count < input_column.bin \n"; + return 1; + } - std::cout << "Test insert into HashMap preallocated=0" << std::endl; - testInsertElementsIntoHashMap(hash_map_size, numbers, true); - std::cout << std::endl; + size_t method = std::stoull(argv[1]); + std::string type_name = std::string(argv[2]); + size_t n = std::stoull(argv[3]); - std::cout << "Test insert into HashMap preallocated=1" << std::endl; - testInsertElementsIntoHashMap(hash_map_size, numbers, true); - std::cout << std::endl; - - std::cout << "Test LRUHashMap preallocated=0" << std::endl; - testInsertIntoEmptyCache>(hash_map_size, numbers, false); - std::cout << std::endl; - - std::cout << "Test LRUHashMap preallocated=1" << std::endl; - testInsertIntoEmptyCache>(hash_map_size, numbers, true); - std::cout << std::endl; - - std::cout << "Test LRUHashMapBasic preallocated=0" << std::endl; - testInsertIntoEmptyCache>(hash_map_size, numbers, false); - std::cout << std::endl; - - std::cout << "Test LRUHashMapBasic preallocated=1" << std::endl; - testInsertIntoEmptyCache>(hash_map_size, numbers, true); - std::cout << std::endl; + if (type_name == "UInt8") + testForType(method, n); + else if (type_name == "UInt16") + testForType(method, n); + else if (type_name == "UInt32") + testForType(method, n); + else if (type_name == "UInt64") + testForType(method, n); + else if (type_name == "Int8") + testForType(method, n); + else if (type_name == "Int16") + testForType(method, n); + else if (type_name == "Int32") + testForType(method, n); + else if (type_name == "Int64") + testForType(method, n); + else + std::cerr << "Unexpected type passed " << type_name << std::endl; return 0; } diff --git a/src/Common/isLocalAddress.cpp b/src/Common/isLocalAddress.cpp index 8da281e3051..4167a24ab21 100644 --- a/src/Common/isLocalAddress.cpp +++ b/src/Common/isLocalAddress.cpp @@ -1,29 +1,88 @@ #include +#include #include +#include #include -#include -#include +#include +#include #include namespace DB { +namespace ErrorCodes +{ + extern const int SYSTEM_ERROR; +} + +namespace +{ + +struct NetworkInterfaces +{ + ifaddrs * ifaddr; + NetworkInterfaces() + { + if (getifaddrs(&ifaddr) == -1) + { + throwFromErrno("Cannot getifaddrs", ErrorCodes::SYSTEM_ERROR); + } + } + + bool hasAddress(const Poco::Net::IPAddress & address) const + { + ifaddrs * iface; + for (iface = ifaddr; iface != nullptr; iface = iface->ifa_next) + { + /// Point-to-point (VPN) addresses may have NULL ifa_addr + if (!iface->ifa_addr) + continue; + + auto family = iface->ifa_addr->sa_family; + std::optional interface_address; + switch (family) + { + /// We interested only in IP-adresses + case AF_INET: + { + interface_address.emplace(*(iface->ifa_addr)); + break; + } + case AF_INET6: + { + interface_address.emplace(&reinterpret_cast(iface->ifa_addr)->sin6_addr, sizeof(struct in6_addr)); + break; + } + default: + continue; + } + + /** Compare the addresses without taking into account `scope`. + * Theoretically, this may not be correct - depends on `route` setting + * - through which interface we will actually access the specified address. + */ + if (interface_address->length() == address.length() + && 0 == memcmp(interface_address->addr(), address.addr(), address.length())) + return true; + } + return false; + } + + ~NetworkInterfaces() + { + freeifaddrs(ifaddr); + } +}; + +} + + bool isLocalAddress(const Poco::Net::IPAddress & address) { - static auto interfaces = Poco::Net::NetworkInterface::list(); - - return