mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-22 23:52:03 +00:00
Merge branch 'master' into vdimir/fix_function_printf_style
This commit is contained in:
vdimir
GitHub
commit
cfc931160d
1
.github/workflows/release_branches.yml
vendored
1
.github/workflows/release_branches.yml
vendored
@ -130,6 +130,7 @@ jobs:
|
||||
with:
|
||||
build_name: package_debug
|
||||
data: ${{ needs.RunConfig.outputs.data }}
|
||||
force: true
|
||||
BuilderBinDarwin:
|
||||
needs: [RunConfig, BuildDockers]
|
||||
if: ${{ !failure() && !cancelled() }}
|
||||
|
||||
@ -30,7 +30,6 @@
|
||||
* Support more variants of JOIN strictness (`LEFT/RIGHT SEMI/ANTI/ANY JOIN`) with inequality conditions which involve columns from both left and right table. e.g. `t1.y < t2.y` (see the setting `allow_experimental_join_condition`). [#64281](https://github.com/ClickHouse/ClickHouse/pull/64281) ([lgbo](https://github.com/lgbo-ustc)).
|
||||
* Intrpret Hive-style partitioning for different engines (`File`, `URL`, `S3`, `AzureBlobStorage`, `HDFS`). Hive-style partitioning organizes data into partitioned sub-directories, making it efficient to query and manage large datasets. Currently, it only creates virtual columns with the appropriate name and data. The follow-up PR will introduce the appropriate data filtering (performance speedup). [#65997](https://github.com/ClickHouse/ClickHouse/pull/65997) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
|
||||
* Add function `printf` for Spark compatiability (but you can use the existing `format` function). [#66257](https://github.com/ClickHouse/ClickHouse/pull/66257) ([李扬](https://github.com/taiyang-li)).
|
||||
* Added a new server setting, `disable_insertion_and_mutation`. If it is enabled, the server will deny all insertions and mutations. This includes asynchronous INSERTs. This setting can be used to create read-only replicas. [#66519](https://github.com/ClickHouse/ClickHouse/pull/66519) ([Xu Jia](https://github.com/XuJia0210)).
|
||||
* Add options `restore_replace_external_engines_to_null` and `restore_replace_external_table_functions_to_null` to replace external engines and table_engines to `Null` engine that can be useful for testing. It should work for RESTORE and explicit table creation. [#66536](https://github.com/ClickHouse/ClickHouse/pull/66536) ([Ilya Yatsishin](https://github.com/qoega)).
|
||||
* Added support for reading `MULTILINESTRING` geometry in `WKT` format using function `readWKTLineString`. [#67647](https://github.com/ClickHouse/ClickHouse/pull/67647) ([Jacob Reckhard](https://github.com/jacobrec)).
|
||||
* Add a new table function `fuzzQuery`. This function allows the modification of a given query string with random variations. Example: `SELECT query FROM fuzzQuery('SELECT 1') LIMIT 5;`. [#67655](https://github.com/ClickHouse/ClickHouse/pull/67655) ([pufit](https://github.com/pufit)).
|
||||
|
||||
26
README.md
26
README.md
@ -34,7 +34,7 @@ curl https://clickhouse.com/ | sh
|
||||
|
||||
Every month we get together with the community (users, contributors, customers, those interested in learning more about ClickHouse) to discuss what is coming in the latest release. If you are interested in sharing what you've built on ClickHouse, let us know.
|
||||
|
||||
* [v24.8 Community Call](https://clickhouse.com/company/events/v24-8-community-release-call) - August 20
|
||||
* [v24.9 Community Call](https://clickhouse.com/company/events/v24-9-community-release-call) - September 26
|
||||
|
||||
## Upcoming Events
|
||||
|
||||
@ -44,13 +44,31 @@ The following upcoming meetups are featuring creator of ClickHouse & CTO, Alexey
|
||||
|
||||
* [ClickHouse Guangzhou User Group Meetup](https://mp.weixin.qq.com/s/GSvo-7xUoVzCsuUvlLTpCw) - August 25
|
||||
* [San Francisco Meetup (Cloudflare)](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/302540575) - September 5
|
||||
* [Raleigh Meetup (Deutsche Bank)](https://www.meetup.com/clickhouse-nc-meetup-group/events/302557230) - September 9
|
||||
* [New York Meetup (Ramp)](https://www.meetup.com/clickhouse-new-york-user-group/events/302575342) - September 10
|
||||
* [Raleigh Meetup (Deutsche Bank)](https://www.meetup.com/triangletechtalks/events/302723486/) - September 9
|
||||
* [New York Meetup (Rokt)](https://www.meetup.com/clickhouse-new-york-user-group/events/302575342) - September 10
|
||||
* [Chicago Meetup (Jump Capital)](https://lu.ma/43tvmrfw) - September 12
|
||||
|
||||
Other upcoming meetups
|
||||
* [Seattle Meetup (Statsig)](https://www.meetup.com/clickhouse-seattle-user-group/events/302518075/) - August 27
|
||||
* [Melbourne Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302732666/) - August 27
|
||||
* [Sydney Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/302862966/) - September 5
|
||||
* [Zurich Meetup](https://www.meetup.com/clickhouse-switzerland-meetup-group/events/302267429/) - September 5
|
||||
* [Toronto Meetup (Shopify)](https://www.meetup.com/clickhouse-toronto-user-group/events/301490855/) - September 10
|
||||
* [Austin Meetup](https://www.meetup.com/clickhouse-austin-user-group/events/302558689/) - September 17
|
||||
* [London Meetup](https://www.meetup.com/clickhouse-london-user-group/events/302977267) - September 17
|
||||
* [Tel Aviv Meetup](https://www.meetup.com/clickhouse-meetup-israel/events/303095121) - September 22
|
||||
* [Madrid Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096564/) - October 22
|
||||
* [Barcelona Meetup](https://www.meetup.com/clickhouse-spain-user-group/events/303096876/) - October 29
|
||||
* [Oslo Meetup](https://www.meetup.com/open-source-real-time-data-warehouse-real-time-analytics/events/302938622) - October 31
|
||||
* [Ghent Meetup](https://www.meetup.com/clickhouse-belgium-user-group/events/303049405/) - November 19
|
||||
* [Dubai Meetup](https://www.meetup.com/clickhouse-dubai-meetup-group/events/303096989/) - November 21
|
||||
* [Paris Meetup](https://www.meetup.com/clickhouse-france-user-group/events/303096434) - November 26
|
||||
|
||||
|
||||
|
||||
## Recent Recordings
|
||||
* **Recent Meetup Videos**: [Meetup Playlist](https://www.youtube.com/playlist?list=PL0Z2YDlm0b3iNDUzpY1S3L_iV4nARda_U) Whenever possible recordings of the ClickHouse Community Meetups are edited and presented as individual talks. Current featuring "Modern SQL in 2023", "Fast, Concurrent, and Consistent Asynchronous INSERTS in ClickHouse", and "Full-Text Indices: Design and Experiments"
|
||||
* **Recording available**: [**v24.4 Release Call**](https://www.youtube.com/watch?v=dtUqgcfOGmE) All the features of 24.4, one convenient video! Watch it now!
|
||||
* **Recording available**: [**v24.8 LTS Release Call**](https://www.youtube.com/watch?v=AeLmp2jc51k) All the features of 24.8 LTS, one convenient video! Watch it now!
|
||||
|
||||
## Interested in joining ClickHouse and making it your full-time job?
|
||||
|
||||
|
||||
@ -18,7 +18,9 @@
|
||||
#define Net_HTTPResponse_INCLUDED
|
||||
|
||||
|
||||
#include <map>
|
||||
#include <vector>
|
||||
|
||||
#include "Poco/Net/HTTPCookie.h"
|
||||
#include "Poco/Net/HTTPMessage.h"
|
||||
#include "Poco/Net/Net.h"
|
||||
@ -180,6 +182,8 @@ namespace Net
|
||||
/// May throw an exception in case of a malformed
|
||||
/// Set-Cookie header.
|
||||
|
||||
void getHeaders(std::map<std::string, std::string> & headers) const;
|
||||
|
||||
void write(std::ostream & ostr) const;
|
||||
/// Writes the HTTP response to the given
|
||||
/// output stream.
|
||||
|
||||
@ -209,6 +209,15 @@ void HTTPResponse::getCookies(std::vector<HTTPCookie>& cookies) const
|
||||
}
|
||||
}
|
||||
|
||||
void HTTPResponse::getHeaders(std::map<std::string, std::string> & headers) const
|
||||
{
|
||||
headers.clear();
|
||||
for (const auto & it : *this)
|
||||
{
|
||||
headers.emplace(it.first, it.second);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
void HTTPResponse::write(std::ostream& ostr) const
|
||||
{
|
||||
|
||||
@ -311,6 +311,14 @@ int SecureSocketImpl::sendBytes(const void* buffer, int length, int flags)
|
||||
while (mustRetry(rc, remaining_time));
|
||||
if (rc <= 0)
|
||||
{
|
||||
// At this stage we still can have last not yet received SSL message containing SSL error
|
||||
// so make a read to force SSL to process possible SSL error
|
||||
if (SSL_get_error(_pSSL, rc) == SSL_ERROR_SYSCALL && SocketImpl::lastError() == POCO_ECONNRESET)
|
||||
{
|
||||
char c = 0;
|
||||
SSL_read(_pSSL, &c, 1);
|
||||
}
|
||||
|
||||
rc = handleError(rc);
|
||||
if (rc == 0) throw SSLConnectionUnexpectedlyClosedException();
|
||||
}
|
||||
|
||||
@ -8,4 +8,7 @@ set (CMAKE_CXX_COMPILER_TARGET "x86_64-pc-freebsd11")
|
||||
set (CMAKE_ASM_COMPILER_TARGET "x86_64-pc-freebsd11")
|
||||
set (CMAKE_SYSROOT "${CMAKE_CURRENT_LIST_DIR}/../../contrib/sysroot/freebsd-x86_64")
|
||||
|
||||
# dprintf is used in a patched version of replxx
|
||||
add_compile_definitions(_WITH_DPRINTF)
|
||||
|
||||
set (CMAKE_TRY_COMPILE_TARGET_TYPE STATIC_LIBRARY) # disable linkage check - it doesn't work in CMake
|
||||
|
||||
2
contrib/libfiu
vendored
2
contrib/libfiu
vendored
@ -1 +1 @@
|
||||
Subproject commit b85edbde4cf974b1b40d27828a56f0505f4e2ee5
|
||||
Subproject commit a1290d8cd3d7b4541d6c976e0a54f572ac03f2a3
|
||||
2
contrib/replxx
vendored
2
contrib/replxx
vendored
@ -1 +1 @@
|
||||
Subproject commit 5d04501f93a4fb7f0bb8b73b8f614bc986f9e25b
|
||||
Subproject commit 711c18e7f4d951255aa8b0851e5a55d5a5fb0ddb
|
||||
2
contrib/usearch
vendored
2
contrib/usearch
vendored
@ -1 +1 @@
|
||||
Subproject commit e21a5778a0d4469ddaf38c94b7be0196bb701ee4
|
||||
Subproject commit 7a8967cb442b08ca20c3dd781414378e65957d37
|
||||
@ -34,7 +34,7 @@ RUN arch=${TARGETARCH:-amd64} \
|
||||
# lts / testing / prestable / etc
|
||||
ARG REPO_CHANNEL="stable"
|
||||
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
|
||||
ARG VERSION="24.8.1.2684"
|
||||
ARG VERSION="24.8.2.3"
|
||||
ARG PACKAGES="clickhouse-keeper"
|
||||
ARG DIRECT_DOWNLOAD_URLS=""
|
||||
|
||||
|
||||
@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
|
||||
# lts / testing / prestable / etc
|
||||
ARG REPO_CHANNEL="stable"
|
||||
ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
|
||||
ARG VERSION="24.8.1.2684"
|
||||
ARG VERSION="24.8.2.3"
|
||||
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
|
||||
ARG DIRECT_DOWNLOAD_URLS=""
|
||||
|
||||
|
||||
@ -28,7 +28,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list
|
||||
|
||||
ARG REPO_CHANNEL="stable"
|
||||
ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
|
||||
ARG VERSION="24.8.1.2684"
|
||||
ARG VERSION="24.8.2.3"
|
||||
ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"
|
||||
|
||||
#docker-official-library:off
|
||||
|
||||
@ -112,3 +112,5 @@ wadllib==1.3.6
|
||||
websocket-client==0.59.0
|
||||
wheel==0.37.1
|
||||
zipp==1.0.0
|
||||
deltalake==0.16.0
|
||||
|
||||
|
||||
@ -13,7 +13,8 @@ entry="/usr/share/clickhouse-test/performance/scripts/entrypoint.sh"
