Merge branch 'master' into kssenii-patch-6

This commit is contained in:
Kseniia Sumarokova 2023-08-01 18:40:20 +02:00 committed by GitHub
commit dbc11b83fd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
330 changed files with 6932 additions and 1011 deletions

View File

@ -3643,7 +3643,7 @@ jobs:
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/unit_tests_asan
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Unit tests (release-clang)
CHECK_NAME=Unit tests (release)
REPO_COPY=${{runner.temp}}/unit_tests_asan/ClickHouse
EOF
- name: Download json reports

View File

@ -4541,7 +4541,7 @@ jobs:
cat >> "$GITHUB_ENV" << 'EOF'
TEMP_PATH=${{runner.temp}}/unit_tests_asan
REPORTS_PATH=${{runner.temp}}/reports_dir
CHECK_NAME=Unit tests (release-clang)
CHECK_NAME=Unit tests (release)
REPO_COPY=${{runner.temp}}/unit_tests_asan/ClickHouse
EOF
- name: Download json reports

View File

@ -23,7 +23,6 @@
* Added `Overlay` database engine to combine multiple databases into one. Added `Filesystem` database engine to represent a directory in the filesystem as a set of implicitly available tables with auto-detected formats and structures. A new `S3` database engine allows to read-only interact with s3 storage by representing a prefix as a set of tables. A new `HDFS` database engine allows to interact with HDFS storage in the same way. [#48821](https://github.com/ClickHouse/ClickHouse/pull/48821) ([alekseygolub](https://github.com/alekseygolub)).
* Add support for external disks in Keeper for storing snapshots and logs. [#50098](https://github.com/ClickHouse/ClickHouse/pull/50098) ([Antonio Andelic](https://github.com/antonio2368)).
* Add support for multi-directory selection (`{}`) globs. [#50559](https://github.com/ClickHouse/ClickHouse/pull/50559) ([Andrey Zvonov](https://github.com/zvonand)).
* Support ZooKeeper `reconfig` command for ClickHouse Keeper with incremental reconfiguration which can be enabled via `keeper_server.enable_reconfiguration` setting. Support adding servers, removing servers, and changing server priorities. [#49450](https://github.com/ClickHouse/ClickHouse/pull/49450) ([Mike Kot](https://github.com/myrrc)).
* Kafka connector can fetch Avro schema from schema registry with basic authentication using url-encoded credentials. [#49664](https://github.com/ClickHouse/ClickHouse/pull/49664) ([Ilya Golshtein](https://github.com/ilejn)).
* Add function `arrayJaccardIndex` which computes the Jaccard similarity between two arrays. [#50076](https://github.com/ClickHouse/ClickHouse/pull/50076) ([FFFFFFFHHHHHHH](https://github.com/FFFFFFFHHHHHHH)).
* Add a column `is_obsolete` to `system.settings` and similar tables. Closes [#50819](https://github.com/ClickHouse/ClickHouse/issues/50819). [#50826](https://github.com/ClickHouse/ClickHouse/pull/50826) ([flynn](https://github.com/ucasfl)).
@ -124,6 +123,7 @@
* (experimental MaterializedMySQL) Now double quoted comments are supported in MaterializedMySQL. [#52355](https://github.com/ClickHouse/ClickHouse/pull/52355) ([Val Doroshchuk](https://github.com/valbok)).
* Upgrade Intel QPL from v1.1.0 to v1.2.0 2. Upgrade Intel accel-config from v3.5 to v4.0 3. Fixed issue that Device IOTLB miss has big perf. impact for IAA accelerators. [#52180](https://github.com/ClickHouse/ClickHouse/pull/52180) ([jasperzhu](https://github.com/jinjunzh)).
* The `session_timezone` setting (new in version 23.6) is demoted to experimental. [#52445](https://github.com/ClickHouse/ClickHouse/pull/52445) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Support ZooKeeper `reconfig` command for ClickHouse Keeper with incremental reconfiguration which can be enabled via `keeper_server.enable_reconfiguration` setting. Support adding servers, removing servers, and changing server priorities. [#49450](https://github.com/ClickHouse/ClickHouse/pull/49450) ([Mike Kot](https://github.com/myrrc)). It is suspected that this feature is incomplete.
#### Build/Testing/Packaging Improvement
* Add experimental ClickHouse builds for Linux RISC-V 64 to CI. [#31398](https://github.com/ClickHouse/ClickHouse/pull/31398) ([Alexey Milovidov](https://github.com/alexey-milovidov)).

View File

@ -8,6 +8,7 @@
#include <functional>
#include <iosfwd>
#include <base/defines.h>
#include <base/types.h>
#include <base/unaligned.h>
@ -274,6 +275,8 @@ struct CRC32Hash
if (size == 0)
return 0;
chassert(pos);
if (size < 8)
{
return static_cast<unsigned>(hashLessThan8(x.data, x.size));

View File

@ -115,8 +115,15 @@
/// because SIGABRT is easier to debug than SIGTRAP (the second one makes gdb crazy)
#if !defined(chassert)
#if defined(ABORT_ON_LOGICAL_ERROR)
// clang-format off
#include <base/types.h>
namespace DB
{
void abortOnFailedAssertion(const String & description);
}
#define chassert(x) static_cast<bool>(x) ? void(0) : ::DB::abortOnFailedAssertion(#x)
#define UNREACHABLE() abort()
// clang-format off
#else
/// Here sizeof() trick is used to suppress unused warning for result,
/// since simple "(void)x" will evaluate the expression, while

View File

@ -57,7 +57,7 @@ public:
URI();
/// Creates an empty URI.
explicit URI(const std::string & uri, bool disable_url_encoding = false);
explicit URI(const std::string & uri, bool enable_url_encoding = true);
/// Parses an URI from the given string. Throws a
/// SyntaxException if the uri is not valid.
@ -362,7 +362,7 @@ private:
std::string _query;
std::string _fragment;
bool _disable_url_encoding = false;
bool _enable_url_encoding = true;
};

View File

@ -36,8 +36,8 @@ URI::URI():
}
URI::URI(const std::string& uri, bool decode_and_encode_path):
_port(0), _disable_url_encoding(decode_and_encode_path)
URI::URI(const std::string& uri, bool enable_url_encoding):
_port(0), _enable_url_encoding(enable_url_encoding)
{
parse(uri);
}
@ -108,7 +108,7 @@ URI::URI(const URI& uri):
_path(uri._path),
_query(uri._query),
_fragment(uri._fragment),
_disable_url_encoding(uri._disable_url_encoding)
_enable_url_encoding(uri._enable_url_encoding)
{
}
@ -121,7 +121,7 @@ URI::URI(const URI& baseURI, const std::string& relativeURI):
_path(baseURI._path),
_query(baseURI._query),
_fragment(baseURI._fragment),
_disable_url_encoding(baseURI._disable_url_encoding)
_enable_url_encoding(baseURI._enable_url_encoding)
{
resolve(relativeURI);
}
@ -153,7 +153,7 @@ URI& URI::operator = (const URI& uri)
_path = uri._path;
_query = uri._query;
_fragment = uri._fragment;
_disable_url_encoding = uri._disable_url_encoding;
_enable_url_encoding = uri._enable_url_encoding;
}
return *this;
}
@ -184,7 +184,7 @@ void URI::swap(URI& uri)
std::swap(_path, uri._path);
std::swap(_query, uri._query);
std::swap(_fragment, uri._fragment);
std::swap(_disable_url_encoding, uri._disable_url_encoding);
std::swap(_enable_url_encoding, uri._enable_url_encoding);
}
@ -687,18 +687,18 @@ void URI::decode(const std::string& str, std::string& decodedStr, bool plusAsSpa
void URI::encodePath(std::string & encodedStr) const
{
if (_disable_url_encoding)
encodedStr = _path;
else
if (_enable_url_encoding)
encode(_path, RESERVED_PATH, encodedStr);
else
encodedStr = _path;
}
void URI::decodePath(const std::string & encodedStr)
{
if (_disable_url_encoding)
_path = encodedStr;
else
if (_enable_url_encoding)
decode(encodedStr, _path);
else
_path = encodedStr;
}
bool URI::isWellKnownPort() const

View File

@ -161,5 +161,9 @@
"docker/test/sqllogic": {
"name": "clickhouse/sqllogic-test",
"dependent": []
},
"docker/test/integration/nginx_dav": {
"name": "clickhouse/nginx-dav",
"dependent": []
}
}

View File

@ -32,7 +32,7 @@ ENV MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1'
RUN echo "en_US.UTF-8 UTF-8" > /etc/locale.gen && locale-gen en_US.UTF-8
ENV LC_ALL en_US.UTF-8
ENV TZ=Europe/Moscow
ENV TZ=Europe/Amsterdam
RUN ln -snf "/usr/share/zoneinfo/$TZ" /etc/localtime && echo "$TZ" > /etc/timezone
CMD sleep 1

View File

@ -32,7 +32,7 @@ RUN mkdir -p /tmp/clickhouse-odbc-tmp \
&& odbcinst -i -s -l -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbc.ini.sample \
&& rm -rf /tmp/clickhouse-odbc-tmp
ENV TZ=Europe/Moscow
ENV TZ=Europe/Amsterdam
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
ENV COMMIT_SHA=''

View File

@ -8,7 +8,7 @@ ARG apt_archive="http://archive.ubuntu.com"
RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
ENV LANG=C.UTF-8
ENV TZ=Europe/Moscow
ENV TZ=Europe/Amsterdam
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
RUN apt-get update \

View File

@ -0,0 +1,6 @@
FROM nginx:alpine-slim
COPY default.conf /etc/nginx/conf.d/
RUN mkdir /usr/share/nginx/files/ \
&& chown nginx: /usr/share/nginx/files/ -R

View File

@ -0,0 +1,25 @@
server {
listen 80;
#root /usr/share/nginx/test.com;
index index.html index.htm;
server_name test.com localhost;
location / {
expires max;
root /usr/share/nginx/files;
client_max_body_size 20m;
client_body_temp_path /usr/share/nginx/tmp;
dav_methods PUT; # Allowed methods, only PUT is necessary
create_full_put_path on; # nginx automatically creates nested directories
dav_access user:rw group:r all:r; # access permissions for files
limit_except GET {
allow all;
}
}
error_page 405 =200 $uri;
}

View File

@ -13,4 +13,3 @@ services:
- ${MEILI_SECURE_EXTERNAL_PORT:-7700}:${MEILI_SECURE_INTERNAL_PORT:-7700}
environment:
MEILI_MASTER_KEY: "password"

View File

@ -5,7 +5,7 @@ services:
# Files will be put into /usr/share/nginx/files.
nginx:
image: kssenii/nginx-test:1.1
image: clickhouse/nginx-dav:${DOCKER_NGINX_DAV_TAG:-latest}
restart: always
ports:
- 80:80

View File

@ -64,15 +64,16 @@ export CLICKHOUSE_ODBC_BRIDGE_BINARY_PATH=/clickhouse-odbc-bridge
export CLICKHOUSE_LIBRARY_BRIDGE_BINARY_PATH=/clickhouse-library-bridge
export DOCKER_BASE_TAG=${DOCKER_BASE_TAG:=latest}
export DOCKER_HELPER_TAG=${DOCKER_HELPER_TAG:=latest}
export DOCKER_MYSQL_GOLANG_CLIENT_TAG=${DOCKER_MYSQL_GOLANG_CLIENT_TAG:=latest}
export DOCKER_DOTNET_CLIENT_TAG=${DOCKER_DOTNET_CLIENT_TAG:=latest}
export DOCKER_HELPER_TAG=${DOCKER_HELPER_TAG:=latest}
export DOCKER_KERBERIZED_HADOOP_TAG=${DOCKER_KERBERIZED_HADOOP_TAG:=latest}
export DOCKER_KERBEROS_KDC_TAG=${DOCKER_KERBEROS_KDC_TAG:=latest}
export DOCKER_MYSQL_GOLANG_CLIENT_TAG=${DOCKER_MYSQL_GOLANG_CLIENT_TAG:=latest}
export DOCKER_MYSQL_JAVA_CLIENT_TAG=${DOCKER_MYSQL_JAVA_CLIENT_TAG:=latest}
export DOCKER_MYSQL_JS_CLIENT_TAG=${DOCKER_MYSQL_JS_CLIENT_TAG:=latest}
export DOCKER_MYSQL_PHP_CLIENT_TAG=${DOCKER_MYSQL_PHP_CLIENT_TAG:=latest}
export DOCKER_NGINX_DAV_TAG=${DOCKER_NGINX_DAV_TAG:=latest}
export DOCKER_POSTGRESQL_JAVA_CLIENT_TAG=${DOCKER_POSTGRESQL_JAVA_CLIENT_TAG:=latest}
export DOCKER_KERBEROS_KDC_TAG=${DOCKER_KERBEROS_KDC_TAG:=latest}
export DOCKER_KERBERIZED_HADOOP_TAG=${DOCKER_KERBERIZED_HADOOP_TAG:=latest}
cd /ClickHouse/tests/integration
exec "$@"

View File

@ -11,7 +11,7 @@ ARG apt_archive="http://archive.ubuntu.com"
RUN sed -i "s|http://archive.ubuntu.com|$apt_archive|g" /etc/apt/sources.list
ENV LANG=C.UTF-8
ENV TZ=Europe/Moscow
ENV TZ=Europe/Amsterdam
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
RUN apt-get update \

View File

@ -52,7 +52,7 @@ RUN mkdir -p /tmp/clickhouse-odbc-tmp \
&& odbcinst -i -s -l -f /tmp/clickhouse-odbc-tmp/share/doc/clickhouse-odbc/config/odbc.ini.sample \
&& rm -rf /tmp/clickhouse-odbc-tmp
ENV TZ=Europe/Moscow
ENV TZ=Europe/Amsterdam
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
ENV NUM_TRIES=1

View File

@ -233,4 +233,10 @@ rowNumberInAllBlocks()
LIMIT 1" < /test_output/test_results.tsv > /test_output/check_status.tsv || echo "failure\tCannot parse test_results.tsv" > /test_output/check_status.tsv
[ -s /test_output/check_status.tsv ] || echo -e "success\tNo errors found" > /test_output/check_status.tsv
# But OOMs in stress test are allowed
if rg 'OOM in dmesg|Signal 9' /test_output/check_status.tsv
then
sed -i 's/failure/success/' /test_output/check_status.tsv
fi
collect_core_dumps

View File

@ -231,4 +231,10 @@ rowNumberInAllBlocks()
LIMIT 1" < /test_output/test_results.tsv > /test_output/check_status.tsv || echo "failure\tCannot parse test_results.tsv" > /test_output/check_status.tsv
[ -s /test_output/check_status.tsv ] || echo -e "success\tNo errors found" > /test_output/check_status.tsv
# But OOMs in stress test are allowed
if rg 'OOM in dmesg|Signal 9' /test_output/check_status.tsv
then
sed -i 's/failure/success/' /test_output/check_status.tsv
fi
collect_core_dumps

View File

@ -106,4 +106,4 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
## Storage Settings {#storage-settings}
- [engine_url_skip_empty_files](/docs/en/operations/settings/settings.md#engine_url_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
- [disable_url_encoding](/docs/en/operations/settings/settings.md#disable_url_encoding) -allows to disable decoding/encoding path in uri. Disabled by default.
- [enable_url_encoding](/docs/en/operations/settings/settings.md#enable_url_encoding) - allows to enable/disable decoding/encoding path in uri. Enabled by default.