interfaces.end() != std::find_if(interfaces.begin(), interfaces.end(), - [&] (const Poco::Net::NetworkInterface & interface) - { - /** Compare the addresses without taking into account `scope`. - * Theoretically, this may not be correct - depends on `route` setting - * - through which interface we will actually access the specified address. - */ - return interface.address().length() == address.length() - && 0 == memcmp(interface.address().addr(), address.addr(), address.length()); - }); + NetworkInterfaces interfaces; + return interfaces.hasAddress(address); } bool isLocalAddress(const Poco::Net::SocketAddress & address, UInt16 clickhouse_port) diff --git a/src/Common/tests/gtest_local_address.cpp b/src/Common/tests/gtest_local_address.cpp new file mode 100644 index 00000000000..504fba19713 --- /dev/null +++ b/src/Common/tests/gtest_local_address.cpp @@ -0,0 +1,19 @@ +#include +#include +#include +#include +#include + + +TEST(LocalAddress, SmokeTest) +{ + auto cmd = DB::ShellCommand::executeDirect("/bin/hostname", {"-i"}); + std::string address_str; + DB::readString(address_str, cmd->out); + cmd->wait(); + std::cerr << "Got Address:" << address_str << std::endl; + + Poco::Net::IPAddress address(address_str); + + EXPECT_TRUE(DB::isLocalAddress(address)); +} diff --git a/src/Common/tests/gtest_pod_array.cpp b/src/Common/tests/gtest_pod_array.cpp index 74fbf447f29..b5ec45c3e5d 100644 --- a/src/Common/tests/gtest_pod_array.cpp +++ b/src/Common/tests/gtest_pod_array.cpp @@ -419,31 +419,56 @@ TEST(Common, PODArrayBasicSwapMoveConstructor) TEST(Common, PODArrayInsert) { - std::string str = "test_string_abacaba"; - PODArray chars; - chars.insert(chars.end(), str.begin(), str.end()); - EXPECT_EQ(str, std::string(chars.data(), chars.size())); - - std::string insert_in_the_middle = "insert_in_the_middle"; - auto pos = str.size() / 2; - str.insert(str.begin() + pos, insert_in_the_middle.begin(), insert_in_the_middle.end()); - chars.insert(chars.begin() + pos, insert_in_the_middle.begin(), insert_in_the_middle.end()); - EXPECT_EQ(str, std::string(chars.data(), chars.size())); - - std::string insert_with_resize; - insert_with_resize.reserve(chars.capacity() * 2); - char cur_char = 'a'; - while (insert_with_resize.size() < insert_with_resize.capacity()) { - insert_with_resize += cur_char; - if (cur_char == 'z') - cur_char = 'a'; - else - ++cur_char; + std::string str = "test_string_abacaba"; + PODArray chars; + chars.insert(chars.end(), str.begin(), str.end()); + EXPECT_EQ(str, std::string(chars.data(), chars.size())); + + std::string insert_in_the_middle = "insert_in_the_middle"; + auto pos = str.size() / 2; + str.insert(str.begin() + pos, insert_in_the_middle.begin(), insert_in_the_middle.end()); + chars.insert(chars.begin() + pos, insert_in_the_middle.begin(), insert_in_the_middle.end()); + EXPECT_EQ(str, std::string(chars.data(), chars.size())); + + std::string insert_with_resize; + insert_with_resize.reserve(chars.capacity() * 2); + char cur_char = 'a'; + while (insert_with_resize.size() < insert_with_resize.capacity()) + { + insert_with_resize += cur_char; + if (cur_char == 'z') + cur_char = 'a'; + else + ++cur_char; + } + str.insert(str.begin(), insert_with_resize.begin(), insert_with_resize.end()); + chars.insert(chars.begin(), insert_with_resize.begin(), insert_with_resize.end()); + EXPECT_EQ(str, std::string(chars.data(), chars.size())); + } + { + PODArray values; + PODArray values_to_insert; + + for (size_t i = 0; i < 