|
||||
# https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt
|
||||
# Double-escaped backslashes are a tribute to the engineering wonder of docker --
|
||||
# it gives '/bin/sh: 1: [bash,: not found' otherwise.
|
||||
numactl --hardware
|
||||
echo > compare.log
|
||||
numactl --hardware | tee -a compare.log
|
||||
node=$(( RANDOM % $(numactl --hardware | sed -n 's/^.*available:\(.*\)nodes.*$/\1/p') ));
|
||||
echo Will bind to NUMA node $node;
|
||||
echo Will bind to NUMA node $node | tee -a compare.log
|
||||
numactl --cpunodebind=$node --membind=$node $entry
|
||||
|
||||
@ -40,6 +40,3 @@ RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
|
||||
ARG sqllogic_test_repo="https://github.com/gregrahn/sqllogictest.git"
|
||||
|
||||
RUN git clone --recursive ${sqllogic_test_repo}
|
||||
|
||||
COPY run.sh /
|
||||
CMD ["/bin/bash", "/run.sh"]
|
||||
|
||||
71
docs/changelogs/v24.5.5.41-stable.md
Normal file
71
docs/changelogs/v24.5.5.41-stable.md
Normal file
@ -0,0 +1,71 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.5.5.41-stable (441d4a6ebe3) FIXME as compared to v24.5.4.49-stable (63b760955a0)
|
||||
|
||||
#### Improvement
|
||||
* Backported in [#66768](https://github.com/ClickHouse/ClickHouse/issues/66768): Make allow_experimental_analyzer be controlled by the initiator for distributed queries. This ensures compatibility and correctness during operations in mixed version clusters. [#65777](https://github.com/ClickHouse/ClickHouse/pull/65777) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#65350](https://github.com/ClickHouse/ClickHouse/issues/65350): Fix possible abort on uncaught exception in ~WriteBufferFromFileDescriptor in StatusFile. [#64206](https://github.com/ClickHouse/ClickHouse/pull/64206) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#65621](https://github.com/ClickHouse/ClickHouse/issues/65621): Fix `Cannot find column` in distributed query with `ARRAY JOIN` by `Nested` column. Fixes [#64755](https://github.com/ClickHouse/ClickHouse/issues/64755). [#64801](https://github.com/ClickHouse/ClickHouse/pull/64801) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#67902](https://github.com/ClickHouse/ClickHouse/issues/67902): Fixing the `Not-ready Set` error after the `PREWHERE` optimization for StorageMerge. [#65057](https://github.com/ClickHouse/ClickHouse/pull/65057) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66884](https://github.com/ClickHouse/ClickHouse/issues/66884): Fix unexpeced size of low cardinality column in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#65933](https://github.com/ClickHouse/ClickHouse/issues/65933): For queries that read from `PostgreSQL`, cancel the internal `PostgreSQL` query if the ClickHouse query is finished. Otherwise, `ClickHouse` query cannot be canceled until the internal `PostgreSQL` query is finished. [#65771](https://github.com/ClickHouse/ClickHouse/pull/65771) ([Maksim Kita](https://github.com/kitaisreal)).
|
||||
* Backported in [#66301](https://github.com/ClickHouse/ClickHouse/issues/66301): Better handling of join conditions involving `IS NULL` checks (for example `ON (a = b AND (a IS NOT NULL) AND (b IS NOT NULL) ) OR ( (a IS NULL) AND (b IS NULL) )` is rewritten to `ON a <=> b`), fix incorrect optimization when condition other then `IS NULL` are present. [#65835](https://github.com/ClickHouse/ClickHouse/pull/65835) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#66328](https://github.com/ClickHouse/ClickHouse/issues/66328): Add missing settings `input_format_csv_skip_first_lines/input_format_tsv_skip_first_lines/input_format_csv_try_infer_numbers_from_strings/input_format_csv_try_infer_strings_from_quoted_tuples` in schema inference cache because they can change the resulting schema. It prevents from incorrect result of schema inference with these settings changed. [#65980](https://github.com/ClickHouse/ClickHouse/pull/65980) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68252](https://github.com/ClickHouse/ClickHouse/issues/68252): Fixed `Not-ready Set` in some system tables when filtering using subqueries. [#66018](https://github.com/ClickHouse/ClickHouse/pull/66018) ([Michael Kolupaev](https://github.com/al13n321)).
|
||||
* Backported in [#66155](https://github.com/ClickHouse/ClickHouse/issues/66155): Fixed buffer overflow bug in `unbin`/`unhex` implementation. [#66106](https://github.com/ClickHouse/ClickHouse/pull/66106) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
* Backported in [#66454](https://github.com/ClickHouse/ClickHouse/issues/66454): Fixed a bug in ZooKeeper client: a session could get stuck in unusable state after receiving a hardware error from ZooKeeper. For example, this might happen due to "soft memory limit" in ClickHouse Keeper. [#66140](https://github.com/ClickHouse/ClickHouse/pull/66140) ([Alexander Tokmakov](https://github.com/tavplubix)).
|
||||
* Backported in [#66226](https://github.com/ClickHouse/ClickHouse/issues/66226): Fix issue in SumIfToCountIfVisitor and signed integers. [#66146](https://github.com/ClickHouse/ClickHouse/pull/66146) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#66680](https://github.com/ClickHouse/ClickHouse/issues/66680): Fix handling limit for `system.numbers_mt` when no index can be used. [#66231](https://github.com/ClickHouse/ClickHouse/pull/66231) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#66604](https://github.com/ClickHouse/ClickHouse/issues/66604): Fixed how the ClickHouse server detects the maximum number of usable CPU cores as specified by cgroups v2 if the server runs in a container such as Docker. In more detail, containers often run their process in the root cgroup which has an empty name. In that case, ClickHouse ignored the CPU limits set by cgroups v2. [#66237](https://github.com/ClickHouse/ClickHouse/pull/66237) ([filimonov](https://github.com/filimonov)).
|
||||
* Backported in [#66360](https://github.com/ClickHouse/ClickHouse/issues/66360): Fix the `Not-ready set` error when a subquery with `IN` is used in the constraint. [#66261](https://github.com/ClickHouse/ClickHouse/pull/66261) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#68064](https://github.com/ClickHouse/ClickHouse/issues/68064): Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#68158](https://github.com/ClickHouse/ClickHouse/issues/68158): Fix cluster() for inter-server secret (preserve initial user as before). [#66364](https://github.com/ClickHouse/ClickHouse/pull/66364) ([Azat Khuzhin](https://github.com/azat)).
|
||||
* Backported in [#66972](https://github.com/ClickHouse/ClickHouse/issues/66972): Fix `Column identifier is already registered` error with `group_by_use_nulls=true` and new analyzer. [#66400](https://github.com/ClickHouse/ClickHouse/pull/66400) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66691](https://github.com/ClickHouse/ClickHouse/issues/66691): Fix the VALID UNTIL clause in the user definition resetting after a restart. Closes [#66405](https://github.com/ClickHouse/ClickHouse/issues/66405). [#66409](https://github.com/ClickHouse/ClickHouse/pull/66409) ([Nikolay Degterinsky](https://github.com/evillique)).
|
||||
* Backported in [#66969](https://github.com/ClickHouse/ClickHouse/issues/66969): Fix `Cannot find column` error for queries with constant expression in `GROUP BY` key and new analyzer enabled. [#66433](https://github.com/ClickHouse/ClickHouse/pull/66433) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66720](https://github.com/ClickHouse/ClickHouse/issues/66720): Correctly track memory for `Allocator::realloc`. [#66548](https://github.com/ClickHouse/ClickHouse/pull/66548) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#66951](https://github.com/ClickHouse/ClickHouse/issues/66951): Fix an invalid result for queries with `WINDOW`. This could happen when `PARTITION` columns have sparse serialization and window functions are executed in parallel. [#66579](https://github.com/ClickHouse/ClickHouse/pull/66579) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66757](https://github.com/ClickHouse/ClickHouse/issues/66757): Fix `Unknown identifier` and `Column is not under aggregate function` errors for queries with the expression `(column IS NULL).` The bug was triggered by [#65088](https://github.com/ClickHouse/ClickHouse/issues/65088), with the disabled analyzer only. [#66654](https://github.com/ClickHouse/ClickHouse/pull/66654) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66948](https://github.com/ClickHouse/ClickHouse/issues/66948): Fix `Method getResultType is not supported for QUERY query node` error when scalar subquery was used as the first argument of IN (with new analyzer). [#66655](https://github.com/ClickHouse/ClickHouse/pull/66655) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#68115](https://github.com/ClickHouse/ClickHouse/issues/68115): Fix possible PARAMETER_OUT_OF_BOUND error during reading variant subcolumn. [#66659](https://github.com/ClickHouse/ClickHouse/pull/66659) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67633](https://github.com/ClickHouse/ClickHouse/issues/67633): Fix for occasional deadlock in Context::getDDLWorker. [#66843](https://github.com/ClickHouse/ClickHouse/pull/66843) ([Alexander Gololobov](https://github.com/davenger)).
|
||||
* Backported in [#67481](https://github.com/ClickHouse/ClickHouse/issues/67481): In rare cases ClickHouse could consider parts as broken because of some unexpected projections on disk. Now it's fixed. [#66898](https://github.com/ClickHouse/ClickHouse/pull/66898) ([alesapin](https://github.com/alesapin)).
|
||||
* Backported in [#67814](https://github.com/ClickHouse/ClickHouse/issues/67814): Only relevant to the experimental Variant data type. Fix crash with Variant + AggregateFunction type. [#67122](https://github.com/ClickHouse/ClickHouse/pull/67122) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67197](https://github.com/ClickHouse/ClickHouse/issues/67197): TRUNCATE DATABASE used to stop replication as if it was a DROP DATABASE query, it's fixed. [#67129](https://github.com/ClickHouse/ClickHouse/pull/67129) ([Alexander Tokmakov](https://github.com/tavplubix)).
|
||||
* Backported in [#67379](https://github.com/ClickHouse/ClickHouse/issues/67379): Fix error `Cannot convert column because it is non constant in source stream but must be constant in result.` for a query that reads from the `Merge` table over the `Distriburted` table with one shard. [#67146](https://github.com/ClickHouse/ClickHouse/pull/67146) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#67501](https://github.com/ClickHouse/ClickHouse/issues/67501): Fix crash in DistributedAsyncInsert when connection is empty. [#67219](https://github.com/ClickHouse/ClickHouse/pull/67219) ([Pablo Marcos](https://github.com/pamarcos)).
|
||||
* Backported in [#67886](https://github.com/ClickHouse/ClickHouse/issues/67886): Correctly parse file name/URI containing `::` if it's not an archive. [#67433](https://github.com/ClickHouse/ClickHouse/pull/67433) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67576](https://github.com/ClickHouse/ClickHouse/issues/67576): Fix execution of nested short-circuit functions. [#67520](https://github.com/ClickHouse/ClickHouse/pull/67520) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67850](https://github.com/ClickHouse/ClickHouse/issues/67850): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
|
||||
* Backported in [#68272](https://github.com/ClickHouse/ClickHouse/issues/68272): Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#67807](https://github.com/ClickHouse/ClickHouse/issues/67807): Fix reloading SQL UDFs with UNION. Previously, restarting the server could make UDF invalid. [#67665](https://github.com/ClickHouse/ClickHouse/pull/67665) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67836](https://github.com/ClickHouse/ClickHouse/issues/67836): Fix potential stack overflow in `JSONMergePatch` function. Renamed this function from `jsonMergePatch` to `JSONMergePatch` because the previous name was wrong. The previous name is still kept for compatibility. Improved diagnostic of errors in the function. This closes [#67304](https://github.com/ClickHouse/ClickHouse/issues/67304). [#67756](https://github.com/ClickHouse/ClickHouse/pull/67756) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Backported in [#67991](https://github.com/ClickHouse/ClickHouse/issues/67991): Validate experimental/suspicious data types in ALTER ADD/MODIFY COLUMN. [#67911](https://github.com/ClickHouse/ClickHouse/pull/67911) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68207](https://github.com/ClickHouse/ClickHouse/issues/68207): Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68091](https://github.com/ClickHouse/ClickHouse/issues/68091): Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* Backported in [#68122](https://github.com/ClickHouse/ClickHouse/issues/68122): Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68171](https://github.com/ClickHouse/ClickHouse/issues/68171): Removes an incorrect optimization to remove sorting in subqueries that use `OFFSET`. Fixes [#67906](https://github.com/ClickHouse/ClickHouse/issues/67906). [#68099](https://github.com/ClickHouse/ClickHouse/pull/68099) ([Graham Campbell](https://github.com/GrahamCampbell)).
|
||||
* Backported in [#68337](https://github.com/ClickHouse/ClickHouse/issues/68337): Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Backported in [#68667](https://github.com/ClickHouse/ClickHouse/issues/68667): Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#66387](https://github.com/ClickHouse/ClickHouse/issues/66387): Disable broken cases from 02911_join_on_nullsafe_optimization. [#66310](https://github.com/ClickHouse/ClickHouse/pull/66310) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#66426](https://github.com/ClickHouse/ClickHouse/issues/66426): Ignore subquery for IN in DDLLoadingDependencyVisitor. [#66395](https://github.com/ClickHouse/ClickHouse/pull/66395) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66544](https://github.com/ClickHouse/ClickHouse/issues/66544): Add additional log masking in CI. [#66523](https://github.com/ClickHouse/ClickHouse/pull/66523) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#66859](https://github.com/ClickHouse/ClickHouse/issues/66859): Fix data race in S3::ClientCache. [#66644](https://github.com/ClickHouse/ClickHouse/pull/66644) ([Konstantin Morozov](https://github.com/k-morozov)).