View File

@ -1723,6 +1723,34 @@ You can select data from a ClickHouse table and save them into some file in the
``` bash
$ clickhouse-client --query = "SELECT * FROM test.hits FORMAT CapnProto SETTINGS format_schema = 'schema:Message'"
```
### Using autogenerated schema {#using-autogenerated-capn-proto-schema}
If you don't have an external CapnProto schema for your data, you can still output/input data in CapnProto format using autogenerated schema.
For example:
```sql
SELECT * FROM test.hits format CapnProto SETTINGS format_capn_proto_use_autogenerated_schema=1
```
In this case ClickHouse will autogenerate CapnProto schema according to the table structure using function [structureToCapnProtoSchema](../sql-reference/functions/other-functions.md#structure_to_capn_proto_schema) and will use this schema to serialize data in CapnProto format.
You can also read CapnProto file with autogenerated schema (in this case the file must be created using the same schema):
```bash
$ cat hits.bin | clickhouse-client --query "INSERT INTO test.hits SETTINGS format_capn_proto_use_autogenerated_schema=1 FORMAT CapnProto"
```
The setting [format_capn_proto_use_autogenerated_schema](../operations/settings/settings-formats.md#format_capn_proto_use_autogenerated_schema) is enabled by default and applies if [format_schema](../operations/settings/settings-formats.md#formatschema-format-schema) is not set.
You can also save autogenerated schema in the file during input/output using setting [output_format_schema](../operations/settings/settings-formats.md#outputformatschema-output-format-schema). For example:
```sql
SELECT * FROM test.hits format CapnProto SETTINGS format_capn_proto_use_autogenerated_schema=1, output_format_schema='path/to/schema/schema.capnp'
```
In this case autogenerated CapnProto schema will be saved in file `path/to/schema/schema.capnp`.
## Prometheus {#prometheus}
Expose metrics in [Prometheus text-based exposition format](https://prometheus.io/docs/instrumenting/exposition_formats/#text-based-format).
@ -1861,6 +1889,33 @@ ClickHouse inputs and outputs protobuf messages in the `length-delimited` format
It means before every message should be written its length as a [varint](https://developers.google.com/protocol-buffers/docs/encoding#varints).
See also [how to read/write length-delimited protobuf messages in popular languages](https://cwiki.apache.org/confluence/display/GEODE/Delimiting+Protobuf+Messages).
### Using autogenerated schema {#using-autogenerated-protobuf-schema}
If you don't have an external Protobuf schema for your data, you can still output/input data in Protobuf format using autogenerated schema.
For example:
```sql
SELECT * FROM test.hits format Protobuf SETTINGS format_protobuf_use_autogenerated_schema=1
```
In this case ClickHouse will autogenerate Protobuf schema according to the table structure using function [structureToProtobufSchema](../sql-reference/functions/other-functions.md#structure_to_protobuf_schema) and will use this schema to serialize data in Protobuf format.
You can also read Protobuf file with autogenerated schema (in this case the file must be created using the same schema):
```bash
$ cat hits.bin | clickhouse-client --query "INSERT INTO test.hits SETTINGS format_protobuf_use_autogenerated_schema=1 FORMAT Protobuf"
```
The setting [format_protobuf_use_autogenerated_schema](../operations/settings/settings-formats.md#format_protobuf_use_autogenerated_schema) is enabled by default and applies if [format_schema](../operations/settings/settings-formats.md#formatschema-format-schema) is not set.
You can also save autogenerated schema in the file during input/output using setting [output_format_schema](../operations/settings/settings-formats.md#outputformatschema-output-format-schema). For example:
```sql
SELECT * FROM test.hits format Protobuf SETTINGS format_protobuf_use_autogenerated_schema=1, output_format_schema='path/to/schema/schema.proto'
```
In this case autogenerated Protobuf schema will be saved in file `path/to/schema/schema.capnp`.
## ProtobufSingle {#protobufsingle}
Same as [Protobuf](#protobuf) but for storing/parsing single Protobuf message without length delimiters.

View File

@ -84,6 +84,7 @@ The BACKUP and RESTORE statements take a list of DATABASE and TABLE names, a des
- `password` for the file on disk
- `base_backup`: the destination of the previous backup of this source. For example, `Disk('backups', '1.zip')`
- `structure_only`: if enabled, allows to only backup or restore the CREATE statements without the data of tables
- `s3_storage_class`: the storage class used for S3 backup. For example, `STANDARD`
### Usage examples

View File

@ -0,0 +1,26 @@
---
slug: /en/operations/optimizing-performance/profile-guided-optimization
sidebar_position: 54
sidebar_label: Profile Guided Optimization (PGO)
---
import SelfManaged from '@site/docs/en/_snippets/_self_managed_only_no_roadmap.md';
# Profile Guided Optimization
Profile-Guided Optimization (PGO) is a compiler optimization technique where a program is optimized based on the runtime profile.
According to the tests, PGO helps with achieving better performance for ClickHouse. According to the tests, we see improvements up to 15% in QPS on the ClickBench test suite. The more detailed results are available [here](https://pastebin.com/xbue3HMU). The performance benefits depend on your typical workload - you can get better or worse results.
More information about PGO in ClickHouse you can read in the corresponding GitHub [issue](https://github.com/ClickHouse/ClickHouse/issues/44567).
## How to build ClickHouse with PGO?
There are two major kinds of PGO: [Instrumentation](https://clang.llvm.org/docs/UsersManual.html#using-sampling-profilers) and [Sampling](https://clang.llvm.org/docs/UsersManual.html#using-sampling-profilers) (also known as AutoFDO). In this guide is described the Instrumentation PGO with ClickHouse.
1. Build ClickHouse in Instrumented mode. In Clang it can be done via passing `-fprofile-instr-generate` option to `CXXFLAGS`.
2. Run instrumented ClickHouse on a sample workload. Here you need to use your usual workload. One of the approaches could be using [ClickBench](https://github.com/ClickHouse/ClickBench) as a sample workload. ClickHouse in the instrumentation mode could work slowly so be ready for that and do not run instrumented ClickHouse in performance-critical environments.
3. Recompile ClickHouse once again with `-fprofile-instr-use` compiler flags and profiles that are collected from the previous step.
A more detailed guide on how to apply PGO is in the Clang [documentation](https://clang.llvm.org/docs/UsersManual.html#profile-guided-optimization).
If you are going to collect a sample workload directly from a production environment, we recommend trying to use Sampling PGO.

View File

@ -2288,6 +2288,8 @@ This section contains the following parameters:
- `session_timeout_ms` — Maximum timeout for the client session in milliseconds.
- `operation_timeout_ms` — Maximum timeout for one operation in milliseconds.
- `root` — The [znode](http://zookeeper.apache.org/doc/r3.5.5/zookeeperOver.html#Nodes+and+ephemeral+nodes) that is used as the root for znodes used by the ClickHouse server. Optional.
- `fallback_session_lifetime.min` - If the first zookeeper host resolved by zookeeper_load_balancing strategy is unavailable, limit the lifetime of a zookeeper session to the fallback node. This is done for load-balancing purposes to avoid excessive load on one of zookeeper hosts. This setting sets the minimal duration of the fallback session. Set in seconds. Optional. Default is 3 hours.
- `fallback_session_lifetime.max` - If the first zookeeper host resolved by zookeeper_load_balancing strategy is unavailable, limit the lifetime of a zookeeper session to the fallback node. This is done for load-balancing purposes to avoid excessive load on one of zookeeper hosts. This setting sets the maximum duration of the fallback session. Set in seconds. Optional. Default is 6 hours.
- `identity` — User and password, that can be required by ZooKeeper to give access to requested znodes. Optional.
- zookeeper_load_balancing - Specifies the algorithm of ZooKeeper node selection.
* random - randomly selects one of ZooKeeper nodes.

View File

@ -327,3 +327,39 @@ The maximum amount of data consumed by temporary files on disk in bytes for all
Zero means unlimited.
Default value: 0.
## max_sessions_for_user {#max-sessions-per-user}
Maximum number of simultaneous sessions per authenticated user to the ClickHouse server.
Example:
``` xml
<profiles>
<single_session_profile>
<max_sessions_for_user>1</max_sessions_for_user>
</single_session_profile>
<two_sessions_profile>
<max_sessions_for_user>2</max_sessions_for_user>
</two_sessions_profile>
<unlimited_sessions_profile>
<max_sessions_for_user>0</max_sessions_for_user>
</unlimited_sessions_profile>
</profiles>
<users>
<!-- User Alice can connect to a ClickHouse server no more than once at a time. -->
<Alice>
<profile>single_session_user</profile>
</Alice>
<!-- User Bob can use 2 simultaneous sessions. -->
<Bob>
<profile>two_sessions_profile</profile>
</Bob>
<!-- User Charles can use arbitrarily many of simultaneous sessions. -->
<Charles>
<profile>unlimited_sessions_profile</profile>
</Charles>
</users>
```
Default value: 0 (Infinite count of simultaneous sessions).

View File

@ -321,6 +321,10 @@ If both `input_format_allow_errors_num` and `input_format_allow_errors_ratio` ar
This parameter is useful when you are using formats that require a schema definition, such as [Capn Proto](https://capnproto.org/) or [Protobuf](https://developers.google.com/protocol-buffers/). The value depends on the format.
## output_format_schema {#output-format-schema}
The path to the file where the automatically generated schema will be saved in [Capn Proto](../../interfaces/formats.md#capnproto-capnproto) or [Protobuf](../../interfaces/formats.md#protobuf-protobuf) formats.
## output_format_enable_streaming {#output_format_enable_streaming}
Enable streaming in output formats that support it.
@ -1330,6 +1334,11 @@ When serializing Nullable columns with Google wrappers, serialize default values
Disabled by default.
### format_protobuf_use_autogenerated_schema {#format_capn_proto_use_autogenerated_schema}
Use autogenerated Protobuf schema when [format_schema](#formatschema-format-schema) is not set.
The schema is generated from ClickHouse table structure using function [structureToProtobufSchema](../../sql-reference/functions/other-functions.md#structure_to_protobuf_schema)
## Avro format settings {#avro-format-settings}
### input_format_avro_allow_missing_fields {#input_format_avro_allow_missing_fields}
@ -1626,6 +1635,11 @@ Possible values:
Default value: `'by_values'`.
### format_capn_proto_use_autogenerated_schema {#format_capn_proto_use_autogenerated_schema}
Use autogenerated CapnProto schema when [format_schema](#formatschema-format-schema) is not set.
The schema is generated from ClickHouse table structure using function [structureToCapnProtoSchema](../../sql-reference/functions/other-functions.md#structure_to_capnproto_schema)
## MySQLDump format settings {#musqldump-format-settings}
### input_format_mysql_dump_table_name (#input_format_mysql_dump_table_name)

View File

@ -39,7 +39,7 @@ Example:
<max_threads>8</max_threads>
</default>
<!-- Settings for quries from the user interface -->
<!-- Settings for queries from the user interface -->
<web>
<max_rows_to_read>1000000000</max_rows_to_read>
<max_bytes_to_read>100000000000</max_bytes_to_read>
@ -67,6 +67,8 @@ Example:
<max_ast_depth>50</max_ast_depth>
<max_ast_elements>100</max_ast_elements>
<max_sessions_for_user>4</max_sessions_for_user>
<readonly>1</readonly>
</web>
</profiles>

View File

@ -3468,11 +3468,11 @@ Possible values:
Default value: `0`.
## disable_url_encoding {#disable_url_encoding}
## enable_url_encoding {#enable_url_encoding}
Allows to disable decoding/encoding path in uri in [URL](../../engines/table-engines/special/url.md) engine tables.
Allows to enable/disable decoding/encoding path in uri in [URL](../../engines/table-engines/special/url.md) engine tables.
Disabled by default.
Enabled by default.
## database_atomic_wait_for_drop_and_detach_synchronously {#database_atomic_wait_for_drop_and_detach_synchronously}

View File

@ -10,6 +10,7 @@ Columns:
- `event` ([String](../../sql-reference/data-types/string.md)) — Event name.
- `value` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Number of events occurred.
- `description` ([String](../../sql-reference/data-types/string.md)) — Event description.
- `name` ([String](../../sql-reference/data-types/string.md)) — Alias for `event`.
You can find all supported events in source file [src/Common/ProfileEvents.cpp](https://github.com/ClickHouse/ClickHouse/blob/master/src/Common/ProfileEvents.cpp).

View File

@ -10,6 +10,7 @@ Columns:
- `metric` ([String](../../sql-reference/data-types/string.md)) — Metric name.
- `value` ([Int64](../../sql-reference/data-types/int-uint.md)) — Metric value.
- `description` ([String](../../sql-reference/data-types/string.md)) — Metric description.
- `name` ([String](../../sql-reference/data-types/string.md)) — Alias for `metric`.
You can find all supported metrics in source file [src/Common/CurrentMetrics.cpp](https://github.com/ClickHouse/ClickHouse/blob/master/src/Common/CurrentMetrics.cpp).

View File

@ -48,7 +48,7 @@ Columns:
- `read_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Total number of rows read from all tables and table functions participated in query. It includes usual subqueries, subqueries for `IN` and `JOIN`. For distributed queries `read_rows` includes the total number of rows read at all replicas. Each replica sends its `read_rows` value, and the server-initiator of the query summarizes all received and local values. The cache volumes do not affect this value.
- `read_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Total number of bytes read from all tables and table functions participated in query. It includes usual subqueries, subqueries for `IN` and `JOIN`. For distributed queries `read_bytes` includes the total number of rows read at all replicas. Each replica sends its `read_bytes` value, and the server-initiator of the query summarizes all received and local values. The cache volumes do not affect this value.
- `written_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written rows. For other queries, the column value is 0.
- `written_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written bytes. For other queries, the column value is 0.
- `written_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — For `INSERT` queries, the number of written bytes (uncompressed). For other queries, the column value is 0.
- `result_rows` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Number of rows in a result of the `SELECT` query, or a number of rows in the `INSERT` query.
- `result_bytes` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — RAM volume in bytes used to store a query result.
- `memory_usage` ([UInt64](../../sql-reference/data-types/int-uint.md#uint-ranges)) — Memory consumption by the query.

View File

@ -51,3 +51,7 @@ keeper foo bar
- `rmr <path>` -- Recursively deletes path. Confirmation required
- `flwc <command>` -- Executes four-letter-word command
- `help` -- Prints this message
- `get_stat [path]` -- Returns the node's stat (default `.`)
- `find_super_nodes <threshold> [path]` -- Finds nodes with number of children larger than some threshold for the given path (default `.`)
- `delete_stable_backups` -- Deletes ClickHouse nodes used for backups that are now inactive
- `find_big_family [path] [n]` -- Returns the top n nodes with the biggest family in the subtree (default path = `.` and n = 10)

View File

@ -140,8 +140,8 @@ Time shifts for multiple days. Some pacific islands changed their timezone offse
- [Type conversion functions](../../sql-reference/functions/type-conversion-functions.md)
- [Functions for working with dates and times](../../sql-reference/functions/date-time-functions.md)
- [Functions for working with arrays](../../sql-reference/functions/array-functions.md)
- [The `date_time_input_format` setting](../../operations/settings/settings.md#settings-date_time_input_format)
- [The `date_time_output_format` setting](../../operations/settings/settings.md#settings-date_time_output_format)
- [The `date_time_input_format` setting](../../operations/settings/settings-formats.md#settings-date_time_input_format)
- [The `date_time_output_format` setting](../../operations/settings/settings-formats.md#settings-date_time_output_format)
- [The `timezone` server configuration parameter](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone)
- [The `session_timezone` setting](../../operations/settings/settings.md#session_timezone)
- [Operators for working with dates and times](../../sql-reference/operators/index.md#operators-datetime)

View File

@ -2552,3 +2552,187 @@ Result:
This function can be used together with [generateRandom](../../sql-reference/table-functions/generate.md) to generate completely random tables.
## structureToCapnProtoSchema {#structure_to_capn_proto_schema}
Converts ClickHouse table structure to CapnProto schema.
**Syntax**
``` sql
structureToCapnProtoSchema(structure)
```
**Arguments**
- `structure` — Table structure in a format `column1_name column1_type, column2_name column2_type, ...`.
- `root_struct_name` — Name for root struct in CapnProto schema. Default value - `Message`;
**Returned value**
- CapnProto schema
Type: [String](../../sql-reference/data-types/string.md).
**Examples**
Query:
``` sql
SELECT structureToCapnProtoSchema('column1 String, column2 UInt32, column3 Array(String)') FORMAT RawBLOB
```
Result:
``` text
@0xf96402dd754d0eb7;
struct Message
{
column1 @0 : Data;
column2 @1 : UInt32;
column3 @2 : List(Data);
}
```
Query:
``` sql
SELECT structureToCapnProtoSchema('column1 Nullable(String), column2 Tuple(element1 UInt32, element2 Array(String)), column3 Map(String, String)') FORMAT RawBLOB
```
Result:
``` text
@0xd1c8320fecad2b7f;
struct Message
{
struct Column1
{
union
{
value @0 : Data;
null @1 : Void;
}
}
column1 @0 : Column1;
struct Column2
{
element1 @0 : UInt32;
element2 @1 : List(Data);
}
column2 @1 : Column2;
struct Column3
{
struct Entry
{
key @0 : Data;
value @1 : Data;
}
entries @0 : List(Entry);
}
column3 @2 : Column3;
}
```
Query:
``` sql
SELECT structureToCapnProtoSchema('column1 String, column2 UInt32', 'Root') FORMAT RawBLOB
```
Result:
``` text
@0x96ab2d4ab133c6e1;
struct Root
{
column1 @0 : Data;
column2 @1 : UInt32;
}
```
## structureToProtobufSchema {#structure_to_protobuf_schema}
Converts ClickHouse table structure to Protobuf schema.
**Syntax**
``` sql
structureToProtobufSchema(structure)
```
**Arguments**
- `structure` — Table structure in a format `column1_name column1_type, column2_name column2_type, ...`.
- `root_message_name` — Name for root message in Protobuf schema. Default value - `Message`;
**Returned value**
- Protobuf schema
Type: [String](../../sql-reference/data-types/string.md).
**Examples**
Query:
``` sql
SELECT structureToProtobufSchema('column1 String, column2 UInt32, column3 Array(String)') FORMAT RawBLOB
```
Result:
``` text
syntax = "proto3";
message Message
{
bytes column1 = 1;
uint32 column2 = 2;
repeated bytes column3 = 3;
}
```
Query:
``` sql
SELECT structureToProtobufSchema('column1 Nullable(String), column2 Tuple(element1 UInt32, element2 Array(String)), column3 Map(String, String)') FORMAT RawBLOB
```
Result:
``` text
syntax = "proto3";
message Message
{
bytes column1 = 1;
message Column2
{
uint32 element1 = 1;
repeated bytes element2 = 2;
}
Column2 column2 = 2;
map<string, bytes> column3 = 3;
}
```
Query:
``` sql
SELECT structureToProtobufSchema('column1 String, column2 UInt32', 'Root') FORMAT RawBLOB
```
Result:
``` text
syntax = "proto3";
message Root
{
bytes column1 = 1;
uint32 column2 = 2;
}
```