120; ++i) + values.emplace_back(i); + + values.insert(values.begin() + 1, values_to_insert.begin(), values_to_insert.end()); + ASSERT_EQ(values.size(), 120); + + values_to_insert.emplace_back(0); + values_to_insert.emplace_back(1); + + values.insert(values.begin() + 1, values_to_insert.begin(), values_to_insert.end()); + ASSERT_EQ(values.size(), 122); + + values_to_insert.clear(); + for (size_t i = 0; i < 240; ++i) + values_to_insert.emplace_back(i); + + values.insert(values.begin() + 1, values_to_insert.begin(), values_to_insert.end()); + ASSERT_EQ(values.size(), 362); } - str.insert(str.begin(), insert_with_resize.begin(), insert_with_resize.end()); - chars.insert(chars.begin(), insert_with_resize.begin(), insert_with_resize.end()); - EXPECT_EQ(str, std::string(chars.data(), chars.size())); } TEST(Common, PODArrayInsertFromItself) diff --git a/src/Common/tests/gtest_sensitive_data_masker.cpp b/src/Common/tests/gtest_sensitive_data_masker.cpp index b8125c77b9b..7ebf141d961 100644 --- a/src/Common/tests/gtest_sensitive_data_masker.cpp +++ b/src/Common/tests/gtest_sensitive_data_masker.cpp @@ -223,7 +223,7 @@ TEST(Common, SensitiveDataMasker) { EXPECT_EQ( std::string(e.message()), - "SensitiveDataMasker: cannot compile re2: ())(, error: missing ): ())(. Look at https://github.com/google/re2/wiki/Syntax for reference.: while adding query masking rule 'test'." + "SensitiveDataMasker: cannot compile re2: ())(, error: unexpected ): ())(. Look at https://github.com/google/re2/wiki/Syntax for reference.: while adding query masking rule 'test'." ); EXPECT_EQ(e.code(), DB::ErrorCodes::CANNOT_COMPILE_REGEXP); } diff --git a/src/Common/ya.make.in b/src/Common/ya.make.in index fd6a805891e..459266a54e7 100644 --- a/src/Common/ya.make.in +++ b/src/Common/ya.make.in @@ -17,6 +17,7 @@ PEERDIR( contrib/libs/openssl contrib/libs/poco/NetSSL_OpenSSL contrib/libs/re2 + contrib/libs/cxxsupp/libcxxabi-parts contrib/restricted/dragonbox ) diff --git a/src/Compression/tests/gtest_compressionCodec.cpp b/src/Compression/tests/gtest_compressionCodec.cpp index 20fe5476807..6ba2d3457ea 100644 --- a/src/Compression/tests/gtest_compressionCodec.cpp +++ b/src/Compression/tests/gtest_compressionCodec.cpp @@ -345,10 +345,12 @@ CodecTestSequence operator*(CodecTestSequence && left, T times) std::ostream & operator<<(std::ostream & ostr, const Codec & codec) { - return ostr << "Codec{" - << "name: " << codec.codec_statement - << ", expected_compression_ratio: " << *codec.expected_compression_ratio - << "}"; + ostr << "Codec{" + << "name: " << codec.codec_statement; + if (codec.expected_compression_ratio) + return ostr << ", expected_compression_ratio: " << *codec.expected_compression_ratio << "}"; + else + return ostr << "}"; } std::ostream & operator<<(std::ostream & ostr, const CodecTestSequence & seq) diff --git a/src/Coordination/KeeperServer.cpp b/src/Coordination/KeeperServer.cpp index a3214474e96..ba904a535d0 100644 --- a/src/Coordination/KeeperServer.cpp +++ b/src/Coordination/KeeperServer.cpp @@ -14,6 +14,7 @@ #include #include #include +#include #include namespace DB @@ -59,6 +60,21 @@ void setSSLParams(nuraft::asio_service::options & asio_opts) } #endif +std::string getSnapshotsPathFromConfig(const Poco::Util::AbstractConfiguration & config, bool standalone_keeper) +{ + /// the most specialized path + if (config.has("keeper_server.snapshot_storage_path")) + return config.getString("keeper_server.snapshot_storage_path"); + + if (config.has("keeper_server.storage_path")) + return