|
||||
* Backported in [#66875](https://github.com/ClickHouse/ClickHouse/issues/66875): Support one more case in JOIN ON ... IS NULL. [#66725](https://github.com/ClickHouse/ClickHouse/pull/66725) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#67059](https://github.com/ClickHouse/ClickHouse/issues/67059): Increase asio pool size in case the server is tiny. [#66761](https://github.com/ClickHouse/ClickHouse/pull/66761) ([alesapin](https://github.com/alesapin)).
|
||||
* Backported in [#66945](https://github.com/ClickHouse/ClickHouse/issues/66945): Small fix in realloc memory tracking. [#66820](https://github.com/ClickHouse/ClickHouse/pull/66820) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67252](https://github.com/ClickHouse/ClickHouse/issues/67252): Followup [#66725](https://github.com/ClickHouse/ClickHouse/issues/66725). [#66869](https://github.com/ClickHouse/ClickHouse/pull/66869) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#67412](https://github.com/ClickHouse/ClickHouse/issues/67412): CI: Fix build results for release branches. [#67402](https://github.com/ClickHouse/ClickHouse/pull/67402) ([Max K.](https://github.com/maxknv)).
|
||||
* Update version after release. [#67862](https://github.com/ClickHouse/ClickHouse/pull/67862) ([robot-clickhouse](https://github.com/robot-clickhouse)).
|
||||
* Backported in [#68077](https://github.com/ClickHouse/ClickHouse/issues/68077): Add an explicit error for `ALTER MODIFY SQL SECURITY` on non-view tables. [#67953](https://github.com/ClickHouse/ClickHouse/pull/67953) ([pufit](https://github.com/pufit)).
|
||||
|
||||
33
docs/changelogs/v24.5.6.45-stable.md
Normal file
33
docs/changelogs/v24.5.6.45-stable.md
Normal file
@ -0,0 +1,33 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.5.6.45-stable (bdca8604c29) FIXME as compared to v24.5.5.78-stable (0138248cb62)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#67902](https://github.com/ClickHouse/ClickHouse/issues/67902): Fixing the `Not-ready Set` error after the `PREWHERE` optimization for StorageMerge. [#65057](https://github.com/ClickHouse/ClickHouse/pull/65057) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#68252](https://github.com/ClickHouse/ClickHouse/issues/68252): Fixed `Not-ready Set` in some system tables when filtering using subqueries. [#66018](https://github.com/ClickHouse/ClickHouse/pull/66018) ([Michael Kolupaev](https://github.com/al13n321)).
|
||||
* Backported in [#68064](https://github.com/ClickHouse/ClickHouse/issues/68064): Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#68158](https://github.com/ClickHouse/ClickHouse/issues/68158): Fix cluster() for inter-server secret (preserve initial user as before). [#66364](https://github.com/ClickHouse/ClickHouse/pull/66364) ([Azat Khuzhin](https://github.com/azat)).
|
||||
* Backported in [#68115](https://github.com/ClickHouse/ClickHouse/issues/68115): Fix possible PARAMETER_OUT_OF_BOUND error during reading variant subcolumn. [#66659](https://github.com/ClickHouse/ClickHouse/pull/66659) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67886](https://github.com/ClickHouse/ClickHouse/issues/67886): Correctly parse file name/URI containing `::` if it's not an archive. [#67433](https://github.com/ClickHouse/ClickHouse/pull/67433) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#68272](https://github.com/ClickHouse/ClickHouse/issues/68272): Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#67807](https://github.com/ClickHouse/ClickHouse/issues/67807): Fix reloading SQL UDFs with UNION. Previously, restarting the server could make UDF invalid. [#67665](https://github.com/ClickHouse/ClickHouse/pull/67665) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67836](https://github.com/ClickHouse/ClickHouse/issues/67836): Fix potential stack overflow in `JSONMergePatch` function. Renamed this function from `jsonMergePatch` to `JSONMergePatch` because the previous name was wrong. The previous name is still kept for compatibility. Improved diagnostic of errors in the function. This closes [#67304](https://github.com/ClickHouse/ClickHouse/issues/67304). [#67756](https://github.com/ClickHouse/ClickHouse/pull/67756) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Backported in [#67991](https://github.com/ClickHouse/ClickHouse/issues/67991): Validate experimental/suspicious data types in ALTER ADD/MODIFY COLUMN. [#67911](https://github.com/ClickHouse/ClickHouse/pull/67911) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68207](https://github.com/ClickHouse/ClickHouse/issues/68207): Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68091](https://github.com/ClickHouse/ClickHouse/issues/68091): Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* Backported in [#68122](https://github.com/ClickHouse/ClickHouse/issues/68122): Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68171](https://github.com/ClickHouse/ClickHouse/issues/68171): Removes an incorrect optimization to remove sorting in subqueries that use `OFFSET`. Fixes [#67906](https://github.com/ClickHouse/ClickHouse/issues/67906). [#68099](https://github.com/ClickHouse/ClickHouse/pull/68099) ([Graham Campbell](https://github.com/GrahamCampbell)).
|
||||
* Backported in [#68337](https://github.com/ClickHouse/ClickHouse/issues/68337): Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Backported in [#68667](https://github.com/ClickHouse/ClickHouse/issues/68667): Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Update version after release. [#67862](https://github.com/ClickHouse/ClickHouse/pull/67862) ([robot-clickhouse](https://github.com/robot-clickhouse)).
|
||||
* Backported in [#68077](https://github.com/ClickHouse/ClickHouse/issues/68077): Add an explicit error for `ALTER MODIFY SQL SECURITY` on non-view tables. [#67953](https://github.com/ClickHouse/ClickHouse/pull/67953) ([pufit](https://github.com/pufit)).
|
||||
* Backported in [#68756](https://github.com/ClickHouse/ClickHouse/issues/68756): To make patch release possible from every commit on release branch, package_debug build is required and must not be skipped. [#68750](https://github.com/ClickHouse/ClickHouse/pull/68750) ([Max K.](https://github.com/maxknv)).
|
||||
|
||||
83
docs/changelogs/v24.6.3.38-stable.md
Normal file
83
docs/changelogs/v24.6.3.38-stable.md
Normal file
@ -0,0 +1,83 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.6.3.38-stable (4e33c831589) FIXME as compared to v24.6.2.17-stable (5710a8b5c0c)
|
||||
|
||||
#### Improvement
|
||||
* Backported in [#66770](https://github.com/ClickHouse/ClickHouse/issues/66770): Make allow_experimental_analyzer be controlled by the initiator for distributed queries. This ensures compatibility and correctness during operations in mixed version clusters. [#65777](https://github.com/ClickHouse/ClickHouse/pull/65777) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#66885](https://github.com/ClickHouse/ClickHouse/issues/66885): Fix unexpeced size of low cardinality column in function calls. [#65298](https://github.com/ClickHouse/ClickHouse/pull/65298) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#66303](https://github.com/ClickHouse/ClickHouse/issues/66303): Better handling of join conditions involving `IS NULL` checks (for example `ON (a = b AND (a IS NOT NULL) AND (b IS NOT NULL) ) OR ( (a IS NULL) AND (b IS NULL) )` is rewritten to `ON a <=> b`), fix incorrect optimization when condition other then `IS NULL` are present. [#65835](https://github.com/ClickHouse/ClickHouse/pull/65835) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#66330](https://github.com/ClickHouse/ClickHouse/issues/66330): Add missing settings `input_format_csv_skip_first_lines/input_format_tsv_skip_first_lines/input_format_csv_try_infer_numbers_from_strings/input_format_csv_try_infer_strings_from_quoted_tuples` in schema inference cache because they can change the resulting schema. It prevents from incorrect result of schema inference with these settings changed. [#65980](https://github.com/ClickHouse/ClickHouse/pull/65980) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#66157](https://github.com/ClickHouse/ClickHouse/issues/66157): Fixed buffer overflow bug in `unbin`/`unhex` implementation. [#66106](https://github.com/ClickHouse/ClickHouse/pull/66106) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
* Backported in [#66210](https://github.com/ClickHouse/ClickHouse/issues/66210): Disable the `merge-filters` optimization introduced in [#64760](https://github.com/ClickHouse/ClickHouse/issues/64760). It may cause an exception if optimization merges two filter expressions and does not apply a short-circuit evaluation. [#66126](https://github.com/ClickHouse/ClickHouse/pull/66126) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66456](https://github.com/ClickHouse/ClickHouse/issues/66456): Fixed a bug in ZooKeeper client: a session could get stuck in unusable state after receiving a hardware error from ZooKeeper. For example, this might happen due to "soft memory limit" in ClickHouse Keeper. [#66140](https://github.com/ClickHouse/ClickHouse/pull/66140) ([Alexander Tokmakov](https://github.com/tavplubix)).
|
||||
* Backported in [#66228](https://github.com/ClickHouse/ClickHouse/issues/66228): Fix issue in SumIfToCountIfVisitor and signed integers. [#66146](https://github.com/ClickHouse/ClickHouse/pull/66146) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#66183](https://github.com/ClickHouse/ClickHouse/issues/66183): Fix rare case with missing data in the result of distributed query, close [#61432](https://github.com/ClickHouse/ClickHouse/issues/61432). [#66174](https://github.com/ClickHouse/ClickHouse/pull/66174) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#66271](https://github.com/ClickHouse/ClickHouse/issues/66271): Don't throw `TIMEOUT_EXCEEDED` for `none_only_active` mode of `distributed_ddl_output_mode`. [#66218](https://github.com/ClickHouse/ClickHouse/pull/66218) ([Alexander Tokmakov](https://github.com/tavplubix)).
|
||||
* Backported in [#66682](https://github.com/ClickHouse/ClickHouse/issues/66682): Fix handling limit for `system.numbers_mt` when no index can be used. [#66231](https://github.com/ClickHouse/ClickHouse/pull/66231) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#66587](https://github.com/ClickHouse/ClickHouse/issues/66587): Fixed how the ClickHouse server detects the maximum number of usable CPU cores as specified by cgroups v2 if the server runs in a container such as Docker. In more detail, containers often run their process in the root cgroup which has an empty name. In that case, ClickHouse ignored the CPU limits set by cgroups v2. [#66237](https://github.com/ClickHouse/ClickHouse/pull/66237) ([filimonov](https://github.com/filimonov)).
|
||||
* Backported in [#66362](https://github.com/ClickHouse/ClickHouse/issues/66362): Fix the `Not-ready set` error when a subquery with `IN` is used in the constraint. [#66261](https://github.com/ClickHouse/ClickHouse/pull/66261) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#68066](https://github.com/ClickHouse/ClickHouse/issues/68066): Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#68566](https://github.com/ClickHouse/ClickHouse/issues/68566): Fix indexHint function case found by fuzzer. [#66286](https://github.com/ClickHouse/ClickHouse/pull/66286) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68159](https://github.com/ClickHouse/ClickHouse/issues/68159): Fix cluster() for inter-server secret (preserve initial user as before). [#66364](https://github.com/ClickHouse/ClickHouse/pull/66364) ([Azat Khuzhin](https://github.com/azat)).
|
||||
* Backported in [#66613](https://github.com/ClickHouse/ClickHouse/issues/66613): Fix `Column identifier is already registered` error with `group_by_use_nulls=true` and new analyzer. [#66400](https://github.com/ClickHouse/ClickHouse/pull/66400) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66693](https://github.com/ClickHouse/ClickHouse/issues/66693): Fix the VALID UNTIL clause in the user definition resetting after a restart. Closes [#66405](https://github.com/ClickHouse/ClickHouse/issues/66405). [#66409](https://github.com/ClickHouse/ClickHouse/pull/66409) ([Nikolay Degterinsky](https://github.com/evillique)).