View File

@ -56,7 +56,7 @@ Character `|` inside patterns is used to specify failover addresses. They are it
## Storage Settings {#storage-settings}
- [engine_url_skip_empty_files](/docs/en/operations/settings/settings.md#engine_url_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
- [disable_url_encoding](/docs/en/operations/settings/settings.md#disable_url_encoding) - allows to disable decoding/encoding path in uri. Disabled by default.
- [enable_url_encoding](/docs/en/operations/settings/settings.md#enable_url_encoding) - allows to enable/disable decoding/encoding path in uri. Enabled by default.
**See Also**

View File

@ -314,3 +314,40 @@ FORMAT Null;
При вставке данных, ClickHouse вычисляет количество партиций во вставленном блоке. Если число партиций больше, чем `max_partitions_per_insert_block`, ClickHouse генерирует исключение со следующим текстом:
> «Too many partitions for single INSERT block (more than» + toString(max_parts) + «). The limit is controlled by max_partitions_per_insert_block setting. Large number of partitions is a common misconception. It will lead to severe negative performance impact, including slow server startup, slow INSERT queries and slow SELECT queries. Recommended total number of partitions for a table is under 1000..10000. Please note, that partitioning is not intended to speed up SELECT queries (ORDER BY key is sufficient to make range queries fast). Partitions are intended for data manipulation (DROP PARTITION, etc).»
## max_sessions_for_user {#max-sessions-per-user}
Максимальное количество одновременных сессий на одного аутентифицированного пользователя.
Пример:
``` xml
<profiles>
<single_session_profile>
<max_sessions_for_user>1</max_sessions_for_user>
</single_session_profile>
<two_sessions_profile>
<max_sessions_for_user>2</max_sessions_for_user>
</two_sessions_profile>
<unlimited_sessions_profile>
<max_sessions_for_user>0</max_sessions_for_user>
</unlimited_sessions_profile>
</profiles>
<users>
<!-- Пользователь Alice может одновременно подключаться не
более одного раза к серверу ClickHouse. -->
<Alice>
<profile>single_session_profile</profile>
</Alice>
<!-- Пользователь Bob может использовать 2 одновременных сессии. -->
<Bob>
<profile>two_sessions_profile</profile>
</Bob>
<!-- Пользователь Charles может иметь любое количество одновременных сессий. -->
<Charles>
<profile>unlimited_sessions_profile</profile>
</Charles>
</users>
```
Значение по умолчанию: 0 (неограниченное количество сессий).

View File

@ -39,7 +39,7 @@ SET profile = 'web'
<max_threads>8</max_threads>
</default>
<!-- Settings for quries from the user interface -->
<!-- Settings for queries from the user interface -->
<web>
<max_rows_to_read>1000000000</max_rows_to_read>
<max_bytes_to_read>100000000000</max_bytes_to_read>
@ -67,6 +67,7 @@ SET profile = 'web'
<max_ast_depth>50</max_ast_depth>
<max_ast_elements>100</max_ast_elements>
<max_sessions_for_user>4</max_sessions_for_user>
<readonly>1</readonly>
</web>
</profiles>

View File

@ -1,5 +1,6 @@
#include "Commands.h"
#include <queue>
#include "KeeperClient.h"
@ -24,8 +25,18 @@ void LSCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) con
else
path = client->cwd;
for (const auto & child : client->zookeeper->getChildren(path))
std::cout << child << " ";
auto children = client->zookeeper->getChildren(path);
std::sort(children.begin(), children.end());
bool need_space = false;
for (const auto & child : children)
{
if (std::exchange(need_space, true))
std::cout << " ";
std::cout << child;
}
std::cout << "\n";
}
@ -130,6 +141,173 @@ void GetCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) co
std::cout << client->zookeeper->get(client->getAbsolutePath(query->args[0].safeGet<String>())) << "\n";
}
bool GetStatCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
if (!parseKeeperPath(pos, expected, arg))
return true;
node->args.push_back(std::move(arg));
return true;
}
void GetStatCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) const
{
Coordination::Stat stat;
String path;
if (!query->args.empty())
path = client->getAbsolutePath(query->args[0].safeGet<String>());
else
path = client->cwd;
client->zookeeper->get(path, &stat);
std::cout << "cZxid = " << stat.czxid << "\n";
std::cout << "mZxid = " << stat.mzxid << "\n";
std::cout << "pZxid = " << stat.pzxid << "\n";
std::cout << "ctime = " << stat.ctime << "\n";
std::cout << "mtime = " << stat.mtime << "\n";
std::cout << "version = " << stat.version << "\n";
std::cout << "cversion = " << stat.cversion << "\n";
std::cout << "aversion = " << stat.aversion << "\n";
std::cout << "ephemeralOwner = " << stat.ephemeralOwner << "\n";
std::cout << "dataLength = " << stat.dataLength << "\n";
std::cout << "numChildren = " << stat.numChildren << "\n";
}
bool FindSuperNodes::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
ASTPtr threshold;
if (!ParserUnsignedInteger{}.parse(pos, threshold, expected))
return false;
node->args.push_back(threshold->as<ASTLiteral &>().value);
String path;
if (!parseKeeperPath(pos, expected, path))
path = ".";
node->args.push_back(std::move(path));
return true;
}
void FindSuperNodes::execute(const ASTKeeperQuery * query, KeeperClient * client) const
{
auto threshold = query->args[0].safeGet<UInt64>();
auto path = client->getAbsolutePath(query->args[1].safeGet<String>());
Coordination::Stat stat;
client->zookeeper->get(path, &stat);
if (stat.numChildren >= static_cast<Int32>(threshold))
{
std::cout << static_cast<String>(path) << "\t" << stat.numChildren << "\n";
return;
}
auto children = client->zookeeper->getChildren(path);
std::sort(children.begin(), children.end());
for (const auto & child : children)
{
auto next_query = *query;
next_query.args[1] = DB::Field(path / child);
execute(&next_query, client);
}
}
bool DeleteStableBackups::parse(IParser::Pos & /* pos */, std::shared_ptr<ASTKeeperQuery> & /* node */, Expected & /* expected */) const
{
return true;
}
void DeleteStableBackups::execute(const ASTKeeperQuery * /* query */, KeeperClient * client) const
{
client->askConfirmation(
"You are going to delete all inactive backups in /clickhouse/backups.",
[client]
{
fs::path backup_root = "/clickhouse/backups";
auto backups = client->zookeeper->getChildren(backup_root);
std::sort(backups.begin(), backups.end());
for (const auto & child : backups)
{
auto backup_path = backup_root / child;
std::cout << "Found backup " << backup_path << ", checking if it's active\n";
String stage_path = backup_path / "stage";
auto stages = client->zookeeper->getChildren(stage_path);
bool is_active = false;
for (const auto & stage : stages)
{
if (startsWith(stage, "alive"))
{
is_active = true;
break;
}
}
if (is_active)
{
std::cout << "Backup " << backup_path << " is active, not going to delete\n";
continue;
}
std::cout << "Backup " << backup_path << " is not active, deleting it\n";
client->zookeeper->removeRecursive(backup_path);
}
});
}
bool FindBigFamily::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String path;
if (!parseKeeperPath(pos, expected, path))
path = ".";
node->args.push_back(std::move(path));
ASTPtr count;
if (ParserUnsignedInteger{}.parse(pos, count, expected))
node->args.push_back(count->as<ASTLiteral &>().value);
else
node->args.push_back(UInt64(10));
return true;
}
void FindBigFamily::execute(const ASTKeeperQuery * query, KeeperClient * client) const
{
auto path = client->getAbsolutePath(query->args[0].safeGet<String>());
auto n = query->args[1].safeGet<UInt64>();
std::vector<std::tuple<Int32, String>> result;
std::queue<fs::path> queue;
queue.push(path);
while (!queue.empty())
{
auto next_path = queue.front();
queue.pop();
auto children = client->zookeeper->getChildren(next_path);
std::transform(children.cbegin(), children.cend(), children.begin(), [&](const String & child) { return next_path / child; });
auto response = client->zookeeper->get(children);
for (size_t i = 0; i < response.size(); ++i)
{
result.emplace_back(response[i].stat.numChildren, children[i]);
queue.push(children[i]);
}
}
std::sort(result.begin(), result.end(), std::greater());
for (UInt64 i = 0; i < std::min(result.size(), static_cast<size_t>(n)); ++i)
std::cout << std::get<1>(result[i]) << "\t" << std::get<0>(result[i]) << "\n";
}
bool RMCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
{
String arg;
@ -170,7 +348,7 @@ bool HelpCommand::parse(IParser::Pos & /* pos */, std::shared_ptr<ASTKeeperQuery
void HelpCommand::execute(const ASTKeeperQuery * /* query */, KeeperClient * /* client */) const
{
for (const auto & pair : KeeperClient::commands)
std::cout << pair.second->getHelpMessage() << "\n";
std::cout << pair.second->generateHelpString() << "\n";
}
bool FourLetterWordCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const

View File

@ -21,6 +21,12 @@ public:
virtual String getName() const = 0;
virtual ~IKeeperClientCommand() = default;
String generateHelpString() const
{
return fmt::vformat(getHelpMessage(), fmt::make_format_args(getName()));
}
};
using Command = std::shared_ptr<IKeeperClientCommand>;
@ -34,7 +40,7 @@ class LSCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "ls [path] -- Lists the nodes for the given path (default: cwd)"; }
String getHelpMessage() const override { return "{} [path] -- Lists the nodes for the given path (default: cwd)"; }
};
class CDCommand : public IKeeperClientCommand
@ -45,7 +51,7 @@ class CDCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "cd [path] -- Change the working path (default `.`)"; }
String getHelpMessage() const override { return "{} [path] -- Change the working path (default `.`)"; }
};
class SetCommand : public IKeeperClientCommand
@ -58,7 +64,7 @@ class SetCommand : public IKeeperClientCommand
String getHelpMessage() const override
{
return "set <path> <value> [version] -- Updates the node's value. Only update if version matches (default: -1)";
return "{} <path> <value> [version] -- Updates the node's value. Only update if version matches (default: -1)";
}
};
@ -70,7 +76,7 @@ class CreateCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "create <path> <value> -- Creates new node"; }
String getHelpMessage() const override { return "{} <path> <value> -- Creates new node"; }
};
class GetCommand : public IKeeperClientCommand
@ -81,9 +87,63 @@ class GetCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "get <path> -- Returns the node's value"; }
String getHelpMessage() const override { return "{} <path> -- Returns the node's value"; }
};
class GetStatCommand : public IKeeperClientCommand
{
String getName() const override { return "get_stat"; }
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "{} [path] -- Returns the node's stat (default `.`)"; }
};
class FindSuperNodes : public IKeeperClientCommand
{
String getName() const override { return "find_super_nodes"; }
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override
{
return "{} <threshold> [path] -- Finds nodes with number of children larger than some threshold for the given path (default `.`)";
}
};
class DeleteStableBackups : public IKeeperClientCommand
{
String getName() const override { return "delete_stable_backups"; }
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override
{
return "{} -- Deletes ClickHouse nodes used for backups that are now inactive";
}
};
class FindBigFamily : public IKeeperClientCommand
{
String getName() const override { return "find_big_family"; }
bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override
{
return "{} [path] [n] -- Returns the top n nodes with the biggest family in the subtree (default path = `.` and n = 10)";
}
};
class RMCommand : public IKeeperClientCommand
{
String getName() const override { return "rm"; }
@ -92,7 +152,7 @@ class RMCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "remove <path> -- Remove the node"; }
String getHelpMessage() const override { return "{} <path> -- Remove the node"; }
};
class RMRCommand : public IKeeperClientCommand
@ -103,7 +163,7 @@ class RMRCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "rmr <path> -- Recursively deletes path. Confirmation required"; }
String getHelpMessage() const override { return "{} <path> -- Recursively deletes path. Confirmation required"; }
};
class HelpCommand : public IKeeperClientCommand
@ -114,7 +174,7 @@ class HelpCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "help -- Prints this message"; }
String getHelpMessage() const override { return "{} -- Prints this message"; }
};
class FourLetterWordCommand : public IKeeperClientCommand
@ -125,7 +185,7 @@ class FourLetterWordCommand : public IKeeperClientCommand
void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
String getHelpMessage() const override { return "flwc <command> -- Executes four-letter-word command"; }
String getHelpMessage() const override { return "{} <command> -- Executes four-letter-word command"; }
};
}

View File

@ -177,6 +177,10 @@ void KeeperClient::initialize(Poco::Util::Application & /* self */)
std::make_shared<SetCommand>(),
std::make_shared<CreateCommand>(),
std::make_shared<GetCommand>(),
std::make_shared<GetStatCommand>(),
std::make_shared<FindSuperNodes>(),
std::make_shared<DeleteStableBackups>(),
std::make_shared<FindBigFamily>(),
std::make_shared<RMCommand>(),
std::make_shared<RMRCommand>(),
std::make_shared<HelpCommand>(),

View File

@ -58,6 +58,7 @@ bool KeeperParser::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
return false;
String command_name(pos->begin, pos->end);
std::transform(command_name.begin(), command_name.end(), command_name.begin(), [](unsigned char c) { return std::tolower(c); });
Command command;
auto iter = KeeperClient::commands.find(command_name);

View File

@ -1691,17 +1691,26 @@ try
global_context->initializeTraceCollector();
/// Set up server-wide memory profiler (for total memory tracker).
UInt64 total_memory_profiler_step = config().getUInt64("total_memory_profiler_step", 0);
if (total_memory_profiler_step)
if (server_settings.total_memory_profiler_step)
{
total_memory_tracker.setProfilerStep(total_memory_profiler_step);
total_memory_tracker.setProfilerStep(server_settings.total_memory_profiler_step);
}
double total_memory_tracker_sample_probability = config().getDouble("total_memory_tracker_sample_probability", 0);
if (total_memory_tracker_sample_probability > 0.0)
if (server_settings.total_memory_tracker_sample_probability > 0.0)
{
total_memory_tracker.setSampleProbability(total_memory_tracker_sample_probability);
total_memory_tracker.setSampleProbability(server_settings.total_memory_tracker_sample_probability);
}
if (server_settings.total_memory_profiler_sample_min_allocation_size)
{
total_memory_tracker.setSampleMinAllocationSize(server_settings.total_memory_profiler_sample_min_allocation_size);
}
if (server_settings.total_memory_profiler_sample_max_allocation_size)
{
total_memory_tracker.setSampleMaxAllocationSize(server_settings.total_memory_profiler_sample_max_allocation_size);
}
}
#endif
@ -2036,27 +2045,26 @@ void Server::createServers(
for (const auto & protocol : protocols)
{
if (!server_type.shouldStart(ServerType::Type::CUSTOM, protocol))
std::string prefix = "protocols." + protocol + ".";
std::string port_name = prefix + "port";
std::string description {"<undefined> protocol"};
if (config.has(prefix + "description"))
description = config.getString(prefix + "description");
if (!config.has(prefix + "port"))
continue;
if (!server_type.shouldStart(ServerType::Type::CUSTOM, port_name))
continue;
std::vector<std::string> hosts;
if (config.has("protocols." + protocol + ".host"))
hosts.push_back(config.getString("protocols." + protocol + ".host"));
if (config.has(prefix + "host"))
hosts.push_back(config.getString(prefix + "host"));
else
hosts = listen_hosts;
for (const auto & host : hosts)
{
std::string conf_name = "protocols." + protocol;
std::string prefix = conf_name + ".";
if (!config.has(prefix + "port"))
continue;
std::string description {"<undefined> protocol"};
if (config.has(prefix + "description"))
description = config.getString(prefix + "description");
std::string port_name = prefix + "port";
bool is_secure = false;
auto stack = buildProtocolStackFromConfig(config, protocol, http_params, async_metrics, is_secure);