std::filesystem::path{config.getString("keeper_server.storage_path")} / "snapshots"; + + if (standalone_keeper) + return std::filesystem::path{config.getString("path", KEEPER_DEFAULT_PATH)} / "snapshots"; + else + return std::filesystem::path{config.getString("path", DBMS_DEFAULT_PATH)} / "coordination/snapshots"; +} + } KeeperServer::KeeperServer( @@ -66,14 +82,15 @@ KeeperServer::KeeperServer( const CoordinationSettingsPtr & coordination_settings_, const Poco::Util::AbstractConfiguration & config, ResponsesQueue & responses_queue_, - SnapshotsQueue & snapshots_queue_) + SnapshotsQueue & snapshots_queue_, + bool standalone_keeper) : server_id(server_id_) , coordination_settings(coordination_settings_) , state_machine(nuraft::cs_new( responses_queue_, snapshots_queue_, - config.getString("keeper_server.snapshot_storage_path", config.getString("path", DBMS_DEFAULT_PATH) + "coordination/snapshots"), + getSnapshotsPathFromConfig(config, standalone_keeper), coordination_settings)) - , state_manager(nuraft::cs_new(server_id, "keeper_server", config, coordination_settings)) + , state_manager(nuraft::cs_new(server_id, "keeper_server", config, coordination_settings, standalone_keeper)) , log(&Poco::Logger::get("KeeperServer")) { if (coordination_settings->quorum_reads) diff --git a/src/Coordination/KeeperServer.h b/src/Coordination/KeeperServer.h index 11900ebb213..421be331537 100644 --- a/src/Coordination/KeeperServer.h +++ b/src/Coordination/KeeperServer.h @@ -55,7 +55,8 @@ public: const CoordinationSettingsPtr & coordination_settings_, const Poco::Util::AbstractConfiguration & config, ResponsesQueue & responses_queue_, - SnapshotsQueue & snapshots_queue_); + SnapshotsQueue & snapshots_queue_, + bool standalone_keeper); void startup(); diff --git a/src/Coordination/KeeperStateManager.cpp b/src/Coordination/KeeperStateManager.cpp index e57ae7e7c19..d54752ec168 100644 --- a/src/Coordination/KeeperStateManager.cpp +++ b/src/Coordination/KeeperStateManager.cpp @@ -1,5 +1,6 @@ #include #include +#include namespace DB { @@ -9,6 +10,26 @@ namespace ErrorCodes extern const int RAFT_ERROR; } +namespace +{ + std::string getLogsPathFromConfig( + const std::string & config_prefix, const Poco::Util::AbstractConfiguration & config, bool standalone_keeper) +{ + /// the most specialized path + if (config.has(config_prefix + ".log_storage_path")) + return config.getString(config_prefix + ".log_storage_path"); + + if (config.has(config_prefix + ".storage_path")) + return std::filesystem::path{config.getString(config_prefix + ".storage_path")} / "logs"; + + if (standalone_keeper) + return std::filesystem::path{config.getString("path", KEEPER_DEFAULT_PATH)} / "logs"; + else + return std::filesystem::path{config.getString("path", DBMS_DEFAULT_PATH)} / "coordination/logs"; +} + +} + KeeperStateManager::KeeperStateManager(int server_id_, const std::string & host, int port, const std::string & logs_path) : my_server_id(server_id_) , my_port(port) @@ -24,11 +45,12 @@ KeeperStateManager::KeeperStateManager( int my_server_id_, const std::string & config_prefix, const Poco::Util::AbstractConfiguration & config, - const CoordinationSettingsPtr & coordination_settings) + const CoordinationSettingsPtr & coordination_settings, + bool standalone_keeper) : my_server_id(my_server_id_) , secure(config.getBool(config_prefix + ".raft_configuration.secure", false)) , log_store(nuraft::cs_new( - config.getString(config_prefix + ".log_storage_path", config.getString("path", DBMS_DEFAULT_PATH) + "coordination/logs"), + getLogsPathFromConfig(config_prefix, config, standalone_keeper), coordination_settings->rotate_log_storage_interval, coordination_settings->force_sync)) , cluster_config(nuraft::cs_new()) { diff --git a/src/Coordination/KeeperStateManager.h b/src/Coordination/KeeperStateManager.h index cb5181760cb..2a93a1dc62b 100644 --- a/src/Coordination/KeeperStateManager.h +++ b/src/Coordination/KeeperStateManager.h @@ -17,7 +17,8 @@ public: int server_id_, const std::string & config_prefix, const Poco::Util::AbstractConfiguration & config, - const CoordinationSettingsPtr & coordination_settings); + const CoordinationSettingsPtr & coordination_settings, + bool standalone_keeper); KeeperStateManager( int server_id_, diff --git a/src/Coordination/KeeperStorage.cpp b/src/Coordination/KeeperStorage.cpp index 5f2d6141be9..9e8d2a124e9 100644 --- a/src/Coordination/KeeperStorage.cpp +++ b/src/Coordination/KeeperStorage.cpp @@ -547,6 +547,17 @@ struct KeeperStorageCloseRequest final : public KeeperStorageRequest } }; +/// Dummy implementation TODO: implement simple ACL +struct KeeperStorageAuthRequest final : public KeeperStorageRequest +{ + using KeeperStorageRequest::KeeperStorageRequest; + std::pair process(KeeperStorage::Container &, KeeperStorage::Ephemerals &, int64_t, int64_t) const override + { + Coordination::ZooKeeperResponsePtr response_ptr = zk_request->makeResponse(); + return { response_ptr, {} }; + } +}; + void KeeperStorage::finalize() { if (finalized) @@ -611,7 +622,7 @@ KeeperWrapperFactory::KeeperWrapperFactory() { registerKeeperRequestWrapper(*this); registerKeeperRequestWrapper(*this); - //registerKeeperRequestWrapper(*this); + registerKeeperRequestWrapper(*this); registerKeeperRequestWrapper(*this); registerKeeperRequestWrapper(*this); registerKeeperRequestWrapper(*this); diff --git a/src/Coordination/KeeperStorageDispatcher.cpp b/src/Coordination/KeeperStorageDispatcher.cpp index c27d3b80e3c..14a44ee6f3f 100644 --- a/src/Coordination/KeeperStorageDispatcher.cpp +++ b/src/Coordination/KeeperStorageDispatcher.cpp @@ -234,7 +234,7 @@ bool KeeperStorageDispatcher::putRequest(const Coordination::ZooKeeperRequestPtr return true; } -void KeeperStorageDispatcher::initialize(const Poco::Util::AbstractConfiguration & config) +void KeeperStorageDispatcher::initialize(const Poco::Util::AbstractConfiguration & config, bool standalone_keeper) { LOG_DEBUG(log, "Initializing storage dispatcher"); int myid = config.getInt("keeper_server.server_id"); @@ -246,7 +246,8 @@ void KeeperStorageDispatcher::initialize(const Poco::Util::AbstractConfiguration responses_thread = ThreadFromGlobalPool([this] { responseThread(); }); snapshot_thread = ThreadFromGlobalPool([this] { snapshotThread(); }); - server = std::make_unique(myid, coordination_settings, config, responses_queue, snapshots_queue); + server = std::make_unique( + myid, coordination_settings, config, responses_queue, snapshots_queue, standalone_keeper); try { LOG_DEBUG(log, "Waiting server to initialize"); diff --git a/src/Coordination/KeeperStorageDispatcher.h b/src/Coordination/KeeperStorageDispatcher.h index e4cfa620e6c..cc95de04ce9 100644 --- a/src/Coordination/KeeperStorageDispatcher.h +++ b/src/Coordination/KeeperStorageDispatcher.h @@ -86,7 +86,7 @@ private: public: KeeperStorageDispatcher(); - void initialize(const Poco::Util::AbstractConfiguration & config); + void initialize(const Poco::Util::AbstractConfiguration & config, bool standalone_keeper); void shutdown(); diff --git a/src/Core/Defines.h b/src/Core/Defines.h index 668a60f9be8..94df16758bf 100644 --- a/src/Core/Defines.h +++ b/src/Core/Defines.h @@ -98,6 +98,8 @@ #define DBMS_DEFAULT_PATH "/var/lib/clickhouse/" +#define KEEPER_DEFAULT_PATH "/var/lib/clickhouse-keeper/" + // more aliases: https://mailman.videolan.org/pipermail/x264-devel/2014-May/010660.html /// Marks that extra information is sent to a shard. It could be any magic numbers. diff --git a/src/Core/Settings.h b/src/Core/Settings.h index 4e04362cfe5..5a8a5c163d0 100644 --- a/src/Core/Settings.h +++ b/src/Core/Settings.h @@ -115,7 +115,7 @@ class IColumn; M(Bool, skip_unavailable_shards, false, "If 1, ClickHouse silently skips unavailable shards and nodes unresolvable through DNS. Shard is marked as unavailable when none of the replicas can be reached.", 0) \ \ M(UInt64, parallel_distributed_insert_select, 0, "Process distributed INSERT SELECT query in the same cluster on local tables on every shard, if 1 SELECT is executed on each shard, if 2 SELECT and INSERT is executed on each shard", 0) \ - M(UInt64, distributed_group_by_no_merge, 0, "If 1, Do not merge aggregation states from different servers for distributed query processing - in case it is for certain that there are different keys on different shards. If 2 - same as 1 but also apply ORDER BY and LIMIT stages", 0) \ + M(UInt64, distributed_group_by_no_merge, 0, "If 1, Do not merge aggregation states from different servers for distributed queries (shards will process query up to the Complete stage, initiator just proxies the data from the shards). If 2 the initiator will apply ORDER BY and LIMIT stages (it is not in case when shard process query up to the Complete stage)", 0) \ M(Bool, optimize_distributed_group_by_sharding_key, false, "Optimize GROUP BY sharding_key queries (by avoiding costly aggregation on the initiator server).", 0) \ M(UInt64, optimize_skip_unused_shards_limit, 1000, "Limit for number of sharding key values, turns off optimize_skip_unused_shards if the limit is reached", 0) \ M(Bool, optimize_skip_unused_shards, false, "Assumes that data is distributed by sharding_key. Optimization to skip unused shards if SELECT query filters by sharding_key.", 0) \ diff --git a/src/DataStreams/AddingDefaultBlockOutputStream.cpp b/src/DataStreams/AddingDefaultBlockOutputStream.cpp index 46799a109d3..6f7975d492d 100644 --- a/src/DataStreams/AddingDefaultBlockOutputStream.cpp +++ b/src/DataStreams/AddingDefaultBlockOutputStream.cpp @@ -15,7 +15,7 @@ AddingDefaultBlockOutputStream::AddingDefaultBlockOutputStream( : output(output_), header(header_) { auto dag = addMissingDefaults(header_, output->getHeader().getNamesAndTypesList(), columns_, context_, null_as_default_); - adding_defaults_actions = std::make_shared(std::move(dag), ExpressionActionsSettings::fromContext(context_)); + adding_defaults_actions = std::make_shared(std::move(dag), ExpressionActionsSettings::fromContext(context_, CompileExpressions::yes)); } void AddingDefaultBlockOutputStream::write(const Block & block) diff --git a/src/DataStreams/AddingDefaultsBlockInputStream.cpp b/src/DataStreams/AddingDefaultsBlockInputStream.cpp index e3f0906cb03..81be24439a5 100644 --- a/src/DataStreams/AddingDefaultsBlockInputStream.cpp +++ b/src/DataStreams/AddingDefaultsBlockInputStream.cpp @@ -174,7 +174,7 @@ Block AddingDefaultsBlockInputStream::readImpl() auto dag = evaluateMissingDefaults(evaluate_block, header.getNamesAndTypesList(), columns, context, false); if (dag) { - auto actions = std::make_shared(std::move(dag), ExpressionActionsSettings::fromContext(context)); + auto actions = std::make_shared(std::move(dag), ExpressionActionsSettings::fromContext(context, CompileExpressions::yes)); actions->execute(evaluate_block); } diff --git a/src/DataTypes/DataTypeDateTime64.h b/src/DataTypes/DataTypeDateTime64.h index f51e0f5d047..ac0f49613a2 100644 --- a/src/DataTypes/DataTypeDateTime64.h +++ b/src/DataTypes/DataTypeDateTime64.h @@ -35,6 +35,8 @@ public: bool canBePromoted() const override { return false; } + bool canBeUsedAsVersion() const override { return true; } + protected: SerializationPtr doGetDefaultSerialization() const override; }; diff --git a/src/DataTypes/DataTypeUUID.h b/src/DataTypes/DataTypeUUID.h index 70104a03478..5ed7a912607 100644 --- a/src/DataTypes/DataTypeUUID.h +++ b/src/DataTypes/DataTypeUUID.h @@ -35,6 +35,7 @@ public: bool textCanContainOnlyValidUTF8() const override { return true; } bool isComparable() const override { return true; } bool isValueUnambiguouslyRepresentedInContiguousMemoryRegion() const override { return true; } + bool isValueUnambiguouslyRepresentedInFixedSizeContiguousMemoryRegion() const override { return true; } bool haveMaximumSizeOfValue() const override { return true; } size_t getSizeOfValueInMemory() const override { return sizeof(UUID); } bool isCategorial() const override { return true; } diff --git a/src/DataTypes/EnumValues.cpp b/src/DataTypes/EnumValues.cpp index 39c24bf1122..6df899ba9a2 100644 --- a/src/DataTypes/EnumValues.cpp +++ b/src/DataTypes/EnumValues.cpp @@ -67,7 +67,7 @@ T EnumValues::getValue(StringRef field_name, bool try_treat_as_id) const return x; } auto hints = this->getHints(field_name.toString()); - auto hints_string = !hints.empty() ? ", may be you meant: " + toString(hints) : ""; + auto hints_string = !hints.empty() ? ", maybe you meant: " + toString(hints) : ""; throw Exception{"Unknown element '" + field_name.toString() + "' for enum" + hints_string, ErrorCodes::BAD_ARGUMENTS}; } return it->getMapped(); diff --git a/src/DataTypes/IDataType.h b/src/DataTypes/IDataType.h index 4602083f488..85526cd98de 100644 --- a/src/DataTypes/IDataType.h +++ b/src/DataTypes/IDataType.h @@ -177,7 +177,7 @@ public: */ virtual bool canBeComparedWithCollation() const { return false; } - /** If the type is totally comparable (Ints, Date, DateTime, not nullable, not floats) + /** If the type is totally comparable (Ints, Date, DateTime, DateTime64, not nullable, not floats) * and "simple" enough (not String, FixedString) to be used as version number * (to select rows with maximum version). */ diff --git a/src/Databases/DatabaseLazy.cpp b/src/Databases/DatabaseLazy.cpp index d498cb96062..80179de104a 100644 --- a/src/Databases/DatabaseLazy.cpp +++ b/src/Databases/DatabaseLazy.cpp @@ -203,7 +203,7 @@ void DatabaseLazy::shutdown() for (const auto & kv : tables_snapshot) { if (kv.second.table) - kv.second.table->shutdown(); + kv.second.table->flushAndShutdown(); } std::lock_guard lock(mutex); diff --git a/src/Databases/DatabaseReplicated.cpp b/src/Databases/DatabaseReplicated.cpp index b7214917ce8..d36fe45f748 100644 --- a/src/Databases/DatabaseReplicated.cpp +++ b/src/Databases/DatabaseReplicated.cpp @@ -529,7 +529,7 @@ void DatabaseReplicated::recoverLostReplica(const ZooKeeperPtr & current_zookeep dropped_tables.push_back(tryGetTableUUID(table_name)); dropped_dictionaries += table->isDictionary(); - table->shutdown(); + table->flushAndShutdown(); DatabaseAtomic::dropTable(getContext(), table_name, true); } else diff --git a/src/Databases/DatabasesCommon.cpp b/src/Databases/DatabasesCommon.cpp index 9329b0a4210..9d79a0dfe96 100644 --- a/src/Databases/DatabasesCommon.cpp +++ b/src/Databases/DatabasesCommon.cpp @@ -125,10 +125,15 @@ void DatabaseWithOwnTablesBase::shutdown() tables_snapshot = tables; } + for (const auto & kv : tables_snapshot) + { + kv.second->flush(); + } + for (const auto & kv : tables_snapshot) { auto table_id = kv.second->getStorageID(); - kv.second->shutdown(); + kv.second->flushAndShutdown(); if (table_id.hasUUID()) { assert(getDatabaseName() == DatabaseCatalog::TEMPORARY_DATABASE || getUUID() != UUIDHelpers::Nil); diff --git a/src/Databases/MySQL/DatabaseConnectionMySQL.cpp b/src/Databases/MySQL/DatabaseConnectionMySQL.cpp index 59a575996ee..5cd59f8a7c8 100644 --- a/src/Databases/MySQL/DatabaseConnectionMySQL.cpp +++ b/src/Databases/MySQL/DatabaseConnectionMySQL.cpp @@ -316,7 +316,7 @@ void DatabaseConnectionMySQL::shutdown() } for (const auto & [table_name, modify_time_and_storage] : tables_snapshot) - modify_time_and_storage.second->shutdown(); + modify_time_and_storage.second->flushAndShutdown(); std::lock_guard lock(mutex); local_tables_cache.clear(); @@ -343,7 +343,7 @@ void DatabaseConnectionMySQL::cleanOutdatedTables() { const auto table_lock = (*iterator)->lockExclusively(RWLockImpl::NO_QUERY, lock_acquire_timeout); - (*iterator)->shutdown(); + (*iterator)->flushAndShutdown(); (*iterator)->is_dropped = true; iterator = outdated_tables.erase(iterator); } diff --git a/src/Functions/CMakeLists.txt b/src/Functions/CMakeLists.txt index 7e9e953eabe..271deb0f42c 100644 --- a/src/Functions/CMakeLists.txt +++ b/src/Functions/CMakeLists.txt @@ -5,8 +5,8 @@ add_subdirectory(divide) include("${ClickHouse_SOURCE_DIR}/cmake/dbms_glob_sources.cmake") add_headers_and_sources(clickhouse_functions .) -list(REMOVE_ITEM clickhouse_functions_sources IFunctionImpl.cpp FunctionFactory.cpp FunctionHelpers.cpp) -list(REMOVE_ITEM clickhouse_functions_headers IFunctionImpl.h FunctionFactory.h FunctionHelpers.h) +list(REMOVE_ITEM clickhouse_functions_sources IFunction.cpp FunctionFactory.cpp FunctionHelpers.cpp) +list(REMOVE_ITEM clickhouse_functions_headers IFunction.h FunctionFactory.h FunctionHelpers.h) add_library(clickhouse_functions ${clickhouse_functions_sources}) diff --git a/src/Functions/CustomWeekTransforms.h b/src/Functions/CustomWeekTransforms.h index 98b7c38f266..d1a8e3a54fd 100644 --- a/src/Functions/CustomWeekTransforms.h +++ b/src/Functions/CustomWeekTransforms.h @@ -6,7 +6,7 @@ #include #include #include -#include +#include #include #include diff --git a/src/Functions/DateTimeTransforms.h b/src/Functions/DateTimeTransforms.h index 86cac4f4222..03f35333150 100644 --- a/src/Functions/DateTimeTransforms.h +++ b/src/Functions/DateTimeTransforms.h @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/src/Functions/FunctionBinaryArithmetic.h b/src/Functions/FunctionBinaryArithmetic.h index 508c598b0ed..927b870891f 100644 --- a/src/Functions/FunctionBinaryArithmetic.h +++ b/src/Functions/FunctionBinaryArithmetic.h @@ -23,7 +23,7 @@ #include #include #include "Core/DecimalFunctions.h" -#include "IFunctionImpl.h" +#include "IFunction.h" #include "FunctionHelpers.h" #include "IsOperation.h" #include "DivisionUtils.h" @@ -1532,11 +1532,11 @@ private: }; template