|
||||
* Backported in [#66577](https://github.com/ClickHouse/ClickHouse/issues/66577): Fix `Cannot find column` error for queries with constant expression in `GROUP BY` key and new analyzer enabled. [#66433](https://github.com/ClickHouse/ClickHouse/pull/66433) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66721](https://github.com/ClickHouse/ClickHouse/issues/66721): Correctly track memory for `Allocator::realloc`. [#66548](https://github.com/ClickHouse/ClickHouse/pull/66548) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#66670](https://github.com/ClickHouse/ClickHouse/issues/66670): Fix reading of uninitialized memory when hashing empty tuples. This closes [#66559](https://github.com/ClickHouse/ClickHouse/issues/66559). [#66562](https://github.com/ClickHouse/ClickHouse/pull/66562) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Backported in [#66952](https://github.com/ClickHouse/ClickHouse/issues/66952): Fix an invalid result for queries with `WINDOW`. This could happen when `PARTITION` columns have sparse serialization and window functions are executed in parallel. [#66579](https://github.com/ClickHouse/ClickHouse/pull/66579) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66956](https://github.com/ClickHouse/ClickHouse/issues/66956): Fix removing named collections in local storage. [#66599](https://github.com/ClickHouse/ClickHouse/pull/66599) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#66716](https://github.com/ClickHouse/ClickHouse/issues/66716): Fix removing named collections in local storage. [#66599](https://github.com/ClickHouse/ClickHouse/pull/66599) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#66759](https://github.com/ClickHouse/ClickHouse/issues/66759): Fix `Unknown identifier` and `Column is not under aggregate function` errors for queries with the expression `(column IS NULL).` The bug was triggered by [#65088](https://github.com/ClickHouse/ClickHouse/issues/65088), with the disabled analyzer only. [#66654](https://github.com/ClickHouse/ClickHouse/pull/66654) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66751](https://github.com/ClickHouse/ClickHouse/issues/66751): Fix `Method getResultType is not supported for QUERY query node` error when scalar subquery was used as the first argument of IN (with new analyzer). [#66655](https://github.com/ClickHouse/ClickHouse/pull/66655) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#68116](https://github.com/ClickHouse/ClickHouse/issues/68116): Fix possible PARAMETER_OUT_OF_BOUND error during reading variant subcolumn. [#66659](https://github.com/ClickHouse/ClickHouse/pull/66659) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67635](https://github.com/ClickHouse/ClickHouse/issues/67635): Fix for occasional deadlock in Context::getDDLWorker. [#66843](https://github.com/ClickHouse/ClickHouse/pull/66843) ([Alexander Gololobov](https://github.com/davenger)).
|
||||
* Backported in [#67482](https://github.com/ClickHouse/ClickHouse/issues/67482): In rare cases ClickHouse could consider parts as broken because of some unexpected projections on disk. Now it's fixed. [#66898](https://github.com/ClickHouse/ClickHouse/pull/66898) ([alesapin](https://github.com/alesapin)).
|
||||
* Backported in [#67816](https://github.com/ClickHouse/ClickHouse/issues/67816): Only relevant to the experimental Variant data type. Fix crash with Variant + AggregateFunction type. [#67122](https://github.com/ClickHouse/ClickHouse/pull/67122) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67199](https://github.com/ClickHouse/ClickHouse/issues/67199): TRUNCATE DATABASE used to stop replication as if it was a DROP DATABASE query, it's fixed. [#67129](https://github.com/ClickHouse/ClickHouse/pull/67129) ([Alexander Tokmakov](https://github.com/tavplubix)).
|
||||
* Backported in [#67381](https://github.com/ClickHouse/ClickHouse/issues/67381): Fix error `Cannot convert column because it is non constant in source stream but must be constant in result.` for a query that reads from the `Merge` table over the `Distriburted` table with one shard. [#67146](https://github.com/ClickHouse/ClickHouse/pull/67146) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#67244](https://github.com/ClickHouse/ClickHouse/issues/67244): This closes [#67156](https://github.com/ClickHouse/ClickHouse/issues/67156). This closes [#66447](https://github.com/ClickHouse/ClickHouse/issues/66447). The bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/62907. [#67178](https://github.com/ClickHouse/ClickHouse/pull/67178) ([Maksim Kita](https://github.com/kitaisreal)).
|
||||
* Backported in [#67503](https://github.com/ClickHouse/ClickHouse/issues/67503): Fix crash in DistributedAsyncInsert when connection is empty. [#67219](https://github.com/ClickHouse/ClickHouse/pull/67219) ([Pablo Marcos](https://github.com/pamarcos)).
|
||||
* Backported in [#67887](https://github.com/ClickHouse/ClickHouse/issues/67887): Correctly parse file name/URI containing `::` if it's not an archive. [#67433](https://github.com/ClickHouse/ClickHouse/pull/67433) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67578](https://github.com/ClickHouse/ClickHouse/issues/67578): Fix execution of nested short-circuit functions. [#67520](https://github.com/ClickHouse/ClickHouse/pull/67520) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68611](https://github.com/ClickHouse/ClickHouse/issues/68611): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
|
||||
* Backported in [#67852](https://github.com/ClickHouse/ClickHouse/issues/67852): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
|
||||
* Backported in [#68275](https://github.com/ClickHouse/ClickHouse/issues/68275): Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#67808](https://github.com/ClickHouse/ClickHouse/issues/67808): Fix reloading SQL UDFs with UNION. Previously, restarting the server could make UDF invalid. [#67665](https://github.com/ClickHouse/ClickHouse/pull/67665) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67838](https://github.com/ClickHouse/ClickHouse/issues/67838): Fix potential stack overflow in `JSONMergePatch` function. Renamed this function from `jsonMergePatch` to `JSONMergePatch` because the previous name was wrong. The previous name is still kept for compatibility. Improved diagnostic of errors in the function. This closes [#67304](https://github.com/ClickHouse/ClickHouse/issues/67304). [#67756](https://github.com/ClickHouse/ClickHouse/pull/67756) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Backported in [#67993](https://github.com/ClickHouse/ClickHouse/issues/67993): Validate experimental/suspicious data types in ALTER ADD/MODIFY COLUMN. [#67911](https://github.com/ClickHouse/ClickHouse/pull/67911) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68208](https://github.com/ClickHouse/ClickHouse/issues/68208): Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68093](https://github.com/ClickHouse/ClickHouse/issues/68093): Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* Backported in [#68124](https://github.com/ClickHouse/ClickHouse/issues/68124): Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68221](https://github.com/ClickHouse/ClickHouse/issues/68221): Fixed a NULL pointer dereference, triggered by a specially crafted query, that crashed the server via hopEnd, hopStart, tumbleEnd, and tumbleStart. [#68098](https://github.com/ClickHouse/ClickHouse/pull/68098) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
|
||||
* Backported in [#68173](https://github.com/ClickHouse/ClickHouse/issues/68173): Removes an incorrect optimization to remove sorting in subqueries that use `OFFSET`. Fixes [#67906](https://github.com/ClickHouse/ClickHouse/issues/67906). [#68099](https://github.com/ClickHouse/ClickHouse/pull/68099) ([Graham Campbell](https://github.com/GrahamCampbell)).
|
||||
* Backported in [#68339](https://github.com/ClickHouse/ClickHouse/issues/68339): Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Backported in [#68396](https://github.com/ClickHouse/ClickHouse/issues/68396): Fix missing sync replica mode in query `SYSTEM SYNC REPLICA`. [#68326](https://github.com/ClickHouse/ClickHouse/pull/68326) ([Duc Canh Le](https://github.com/canhld94)).
|
||||
* Backported in [#68668](https://github.com/ClickHouse/ClickHouse/issues/68668): Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
#### NO CL ENTRY
|
||||
|
||||
* NO CL ENTRY: 'Revert "Backport [#66599](https://github.com/ClickHouse/ClickHouse/issues/66599) to 24.6: Fix dropping named collection in local storage"'. [#66922](https://github.com/ClickHouse/ClickHouse/pull/66922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#66332](https://github.com/ClickHouse/ClickHouse/issues/66332): Do not raise a NOT_IMPLEMENTED error when getting s3 metrics with a multiple disk configuration. [#65403](https://github.com/ClickHouse/ClickHouse/pull/65403) ([Elena Torró](https://github.com/elenatorro)).
|
||||
* Backported in [#66142](https://github.com/ClickHouse/ClickHouse/issues/66142): Fix flaky test_storage_s3_queue tests. [#66009](https://github.com/ClickHouse/ClickHouse/pull/66009) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Backported in [#66389](https://github.com/ClickHouse/ClickHouse/issues/66389): Disable broken cases from 02911_join_on_nullsafe_optimization. [#66310](https://github.com/ClickHouse/ClickHouse/pull/66310) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#66428](https://github.com/ClickHouse/ClickHouse/issues/66428): Ignore subquery for IN in DDLLoadingDependencyVisitor. [#66395](https://github.com/ClickHouse/ClickHouse/pull/66395) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
|
||||
* Backported in [#66546](https://github.com/ClickHouse/ClickHouse/issues/66546): Add additional log masking in CI. [#66523](https://github.com/ClickHouse/ClickHouse/pull/66523) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#66861](https://github.com/ClickHouse/ClickHouse/issues/66861): Fix data race in S3::ClientCache. [#66644](https://github.com/ClickHouse/ClickHouse/pull/66644) ([Konstantin Morozov](https://github.com/k-morozov)).
|
||||
* Backported in [#66877](https://github.com/ClickHouse/ClickHouse/issues/66877): Support one more case in JOIN ON ... IS NULL. [#66725](https://github.com/ClickHouse/ClickHouse/pull/66725) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#67061](https://github.com/ClickHouse/ClickHouse/issues/67061): Increase asio pool size in case the server is tiny. [#66761](https://github.com/ClickHouse/ClickHouse/pull/66761) ([alesapin](https://github.com/alesapin)).
|
||||
* Backported in [#66940](https://github.com/ClickHouse/ClickHouse/issues/66940): Small fix in realloc memory tracking. [#66820](https://github.com/ClickHouse/ClickHouse/pull/66820) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67254](https://github.com/ClickHouse/ClickHouse/issues/67254): Followup [#66725](https://github.com/ClickHouse/ClickHouse/issues/66725). [#66869](https://github.com/ClickHouse/ClickHouse/pull/66869) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#67414](https://github.com/ClickHouse/ClickHouse/issues/67414): CI: Fix build results for release branches. [#67402](https://github.com/ClickHouse/ClickHouse/pull/67402) ([Max K.](https://github.com/maxknv)).
|
||||
* Update version after release. [#67909](https://github.com/ClickHouse/ClickHouse/pull/67909) ([robot-clickhouse](https://github.com/robot-clickhouse)).
|
||||
* Backported in [#68079](https://github.com/ClickHouse/ClickHouse/issues/68079): Add an explicit error for `ALTER MODIFY SQL SECURITY` on non-view tables. [#67953](https://github.com/ClickHouse/ClickHouse/pull/67953) ([pufit](https://github.com/pufit)).
|
||||
|
||||
33
docs/changelogs/v24.6.4.42-stable.md
Normal file
33
docs/changelogs/v24.6.4.42-stable.md
Normal file
@ -0,0 +1,33 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.6.4.42-stable (c534bb4b4dd) FIXME as compared to v24.6.3.95-stable (8325c920d11)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#68066](https://github.com/ClickHouse/ClickHouse/issues/68066): Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#68566](https://github.com/ClickHouse/ClickHouse/issues/68566): Fix indexHint function case found by fuzzer. [#66286](https://github.com/ClickHouse/ClickHouse/pull/66286) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68159](https://github.com/ClickHouse/ClickHouse/issues/68159): Fix cluster() for inter-server secret (preserve initial user as before). [#66364](https://github.com/ClickHouse/ClickHouse/pull/66364) ([Azat Khuzhin](https://github.com/azat)).
|
||||
* Backported in [#68116](https://github.com/ClickHouse/ClickHouse/issues/68116): Fix possible PARAMETER_OUT_OF_BOUND error during reading variant subcolumn. [#66659](https://github.com/ClickHouse/ClickHouse/pull/66659) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67887](https://github.com/ClickHouse/ClickHouse/issues/67887): Correctly parse file name/URI containing `::` if it's not an archive. [#67433](https://github.com/ClickHouse/ClickHouse/pull/67433) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#68611](https://github.com/ClickHouse/ClickHouse/issues/68611): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
|
||||
* Backported in [#68275](https://github.com/ClickHouse/ClickHouse/issues/68275): Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#67993](https://github.com/ClickHouse/ClickHouse/issues/67993): Validate experimental/suspicious data types in ALTER ADD/MODIFY COLUMN. [#67911](https://github.com/ClickHouse/ClickHouse/pull/67911) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68208](https://github.com/ClickHouse/ClickHouse/issues/68208): Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68093](https://github.com/ClickHouse/ClickHouse/issues/68093): Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* Backported in [#68124](https://github.com/ClickHouse/ClickHouse/issues/68124): Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68221](https://github.com/ClickHouse/ClickHouse/issues/68221): Fixed a NULL pointer dereference, triggered by a specially crafted query, that crashed the server via hopEnd, hopStart, tumbleEnd, and tumbleStart. [#68098](https://github.com/ClickHouse/ClickHouse/pull/68098) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
|
||||
* Backported in [#68173](https://github.com/ClickHouse/ClickHouse/issues/68173): Removes an incorrect optimization to remove sorting in subqueries that use `OFFSET`. Fixes [#67906](https://github.com/ClickHouse/ClickHouse/issues/67906). [#68099](https://github.com/ClickHouse/ClickHouse/pull/68099) ([Graham Campbell](https://github.com/GrahamCampbell)).