View File

@ -328,9 +328,6 @@ void ContextAccess::setRolesInfo(const std::shared_ptr<const EnabledRolesInfo> &
enabled_row_policies = access_control->getEnabledRowPolicies(*params.user_id, roles_info->enabled_roles);
enabled_quota = access_control->getEnabledQuota(
*params.user_id, user_name, roles_info->enabled_roles, params.address, params.forwarded_address, params.quota_key);
enabled_settings = access_control->getEnabledSettings(
*params.user_id, user->settings, roles_info->enabled_roles, roles_info->settings_from_enabled_roles);
@ -416,19 +413,32 @@ RowPolicyFilterPtr ContextAccess::getRowPolicyFilter(const String & database, co
std::shared_ptr<const EnabledQuota> ContextAccess::getQuota() const
{
std::lock_guard lock{mutex};
if (enabled_quota)
return enabled_quota;
if (!enabled_quota)
{
if (roles_info)
{
enabled_quota = access_control->getEnabledQuota(*params.user_id,
user_name,
roles_info->enabled_roles,
params.address,
params.forwarded_address,
params.quota_key);
}
else
{
static const auto unlimited_quota = EnabledQuota::getUnlimitedQuota();
return unlimited_quota;
}
}
return enabled_quota;
}
std::optional<QuotaUsage> ContextAccess::getQuotaUsage() const
{
std::lock_guard lock{mutex};
if (enabled_quota)
return enabled_quota->getUsage();
return {};
return getQuota()->getUsage();
}

View File

@ -1,4 +1,5 @@
#include <string_view>
#include <unordered_map>
#include <Access/SettingsConstraints.h>
#include <Access/resolveSetting.h>
#include <Access/AccessControl.h>
@ -6,6 +7,7 @@
#include <Storages/MergeTree/MergeTreeSettings.h>
#include <Common/FieldVisitorToString.h>
#include <Common/FieldVisitorsAccurateComparison.h>
#include <Common/SettingSource.h>
#include <IO/WriteHelpers.h>
#include <Poco/Util/AbstractConfiguration.h>
#include <boost/range/algorithm_ext/erase.hpp>
@ -20,6 +22,39 @@ namespace ErrorCodes
extern const int UNKNOWN_SETTING;
}
namespace
{
struct SettingSourceRestrictions
{
constexpr SettingSourceRestrictions() { allowed_sources.set(); }
constexpr SettingSourceRestrictions(std::initializer_list<SettingSource> allowed_sources_)
{
for (auto allowed_source : allowed_sources_)
setSourceAllowed(allowed_source, true);
}
constexpr bool isSourceAllowed(SettingSource source) { return allowed_sources[source]; }
constexpr void setSourceAllowed(SettingSource source, bool allowed) { allowed_sources[source] = allowed; }
std::bitset<SettingSource::COUNT> allowed_sources;
};
const std::unordered_map<std::string_view, SettingSourceRestrictions> SETTINGS_SOURCE_RESTRICTIONS = {
{"max_sessions_for_user", {SettingSource::PROFILE}},
};
SettingSourceRestrictions getSettingSourceRestrictions(std::string_view name)
{
auto settingConstraintIter = SETTINGS_SOURCE_RESTRICTIONS.find(name);
if (settingConstraintIter != SETTINGS_SOURCE_RESTRICTIONS.end())
return settingConstraintIter->second;
else
return SettingSourceRestrictions(); // allows everything
}
}
SettingsConstraints::SettingsConstraints(const AccessControl & access_control_) : access_control(&access_control_)
{
}
@ -98,7 +133,7 @@ void SettingsConstraints::merge(const SettingsConstraints & other)
}
void SettingsConstraints::check(const Settings & current_settings, const SettingsProfileElements & profile_elements) const
void SettingsConstraints::check(const Settings & current_settings, const SettingsProfileElements & profile_elements, SettingSource source) const
{
for (const auto & element : profile_elements)
{
@ -108,19 +143,19 @@ void SettingsConstraints::check(const Settings & current_settings, const Setting
if (element.value)
{
SettingChange value(element.setting_name, *element.value);
check(current_settings, value);
check(current_settings, value, source);
}
if (element.min_value)
{
SettingChange value(element.setting_name, *element.min_value);
check(current_settings, value);
check(current_settings, value, source);
}
if (element.max_value)
{
SettingChange value(element.setting_name, *element.max_value);
check(current_settings, value);
check(current_settings, value, source);
}
SettingConstraintWritability new_value = SettingConstraintWritability::WRITABLE;
@ -142,24 +177,24 @@ void SettingsConstraints::check(const Settings & current_settings, const Setting
}
}
void SettingsConstraints::check(const Settings & current_settings, const SettingChange & change) const
void SettingsConstraints::check(const Settings & current_settings, const SettingChange & change, SettingSource source) const
{
checkImpl(current_settings, const_cast<SettingChange &>(change), THROW_ON_VIOLATION);
checkImpl(current_settings, const_cast<SettingChange &>(change), THROW_ON_VIOLATION, source);
}
void SettingsConstraints::check(const Settings & current_settings, const SettingsChanges & changes) const
void SettingsConstraints::check(const Settings & current_settings, const SettingsChanges & changes, SettingSource source) const
{
for (const auto & change : changes)
check(current_settings, change);
check(current_settings, change, source);
}
void SettingsConstraints::check(const Settings & current_settings, SettingsChanges & changes) const
void SettingsConstraints::check(const Settings & current_settings, SettingsChanges & changes, SettingSource source) const
{
boost::range::remove_erase_if(
changes,
[&](SettingChange & change) -> bool
{
return !checkImpl(current_settings, const_cast<SettingChange &>(change), THROW_ON_VIOLATION);
return !checkImpl(current_settings, const_cast<SettingChange &>(change), THROW_ON_VIOLATION, source);
});
}
@ -174,13 +209,13 @@ void SettingsConstraints::check(const MergeTreeSettings & current_settings, cons
check(current_settings, change);
}
void SettingsConstraints::clamp(const Settings & current_settings, SettingsChanges & changes) const
void SettingsConstraints::clamp(const Settings & current_settings, SettingsChanges & changes, SettingSource source) const
{
boost::range::remove_erase_if(
changes,
[&](SettingChange & change) -> bool
{
return !checkImpl(current_settings, change, CLAMP_ON_VIOLATION);
return !checkImpl(current_settings, change, CLAMP_ON_VIOLATION, source);
});
}
@ -215,7 +250,10 @@ bool getNewValueToCheck(const T & current_settings, SettingChange & change, Fiel
return true;
}
bool SettingsConstraints::checkImpl(const Settings & current_settings, SettingChange & change, ReactionOnViolation reaction) const
bool SettingsConstraints::checkImpl(const Settings & current_settings,
SettingChange & change,
ReactionOnViolation reaction,
SettingSource source) const
{
std::string_view setting_name = Settings::Traits::resolveName(change.name);
@ -247,7 +285,7 @@ bool SettingsConstraints::checkImpl(const Settings & current_settings, SettingCh
if (!getNewValueToCheck(current_settings, change, new_value, reaction == THROW_ON_VIOLATION))
return false;
return getChecker(current_settings, setting_name).check(change, new_value, reaction);
return getChecker(current_settings, setting_name).check(change, new_value, reaction, source);
}
bool SettingsConstraints::checkImpl(const MergeTreeSettings & current_settings, SettingChange & change, ReactionOnViolation reaction) const
@ -255,10 +293,13 @@ bool SettingsConstraints::checkImpl(const MergeTreeSettings & current_settings,
Field new_value;
if (!getNewValueToCheck(current_settings, change, new_value, reaction == THROW_ON_VIOLATION))
return false;
return getMergeTreeChecker(change.name).check(change, new_value, reaction);
return getMergeTreeChecker(change.name).check(change, new_value, reaction, SettingSource::QUERY);
}
bool SettingsConstraints::Checker::check(SettingChange & change, const Field & new_value, ReactionOnViolation reaction) const
bool SettingsConstraints::Checker::check(SettingChange & change,
const Field & new_value,
ReactionOnViolation reaction,
SettingSource source) const
{
if (!explain.empty())
{
@ -326,6 +367,14 @@ bool SettingsConstraints::Checker::check(SettingChange & change, const Field & n
change.value = max_value;
}
if (!getSettingSourceRestrictions(setting_name).isSourceAllowed(source))
{
if (reaction == THROW_ON_VIOLATION)
throw Exception(ErrorCodes::READONLY, "Setting {} is not allowed to be set by {}", setting_name, toString(source));
else
return false;
}
return true;
}

View File

@ -2,6 +2,7 @@
#include <Access/SettingsProfileElement.h>
#include <Common/SettingsChanges.h>
#include <Common/SettingSource.h>
#include <unordered_map>
namespace Poco::Util
@ -73,17 +74,18 @@ public:
void merge(const SettingsConstraints & other);
/// Checks whether `change` violates these constraints and throws an exception if so.
void check(const Settings & current_settings, const SettingsProfileElements & profile_elements) const;
void check(const Settings & current_settings, const SettingChange & change) const;
void check(const Settings & current_settings, const SettingsChanges & changes) const;
void check(const Settings & current_settings, SettingsChanges & changes) const;
void check(const Settings & current_settings, const SettingsProfileElements & profile_elements, SettingSource source) const;
void check(const Settings & current_settings, const SettingChange & change, SettingSource source) const;
void check(const Settings & current_settings, const SettingsChanges & changes, SettingSource source) const;
void check(const Settings & current_settings, SettingsChanges & changes, SettingSource source) const;
/// Checks whether `change` violates these constraints and throws an exception if so. (setting short name is expected inside `changes`)
void check(const MergeTreeSettings & current_settings, const SettingChange & change) const;
void check(const MergeTreeSettings & current_settings, const SettingsChanges & changes) const;
/// Checks whether `change` violates these and clamps the `change` if so.
void clamp(const Settings & current_settings, SettingsChanges & changes) const;
void clamp(const Settings & current_settings, SettingsChanges & changes, SettingSource source) const;
friend bool operator ==(const SettingsConstraints & left, const SettingsConstraints & right);
friend bool operator !=(const SettingsConstraints & left, const SettingsConstraints & right) { return !(left == right); }
@ -133,7 +135,10 @@ private:
{}
// Perform checking
bool check(SettingChange & change, const Field & new_value, ReactionOnViolation reaction) const;
bool check(SettingChange & change,
const Field & new_value,
ReactionOnViolation reaction,
SettingSource source) const;
};
struct StringHash
@ -145,7 +150,11 @@ private:
}
};
bool checkImpl(const Settings & current_settings, SettingChange & change, ReactionOnViolation reaction) const;
bool checkImpl(const Settings & current_settings,
SettingChange & change,
ReactionOnViolation reaction,
SettingSource source) const;
bool checkImpl(const MergeTreeSettings & current_settings, SettingChange & change, ReactionOnViolation reaction) const;
Checker getChecker(const Settings & current_settings, std::string_view setting_name) const;

View File

@ -0,0 +1,221 @@
#include <Analyzer/Passes/OptimizeDateOrDateTimeConverterWithPreimagePass.h>
#include <Functions/FunctionFactory.h>
#include <Analyzer/InDepthQueryTreeVisitor.h>
#include <Analyzer/ColumnNode.h>
#include <Analyzer/ConstantNode.h>
#include <Analyzer/FunctionNode.h>
#include <Common/DateLUT.h>
#include <Common/DateLUTImpl.h>
namespace DB
{
namespace ErrorCodes
{
extern const int LOGICAL_ERROR;
}
namespace
{
class OptimizeDateOrDateTimeConverterWithPreimageVisitor : public InDepthQueryTreeVisitorWithContext<OptimizeDateOrDateTimeConverterWithPreimageVisitor>
{
public:
using Base = InDepthQueryTreeVisitorWithContext<OptimizeDateOrDateTimeConverterWithPreimageVisitor>;
explicit OptimizeDateOrDateTimeConverterWithPreimageVisitor(ContextPtr context)
: Base(std::move(context))
{}
static bool needChildVisit(QueryTreeNodePtr & node, QueryTreeNodePtr & /*child*/)
{
const static std::unordered_set<String> relations = {
"equals",
"notEquals",
"less",
"greater",
"lessOrEquals",
"greaterOrEquals",
};
if (const auto * function = node->as<FunctionNode>())
{
return !relations.contains(function->getFunctionName());
}
return true;
}
void enterImpl(QueryTreeNodePtr & node) const
{
const static std::unordered_map<String, String> swap_relations = {
{"equals", "equals"},
{"notEquals", "notEquals"},
{"less", "greater"},
{"greater", "less"},
{"lessOrEquals", "greaterOrEquals"},
{"greaterOrEquals", "lessOrEquals"},
};
const auto * function = node->as<FunctionNode>();
if (!function || !swap_relations.contains(function->getFunctionName())) return;
if (function->getArguments().getNodes().size() != 2) return;
size_t func_id = function->getArguments().getNodes().size();
for (size_t i = 0; i < function->getArguments().getNodes().size(); i++)
{
if (const auto * func = function->getArguments().getNodes()[i]->as<FunctionNode>())
{
func_id = i;
}
}
if (func_id == function->getArguments().getNodes().size()) return;
size_t literal_id = 1 - func_id;
const auto * literal = function->getArguments().getNodes()[literal_id]->as<ConstantNode>();
if (!literal || literal->getValue().getType() != Field::Types::UInt64) return;
String comparator = literal_id > func_id ? function->getFunctionName(): swap_relations.at(function->getFunctionName());
const auto * func_node = function->getArguments().getNodes()[func_id]->as<FunctionNode>();
/// Currently we only handle single-argument functions.
if (!func_node || func_node->getArguments().getNodes().size() != 1) return;
const auto * column_id = func_node->getArguments().getNodes()[0]->as<ColumnNode>();
if (!column_id) return;
const auto * column_type = column_id->getColumnType().get();
if (!isDateOrDate32(column_type) && !isDateTime(column_type) && !isDateTime64(column_type)) return;
const auto & converter = FunctionFactory::instance().tryGet(func_node->getFunctionName(), getContext());
if (!converter) return;
ColumnsWithTypeAndName args;
args.emplace_back(column_id->getColumnType(), "tmp");
auto converter_base = converter->build(args);
if (!converter_base || !converter_base->hasInformationAboutPreimage()) return;
auto preimage_range = converter_base->getPreimage(*(column_id->getColumnType()), literal->getValue());
if (!preimage_range) return;
const auto new_node = generateOptimizedDateFilter(comparator, *column_id, *preimage_range);
if (!new_node) return;
node = new_node;
}
private:
QueryTreeNodePtr generateOptimizedDateFilter(const String & comparator, const ColumnNode & column_node, const std::pair<Field, Field>& range) const
{
const DateLUTImpl & date_lut = DateLUT::instance("UTC");
String start_date_or_date_time;
String end_date_or_date_time;
if (isDateOrDate32(column_node.getColumnType().get()))
{
start_date_or_date_time = date_lut.dateToString(range.first.get<DateLUTImpl::Time>());
end_date_or_date_time = date_lut.dateToString(range.second.get<DateLUTImpl::Time>());
}
else if (isDateTime(column_node.getColumnType().get()) || isDateTime64(column_node.getColumnType().get()))
{
start_date_or_date_time = date_lut.timeToString(range.first.get<DateLUTImpl::Time>());
end_date_or_date_time = date_lut.timeToString(range.second.get<DateLUTImpl::Time>());
}
else [[unlikely]] return {};
if (comparator == "equals")
{
const auto lhs = std::make_shared<FunctionNode>("greaterOrEquals");
lhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
lhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(start_date_or_date_time));
resolveOrdinaryFunctionNode(*lhs, lhs->getFunctionName());
const auto rhs = std::make_shared<FunctionNode>("less");
rhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
rhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
resolveOrdinaryFunctionNode(*rhs, rhs->getFunctionName());
const auto new_date_filter = std::make_shared<FunctionNode>("and");
new_date_filter->getArguments().getNodes() = {lhs, rhs};
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
return new_date_filter;
}
else if (comparator == "notEquals")
{
const auto lhs = std::make_shared<FunctionNode>("less");
lhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
lhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(start_date_or_date_time));
resolveOrdinaryFunctionNode(*lhs, lhs->getFunctionName());
const auto rhs = std::make_shared<FunctionNode>("greaterOrEquals");
rhs->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
rhs->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
resolveOrdinaryFunctionNode(*rhs, rhs->getFunctionName());
const auto new_date_filter = std::make_shared<FunctionNode>("or");
new_date_filter->getArguments().getNodes() = {lhs, rhs};
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
return new_date_filter;
}
else if (comparator == "greater")
{
const auto new_date_filter = std::make_shared<FunctionNode>("greaterOrEquals");
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
return new_date_filter;
}
else if (comparator == "lessOrEquals")
{
const auto new_date_filter = std::make_shared<FunctionNode>("less");
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(end_date_or_date_time));
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
return new_date_filter;
}
else if (comparator == "less" || comparator == "greaterOrEquals")
{
const auto new_date_filter = std::make_shared<FunctionNode>(comparator);
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ColumnNode>(column_node.getColumn(), column_node.getColumnSource()));
new_date_filter->getArguments().getNodes().push_back(std::make_shared<ConstantNode>(start_date_or_date_time));
resolveOrdinaryFunctionNode(*new_date_filter, new_date_filter->getFunctionName());
return new_date_filter;
}
else [[unlikely]]
{
throw Exception(ErrorCodes::LOGICAL_ERROR,
"Expected equals, notEquals, less, lessOrEquals, greater, greaterOrEquals. Actual {}",
comparator);
}
}
void resolveOrdinaryFunctionNode(FunctionNode & function_node, const String & function_name) const
{
auto function = FunctionFactory::instance().get(function_name, getContext());
function_node.resolveAsFunction(function->build(function_node.getArgumentColumns()));
}
};
}
void OptimizeDateOrDateTimeConverterWithPreimagePass::run(QueryTreeNodePtr query_tree_node, ContextPtr context)
{
OptimizeDateOrDateTimeConverterWithPreimageVisitor visitor(std::move(context));
visitor.visit(query_tree_node);
}
}

View File

@ -0,0 +1,24 @@
#pragma once
#include <Analyzer/IQueryTreePass.h>
namespace DB
{
/** Replace predicate having Date/DateTime converters with their preimages to improve performance.
* Given a Date column c, toYear(c) = 2023 -> c >= '2023-01-01' AND c < '2024-01-01'
* Or if c is a DateTime column, toYear(c) = 2023 -> c >= '2023-01-01 00:00:00' AND c < '2024-01-01 00:00:00'.
* The similar optimization also applies to other converters.
*/
class OptimizeDateOrDateTimeConverterWithPreimagePass final : public IQueryTreePass
{
public:
String getName() override { return "OptimizeDateOrDateTimeConverterWithPreimagePass"; }
String getDescription() override { return "Replace predicate having Date/DateTime converters with their preimages"; }
void run(QueryTreeNodePtr query_tree_node, ContextPtr context) override;
};
}

View File

@ -6494,7 +6494,9 @@ void QueryAnalyzer::resolveArrayJoin(QueryTreeNodePtr & array_join_node, Identif
resolveExpressionNode(array_join_expression, scope, false /*allow_lambda_expression*/, false /*allow_table_expression*/);
auto result_type = array_join_expression->getResultType();
auto process_array_join_expression = [&](QueryTreeNodePtr & expression)
{
auto result_type = expression->getResultType();
bool is_array_type = isArray(result_type);
bool is_map_type = isMap(result_type);
@ -6502,7 +6504,7 @@ void QueryAnalyzer::resolveArrayJoin(QueryTreeNodePtr & array_join_node, Identif
throw Exception(ErrorCodes::TYPE_MISMATCH,
"ARRAY JOIN {} requires expression {} with Array or Map type. Actual {}. In scope {}",
array_join_node_typed.formatASTForErrorMessage(),
array_join_expression->formatASTForErrorMessage(),
expression->formatASTForErrorMessage(),
result_type->getName(),
scope.scope_node->formatASTForErrorMessage());
@ -6540,9 +6542,21 @@ void QueryAnalyzer::resolveArrayJoin(QueryTreeNodePtr & array_join_node, Identif
array_join_column_names.emplace(array_join_column_name);
NameAndTypePair array_join_column(array_join_column_name, result_type);
auto array_join_column_node = std::make_shared<ColumnNode>(std::move(array_join_column), array_join_expression, array_join_node);
auto array_join_column_node = std::make_shared<ColumnNode>(std::move(array_join_column), expression, array_join_node);
array_join_column_node->setAlias(array_join_expression_alias);
array_join_column_expressions.push_back(std::move(array_join_column_node));
};
// Support ARRAY JOIN COLUMNS(...). COLUMNS transformer is resolved to list of columns.
if (auto * columns_list = array_join_expression->as<ListNode>())
{
for (auto & array_join_subexpression : columns_list->getNodes())
process_array_join_expression(array_join_subexpression);
}
else
{
process_array_join_expression(array_join_expression);
}
}
/** Allow to resolve ARRAY JOIN columns from aliases with types after ARRAY JOIN only after ARRAY JOIN expression list is resolved, because
@ -6554,11 +6568,9 @@ void QueryAnalyzer::resolveArrayJoin(QueryTreeNodePtr & array_join_node, Identif
* And it is expected that `value_element` inside projection expression list will be resolved as `value_element` expression
* with type after ARRAY JOIN.
*/
for (size_t i = 0; i < array_join_nodes_size; ++i)
array_join_nodes = std::move(array_join_column_expressions);
for (auto & array_join_column_expression : array_join_nodes)
{
auto & array_join_column_expression = array_join_nodes[i];
array_join_column_expression = std::move(array_join_column_expressions[i]);
auto it = scope.alias_name_to_expression_node.find(array_join_column_expression->getAlias());
if (it != scope.alias_name_to_expression_node.end())
{

View File

@ -42,6 +42,7 @@
#include <Analyzer/Passes/CrossToInnerJoinPass.h>
#include <Analyzer/Passes/ShardNumColumnToFunctionPass.h>
#include <Analyzer/Passes/ConvertQueryToCNFPass.h>
#include <Analyzer/Passes/OptimizeDateOrDateTimeConverterWithPreimagePass.h>
namespace DB
{
@ -278,6 +279,7 @@ void addQueryTreePasses(QueryTreePassManager & manager)
manager.addPass(std::make_unique<AutoFinalOnQueryPass>());
manager.addPass(std::make_unique<CrossToInnerJoinPass>());
manager.addPass(std::make_unique<ShardNumColumnToFunctionPass>());
manager.addPass(std::make_unique<OptimizeDateOrDateTimeConverterWithPreimagePass>());
}
}

View File

@ -30,6 +30,7 @@ public:
String compression_method;
int compression_level = -1;
String password;
String s3_storage_class;
ContextPtr context;
bool is_internal_backup = false;
std::shared_ptr<IBackupCoordination> backup_coordination;

View File

@ -88,7 +88,7 @@ namespace
request.SetMaxKeys(1);
auto outcome = client.ListObjects(request);
if (!outcome.IsSuccess())
throw Exception::createDeprecated(outcome.GetError().GetMessage(), ErrorCodes::S3_ERROR);
throw S3Exception(outcome.GetError().GetMessage(), outcome.GetError().GetErrorType());
return outcome.GetResult().GetContents();
}
@ -178,7 +178,7 @@ void BackupReaderS3::copyFileToDisk(const String & path_in_backup, size_t file_s
BackupWriterS3::BackupWriterS3(
const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const ContextPtr & context_)
const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const String & storage_class_name, const ContextPtr & context_)
: BackupWriterDefault(&Poco::Logger::get("BackupWriterS3"), context_)
, s3_uri(s3_uri_)
, client(makeS3Client(s3_uri_, access_key_id_, secret_access_key_, context_))
@ -188,6 +188,7 @@ BackupWriterS3::BackupWriterS3(
request_settings.updateFromSettings(context_->getSettingsRef());
request_settings.max_single_read_retries = context_->getSettingsRef().s3_max_single_read_retries; // FIXME: Avoid taking value for endpoint
request_settings.allow_native_copy = allow_s3_native_copy;
request_settings.setStorageClassName(storage_class_name);
}
void BackupWriterS3::copyFileFromDisk(const String & path_in_backup, DiskPtr src_disk, const String & src_path,
@ -271,7 +272,7 @@ void BackupWriterS3::removeFile(const String & file_name)
request.SetKey(fs::path(s3_uri.key) / file_name);
auto outcome = client->DeleteObject(request);
if (!outcome.IsSuccess() && !isNotFoundError(outcome.GetError().GetErrorType()))
throw Exception::createDeprecated(outcome.GetError().GetMessage(), ErrorCodes::S3_ERROR);
throw S3Exception(outcome.GetError().GetMessage(), outcome.GetError().GetErrorType());
}
void BackupWriterS3::removeFiles(const Strings & file_names)
@ -329,7 +330,7 @@ void BackupWriterS3::removeFilesBatch(const Strings & file_names)
auto outcome = client->DeleteObjects(request);
if (!outcome.IsSuccess() && !isNotFoundError(outcome.GetError().GetErrorType()))
throw Exception::createDeprecated(outcome.GetError().GetMessage(), ErrorCodes::S3_ERROR);
throw S3Exception(outcome.GetError().GetMessage(), outcome.GetError().GetErrorType());
}
}

View File

@ -38,7 +38,7 @@ private:
class BackupWriterS3 : public BackupWriterDefault
{
public:
BackupWriterS3(const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const ContextPtr & context_);
BackupWriterS3(const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const String & storage_class_name, const ContextPtr & context_);
~BackupWriterS3() override;
bool fileExists(const String & file_name) override;

View File

@ -21,6 +21,7 @@ namespace ErrorCodes
M(String, id) \
M(String, compression_method) \
M(String, password) \
M(String, s3_storage_class) \
M(Bool, structure_only) \
M(Bool, async) \
M(Bool, decrypt_files_from_encrypted_disks) \

View File

@ -25,6 +25,9 @@ struct BackupSettings
/// Password used to encrypt the backup.
String password;
/// S3 storage class.
String s3_storage_class = "";
/// If this is set to true then only create queries will be written to backup,
/// without the data of tables.
bool structure_only = false;

View File

@ -344,6 +344,7 @@ void BackupsWorker::doBackup(
backup_create_params.compression_method = backup_settings.compression_method;
backup_create_params.compression_level = backup_settings.compression_level;
backup_create_params.password = backup_settings.password;
backup_create_params.s3_storage_class = backup_settings.s3_storage_class;
backup_create_params.is_internal_backup = backup_settings.internal;
backup_create_params.backup_coordination = backup_coordination;
backup_create_params.backup_uuid = backup_settings.backup_uuid;

View File

@ -112,7 +112,7 @@ void registerBackupEngineS3(BackupFactory & factory)
}
else
{
auto writer = std::make_shared<BackupWriterS3>(S3::URI{s3_uri}, access_key_id, secret_access_key, params.allow_s3_native_copy, params.context);
auto writer = std::make_shared<BackupWriterS3>(S3::URI{s3_uri}, access_key_id, secret_access_key, params.allow_s3_native_copy, params.s3_storage_class, params.context);
return std::make_unique<BackupImpl>(
backup_name_for_logging,
archive_params,

View File

@ -124,6 +124,9 @@ void Suggest::load(ContextPtr context, const ConnectionParameters & connection_p
if (e.code() == ErrorCodes::DEADLOCK_AVOIDED)
continue;
/// Client can successfully connect to the server and
/// get ErrorCodes::USER_SESSION_LIMIT_EXCEEDED for suggestion connection.
/// We should not use std::cerr here, because this method works concurrently with the main thread.
/// WriteBufferFromFileDescriptor will write directly to the file descriptor, avoiding data race on std::cerr.

View File

@ -564,16 +564,23 @@ void ColumnNullable::updatePermutationImpl(IColumn::PermutationSortDirection dir
else
getNestedColumn().updatePermutation(direction, stability, limit, null_direction_hint, res, new_ranges);
equal_ranges = std::move(new_ranges);
if (unlikely(stability == PermutationSortStability::Stable))
{
for (auto & null_range : null_ranges)
::sort(res.begin() + null_range.first, res.begin() + null_range.second);
}
if (is_nulls_last || null_ranges.empty())
{
equal_ranges = std::move(new_ranges);
std::move(null_ranges.begin(), null_ranges.end(), std::back_inserter(equal_ranges));
}
else
{
equal_ranges = std::move(null_ranges);
std::move(new_ranges.begin(), new_ranges.end(), std::back_inserter(equal_ranges));
}
}
void ColumnNullable::getPermutation(IColumn::PermutationSortDirection direction, IColumn::PermutationSortStability stability,
size_t limit, int null_direction_hint, Permutation & res) const

View File

@ -439,7 +439,7 @@ void ColumnSparse::compareColumn(const IColumn & rhs, size_t rhs_row_num,
PaddedPODArray<UInt64> * row_indexes, PaddedPODArray<Int8> & compare_results,
int direction, int nan_direction_hint) const
{
if (row_indexes)
if (row_indexes || !typeid_cast<const ColumnSparse *>(&rhs))
{
/// TODO: implement without conversion to full column.
auto this_full = convertToFullColumnIfSparse();

View File

@ -582,6 +582,7 @@
M(697, CANNOT_RESTORE_TO_NONENCRYPTED_DISK) \
M(698, INVALID_REDIS_STORAGE_TYPE) \
M(699, INVALID_REDIS_TABLE_STRUCTURE) \
M(700, USER_SESSION_LIMIT_EXCEEDED) \
\
M(999, KEEPER_EXCEPTION) \
M(1000, POCO_EXCEPTION) \

View File

@ -229,7 +229,7 @@ void MemoryTracker::allocImpl(Int64 size, bool throw_if_memory_exceeded, MemoryT
}
std::bernoulli_distribution sample(sample_probability);
if (unlikely(sample_probability > 0.0 && sample(thread_local_rng)))
if (unlikely(sample_probability > 0.0 && isSizeOkForSampling(size) && sample(thread_local_rng)))
{
MemoryTrackerBlockerInThread untrack_lock(VariableContext::Global);
DB::TraceSender::send(DB::TraceType::MemorySample, StackTrace(), {.size = size});
@ -413,7 +413,7 @@ void MemoryTracker::free(Int64 size)
}
std::bernoulli_distribution sample(sample_probability);
if (unlikely(sample_probability > 0.0 && sample(thread_local_rng)))
if (unlikely(sample_probability > 0.0 && isSizeOkForSampling(size) && sample(thread_local_rng)))
{
MemoryTrackerBlockerInThread untrack_lock(VariableContext::Global);
DB::TraceSender::send(DB::TraceType::MemorySample, StackTrace(), {.size = -size});
@ -534,6 +534,12 @@ void MemoryTracker::setOrRaiseProfilerLimit(Int64 value)
;
}
bool MemoryTracker::isSizeOkForSampling(UInt64 size) const
{
/// We can avoid comparison min_allocation_size_bytes with zero, because we cannot have 0 bytes allocation/deallocation
return ((max_allocation_size_bytes == 0 || size <= max_allocation_size_bytes) && size >= min_allocation_size_bytes);
}
bool canEnqueueBackgroundTask()
{
auto limit = background_memory_tracker.getSoftLimit();