|
||||
* Backported in [#68339](https://github.com/ClickHouse/ClickHouse/issues/68339): Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Backported in [#68396](https://github.com/ClickHouse/ClickHouse/issues/68396): Fix missing sync replica mode in query `SYSTEM SYNC REPLICA`. [#68326](https://github.com/ClickHouse/ClickHouse/pull/68326) ([Duc Canh Le](https://github.com/canhld94)).
|
||||
* Backported in [#68668](https://github.com/ClickHouse/ClickHouse/issues/68668): Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Update version after release. [#67909](https://github.com/ClickHouse/ClickHouse/pull/67909) ([robot-clickhouse](https://github.com/robot-clickhouse)).
|
||||
* Backported in [#68079](https://github.com/ClickHouse/ClickHouse/issues/68079): Add an explicit error for `ALTER MODIFY SQL SECURITY` on non-view tables. [#67953](https://github.com/ClickHouse/ClickHouse/pull/67953) ([pufit](https://github.com/pufit)).
|
||||
* Backported in [#68758](https://github.com/ClickHouse/ClickHouse/issues/68758): To make patch release possible from every commit on release branch, package_debug build is required and must not be skipped. [#68750](https://github.com/ClickHouse/ClickHouse/pull/68750) ([Max K.](https://github.com/maxknv)).
|
||||
|
||||
55
docs/changelogs/v24.7.3.47-stable.md
Normal file
55
docs/changelogs/v24.7.3.47-stable.md
Normal file
@ -0,0 +1,55 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.7.3.47-stable (2e50fe27a14) FIXME as compared to v24.7.2.13-stable (6e41f601b2f)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#68232](https://github.com/ClickHouse/ClickHouse/issues/68232): Fixed `Not-ready Set` in some system tables when filtering using subqueries. [#66018](https://github.com/ClickHouse/ClickHouse/pull/66018) ([Michael Kolupaev](https://github.com/al13n321)).
|
||||
* Backported in [#67969](https://github.com/ClickHouse/ClickHouse/issues/67969): Fixed reading of subcolumns after `ALTER ADD COLUMN` query. [#66243](https://github.com/ClickHouse/ClickHouse/pull/66243) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68068](https://github.com/ClickHouse/ClickHouse/issues/68068): Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#67637](https://github.com/ClickHouse/ClickHouse/issues/67637): Fix for occasional deadlock in Context::getDDLWorker. [#66843](https://github.com/ClickHouse/ClickHouse/pull/66843) ([Alexander Gololobov](https://github.com/davenger)).
|
||||
* Backported in [#67820](https://github.com/ClickHouse/ClickHouse/issues/67820): Fix possible deadlock on query cancel with parallel replicas. [#66905](https://github.com/ClickHouse/ClickHouse/pull/66905) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
* Backported in [#67818](https://github.com/ClickHouse/ClickHouse/issues/67818): Only relevant to the experimental Variant data type. Fix crash with Variant + AggregateFunction type. [#67122](https://github.com/ClickHouse/ClickHouse/pull/67122) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67766](https://github.com/ClickHouse/ClickHouse/issues/67766): Fix crash of `uniq` and `uniqTheta ` with `tuple()` argument. Closes [#67303](https://github.com/ClickHouse/ClickHouse/issues/67303). [#67306](https://github.com/ClickHouse/ClickHouse/pull/67306) ([flynn](https://github.com/ucasfl)).
|
||||
* Backported in [#67881](https://github.com/ClickHouse/ClickHouse/issues/67881): Correctly parse file name/URI containing `::` if it's not an archive. [#67433](https://github.com/ClickHouse/ClickHouse/pull/67433) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#68613](https://github.com/ClickHouse/ClickHouse/issues/68613): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
|
||||
* Backported in [#67854](https://github.com/ClickHouse/ClickHouse/issues/67854): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
|
||||
* Backported in [#68278](https://github.com/ClickHouse/ClickHouse/issues/68278): Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68040](https://github.com/ClickHouse/ClickHouse/issues/68040): Fix creation of view with recursive CTE. [#67587](https://github.com/ClickHouse/ClickHouse/pull/67587) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
|
||||
* Backported in [#68038](https://github.com/ClickHouse/ClickHouse/issues/68038): Fix crash on `percent_rank`. `percent_rank`'s default frame type is changed to `range unbounded preceding and unbounded following`. `IWindowFunction`'s default window frame is considered and now window functions without window frame definition in sql can be put into different `WindowTransfomer`s properly. [#67661](https://github.com/ClickHouse/ClickHouse/pull/67661) ([lgbo](https://github.com/lgbo-ustc)).
|
||||
* Backported in [#67713](https://github.com/ClickHouse/ClickHouse/issues/67713): Fix reloading SQL UDFs with UNION. Previously, restarting the server could make UDF invalid. [#67665](https://github.com/ClickHouse/ClickHouse/pull/67665) ([Antonio Andelic](https://github.com/antonio2368)).
|
||||
* Backported in [#67840](https://github.com/ClickHouse/ClickHouse/issues/67840): Fix potential stack overflow in `JSONMergePatch` function. Renamed this function from `jsonMergePatch` to `JSONMergePatch` because the previous name was wrong. The previous name is still kept for compatibility. Improved diagnostic of errors in the function. This closes [#67304](https://github.com/ClickHouse/ClickHouse/issues/67304). [#67756](https://github.com/ClickHouse/ClickHouse/pull/67756) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
|
||||
* Backported in [#67995](https://github.com/ClickHouse/ClickHouse/issues/67995): Validate experimental/suspicious data types in ALTER ADD/MODIFY COLUMN. [#67911](https://github.com/ClickHouse/ClickHouse/pull/67911) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68224](https://github.com/ClickHouse/ClickHouse/issues/68224): Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68095](https://github.com/ClickHouse/ClickHouse/issues/68095): Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* Backported in [#68126](https://github.com/ClickHouse/ClickHouse/issues/68126): Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68223](https://github.com/ClickHouse/ClickHouse/issues/68223): Fixed a NULL pointer dereference, triggered by a specially crafted query, that crashed the server via hopEnd, hopStart, tumbleEnd, and tumbleStart. [#68098](https://github.com/ClickHouse/ClickHouse/pull/68098) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
|
||||
* Backported in [#68175](https://github.com/ClickHouse/ClickHouse/issues/68175): Removes an incorrect optimization to remove sorting in subqueries that use `OFFSET`. Fixes [#67906](https://github.com/ClickHouse/ClickHouse/issues/67906). [#68099](https://github.com/ClickHouse/ClickHouse/pull/68099) ([Graham Campbell](https://github.com/GrahamCampbell)).
|
||||
* Backported in [#68341](https://github.com/ClickHouse/ClickHouse/issues/68341): Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Backported in [#68398](https://github.com/ClickHouse/ClickHouse/issues/68398): Fix missing sync replica mode in query `SYSTEM SYNC REPLICA`. [#68326](https://github.com/ClickHouse/ClickHouse/pull/68326) ([Duc Canh Le](https://github.com/canhld94)).
|
||||
* Backported in [#68669](https://github.com/ClickHouse/ClickHouse/issues/68669): Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#67518](https://github.com/ClickHouse/ClickHouse/issues/67518): Split slow test 03036_dynamic_read_subcolumns. [#66954](https://github.com/ClickHouse/ClickHouse/pull/66954) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
* Backported in [#67516](https://github.com/ClickHouse/ClickHouse/issues/67516): Split 01508_partition_pruning_long. [#66983](https://github.com/ClickHouse/ClickHouse/pull/66983) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
* Backported in [#67529](https://github.com/ClickHouse/ClickHouse/issues/67529): Reduce max time of 00763_long_lock_buffer_alter_destination_table. [#67185](https://github.com/ClickHouse/ClickHouse/pull/67185) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#67803](https://github.com/ClickHouse/ClickHouse/issues/67803): Disable some Dynamic tests under sanitizers, rewrite 03202_dynamic_null_map_subcolumn to sql. [#67359](https://github.com/ClickHouse/ClickHouse/pull/67359) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#67643](https://github.com/ClickHouse/ClickHouse/issues/67643): [Green CI] Fix potentially flaky test_mask_sensitive_info integration test. [#67506](https://github.com/ClickHouse/ClickHouse/pull/67506) ([Alexey Katsman](https://github.com/alexkats)).
|
||||
* Backported in [#67609](https://github.com/ClickHouse/ClickHouse/issues/67609): Fix test_zookeeper_config_load_balancing after adding the xdist worker name to the instance. [#67590](https://github.com/ClickHouse/ClickHouse/pull/67590) ([Pablo Marcos](https://github.com/pamarcos)).
|
||||
* Backported in [#67871](https://github.com/ClickHouse/ClickHouse/issues/67871): Fix 02434_cancel_insert_when_client_dies. [#67600](https://github.com/ClickHouse/ClickHouse/pull/67600) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#67704](https://github.com/ClickHouse/ClickHouse/issues/67704): Fix 02910_bad_logs_level_in_local in fast tests. [#67603](https://github.com/ClickHouse/ClickHouse/pull/67603) ([Raúl Marín](https://github.com/Algunenano)).
|
||||
* Backported in [#67689](https://github.com/ClickHouse/ClickHouse/issues/67689): Fix 01605_adaptive_granularity_block_borders. [#67605](https://github.com/ClickHouse/ClickHouse/pull/67605) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
* Backported in [#67827](https://github.com/ClickHouse/ClickHouse/issues/67827): Try fix 03143_asof_join_ddb_long. [#67620](https://github.com/ClickHouse/ClickHouse/pull/67620) ([Nikita Taranov](https://github.com/nickitat)).
|
||||
* Backported in [#67892](https://github.com/ClickHouse/ClickHouse/issues/67892): Revert "Merge pull request [#66510](https://github.com/ClickHouse/ClickHouse/issues/66510) from canhld94/fix_trivial_count_non_deterministic_func". [#67800](https://github.com/ClickHouse/ClickHouse/pull/67800) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68081](https://github.com/ClickHouse/ClickHouse/issues/68081): Add an explicit error for `ALTER MODIFY SQL SECURITY` on non-view tables. [#67953](https://github.com/ClickHouse/ClickHouse/pull/67953) ([pufit](https://github.com/pufit)).
|
||||
* Update version after release. [#68044](https://github.com/ClickHouse/ClickHouse/pull/68044) ([robot-clickhouse](https://github.com/robot-clickhouse)).
|
||||
* Backported in [#68269](https://github.com/ClickHouse/ClickHouse/issues/68269): [Green CI] Fix test 01903_correct_block_size_prediction_with_default. [#68203](https://github.com/ClickHouse/ClickHouse/pull/68203) ([Pablo Marcos](https://github.com/pamarcos)).
|
||||
* Backported in [#68432](https://github.com/ClickHouse/ClickHouse/issues/68432): tests: make 01600_parts_states_metrics_long better. [#68265](https://github.com/ClickHouse/ClickHouse/pull/68265) ([Azat Khuzhin](https://github.com/azat)).
|
||||
* Backported in [#68538](https://github.com/ClickHouse/ClickHouse/issues/68538): CI: Native build for package_aarch64. [#68457](https://github.com/ClickHouse/ClickHouse/pull/68457) ([Max K.](https://github.com/maxknv)).
|
||||
* Backported in [#68555](https://github.com/ClickHouse/ClickHouse/issues/68555): CI: Minor release workflow fix. [#68536](https://github.com/ClickHouse/ClickHouse/pull/68536) ([Max K.](https://github.com/maxknv)).
|
||||
|
||||
36
docs/changelogs/v24.7.4.51-stable.md
Normal file
36
docs/changelogs/v24.7.4.51-stable.md
Normal file
@ -0,0 +1,36 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.7.4.51-stable (70fe2f6fa52) FIXME as compared to v24.7.3.42-stable (63730bc4293)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#68232](https://github.com/ClickHouse/ClickHouse/issues/68232): Fixed `Not-ready Set` in some system tables when filtering using subqueries. [#66018](https://github.com/ClickHouse/ClickHouse/pull/66018) ([Michael Kolupaev](https://github.com/al13n321)).
|
||||
* Backported in [#68068](https://github.com/ClickHouse/ClickHouse/issues/68068): Fix boolean literals in query sent to external database (for engines like `PostgreSQL`). [#66282](https://github.com/ClickHouse/ClickHouse/pull/66282) ([vdimir](https://github.com/vdimir)).
|
||||
* Backported in [#68613](https://github.com/ClickHouse/ClickHouse/issues/68613): Fixes [#66026](https://github.com/ClickHouse/ClickHouse/issues/66026). Avoid unresolved table function arguments traversal in `ReplaceTableNodeToDummyVisitor`. [#67522](https://github.com/ClickHouse/ClickHouse/pull/67522) ([Dmitry Novik](https://github.com/novikd)).