View File

@ -67,6 +67,12 @@ private:
/// To randomly sample allocations and deallocations in trace_log.
double sample_probability = 0;
/// Randomly sample allocations only larger or equal to this size
UInt64 min_allocation_size_bytes = 0;
/// Randomly sample allocations only smaller or equal to this size
UInt64 max_allocation_size_bytes = 0;
/// Singly-linked list. All information will be passed to subsequent memory trackers also (it allows to implement trackers hierarchy).
/// In terms of tree nodes it is the list of parents. Lifetime of these trackers should "include" lifetime of current tracker.
std::atomic<MemoryTracker *> parent {};
@ -88,6 +94,8 @@ private:
void setOrRaiseProfilerLimit(Int64 value);
bool isSizeOkForSampling(UInt64 size) const;
/// allocImpl(...) and free(...) should not be used directly
friend struct CurrentMemoryTracker;
void allocImpl(Int64 size, bool throw_if_memory_exceeded, MemoryTracker * query_tracker = nullptr);
@ -166,6 +174,16 @@ public:
sample_probability = value;
}
void setSampleMinAllocationSize(UInt64 value)
{
min_allocation_size_bytes = value;
}
void setSampleMaxAllocationSize(UInt64 value)
{
max_allocation_size_bytes = value;
}
void setProfilerStep(Int64 value)
{
profiler_step = value;

View File

@ -0,0 +1,43 @@
#pragma once
#include <string_view>
namespace DB
{
enum SettingSource
{
/// Query or session change:
/// SET <setting> = <value>
/// SELECT ... SETTINGS [<setting> = <value]
QUERY,
/// Profile creation or altering:
/// CREATE SETTINGS PROFILE ... SETTINGS [<setting> = <value]
/// ALTER SETTINGS PROFILE ... SETTINGS [<setting> = <value]
PROFILE,
/// Role creation or altering:
/// CREATE ROLE ... SETTINGS [<setting> = <value>]
/// ALTER ROLE ... SETTINGS [<setting> = <value]
ROLE,
/// User creation or altering:
/// CREATE USER ... SETTINGS [<setting> = <value>]
/// ALTER USER ... SETTINGS [<setting> = <value]
USER,
COUNT,
};
constexpr std::string_view toString(SettingSource source)
{
switch (source)
{
case SettingSource::QUERY: return "query";
case SettingSource::PROFILE: return "profile";
case SettingSource::USER: return "user";
case SettingSource::ROLE: return "role";
default: return "unknown";
}
}
}

View File

@ -136,6 +136,8 @@ using ResponseCallback = std::function<void(const Response &)>;
struct Response
{
Error error = Error::ZOK;
int64_t zxid = 0;
Response() = default;
Response(const Response &) = default;
Response & operator=(const Response &) = default;
@ -490,8 +492,6 @@ public:
/// Useful to check owner of ephemeral node.
virtual int64_t getSessionID() const = 0;
virtual Poco::Net::SocketAddress getConnectedAddress() const = 0;
/// If the method will throw an exception, callbacks won't be called.
///
/// After the method is executed successfully, you must wait for callbacks
@ -564,6 +564,10 @@ public:
virtual const DB::KeeperFeatureFlags * getKeeperFeatureFlags() const { return nullptr; }
/// A ZooKeeper session can have an optional deadline set on it.
/// After it has been reached, the session needs to be finalized.
virtual bool hasReachedDeadline() const = 0;
/// Expire session and finish all pending requests
virtual void finalize(const String & reason) = 0;
};

View File

@ -195,6 +195,7 @@ struct TestKeeperMultiRequest final : MultiRequest, TestKeeperRequest
std::pair<ResponsePtr, Undo> TestKeeperCreateRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
CreateResponse response;
response.zxid = zxid;
Undo undo;
if (container.contains(path))
@ -257,9 +258,10 @@ std::pair<ResponsePtr, Undo> TestKeeperCreateRequest::process(TestKeeper::Contai
return { std::make_shared<CreateResponse>(response), undo };
}
std::pair<ResponsePtr, Undo> TestKeeperRemoveRequest::process(TestKeeper::Container & container, int64_t) const
std::pair<ResponsePtr, Undo> TestKeeperRemoveRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
RemoveResponse response;
response.zxid = zxid;
Undo undo;
auto it = container.find(path);
@ -296,9 +298,10 @@ std::pair<ResponsePtr, Undo> TestKeeperRemoveRequest::process(TestKeeper::Contai
return { std::make_shared<RemoveResponse>(response), undo };
}
std::pair<ResponsePtr, Undo> TestKeeperExistsRequest::process(TestKeeper::Container & container, int64_t) const
std::pair<ResponsePtr, Undo> TestKeeperExistsRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
ExistsResponse response;
response.zxid = zxid;
auto it = container.find(path);
if (it != container.end())
@ -314,9 +317,10 @@ std::pair<ResponsePtr, Undo> TestKeeperExistsRequest::process(TestKeeper::Contai
return { std::make_shared<ExistsResponse>(response), {} };
}
std::pair<ResponsePtr, Undo> TestKeeperGetRequest::process(TestKeeper::Container & container, int64_t) const
std::pair<ResponsePtr, Undo> TestKeeperGetRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
GetResponse response;
response.zxid = zxid;
auto it = container.find(path);
if (it == container.end())
@ -336,6 +340,7 @@ std::pair<ResponsePtr, Undo> TestKeeperGetRequest::process(TestKeeper::Container
std::pair<ResponsePtr, Undo> TestKeeperSetRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
SetResponse response;
response.zxid = zxid;
Undo undo;
auto it = container.find(path);
@ -370,9 +375,10 @@ std::pair<ResponsePtr, Undo> TestKeeperSetRequest::process(TestKeeper::Container
return { std::make_shared<SetResponse>(response), undo };
}
std::pair<ResponsePtr, Undo> TestKeeperListRequest::process(TestKeeper::Container & container, int64_t) const
std::pair<ResponsePtr, Undo> TestKeeperListRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
ListResponse response;
response.zxid = zxid;
auto it = container.find(path);
if (it == container.end())
@ -414,9 +420,10 @@ std::pair<ResponsePtr, Undo> TestKeeperListRequest::process(TestKeeper::Containe
return { std::make_shared<ListResponse>(response), {} };
}
std::pair<ResponsePtr, Undo> TestKeeperCheckRequest::process(TestKeeper::Container & container, int64_t) const
std::pair<ResponsePtr, Undo> TestKeeperCheckRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
CheckResponse response;
response.zxid = zxid;
auto it = container.find(path);
if (it == container.end())
{
@ -434,10 +441,11 @@ std::pair<ResponsePtr, Undo> TestKeeperCheckRequest::process(TestKeeper::Contain
return { std::make_shared<CheckResponse>(response), {} };
}
std::pair<ResponsePtr, Undo> TestKeeperSyncRequest::process(TestKeeper::Container & /*container*/, int64_t) const
std::pair<ResponsePtr, Undo> TestKeeperSyncRequest::process(TestKeeper::Container & /*container*/, int64_t zxid) const
{
SyncResponse response;
response.path = path;
response.zxid = zxid;
return { std::make_shared<SyncResponse>(std::move(response)), {} };
}
@ -456,6 +464,7 @@ std::pair<ResponsePtr, Undo> TestKeeperReconfigRequest::process(TestKeeper::Cont
std::pair<ResponsePtr, Undo> TestKeeperMultiRequest::process(TestKeeper::Container & container, int64_t zxid) const
{
MultiResponse response;
response.zxid = zxid;
response.responses.reserve(requests.size());
std::vector<Undo> undo_actions;

View File

@ -39,8 +39,8 @@ public:
~TestKeeper() override;
bool isExpired() const override { return expired; }
bool hasReachedDeadline() const override { return false; }
int64_t getSessionID() const override { return 0; }
Poco::Net::SocketAddress getConnectedAddress() const override { return connected_zk_address; }
void create(
@ -135,8 +135,6 @@ private:
zkutil::ZooKeeperArgs args;
Poco::Net::SocketAddress connected_zk_address;
std::mutex push_request_mutex;
std::atomic<bool> expired{false};

View File

@ -112,31 +112,17 @@ void ZooKeeper::init(ZooKeeperArgs args_)
throw KeeperException("Cannot use any of provided ZooKeeper nodes", Coordination::Error::ZCONNECTIONLOSS);
}
impl = std::make_unique<Coordination::ZooKeeper>(nodes, args, zk_log);
impl = std::make_unique<Coordination::ZooKeeper>(nodes, args, zk_log, [this](size_t node_idx, const Coordination::ZooKeeper::Node & node)
{
connected_zk_host = node.address.host().toString();
connected_zk_port = node.address.port();
connected_zk_index = node_idx;
});
if (args.chroot.empty())
LOG_TRACE(log, "Initialized, hosts: {}", fmt::join(args.hosts, ","));
else
LOG_TRACE(log, "Initialized, hosts: {}, chroot: {}", fmt::join(args.hosts, ","), args.chroot);
Poco::Net::SocketAddress address = impl->getConnectedAddress();
connected_zk_host = address.host().toString();
connected_zk_port = address.port();
connected_zk_index = 0;
if (args.hosts.size() > 1)
{
for (size_t i = 0; i < args.hosts.size(); i++)
{
if (args.hosts[i] == address.toString())
{
connected_zk_index = i;
break;
}
}
}
}
else if (args.implementation == "testkeeper")
{

View File

@ -521,6 +521,7 @@ public:
void setZooKeeperLog(std::shared_ptr<DB::ZooKeeperLog> zk_log_);
UInt32 getSessionUptime() const { return static_cast<UInt32>(session_uptime.elapsedSeconds()); }
bool hasReachedDeadline() const { return impl->hasReachedDeadline(); }
void setServerCompletelyStarted();

View File

@ -204,6 +204,14 @@ void ZooKeeperArgs::initFromKeeperSection(const Poco::Util::AbstractConfiguratio
throw DB::Exception(DB::ErrorCodes::BAD_ARGUMENTS, "Unknown load balancing: {}", load_balancing_str);
get_priority_load_balancing.load_balancing = *load_balancing;
}
else if (key == "fallback_session_lifetime")
{
fallback_session_lifetime = SessionLifetimeConfiguration
{
.min_sec = config.getUInt(config_name + "." + key + ".min"),
.max_sec = config.getUInt(config_name + "." + key + ".max"),
};
}
else
throw KeeperException(std::string("Unknown key ") + key + " in config file", Coordination::Error::ZBADARGUMENTS);
}

View File

@ -11,8 +11,17 @@ namespace Poco::Util
namespace zkutil
{
constexpr UInt32 ZK_MIN_FALLBACK_SESSION_DEADLINE_SEC = 3 * 60 * 60;
constexpr UInt32 ZK_MAX_FALLBACK_SESSION_DEADLINE_SEC = 6 * 60 * 60;
struct ZooKeeperArgs
{
struct SessionLifetimeConfiguration
{
UInt32 min_sec = ZK_MIN_FALLBACK_SESSION_DEADLINE_SEC;
UInt32 max_sec = ZK_MAX_FALLBACK_SESSION_DEADLINE_SEC;
bool operator == (const SessionLifetimeConfiguration &) const = default;
};
ZooKeeperArgs(const Poco::Util::AbstractConfiguration & config, const String & config_name);
/// hosts_string -- comma separated [secure://]host:port list
@ -36,6 +45,7 @@ struct ZooKeeperArgs
UInt64 send_sleep_ms = 0;
UInt64 recv_sleep_ms = 0;
SessionLifetimeConfiguration fallback_session_lifetime = {};
DB::GetPriorityForLoadBalancing get_priority_load_balancing;
private:

View File

@ -642,6 +642,8 @@ void ZooKeeperMultiResponse::readImpl(ReadBuffer & in)
if (op_error == Error::ZOK || op_num == OpNum::Error)
dynamic_cast<ZooKeeperResponse &>(*response).readImpl(in);
response->zxid = zxid;
}
/// Footer.

View File

@ -28,7 +28,6 @@ using LogElements = std::vector<ZooKeeperLogElement>;
struct ZooKeeperResponse : virtual Response
{
XID xid = 0;
int64_t zxid = 0;
UInt64 response_created_time_ns = 0;

View File

@ -313,8 +313,8 @@ ZooKeeper::~ZooKeeper()
ZooKeeper::ZooKeeper(
const Nodes & nodes,
const zkutil::ZooKeeperArgs & args_,
std::shared_ptr<ZooKeeperLog> zk_log_)
: args(args_)
std::shared_ptr<ZooKeeperLog> zk_log_, std::optional<ConnectedCallback> && connected_callback_)
: args(args_), connected_callback(std::move(connected_callback_))
{
log = &Poco::Logger::get("ZooKeeperClient");
std::atomic_store(&zk_log, std::move(zk_log_));
@ -395,8 +395,9 @@ void ZooKeeper::connect(
WriteBufferFromOwnString fail_reasons;
for (size_t try_no = 0; try_no < num_tries; ++try_no)
{
for (const auto & node : nodes)
for (size_t i = 0; i < nodes.size(); ++i)
{
const auto & node = nodes[i];
try
{
/// Reset the state of previous attempt.
@ -443,9 +444,25 @@ void ZooKeeper::connect(
e.addMessage("while receiving handshake from ZooKeeper");
throw;
}
connected = true;
connected_zk_address = node.address;
if (connected_callback.has_value())
(*connected_callback)(i, node);
if (i != 0)
{
std::uniform_int_distribution<UInt32> fallback_session_lifetime_distribution
{
args.fallback_session_lifetime.min_sec,
args.fallback_session_lifetime.max_sec,
};
UInt32 session_lifetime_seconds = fallback_session_lifetime_distribution(thread_local_rng);
client_session_deadline = clock::now() + std::chrono::seconds(session_lifetime_seconds);
LOG_DEBUG(log, "Connected to a suboptimal ZooKeeper host ({}, index {})."
" To preserve balance in ZooKeeper usage, this ZooKeeper session will expire in {} seconds",
node.address.toString(), i, session_lifetime_seconds);
}
break;
}
@ -462,7 +479,6 @@ void ZooKeeper::connect(
if (!connected)
{
WriteBufferFromOwnString message;
connected_zk_address = Poco::Net::SocketAddress();
message << "All connection tries failed while connecting to ZooKeeper. nodes: ";
bool first = true;
@ -1060,6 +1076,7 @@ void ZooKeeper::pushRequest(RequestInfo && info)
{
try
{
checkSessionDeadline();
info.time = clock::now();
if (zk_log)
{
@ -1482,6 +1499,17 @@ void ZooKeeper::setupFaultDistributions()
inject_setup.test_and_set();
}
void ZooKeeper::checkSessionDeadline() const
{
if (unlikely(hasReachedDeadline()))
throw Exception(Error::ZSESSIONEXPIRED, "Session expired (force expiry client-side)");
}
bool ZooKeeper::hasReachedDeadline() const
{
return client_session_deadline.has_value() && clock::now() >= client_session_deadline.value();
}
void ZooKeeper::maybeInjectSendFault()
{
if (unlikely(inject_setup.test() && send_inject_fault && send_inject_fault.value()(thread_local_rng)))

View File

@ -107,6 +107,7 @@ public:
};
using Nodes = std::vector<Node>;
using ConnectedCallback = std::function<void(size_t, const Node&)>;
/** Connection to nodes is performed in order. If you want, shuffle them manually.
* Operation timeout couldn't be greater than session timeout.
@ -115,7 +116,8 @@ public:
ZooKeeper(
const Nodes & nodes,
const zkutil::ZooKeeperArgs & args_,
std::shared_ptr<ZooKeeperLog> zk_log_);
std::shared_ptr<ZooKeeperLog> zk_log_,
std::optional<ConnectedCallback> && connected_callback_ = {});
~ZooKeeper() override;
@ -123,11 +125,13 @@ public:
/// If expired, you can only destroy the object. All other methods will throw exception.
bool isExpired() const override { return requests_queue.isFinished(); }
/// A ZooKeeper session can have an optional deadline set on it.
/// After it has been reached, the session needs to be finalized.
bool hasReachedDeadline() const override;
/// Useful to check owner of ephemeral node.
int64_t getSessionID() const override { return session_id; }
Poco::Net::SocketAddress getConnectedAddress() const override { return connected_zk_address; }
void executeGenericRequest(
const ZooKeeperRequestPtr & request,
ResponseCallback callback);
@ -213,9 +217,9 @@ public:
private:
ACLs default_acls;
Poco::Net::SocketAddress connected_zk_address;
zkutil::ZooKeeperArgs args;
std::optional<ConnectedCallback> connected_callback = {};
/// Fault injection
void maybeInjectSendFault();
@ -252,6 +256,7 @@ private:
clock::time_point time;
};
std::optional<clock::time_point> client_session_deadline {};
using RequestsQueue = ConcurrentBoundedQueue<RequestInfo>;
RequestsQueue requests_queue{1024};
@ -324,6 +329,8 @@ private:
void initFeatureFlags();
void checkSessionDeadline() const;
CurrentMetrics::Increment active_session_metric_increment{CurrentMetrics::ZooKeeperSession};
std::shared_ptr<ZooKeeperLog> zk_log;

View File

@ -153,8 +153,11 @@ Pool::Entry Pool::get(uint64_t wait_timeout)
for (auto & connection : connections)
{
if (connection->ref_count == 0)
{
logger.test("Found free connection in pool, returning it to the caller");
return Entry(connection, this);
}
}
logger.trace("(%s): Trying to allocate a new connection.", getDescription());
if (connections.size() < static_cast<size_t>(max_connections))

View File

@ -320,8 +320,6 @@ bool KeeperDispatcher::putRequest(const Coordination::ZooKeeperRequestPtr & requ
request_info.time = duration_cast<milliseconds>(system_clock::now().time_since_epoch()).count();
request_info.session_id = session_id;
std::lock_guard lock(push_request_mutex);
if (shutdown_called)
return false;
@ -423,13 +421,10 @@ void KeeperDispatcher::shutdown()
try
{
{
std::lock_guard lock(push_request_mutex);
if (shutdown_called)
if (shutdown_called.exchange(true))
return;
LOG_DEBUG(log, "Shutting down storage dispatcher");
shutdown_called = true;
if (session_cleaner_thread.joinable())
session_cleaner_thread.join();
@ -582,12 +577,9 @@ void KeeperDispatcher::sessionCleanerTask()
.time = duration_cast<milliseconds>(system_clock::now().time_since_epoch()).count(),
.request = std::move(request),
};
{
std::lock_guard lock(push_request_mutex);
if (!requests_queue->push(std::move(request_info)))
LOG_INFO(log, "Cannot push close request to queue while cleaning outdated sessions");
CurrentMetrics::add(CurrentMetrics::KeeperOutstandingRequets);
}
/// Remove session from registered sessions
finishSession(dead_session);
@ -607,6 +599,10 @@ void KeeperDispatcher::sessionCleanerTask()
void KeeperDispatcher::finishSession(int64_t session_id)
{
/// shutdown() method will cleanup sessions if needed
if (shutdown_called)
return;
{
std::lock_guard lock(session_to_response_callback_mutex);
auto session_it = session_to_response_callback.find(session_id);
@ -698,12 +694,9 @@ int64_t KeeperDispatcher::getSessionID(int64_t session_timeout_ms)
}
/// Push new session request to queue
{
std::lock_guard lock(push_request_mutex);
if (!requests_queue->tryPush(std::move(request_info), session_timeout_ms))
throw Exception(ErrorCodes::TIMEOUT_EXCEEDED, "Cannot push session id request to queue within session timeout");
CurrentMetrics::add(CurrentMetrics::KeeperOutstandingRequets);
}
if (future.wait_for(std::chrono::milliseconds(session_timeout_ms)) != std::future_status::ready)
throw Exception(ErrorCodes::TIMEOUT_EXCEEDED, "Cannot receive session id within session timeout");
@ -871,10 +864,7 @@ uint64_t KeeperDispatcher::getSnapDirSize() const
Keeper4LWInfo KeeperDispatcher::getKeeper4LWInfo() const
{
Keeper4LWInfo result = server->getPartiallyFilled4LWInfo();
{
std::lock_guard lock(push_request_mutex);
result.outstanding_requests_count = requests_queue->size();
}
{
std::lock_guard lock(session_to_response_callback_mutex);
result.alive_connections_count = session_to_response_callback.size();

View File

@ -27,8 +27,6 @@ using ZooKeeperResponseCallback = std::function<void(const Coordination::ZooKeep
class KeeperDispatcher
{
private:
mutable std::mutex push_request_mutex;
using RequestsQueue = ConcurrentBoundedQueue<KeeperStorage::RequestForSession>;
using SessionToResponseCallback = std::unordered_map<int64_t, ZooKeeperResponseCallback>;
using ClusterUpdateQueue = ConcurrentBoundedQueue<ClusterUpdateAction>;

View File

@ -794,8 +794,14 @@ bool KeeperServer::applyConfigUpdate(const ClusterUpdateAction & action)
std::lock_guard _{server_write_mutex};
if (const auto * add = std::get_if<AddRaftServer>(&action))
return raft_instance->get_srv_config(add->id) != nullptr
|| raft_instance->add_srv(static_cast<nuraft::srv_config>(*add))->get_accepted();
{
if (raft_instance->get_srv_config(add->id) != nullptr)
return true;
auto resp = raft_instance->add_srv(static_cast<nuraft::srv_config>(*add));
resp->get();
return resp->get_accepted();
}
else if (const auto * remove = std::get_if<RemoveRaftServer>(&action))
{
if (remove->id == raft_instance->get_leader())
@ -807,8 +813,12 @@ bool KeeperServer::applyConfigUpdate(const ClusterUpdateAction & action)
return false;
}
return raft_instance->get_srv_config(remove->id) == nullptr
|| raft_instance->remove_srv(remove->id)->get_accepted();
if (raft_instance->get_srv_config(remove->id) == nullptr)
return true;
auto resp = raft_instance->remove_srv(remove->id);
resp->get();
return resp->get_accepted();
}
else if (const auto * update = std::get_if<UpdateRaftServerPriority>(&action))
{

View File

@ -83,8 +83,12 @@ namespace DB
M(UInt64, background_schedule_pool_size, 128, "The maximum number of threads that will be used for constantly executing some lightweight periodic operations.", 0) \
M(UInt64, background_message_broker_schedule_pool_size, 16, "The maximum number of threads that will be used for executing background operations for message streaming.", 0) \
M(UInt64, background_distributed_schedule_pool_size, 16, "The maximum number of threads that will be used for executing distributed sends.", 0) \
M(Bool, display_secrets_in_show_and_select, false, "Allow showing secrets in SHOW and SELECT queries via a format setting and a grant", 0)
M(Bool, display_secrets_in_show_and_select, false, "Allow showing secrets in SHOW and SELECT queries via a format setting and a grant", 0) \
\
M(UInt64, total_memory_profiler_step, 0, "Whenever server memory usage becomes larger than every next step in number of bytes the memory profiler will collect the allocating stack trace. Zero means disabled memory profiler. Values lower than a few megabytes will slow down server.", 0) \
M(Double, total_memory_tracker_sample_probability, 0, "Collect random allocations and deallocations and write them into system.trace_log with 'MemorySample' trace_type. The probability is for every alloc/free regardless to the size of the allocation (can be changed with `memory_profiler_sample_min_allocation_size` and `memory_profiler_sample_max_allocation_size`). Note that sampling happens only when the amount of untracked memory exceeds 'max_untracked_memory'. You may want to set 'max_untracked_memory' to 0 for extra fine grained sampling.", 0) \
M(UInt64, total_memory_profiler_sample_min_allocation_size, 0, "Collect random allocations of size greater or equal than specified value with probability equal to `total_memory_profiler_sample_probability`. 0 means disabled. You may want to set 'max_untracked_memory' to 0 to make this threshold to work as expected.", 0) \
M(UInt64, total_memory_profiler_sample_max_allocation_size, 0, "Collect random allocations of size less or equal than specified value with probability equal to `total_memory_profiler_sample_probability`. 0 means disabled. You may want to set 'max_untracked_memory' to 0 to make this threshold to work as expected.", 0)
DECLARE_SETTINGS_TRAITS(ServerSettingsTraits, SERVER_SETTINGS)

View File

@ -386,6 +386,8 @@ class IColumn;
M(UInt64, max_temporary_columns, 0, "If a query generates more than the specified number of temporary columns in memory as a result of intermediate calculation, exception is thrown. Zero value means unlimited. This setting is useful to prevent too complex queries.", 0) \
M(UInt64, max_temporary_non_const_columns, 0, "Similar to the 'max_temporary_columns' setting but applies only to non-constant columns. This makes sense, because constant columns are cheap and it is reasonable to allow more of them.", 0) \
\
M(UInt64, max_sessions_for_user, 0, "Maximum number of simultaneous sessions for a user.", 0) \
\
M(UInt64, max_subquery_depth, 100, "If a query has more than specified number of nested subqueries, throw an exception. This allows you to have a sanity check to protect the users of your cluster from going insane with their queries.", 0) \
M(UInt64, max_analyze_depth, 5000, "Maximum number of analyses performed by interpreter.", 0) \
M(UInt64, max_ast_depth, 1000, "Maximum depth of query syntax tree. Checked after parsing.", 0) \
@ -427,7 +429,9 @@ class IColumn;
M(UInt64, memory_overcommit_ratio_denominator_for_user, 1_GiB, "It represents soft memory limit on the global level. This value is used to compute query overcommit ratio.", 0) \
M(UInt64, max_untracked_memory, (4 * 1024 * 1024), "Small allocations and deallocations are grouped in thread local variable and tracked or profiled only when amount (in absolute value) becomes larger than specified value. If the value is higher than 'memory_profiler_step' it will be effectively lowered to 'memory_profiler_step'.", 0) \
M(UInt64, memory_profiler_step, (4 * 1024 * 1024), "Whenever query memory usage becomes larger than every next step in number of bytes the memory profiler will collect the allocating stack trace. Zero means disabled memory profiler. Values lower than a few megabytes will slow down query processing.", 0) \
M(Float, memory_profiler_sample_probability, 0., "Collect random allocations and deallocations and write them into system.trace_log with 'MemorySample' trace_type. The probability is for every alloc/free regardless to the size of the allocation. Note that sampling happens only when the amount of untracked memory exceeds 'max_untracked_memory'. You may want to set 'max_untracked_memory' to 0 for extra fine grained sampling.", 0) \
M(Float, memory_profiler_sample_probability, 0., "Collect random allocations and deallocations and write them into system.trace_log with 'MemorySample' trace_type. The probability is for every alloc/free regardless to the size of the allocation (can be changed with `memory_profiler_sample_min_allocation_size` and `memory_profiler_sample_max_allocation_size`). Note that sampling happens only when the amount of untracked memory exceeds 'max_untracked_memory'. You may want to set 'max_untracked_memory' to 0 for extra fine grained sampling.", 0) \
M(UInt64, memory_profiler_sample_min_allocation_size, 0, "Collect random allocations of size greater or equal than specified value with probability equal to `memory_profiler_sample_probability`. 0 means disabled. You may want to set 'max_untracked_memory' to 0 to make this threshold to work as expected.", 0) \
M(UInt64, memory_profiler_sample_max_allocation_size, 0, "Collect random allocations of size less or equal than specified value with probability equal to `memory_profiler_sample_probability`. 0 means disabled. You may want to set 'max_untracked_memory' to 0 to make this threshold to work as expected.", 0) \
M(Bool, trace_profile_events, false, "Send to system.trace_log profile event and value of increment on each increment with 'ProfileEvent' trace_type", 0) \
\
M(UInt64, memory_usage_overcommit_max_wait_microseconds, 5'000'000, "Maximum time thread will wait for memory to be freed in the case of memory overcommit. If timeout is reached and memory is not freed, exception is thrown.", 0) \
@ -622,7 +626,7 @@ class IColumn;
M(Bool, engine_file_allow_create_multiple_files, false, "Enables or disables creating a new file on each insert in file engine tables if format has suffix.", 0) \
M(Bool, engine_file_skip_empty_files, false, "Allows to skip empty files in file table engine", 0) \
M(Bool, engine_url_skip_empty_files, false, "Allows to skip empty files in url table engine", 0) \
M(Bool, disable_url_encoding, false, " Allows to disable decoding/encoding path in uri in URL table engine", 0) \
M(Bool, enable_url_encoding, true, " Allows to enable/disable decoding/encoding path in uri in URL table engine", 0) \
M(Bool, allow_experimental_database_replicated, false, "Allow to create databases with Replicated engine", 0) \
M(UInt64, database_replicated_initial_query_timeout_sec, 300, "How long initial DDL query should wait for Replicated database to precess previous DDL queue entries", 0) \
M(Bool, database_replicated_enforce_synchronous_settings, false, "Enforces synchronous waiting for some queries (see also database_atomic_wait_for_drop_and_detach_synchronously, mutation_sync, alter_sync). Not recommended to enable these settings.", 0) \
@ -1007,6 +1011,10 @@ class IColumn;
\
M(CapnProtoEnumComparingMode, format_capn_proto_enum_comparising_mode, FormatSettings::CapnProtoEnumComparingMode::BY_VALUES, "How to map ClickHouse Enum and CapnProto Enum", 0) \
\
M(Bool, format_capn_proto_use_autogenerated_schema, true, "Use autogenerated CapnProto schema when format_schema is not set", 0) \
M(Bool, format_protobuf_use_autogenerated_schema, true, "Use autogenerated Protobuf when format_schema is not set", 0) \
M(String, output_format_schema, "", "The path to the file where the automatically generated schema will be saved", 0) \
\
M(String, input_format_mysql_dump_table_name, "", "Name of the table in MySQL dump from which to read data", 0) \
M(Bool, input_format_mysql_dump_map_column_names, true, "Match columns from table in MySQL dump and columns from ClickHouse table by names", 0) \
\

View File

@ -37,6 +37,7 @@ public:
bool canBeInsideNullable() const override { return false; }
bool supportsSparseSerialization() const override { return true; }
bool canBeInsideSparseColumns() const override { return false; }
MutableColumnPtr createColumn() const override;
MutableColumnPtr createColumn(const ISerialization & serialization) const override;

View File

@ -110,6 +110,7 @@ public:
/// TODO: support more types.
virtual bool supportsSparseSerialization() const { return !haveSubtypes(); }
virtual bool canBeInsideSparseColumns() const { return supportsSparseSerialization(); }
SerializationPtr getDefaultSerialization() const;
SerializationPtr getSparseSerialization() const;

View File

@ -65,6 +65,7 @@ void DatabaseMaterializedMySQL::setException(const std::exception_ptr & exceptio
void DatabaseMaterializedMySQL::startupTables(ThreadPool & thread_pool, LoadingStrictnessLevel mode)
{
LOG_TRACE(log, "Starting MaterializeMySQL tables");
DatabaseAtomic::startupTables(thread_pool, mode);
if (mode < LoadingStrictnessLevel::FORCE_ATTACH)
@ -122,6 +123,7 @@ void DatabaseMaterializedMySQL::alterTable(ContextPtr context_, const StorageID
void DatabaseMaterializedMySQL::drop(ContextPtr context_)
{
LOG_TRACE(log, "Dropping MaterializeMySQL database");
/// Remove metadata info
fs::path metadata(getMetadataPath() + "/.metadata");

View File

@ -11,6 +11,7 @@
#include <Databases/DatabaseAtomic.h>
#include <Databases/MySQL/MaterializedMySQLSettings.h>
#include <Databases/MySQL/MaterializedMySQLSyncThread.h>
#include <Common/logger_useful.h>
namespace DB
{

View File

@ -1,3 +1,4 @@
#include "Common/logger_useful.h"
#include "config.h"
#if USE_MYSQL
@ -499,7 +500,10 @@ bool MaterializedMySQLSyncThread::prepareSynchronized(MaterializeMetadata & meta
{
throw;
}
catch (const mysqlxx::ConnectionFailed &) {}
catch (const mysqlxx::ConnectionFailed & ex)
{
LOG_TRACE(log, "Connection to MySQL failed {}", ex.displayText());
}
catch (const mysqlxx::BadQuery & e)
{
// Lost connection to MySQL server during query

View File

@ -17,13 +17,13 @@ namespace ErrorCodes
extern const int UNKNOWN_ELEMENT_IN_CONFIG;
}
void DictionaryFactory::registerLayout(const std::string & layout_type, LayoutCreateFunction create_layout, bool is_layout_complex)
void DictionaryFactory::registerLayout(const std::string & layout_type, LayoutCreateFunction create_layout, bool is_layout_complex, bool has_layout_complex)
{
auto it = registered_layouts.find(layout_type);
if (it != registered_layouts.end())
throw Exception(ErrorCodes::LOGICAL_ERROR, "DictionaryFactory: the layout name '{}' is not unique", layout_type);
RegisteredLayout layout { .layout_create_function = create_layout, .is_layout_complex = is_layout_complex };
RegisteredLayout layout { .layout_create_function = create_layout, .is_layout_complex = is_layout_complex, .has_layout_complex = has_layout_complex };
registered_layouts.emplace(layout_type, std::move(layout));
}
@ -89,6 +89,25 @@ bool DictionaryFactory::isComplex(const std::string & layout_type) const
return it->second.is_layout_complex;
}
bool DictionaryFactory::convertToComplex(std::string & layout_type) const
{
auto it = registered_layouts.find(layout_type);
if (it == registered_layouts.end())
{
throw Exception(ErrorCodes::UNKNOWN_ELEMENT_IN_CONFIG,
"Unknown dictionary layout type: {}",
layout_type);
}
if (!it->second.is_layout_complex && it->second.has_layout_complex)
{
layout_type = "complex_key_" + layout_type;
return true;
}
return false;
}
DictionaryFactory & DictionaryFactory::instance()
{