|
||||
* Backported in [#68278](https://github.com/ClickHouse/ClickHouse/issues/68278): Fix inserting into stream like engines (Kafka, RabbitMQ, NATS) through HTTP interface. [#67554](https://github.com/ClickHouse/ClickHouse/pull/67554) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68040](https://github.com/ClickHouse/ClickHouse/issues/68040): Fix creation of view with recursive CTE. [#67587](https://github.com/ClickHouse/ClickHouse/pull/67587) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
|
||||
* Backported in [#68038](https://github.com/ClickHouse/ClickHouse/issues/68038): Fix crash on `percent_rank`. `percent_rank`'s default frame type is changed to `range unbounded preceding and unbounded following`. `IWindowFunction`'s default window frame is considered and now window functions without window frame definition in sql can be put into different `WindowTransfomer`s properly. [#67661](https://github.com/ClickHouse/ClickHouse/pull/67661) ([lgbo](https://github.com/lgbo-ustc)).
|
||||
* Backported in [#68224](https://github.com/ClickHouse/ClickHouse/issues/68224): Fix wrong `count()` result when there is non-deterministic function in predicate. [#67922](https://github.com/ClickHouse/ClickHouse/pull/67922) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
|
||||
* Backported in [#68095](https://github.com/ClickHouse/ClickHouse/issues/68095): Fixed the calculation of the maximum thread soft limit in containerized environments where the usable CPU count is limited. [#67963](https://github.com/ClickHouse/ClickHouse/pull/67963) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
* Backported in [#68126](https://github.com/ClickHouse/ClickHouse/issues/68126): Fixed skipping of untouched parts in mutations with new analyzer. Previously with enabled analyzer data in part could be rewritten by mutation even if mutation doesn't affect this part according to predicate. [#68052](https://github.com/ClickHouse/ClickHouse/pull/68052) ([Anton Popov](https://github.com/CurtizJ)).
|
||||
* Backported in [#68223](https://github.com/ClickHouse/ClickHouse/issues/68223): Fixed a NULL pointer dereference, triggered by a specially crafted query, that crashed the server via hopEnd, hopStart, tumbleEnd, and tumbleStart. [#68098](https://github.com/ClickHouse/ClickHouse/pull/68098) ([Salvatore Mesoraca](https://github.com/aiven-sal)).
|
||||
* Backported in [#68175](https://github.com/ClickHouse/ClickHouse/issues/68175): Removes an incorrect optimization to remove sorting in subqueries that use `OFFSET`. Fixes [#67906](https://github.com/ClickHouse/ClickHouse/issues/67906). [#68099](https://github.com/ClickHouse/ClickHouse/pull/68099) ([Graham Campbell](https://github.com/GrahamCampbell)).
|
||||
* Backported in [#68341](https://github.com/ClickHouse/ClickHouse/issues/68341): Try fix postgres crash when query is cancelled. [#68288](https://github.com/ClickHouse/ClickHouse/pull/68288) ([Kseniia Sumarokova](https://github.com/kssenii)).
|
||||
* Backported in [#68398](https://github.com/ClickHouse/ClickHouse/issues/68398): Fix missing sync replica mode in query `SYSTEM SYNC REPLICA`. [#68326](https://github.com/ClickHouse/ClickHouse/pull/68326) ([Duc Canh Le](https://github.com/canhld94)).
|
||||
* Backported in [#68669](https://github.com/ClickHouse/ClickHouse/issues/68669): Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
#### NOT FOR CHANGELOG / INSIGNIFICANT
|
||||
|
||||
* Backported in [#67803](https://github.com/ClickHouse/ClickHouse/issues/67803): Disable some Dynamic tests under sanitizers, rewrite 03202_dynamic_null_map_subcolumn to sql. [#67359](https://github.com/ClickHouse/ClickHouse/pull/67359) ([Kruglov Pavel](https://github.com/Avogar)).
|
||||
* Backported in [#68081](https://github.com/ClickHouse/ClickHouse/issues/68081): Add an explicit error for `ALTER MODIFY SQL SECURITY` on non-view tables. [#67953](https://github.com/ClickHouse/ClickHouse/pull/67953) ([pufit](https://github.com/pufit)).
|
||||
* Update version after release. [#68044](https://github.com/ClickHouse/ClickHouse/pull/68044) ([robot-clickhouse](https://github.com/robot-clickhouse)).
|
||||
* Backported in [#68269](https://github.com/ClickHouse/ClickHouse/issues/68269): [Green CI] Fix test 01903_correct_block_size_prediction_with_default. [#68203](https://github.com/ClickHouse/ClickHouse/pull/68203) ([Pablo Marcos](https://github.com/pamarcos)).
|
||||
* Backported in [#68432](https://github.com/ClickHouse/ClickHouse/issues/68432): tests: make 01600_parts_states_metrics_long better. [#68265](https://github.com/ClickHouse/ClickHouse/pull/68265) ([Azat Khuzhin](https://github.com/azat)).
|
||||
* Backported in [#68538](https://github.com/ClickHouse/ClickHouse/issues/68538): CI: Native build for package_aarch64. [#68457](https://github.com/ClickHouse/ClickHouse/pull/68457) ([Max K.](https://github.com/maxknv)).
|
||||
* Backported in [#68555](https://github.com/ClickHouse/ClickHouse/issues/68555): CI: Minor release workflow fix. [#68536](https://github.com/ClickHouse/ClickHouse/pull/68536) ([Max K.](https://github.com/maxknv)).
|
||||
* Backported in [#68760](https://github.com/ClickHouse/ClickHouse/issues/68760): To make patch release possible from every commit on release branch, package_debug build is required and must not be skipped. [#68750](https://github.com/ClickHouse/ClickHouse/pull/68750) ([Max K.](https://github.com/maxknv)).
|
||||
|
||||
12
docs/changelogs/v24.8.2.3-lts.md
Normal file
12
docs/changelogs/v24.8.2.3-lts.md
Normal file
@ -0,0 +1,12 @@
|
||||
---
|
||||
sidebar_position: 1
|
||||
sidebar_label: 2024
|
||||
---
|
||||
|
||||
# 2024 Changelog
|
||||
|
||||
### ClickHouse release v24.8.2.3-lts (b54f79ed323) FIXME as compared to v24.8.1.2684-lts (161c62fd295)
|
||||
|
||||
#### Bug Fix (user-visible misbehavior in an official stable release)
|
||||
* Backported in [#68670](https://github.com/ClickHouse/ClickHouse/issues/68670): Fix `LOGICAL_ERROR`s when functions `sipHash64Keyed`, `sipHash128Keyed`, or `sipHash128ReferenceKeyed` are applied to empty arrays or tuples. [#68630](https://github.com/ClickHouse/ClickHouse/pull/68630) ([Robert Schulze](https://github.com/rschu1ze)).
|
||||
|
||||
@ -6,28 +6,34 @@ sidebar_label: Iceberg
|
||||
|
||||
# Iceberg Table Engine
|
||||
|
||||
This engine provides a read-only integration with existing Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3.
|
||||
This engine provides a read-only integration with existing Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3, Azure and locally stored tables.
|
||||
|
||||
## Create Table
|
||||
|
||||
Note that the Iceberg table must already exist in S3, this command does not take DDL parameters to create a new table.
|
||||
Note that the Iceberg table must already exist in the storage, this command does not take DDL parameters to create a new table.
|
||||
|
||||
``` sql
|
||||
CREATE TABLE iceberg_table
|
||||
ENGINE = Iceberg(url, [aws_access_key_id, aws_secret_access_key,])
|
||||
CREATE TABLE iceberg_table_s3
|
||||
ENGINE = IcebergS3(url, [, NOSIGN | access_key_id, secret_access_key, [session_token]], format, [,compression])
|
||||
|
||||
CREATE TABLE iceberg_table_azure
|
||||
ENGINE = IcebergAzure(connection_string|storage_account_url, container_name, blobpath, [account_name, account_key, format, compression])
|
||||
|
||||
CREATE TABLE iceberg_table_local
|
||||
ENGINE = IcebergLocal(path_to_table, [,format] [,compression_method])
|
||||
```
|
||||
|
||||
**Engine parameters**
|
||||
**Engine arguments**
|
||||
|
||||
- `url` — url with the path to an existing Iceberg table.
|
||||
- `aws_access_key_id`, `aws_secret_access_key` - Long-term credentials for the [AWS](https://aws.amazon.com/) account user. You can use these to authenticate your requests. Parameter is optional. If credentials are not specified, they are used from the configuration file.
|
||||
Description of the arguments coincides with description of arguments in engines `S3`, `AzureBlobStorage` and `File` correspondingly.
|
||||
`format` stands for the format of data files in the Iceberg table.
|
||||
|
||||
Engine parameters can be specified using [Named Collections](../../../operations/named-collections.md)
|
||||
|
||||
**Example**
|
||||
|
||||
```sql
|
||||
CREATE TABLE iceberg_table ENGINE=Iceberg('http://test.s3.amazonaws.com/clickhouse-bucket/test_table', 'test', 'test')
|
||||
CREATE TABLE iceberg_table ENGINE=IcebergS3('http://test.s3.amazonaws.com/clickhouse-bucket/test_table', 'test', 'test')
|
||||
```
|
||||
|
||||
Using named collections:
|
||||
@ -45,9 +51,15 @@ Using named collections:
|
||||
```
|
||||
|
||||
```sql
|
||||
CREATE TABLE iceberg_table ENGINE=Iceberg(iceberg_conf, filename = 'test_table')
|
||||
CREATE TABLE iceberg_table ENGINE=IcebergS3(iceberg_conf, filename = 'test_table')
|
||||
|
||||
```
|
||||
|
||||
**Aliases**
|
||||
|
||||
|
||||
Table engine `Iceberg` is an alias to `IcebergS3` now.
|
||||
|
||||
## See also
|
||||
|
||||
- [iceberg table function](/docs/en/sql-reference/table-functions/iceberg.md)
|
||||
|
||||
@ -54,7 +54,7 @@ Parameters:
|
||||
- `distance_function`: either `L2Distance` (the [Euclidean distance](https://en.wikipedia.org/wiki/Euclidean_distance) - the length of a
|
||||
line between two points in Euclidean space), or `cosineDistance` (the [cosine
|
||||
distance](https://en.wikipedia.org/wiki/Cosine_similarity#Cosine_distance)- the angle between two non-zero vectors).
|
||||
- `quantization`: either `f32`, `f16`, or `i8` for storing the vector with reduced precision (optional, default: `f32`)
|
||||
- `quantization`: either `f64`, `f32`, `f16`, `bf16`, or `i8` for storing the vector with reduced precision (optional, default: `bf16`)
|
||||
- `m`: the number of neighbors per graph node (optional, default: 16)
|
||||
- `ef_construction`: (optional, default: 128)
|
||||
- `ef_search`: (optional, default: 64)
|
||||
|
||||
@ -80,7 +80,7 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
|
||||
`PRIMARY KEY` — The primary key if it [differs from the sorting key](#choosing-a-primary-key-that-differs-from-the-sorting-key). Optional.
|
||||
|
||||
Specifying a sorting key (using `ORDER BY` clause) implicitly specifies a primary key.
|
||||
It is usually not necessary to specify the primary key in addition to the primary key.
|
||||
It is usually not necessary to specify the primary key in addition to the sorting key.
|
||||
|
||||
#### SAMPLE BY
|
||||
|
||||
|
||||
@ -109,6 +109,7 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
|
||||
- `_file` — Resource name of the `URL`. Type: `LowCardinalty(String)`.
|
||||
- `_size` — Size of the resource in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
|
||||
- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
|
||||
- `_headers` - HTTP response headers. Type: `Map(LowCardinality(String), LowCardinality(String))`.
|
||||
|
||||
## Storage Settings {#storage-settings}
|
||||
|
||||
|
||||
@ -58,7 +58,7 @@ Connection: Close
|
||||
Content-Type: text/tab-separated-values; charset=UTF-8
|
||||
X-ClickHouse-Server-Display-Name: clickhouse.ru-central1.internal
|
||||
X-ClickHouse-Query-Id: 5abe861c-239c-467f-b955-8a201abb8b7f
|
||||
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds": "0"}
|
||||
|
||||
1
|
||||
```
|
||||
@ -472,7 +472,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
|
||||
< X-ClickHouse-Format: Template
|
||||
< X-ClickHouse-Timezone: Asia/Shanghai
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
# HELP "Query" "Number of executing queries"
|
||||
# TYPE "Query" counter
|
||||
@ -668,7 +668,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/hi'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
* Connection #0 to host localhost left intact
|
||||
Say Hi!%
|
||||
@ -708,7 +708,7 @@ $ curl -v -H 'XXX:xxx' 'http://localhost:8123/get_config_static_handler'
|
||||
< Content-Type: text/plain; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
* Connection #0 to host localhost left intact
|
||||
<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>%
|
||||
@ -766,7 +766,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_absolute_path_static_handler'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
<html><body>Absolute Path File</body></html>
|
||||
* Connection #0 to host localhost left intact
|
||||
@ -785,7 +785,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_relative_path_static_handler'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
<html><body>Relative Path File</body></html>
|
||||
* Connection #0 to host localhost left intact
|
||||
|
||||
@ -1389,7 +1389,7 @@ DESC format(JSONEachRow, '{"id" : 1, "age" : 25, "name" : "Josh", "status" : nul
|
||||
#### schema_inference_make_columns_nullable
|
||||
|
||||
Controls making inferred types `Nullable` in schema inference for formats without information about nullability.