View File

@ -55,13 +55,18 @@ public:
bool isComplex(const std::string & layout_type) const;
void registerLayout(const std::string & layout_type, LayoutCreateFunction create_layout, bool is_layout_complex);
/// If the argument `layout_type` is not complex layout and has corresponding complex layout,
/// change `layout_type` to corresponding complex and return true; otherwise do nothing and return false.
bool convertToComplex(std::string & layout_type) const;
void registerLayout(const std::string & layout_type, LayoutCreateFunction create_layout, bool is_layout_complex, bool has_layout_complex = true);
private:
struct RegisteredLayout
{
LayoutCreateFunction layout_create_function;
bool is_layout_complex;
bool has_layout_complex;
};
using LayoutRegistry = std::unordered_map<std::string, RegisteredLayout>;

View File

@ -683,7 +683,7 @@ void registerDictionaryFlat(DictionaryFactory & factory)
return std::make_unique<FlatDictionary>(dict_id, dict_struct, std::move(source_ptr), configuration);
};
factory.registerLayout("flat", create_layout, false);
factory.registerLayout("flat", create_layout, false, false);
}

View File

@ -19,6 +19,7 @@
#include <Functions/FunctionFactory.h>
#include <Common/isLocalAddress.h>
#include <Interpreters/Context.h>
#include <DataTypes/DataTypeFactory.h>
namespace DB
@ -614,6 +615,16 @@ getDictionaryConfigurationFromAST(const ASTCreateQuery & query, ContextPtr conte
checkPrimaryKey(all_attr_names_and_types, pk_attrs);
/// If the pk size is 1 and pk's DataType is not number, we should convert to complex.
/// NOTE: the data type of Numeric key(simple layout) is UInt64, so if the type is not under UInt64, type casting will lead to precision loss.
DataTypePtr first_key_type = DataTypeFactory::instance().get(all_attr_names_and_types.find(pk_attrs[0])->second.type);
if ((pk_attrs.size() > 1 || (pk_attrs.size() == 1 && !isNumber(first_key_type)))
&& !complex
&& DictionaryFactory::instance().convertToComplex(dictionary_layout->layout_type))
{
complex = true;
}
buildPrimaryKeyConfiguration(xml_document, structure_element, complex, pk_attrs, query.dictionary_attributes_list);
buildLayoutConfiguration(xml_document, current_dictionary, query.dictionary->dict_settings, dictionary_layout);

View File

@ -14,7 +14,7 @@ namespace ErrorCodes
}
WriteBufferFromTemporaryFile::WriteBufferFromTemporaryFile(TemporaryFileOnDiskHolder && tmp_file_)
: WriteBufferFromFile(tmp_file_->getPath(), DBMS_DEFAULT_BUFFER_SIZE, O_RDWR | O_TRUNC | O_CREAT, /* throttler= */ {}, 0600)
: WriteBufferFromFile(tmp_file_->getAbsolutePath(), DBMS_DEFAULT_BUFFER_SIZE, O_RDWR | O_TRUNC | O_CREAT, /* throttler= */ {}, 0600)
, tmp_file(std::move(tmp_file_))
{
}

View File

@ -3,6 +3,7 @@
#include <IO/ReadBufferFromString.h>
#include <IO/ReadBufferFromFile.h>
#include <IO/ReadBufferFromEmptyFile.h>
#include <IO/ReadHelpers.h>
#include <IO/WriteBufferFromFile.h>
#include <IO/WriteHelpers.h>
@ -485,8 +486,15 @@ std::unique_ptr<ReadBufferFromFileBase> DiskObjectStorage::readFile(
std::optional<size_t> read_hint,
std::optional<size_t> file_size) const
{
auto storage_objects = metadata_storage->getStorageObjects(path);
const bool file_can_be_empty = !file_size.has_value() || *file_size == 0;
if (storage_objects.empty() && file_can_be_empty)
return std::make_unique<ReadBufferFromEmptyFile>();
return object_storage->readObjects(
metadata_storage->getStorageObjects(path),
storage_objects,
object_storage->getAdjustedSettingsFromMetadataFile(settings, path),
read_hint,
file_size);

View File

@ -135,7 +135,7 @@ private:
return result;
}
throw Exception(ErrorCodes::S3_ERROR, "Could not list objects in bucket {} with prefix {}, S3 exception: {}, message: {}",
throw S3Exception(outcome.GetError().GetErrorType(), "Could not list objects in bucket {} with prefix {}, S3 exception: {}, message: {}",
quoteString(request.GetBucket()), quoteString(request.GetPrefix()),
backQuote(outcome.GetError().GetExceptionName()), quoteString(outcome.GetError().GetMessage()));
}

View File

@ -54,7 +54,7 @@ TemporaryFileOnDisk::TemporaryFileOnDisk(const DiskPtr & disk_, const String & p
throw Exception(ErrorCodes::LOGICAL_ERROR, "Temporary file name is empty");
}
String TemporaryFileOnDisk::getPath() const
String TemporaryFileOnDisk::getAbsolutePath() const
{
return std::filesystem::path(disk->getPath()) / relative_path;
}

View File

@ -22,7 +22,10 @@ public:
~TemporaryFileOnDisk();
DiskPtr getDisk() const { return disk; }
String getPath() const;
/// Return absolute path (disk + relative_path)
String getAbsolutePath() const;
/// Return relative path (without disk)
const String & getRelativePath() const { return relative_path; }
private:
DiskPtr disk;

View File

@ -31,7 +31,7 @@ namespace ErrorCodes
message.empty() ? "" : ": " + message);
}
Poco::AutoPtr<Poco::XML::Document> getDiskConfigurationFromASTImpl(const std::string & root_name, const ASTs & disk_args, ContextPtr context)
Poco::AutoPtr<Poco::XML::Document> getDiskConfigurationFromASTImpl(const ASTs & disk_args, ContextPtr context)
{
if (disk_args.empty())
throwBadConfiguration("expected non-empty list of arguments");
@ -39,8 +39,6 @@ Poco::AutoPtr<Poco::XML::Document> getDiskConfigurationFromASTImpl(const std::st
Poco::AutoPtr<Poco::XML::Document> xml_document(new Poco::XML::Document());
Poco::AutoPtr<Poco::XML::Element> root(xml_document->createElement("disk"));
xml_document->appendChild(root);
Poco::AutoPtr<Poco::XML::Element> disk_configuration(xml_document->createElement(root_name));
root->appendChild(disk_configuration);
for (const auto & arg : disk_args)
{
@ -62,7 +60,7 @@ Poco::AutoPtr<Poco::XML::Document> getDiskConfigurationFromASTImpl(const std::st
const std::string & key = key_identifier->name();
Poco::AutoPtr<Poco::XML::Element> key_element(xml_document->createElement(key));
disk_configuration->appendChild(key_element);
root->appendChild(key_element);
if (!function_args[1]->as<ASTLiteral>() && !function_args[1]->as<ASTIdentifier>())
throwBadConfiguration("expected values to be literals or identifiers");
@ -75,9 +73,9 @@ Poco::AutoPtr<Poco::XML::Document> getDiskConfigurationFromASTImpl(const std::st
return xml_document;
}
DiskConfigurationPtr getDiskConfigurationFromAST(const std::string & root_name, const ASTs & disk_args, ContextPtr context)
DiskConfigurationPtr getDiskConfigurationFromAST(const ASTs & disk_args, ContextPtr context)
{
auto xml_document = getDiskConfigurationFromASTImpl(root_name, disk_args, context);
auto xml_document = getDiskConfigurationFromASTImpl(disk_args, context);
Poco::AutoPtr<Poco::Util::XMLConfiguration> conf(new Poco::Util::XMLConfiguration());
conf->load(xml_document);
return conf;

View File

@ -14,19 +14,19 @@ using DiskConfigurationPtr = Poco::AutoPtr<Poco::Util::AbstractConfiguration>;
/**
* Transform a list of pairs ( key1=value1, key2=value2, ... ), where keys and values are ASTLiteral or ASTIdentifier
* into
* <root_name>
* <disk>
* <key1>value1</key1>
* <key2>value2</key2>
* ...
* </root_name>
* </disk>
*
* Used in case disk configuration is passed via AST when creating
* a disk object on-the-fly without any configuration file.
*/
DiskConfigurationPtr getDiskConfigurationFromAST(const std::string & root_name, const ASTs & disk_args, ContextPtr context);
DiskConfigurationPtr getDiskConfigurationFromAST(const ASTs & disk_args, ContextPtr context);
/// The same as above function, but return XML::Document for easier modification of result configuration.
[[ maybe_unused ]] Poco::AutoPtr<Poco::XML::Document> getDiskConfigurationFromASTImpl(const std::string & root_name, const ASTs & disk_args, ContextPtr context);
[[ maybe_unused ]] Poco::AutoPtr<Poco::XML::Document> getDiskConfigurationFromASTImpl(const ASTs & disk_args, ContextPtr context);
/*
* A reverse function.

View File

@ -26,8 +26,16 @@ namespace
{
std::string getOrCreateDiskFromDiskAST(const ASTFunction & function, ContextPtr context)
{
const auto * function_args_expr = assert_cast<const ASTExpressionList *>(function.arguments.get());
const auto & function_args = function_args_expr->children;
auto config = getDiskConfigurationFromAST(function_args, context);
std::string disk_name;
if (function.name == "disk")
if (config->has("name"))
{
disk_name = config->getString("name");
}
else
{
/// We need a unique name for a created custom disk, but it needs to be the same
/// after table is reattached or server is restarted, so take a hash of the disk
@ -36,21 +44,9 @@ namespace
disk_name = DiskSelector::TMP_INTERNAL_DISK_PREFIX
+ toString(sipHash128(disk_setting_string.data(), disk_setting_string.size()));
}
else
{
static constexpr std::string_view custom_disk_prefix = "disk_";
if (function.name.size() <= custom_disk_prefix.size() || !function.name.starts_with(custom_disk_prefix))
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Invalid disk name: {}", function.name);
disk_name = function.name.substr(custom_disk_prefix.size());
}
auto result_disk = context->getOrCreateDisk(disk_name, [&](const DisksMap & disks_map) -> DiskPtr {
const auto * function_args_expr = assert_cast<const ASTExpressionList *>(function.arguments.get());
const auto & function_args = function_args_expr->children;
auto config = getDiskConfigurationFromAST(disk_name, function_args, context);
auto disk = DiskFactory::instance().create(disk_name, *config, disk_name, context, disks_map);
auto disk = DiskFactory::instance().create(disk_name, *config, "", context, disks_map);
/// Mark that disk can be used without storage policy.
disk->markDiskAsCustom();
return disk;

View File

@ -143,12 +143,14 @@ FormatSettings getFormatSettings(ContextPtr context, const Settings & settings)
format_settings.protobuf.input_flatten_google_wrappers = settings.input_format_protobuf_flatten_google_wrappers;
format_settings.protobuf.output_nullables_with_google_wrappers = settings.output_format_protobuf_nullables_with_google_wrappers;
format_settings.protobuf.skip_fields_with_unsupported_types_in_schema_inference = settings.input_format_protobuf_skip_fields_with_unsupported_types_in_schema_inference;
format_settings.protobuf.use_autogenerated_schema = settings.format_protobuf_use_autogenerated_schema;
format_settings.regexp.escaping_rule = settings.format_regexp_escaping_rule;
format_settings.regexp.regexp = settings.format_regexp;
format_settings.regexp.skip_unmatched = settings.format_regexp_skip_unmatched;
format_settings.schema.format_schema = settings.format_schema;
format_settings.schema.format_schema_path = context->getFormatSchemaPath();
format_settings.schema.is_server = context->hasGlobalContext() && (context->getGlobalContext()->getApplicationType() == Context::ApplicationType::SERVER);
format_settings.schema.output_format_schema = settings.output_format_schema;
format_settings.skip_unknown_fields = settings.input_format_skip_unknown_fields;
format_settings.template_settings.resultset_format = settings.format_template_resultset;
format_settings.template_settings.row_between_delimiter = settings.format_template_rows_between_delimiter;
@ -190,6 +192,7 @@ FormatSettings getFormatSettings(ContextPtr context, const Settings & settings)
format_settings.defaults_for_omitted_fields = settings.input_format_defaults_for_omitted_fields;
format_settings.capn_proto.enum_comparing_mode = settings.format_capn_proto_enum_comparising_mode;
format_settings.capn_proto.skip_fields_with_unsupported_types_in_schema_inference = settings.input_format_capn_proto_skip_fields_with_unsupported_types_in_schema_inference;
format_settings.capn_proto.use_autogenerated_schema = settings.format_capn_proto_use_autogenerated_schema;
format_settings.seekable_read = settings.input_format_allow_seeks;
format_settings.msgpack.number_of_columns = settings.input_format_msgpack_number_of_columns;
format_settings.msgpack.output_uuid_representation = settings.output_format_msgpack_uuid_representation;

View File

@ -1,6 +1,8 @@
#include <Formats/FormatSchemaInfo.h>
#include <Interpreters/Context.h>
#include <Common/Exception.h>
#include <Common/filesystemHelpers.h>
#include <Disks/IO/WriteBufferFromTemporaryFile.h>
#include <filesystem>
@ -105,4 +107,84 @@ FormatSchemaInfo::FormatSchemaInfo(const FormatSettings & settings, const String
{
}
template <typename SchemaGenerator>
MaybeAutogeneratedFormatSchemaInfo<SchemaGenerator>::MaybeAutogeneratedFormatSchemaInfo(
const FormatSettings & settings, const String & format, const Block & header, bool use_autogenerated_schema)
{
if (!use_autogenerated_schema || !settings.schema.format_schema.empty())
{
schema_info = std::make_unique<FormatSchemaInfo>(settings, format, true);
return;
}
String schema_path;
fs::path default_schema_directory_path(fs::canonical(settings.schema.format_schema_path) / "");
fs::path path;
if (!settings.schema.output_format_schema.empty())
{
schema_path = settings.schema.output_format_schema;
path = schema_path;
if (path.is_absolute())
{
if (settings.schema.is_server)
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Absolute path in the 'output_format_schema' setting is prohibited: {}", path.string());
}
else if (path.has_parent_path() && !fs::weakly_canonical(default_schema_directory_path / path).string().starts_with(fs::weakly_canonical(default_schema_directory_path).string()))
{
if (settings.schema.is_server)
throw Exception(
ErrorCodes::BAD_ARGUMENTS,
"Path in the 'format_schema' setting shouldn't go outside the 'format_schema_path' directory: {} ({} not in {})",
default_schema_directory_path.string(),
path.string(),
default_schema_directory_path.string());
path = default_schema_directory_path / path;
}
else
{
path = default_schema_directory_path / path;
}
}
else
{
if (settings.schema.is_server)
{
tmp_file_path = PocoTemporaryFile::tempName(default_schema_directory_path.string()) + '.' + getFormatSchemaDefaultFileExtension(format);
schema_path = fs::path(tmp_file_path).filename();
}
else
{
tmp_file_path = PocoTemporaryFile::tempName() + '.' + getFormatSchemaDefaultFileExtension(format);
schema_path = tmp_file_path;
}
path = tmp_file_path;
}
WriteBufferFromFile buf(path.string());
SchemaGenerator::writeSchema(buf, "Message", header.getNamesAndTypesList());
buf.finalize();
schema_info = std::make_unique<FormatSchemaInfo>(schema_path + ":Message", format, true, settings.schema.is_server, settings.schema.format_schema_path);
}
template <typename SchemaGenerator>
MaybeAutogeneratedFormatSchemaInfo<SchemaGenerator>::~MaybeAutogeneratedFormatSchemaInfo()
{
if (!tmp_file_path.empty())
{
try
{
fs::remove(tmp_file_path);
}
catch (...)
{
tryLogCurrentException("MaybeAutogeneratedFormatSchemaInfo", "Cannot delete temporary schema file");
}
}
}
template class MaybeAutogeneratedFormatSchemaInfo<StructureToCapnProtoSchema>;
template class MaybeAutogeneratedFormatSchemaInfo<StructureToProtobufSchema>;
}

Some files were not shown because too many files have changed in this diff Show More