|
||||
If the setting is enabled, all inferred type will be `Nullable`, if disabled, the inferred type will be `Nullable` only if `input_format_null_as_default` is disabled and the column contains `NULL` in a sample that is parsed during schema inference.
|
||||
If the setting is enabled, all inferred type will be `Nullable`, if disabled, the inferred type will never be `Nullable`, if set to `auto`, the inferred type will be `Nullable` only if the column contains `NULL` in a sample that is parsed during schema inference or file metadata contains information about column nullability.
|
||||
|
||||
Enabled by default.
|
||||
|
||||
@ -1412,15 +1412,13 @@ DESC format(JSONEachRow, $$
|
||||
└─────────┴─────────────────────────┴──────────────┴────────────────────┴─────────┴──────────────────┴────────────────┘
|
||||
```
|
||||
```sql
|
||||
SET schema_inference_make_columns_nullable = 0;
|
||||
SET input_format_null_as_default = 0;
|
||||
SET schema_inference_make_columns_nullable = 'auto';
|
||||
DESC format(JSONEachRow, $$
|
||||
{"id" : 1, "age" : 25, "name" : "Josh", "status" : null, "hobbies" : ["football", "cooking"]}
|
||||
{"id" : 2, "age" : 19, "name" : "Alan", "status" : "married", "hobbies" : ["tennis", "art"]}
|
||||
$$)
|
||||
```
|
||||
```response
|
||||
|
||||
┌─name────┬─type─────────────┬─default_type─┬─default_expression─┬─comment─┬─codec_expression─┬─ttl_expression─┐
|
||||
│ id │ Int64 │ │ │ │ │ │
|
||||
│ age │ Int64 │ │ │ │ │ │
|
||||
@ -1432,7 +1430,6 @@ DESC format(JSONEachRow, $$
|
||||
|
||||
```sql
|
||||
SET schema_inference_make_columns_nullable = 0;
|
||||
SET input_format_null_as_default = 1;
|
||||
DESC format(JSONEachRow, $$
|
||||
{"id" : 1, "age" : 25, "name" : "Josh", "status" : null, "hobbies" : ["football", "cooking"]}
|
||||
{"id" : 2, "age" : 19, "name" : "Alan", "status" : "married", "hobbies" : ["tennis", "art"]}
|
||||
|
||||
@ -155,6 +155,8 @@ SELECT 1 SETTINGS use_query_cache = true, query_cache_tag = 'tag 1';
|
||||
SELECT 1 SETTINGS use_query_cache = true, query_cache_tag = 'tag 2';
|
||||
```
|
||||
|
||||
To remove only entries with tag `tag` from the query cache, you can use statement `SYSTEM DROP QUERY CACHE TAG 'tag'`.
|
||||
|
||||
ClickHouse reads table data in blocks of [max_block_size](settings/settings.md#setting-max_block_size) rows. Due to filtering, aggregation,
|
||||
etc., result blocks are typically much smaller than 'max_block_size' but there are also cases where they are much bigger. Setting
|
||||
[query_cache_squash_partial_results](settings/settings.md#query-cache-squash-partial-results) (enabled by default) controls if result blocks
|
||||
|
||||
@ -171,8 +171,8 @@ If the `schema_inference_hints` is not formated properly, or if there is a typo
|
||||
|
||||
## schema_inference_make_columns_nullable {#schema_inference_make_columns_nullable}
|
||||
|
||||
Controls making inferred types `Nullable` in schema inference for formats without information about nullability.
|
||||
If the setting is enabled, the inferred type will be `Nullable` only if column contains `NULL` in a sample that is parsed during schema inference.
|
||||
Controls making inferred types `Nullable` in schema inference.
|
||||
If the setting is enabled, all inferred type will be `Nullable`, if disabled, the inferred type will never be `Nullable`, if set to `auto`, the inferred type will be `Nullable` only if the column contains `NULL` in a sample that is parsed during schema inference or file metadata contains information about column nullability.
|
||||
|
||||
Default value: `true`.
|
||||
|
||||
|
||||
@ -2855,7 +2855,7 @@ The minimum chunk size in bytes, which each thread will parse in parallel.
|
||||
|
||||
## merge_selecting_sleep_ms {#merge_selecting_sleep_ms}
|
||||
|
||||
Sleep time for merge selecting when no part is selected. A lower setting triggers selecting tasks in `background_schedule_pool` frequently, which results in a large number of requests to ClickHouse Keeper in large-scale clusters.
|
||||
Minimum time to wait before trying to select parts to merge again after no parts were selected. A lower setting triggers selecting tasks in `background_schedule_pool` frequently, which results in a large number of requests to ClickHouse Keeper in large-scale clusters.
|
||||
|
||||
Possible values:
|
||||
|
||||
@ -2863,6 +2863,16 @@ Possible values:
|
||||
|
||||
Default value: `5000`.
|
||||
|
||||
## max_merge_selecting_sleep_ms
|
||||
|
||||
Maximum time to wait before trying to select parts to merge again after no parts were selected. A lower setting triggers selecting tasks in `background_schedule_pool` frequently, which results in a large number of requests to ClickHouse Keeper in large-scale clusters.
|
||||
|
||||
Possible values:
|
||||
|
||||
- Any positive integer.
|
||||
|
||||
Default value: `60000`.
|
||||
|
||||
## parallel_distributed_insert_select {#parallel_distributed_insert_select}
|
||||
|
||||
Enables parallel distributed `INSERT ... SELECT` query.
|
||||
@ -5623,7 +5633,6 @@ Default value: `1GiB`.
|
||||
## use_json_alias_for_old_object_type
|
||||
|
||||
When enabled, `JSON` data type alias will be used to create an old [Object('json')](../../sql-reference/data-types/json.md) type instead of the new [JSON](../../sql-reference/data-types/newjson.md) type.
|
||||
This setting requires server restart to take effect when changed.
|
||||
|
||||
Default value: `false`.
|
||||
|
||||
|
||||
41
docs/en/operations/system-tables/projections.md
Normal file
41
docs/en/operations/system-tables/projections.md
Normal file
@ -0,0 +1,41 @@
|
||||
---
|
||||
slug: /en/operations/system-tables/projections
|
||||
---
|
||||
# projections
|
||||
|
||||
Contains information about existing projections in all the tables.
|
||||
|
||||
Columns:
|
||||
|
||||
- `database` ([String](../../sql-reference/data-types/string.md)) — Database name.
|
||||
- `table` ([String](../../sql-reference/data-types/string.md)) — Table name.
|
||||
- `name` ([String](../../sql-reference/data-types/string.md)) — Projection name.
|
||||
- `type` ([Enum](../../sql-reference/data-types/enum.md)) — Projection type ('Normal' = 0, 'Aggregate' = 1).
|
||||
- `sorting_key` ([Array(String)](../../sql-reference/data-types/array.md)) — Projection sorting key.
|
||||
- `query` ([String](../../sql-reference/data-types/string.md)) — Projection query.
|
||||
|
||||
**Example**
|
||||
|
||||
```sql
|
||||
SELECT * FROM system.projections LIMIT 2 FORMAT Vertical;
|
||||
```
|
||||
|
||||
```text
|
||||
Row 1:
|
||||
──────
|
||||
database: default
|
||||
table: landing
|
||||
name: improved_sorting_key
|
||||
type: Normal
|
||||
sorting_key: ['user_id','date']
|
||||
query: SELECT * ORDER BY user_id, date
|
||||
|
||||
Row 2:
|
||||
──────
|
||||
database: default
|
||||
table: landing
|
||||
name: agg_no_key
|
||||
type: Aggregate
|
||||
sorting_key: []
|
||||
query: SELECT count()
|
||||
```
|
||||
@ -104,7 +104,7 @@ Events that occur at the same second may lay in the sequence in an undefined ord
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `pattern` — Pattern string. See [Pattern syntax](#sequencematch).
|
||||
- `pattern` — Pattern string. See [Pattern syntax](#pattern-syntax).
|
||||
|
||||
**Returned values**
|
||||
|
||||
@ -113,8 +113,7 @@ Events that occur at the same second may lay in the sequence in an undefined ord
|
||||
|
||||
Type: `UInt8`.
|
||||
|
||||
<a name="sequence-function-pattern-syntax"></a>
|
||||
**Pattern syntax**
|
||||
#### Pattern syntax
|
||||
|
||||
- `(?N)` — Matches the condition argument at position `N`. Conditions are numbered in the `[1, 32]` range. For example, `(?1)` matches the argument passed to the `cond1` parameter.
|
||||
|
||||
@ -196,7 +195,7 @@ sequenceCount(pattern)(timestamp, cond1, cond2, ...)
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `pattern` — Pattern string. See [Pattern syntax](#sequencematch).
|
||||
- `pattern` — Pattern string. See [Pattern syntax](#pattern-syntax).
|
||||
|
||||
**Returned values**
|
||||
|
||||
|
||||
@ -70,7 +70,7 @@ SELECT '{"a" : {"b" : 42},"c" : [1, 2, 3], "d" : "Hello, World!"}'::JSON as json
|
||||
└────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
CAST from named `Tuple`, `Map` and `Object('json')` to `JSON` type will be supported later.
|
||||
CAST from `JSON`, named `Tuple`, `Map` and `Object('json')` to `JSON` type will be supported later.
|
||||
|
||||
## Reading JSON paths as subcolumns
|
||||
|
||||
@ -453,8 +453,8 @@ As we can see, after inserting paths `e` and `f.g` the limit was reached and we
|
||||
|
||||
### During merges of data parts in MergeTree table engines
|
||||
|
||||
During merge of several data parts in MergeTree table the `JSON` column in the resulting data part can reach the limit of dynamic paths won't be able to store all paths from source parts as subcolumns.
|
||||
In this case ClickHouse chooses what paths will remain as subcolumns after merge and what types will be stored in the shared data structure. In most cases ClickHouse tries to keep paths that contains
|
||||
During merge of several data parts in MergeTree table the `JSON` column in the resulting data part can reach the limit of dynamic paths and won't be able to store all paths from source parts as subcolumns.
|
||||
In this case ClickHouse chooses what paths will remain as subcolumns after merge and what paths will be stored in the shared data structure. In most cases ClickHouse tries to keep paths that contain
|
||||
the largest number of non-null values and move the rarest paths to the shared data structure, but it depends on the implementation.
|
||||
|
||||
Let's see an example of such merge. First, let's create a table with `JSON` column, set the limit of dynamic paths to `3` and insert values with `5` different paths:
|
||||
|
||||
@ -53,29 +53,28 @@ SELECT now() as current_date_time, current_date_time + INTERVAL 4 DAY
|
||||
└─────────────────────┴───────────────────────────────┘
|
||||
```
|
||||
|
||||
Intervals with different types can’t be combined. You can’t use intervals like `4 DAY 1 HOUR`. Specify intervals in units that are smaller or equal to the smallest unit of the interval, for example, the interval `1 day and an hour` interval can be expressed as `25 HOUR` or `90000 SECOND`.
|
||||
|
||||
You can’t perform arithmetical operations with `Interval`-type values, but you can add intervals of different types consequently to values in `Date` or `DateTime` data types. For example:
|
||||
Also it is possible to use multiple intervals simultaneously:
|
||||
|
||||
``` sql
|
||||
SELECT now() AS current_date_time, current_date_time + INTERVAL 4 DAY + INTERVAL 3 HOUR
|
||||
SELECT now() AS current_date_time, current_date_time + (INTERVAL 4 DAY + INTERVAL 3 HOUR)
|
||||
```
|
||||
|
||||
``` text
|
||||
┌───current_date_time─┬─plus(plus(now(), toIntervalDay(4)), toIntervalHour(3))─┐
|
||||
│ 2019-10-23 11:16:28 │ 2019-10-27 14:16:28 │
|
||||
└─────────────────────┴────────────────────────────────────────────────────────┘
|
||||
┌───current_date_time─┬─plus(current_date_time, plus(toIntervalDay(4), toIntervalHour(3)))─┐
|
||||
│ 2024-08-08 18:31:39 │ 2024-08-12 21:31:39 │
|
||||
└─────────────────────┴────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
The following query causes an exception:
|
||||
And to compare values with different intervals:
|
||||
|
||||
``` sql
|
||||
select now() AS current_date_time, current_date_time + (INTERVAL 4 DAY + INTERVAL 3 HOUR)
|
||||
SELECT toIntervalMicrosecond(3600000000) = toIntervalHour(1);
|
||||
```
|
||||
|
||||
``` text
|
||||
Received exception from server (version 19.14.1):
|
||||
Code: 43. DB::Exception: Received from localhost:9000. DB::Exception: Wrong argument types for function plus: if one argument is Interval, then another must be Date or DateTime..
|
||||
┌─less(toIntervalMicrosecond(179999999), toIntervalMinute(3))─┐
|
||||
│ 1 │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## See Also
|
||||
|
||||
@ -49,7 +49,7 @@ Result:
|
||||
|
||||
## multiIf
|
||||
|
||||
Allows to write the [CASE](../../sql-reference/operators/index.md#operator_case) operator more compactly in the query.
|
||||
Allows to write the [CASE](../../sql-reference/operators/index.md#conditional-expression) operator more compactly in the query.
|
||||
|
||||
**Syntax**
|
||||
|
||||
@ -264,4 +264,4 @@ SELECT clamp(1, 2, 3) result, toTypeName(result) type;
|
||||
┌─result─┬─type────┐
|
||||
│ 2 │ Float64 │
|
||||
└────────┴─────────┘
|
||||
```
|
||||
```
|
||||
|
||||
@ -2019,7 +2019,7 @@ Alias: `dateTrunc`.
|
||||
|
||||
`unit` argument is case-insensitive.
|
||||
|
||||
- `value` — Date and time. [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md).
|
||||
- `value` — Date and time. [Date](../data-types/date.md), [Date32](../data-types/date32.md), [DateTime](../data-types/datetime.md) or [DateTime64](../data-types/datetime64.md).
|
||||
- `timezone` — [Timezone name](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) for the returned value (optional). If not specified, the function uses the timezone of the `value` parameter. [String](../data-types/string.md).
|
||||
|
||||
**Returned value**
|
||||
@ -4287,7 +4287,7 @@ Result:
|
||||
|
||||
## fromModifiedJulianDay
|
||||
|
||||
Converts a [Modified Julian Day](https://en.wikipedia.org/wiki/Julian_day#Variants) number to a [Proleptic Gregorian calendar](https://en.wikipedia.org/wiki/Proleptic_Gregorian_calendar) date in text form `YYYY-MM-DD`. This function supports day number from `-678941` to `2973119` (which represent 0000-01-01 and 9999-12-31 respectively). It raises an exception if the day number is outside of the supported range.
|
||||
Converts a [Modified Julian Day](https://en.wikipedia.org/wiki/Julian_day#Variants) number to a [Proleptic Gregorian calendar](https://en.wikipedia.org/wiki/Proleptic_Gregorian_calendar) date in text form `YYYY-MM-DD`. This function supports day number from `-678941` to `2973483` (which represent 0000-01-01 and 9999-12-31 respectively). It raises an exception if the day number is outside of the supported range.
|
||||
|
||||
**Syntax**
|
||||
|
||||
|
||||
@ -6,7 +6,7 @@ title: "Functions for Working with Geohash"
|
||||
|
||||
## Geohash
|
||||
|
||||
[Geohash](https://en.wikipedia.org/wiki/Geohash) is the geocode system, which subdivides Earth’s surface into buckets of grid shape and encodes each cell into a short string of letters and digits. It is a hierarchical data structure, so the longer is the geohash string, the more precise is the geographic location.
|
||||
[Geohash](https://en.wikipedia.org/wiki/Geohash) is the geocode system, which subdivides Earth’s surface into buckets of grid shape and encodes each cell into a short string of letters and digits. It is a hierarchical data structure, so the longer the geohash string is, the more precise the geographic location will be.
|
||||
|
||||
If you need to manually convert geographic coordinates to geohash strings, you can use [geohash.org](http://geohash.org/).
|
||||
|
||||
@ -14,26 +14,37 @@ If you need to manually convert geographic coordinates to geohash strings, you c
|
||||
|
||||
Encodes latitude and longitude as a [geohash](#geohash)-string.
|
||||
|
||||
**Syntax**
|
||||
|
||||
``` sql
|
||||
geohashEncode(longitude, latitude, [precision])
|
||||
```
|
||||
|
||||
**Input values**
|
||||
|
||||
- longitude - longitude part of the coordinate you want to encode. Floating in range`[-180°, 180°]`
|
||||
- latitude - latitude part of the coordinate you want to encode. Floating in range `[-90°, 90°]`
|
||||
- precision - Optional, length of the resulting encoded string, defaults to `12`. Integer in range `[1, 12]`. Any value less than `1` or greater than `12` is silently converted to `12`.
|
||||
- `longitude` — Longitude part of the coordinate you want to encode. Floating in range`[-180°, 180°]`. [Float](../../data-types/float.md).
|
||||
- `latitude` — Latitude part of the coordinate you want to encode. Floating in range `[-90°, 90°]`. [Float](../../data-types/float.md).
|
||||
- `precision` (optional) — Length of the resulting encoded string. Defaults to `12`. Integer in the range `[1, 12]`. [Int8](../../data-types/int-uint.md).
|
||||
|
||||
:::note
|
||||
- All coordinate parameters must be of the same type: either `Float32` or `Float64`.
|
||||
- For the `precision` parameter, any value less than `1` or greater than `12` is silently converted to `12`.
|
||||
:::
|
||||
|
||||
**Returned values**
|
||||
|
||||
- alphanumeric `String` of encoded coordinate (modified version of the base32-encoding alphabet is used).
|
||||
- Alphanumeric string of the encoded coordinate (modified version of the base32-encoding alphabet is used). [String](../../data-types/string.md).
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
``` sql
|
||||
SELECT geohashEncode(-5.60302734375, 42.593994140625, 0) AS res;
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
``` text
|
||||
┌─res──────────┐
|
||||
│ ezs42d000000 │
|
||||
@ -44,13 +55,19 @@ SELECT geohashEncode(-5.60302734375, 42.593994140625, 0) AS res;
|
||||
|
||||
Decodes any [geohash](#geohash)-encoded string into longitude and latitude.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
geohashDecode(hash_str)
|
||||
```
|
||||
|
||||
**Input values**
|
||||
|
||||
- encoded string - geohash-encoded string.
|
||||
- `hash_str` — Geohash-encoded string.
|
||||
|
||||
**Returned values**
|
||||
|
||||
- (longitude, latitude) - 2-tuple of `Float64` values of longitude and latitude.
|
||||
- Tuple `(longitude, latitude)` of `Float64` values of longitude and latitude. [Tuple](../../data-types/tuple.md)([Float64](../../data-types/float.md))
|
||||
|
||||
**Example**
|
||||
|
||||
|
||||
@ -688,6 +688,40 @@ SELECT kostikConsistentHash(16045690984833335023, 2);
|
||||
└───────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## ripeMD160
|
||||
|
||||
Produces [RIPEMD-160](https://en.wikipedia.org/wiki/RIPEMD) hash value.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
ripeMD160(input)
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `input`: Input string. [String](../data-types/string.md)
|
||||
|
||||
**Returned value**
|
||||
|
||||
- A [UInt256](../data-types/int-uint.md) hash value where the 160-bit RIPEMD-160 hash is stored in the first 20 bytes. The remaining 12 bytes are zero-padded.
|
||||
|
||||
**Example**
|
||||
|
||||
Use the [hex](../functions/encoding-functions.md/#hex) function to represent the result as a hex-encoded string.
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT hex(ripeMD160('The quick brown fox jumps over the lazy dog'));
|
||||
```
|
||||
|
||||
```response
|
||||
┌─hex(ripeMD160('The quick brown fox jumps over the lazy dog'))─┐
|
||||
│ 37F332F68DB77BD9D7EDD4969571AD671CF9DD3B │
|
||||
└───────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## murmurHash2_32, murmurHash2_64
|
||||
|
||||
Produces a [MurmurHash2](https://github.com/aappleby/smhasher) hash value.
|
||||
|
||||
@ -8,6 +8,78 @@ sidebar_label: Replacing in Strings
|
||||
|
||||
[General strings functions](string-functions.md) and [functions for searching in strings](string-search-functions.md) are described separately.
|
||||
|
||||
## overlay
|
||||
|
||||
Replace part of the string `input` with another string `replace`, starting at the 1-based index `offset`.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
overlay(s, replace, offset[, length])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `input`: A string type [String](../data-types/string.md).
|
||||
- `replace`: A string type [String](../data-types/string.md).
|
||||
- `offset`: An integer type [Int](../data-types/int-uint.md). If `offset` is negative, it is counted from the end of the `input` string.
|
||||
- `length`: Optional. An integer type [Int](../data-types/int-uint.md). `length` specifies the length of the snippet within input to be replaced. If `length` is not specified, the number of bytes removed from `input` equals the length of `replace`; otherwise `length` bytes are removed.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- A [String](../data-types/string.md) data type value.
|
||||
|
||||
**Example**
|
||||
|
||||
```sql
|
||||
SELECT overlay('ClickHouse SQL', 'CORE', 12) AS res;
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```text
|
||||
┌─res─────────────┐
|
||||
│ ClickHouse CORE │
|
||||
└─────────────────┘
|
||||
```
|
||||
|
||||
## overlayUTF8
|
||||
|
||||
Replace part of the string `input` with another string `replace`, starting at the 1-based index `offset`.
|
||||
|
||||
Assumes that the string contains valid UTF-8 encoded text. If this assumption is violated, no exception is thrown and the result is undefined.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
overlayUTF8(s, replace, offset[, length])
|
||||
```
|
||||
|
||||
**Parameters**
|
||||
|
||||
- `s`: A string type [String](../data-types/string.md).
|
||||
- `replace`: A string type [String](../data-types/string.md).
|
||||
- `offset`: An integer type [Int](../data-types/int-uint.md). If `offset` is negative, it is counted from the end of the `input` string.
|
||||
- `length`: Optional. An integer type [Int](../data-types/int-uint.md). `length` specifies the length of the snippet within input to be replaced. If `length` is not specified, the number of characters removed from `input` equals the length of `replace`; otherwise `length` characters are removed.
|
||||
|
||||
**Returned value**
|
||||
|
||||
- A [String](../data-types/string.md) data type value.
|
||||
|
||||
**Example**
|
||||
|
||||
```sql
|
||||
SELECT overlayUTF8('ClickHouse是一款OLAP数据库', '开源', 12, 2) AS res;
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```text
|
||||
┌─res────────────────────────┐
|
||||
│ ClickHouse是开源OLAP数据库 │
|
||||
└────────────────────────────┘
|
||||
```
|
||||
|
||||
## replaceOne
|
||||
|
||||
Replaces the first occurrence of the substring `pattern` in `haystack` by the `replacement` string.
|
||||
|
||||
@ -49,6 +49,55 @@ SETTINGS cast_keep_nullable = 1
|
||||
└──────────────────┴─────────────────────┴──────────────────┘
|
||||
```
|
||||
|
||||
## toBool
|
||||
|
||||
Converts an input value to a value of type [`Bool`](../data-types/boolean.md). Throws an exception in case of an error.
|
||||
|
||||
**Syntax**
|
||||
|
||||
```sql
|
||||
toBool(expr)
|
||||
```
|
||||
|
||||
**Arguments**
|
||||
|
||||
- `expr` — Expression returning a number or a string. [Expression](../syntax.md/#syntax-expressions).
|
||||
|
||||
Supported arguments:
|
||||
- Values of type (U)Int8/16/32/64/128/256.
|
||||
- Values of type Float32/64.
|
||||
- Strings `true` or `false` (case-insensitive).
|
||||
|
||||
**Returned value**
|
||||
|
||||
- Returns `true` or `false` based on evaluation of the argument. [Bool](../data-types/boolean.md).
|
||||
|
||||
**Example**
|
||||
|
||||
Query:
|
||||
|
||||
```sql
|
||||
SELECT
|
||||
toBool(toUInt8(1)),
|
||||
toBool(toInt8(-1)),
|
||||
toBool(toFloat32(1.01)),
|
||||
toBool('true'),
|
||||
toBool('false'),
|
||||
toBool('FALSE')
|
||||
FORMAT Vertical
|
||||
```
|
||||
|
||||
Result:
|
||||
|
||||
```response
|
||||
toBool(toUInt8(1)): true
|
||||
toBool(toInt8(-1)): true
|
||||
toBool(toFloat32(1.01)): true
|
||||
toBool('true'): true
|
||||
toBool('false'): false
|
||||
toBool('FALSE'): false
|
||||
```
|
||||
|
||||
## toInt8
|
||||
|
||||
Converts an input value to a value of type [`Int8`](../data-types/int-uint.md). Throws an exception in case of an error.
|
||||
|
||||
@ -8,7 +8,7 @@ title: "CREATE ROW POLICY"
|
||||
Creates a [row policy](../../../guides/sre/user-management/index.md#row-policy-management), i.e. a filter used to determine which rows a user can read from a table.
|
||||
|
||||
:::tip
|
||||
Row policies makes sense only for users with readonly access. If user can modify table or copy partitions between tables, it defeats the restrictions of row policies.
|
||||
Row policies make sense only for users with readonly access. If a user can modify a table or copy partitions between tables, it defeats the restrictions of row policies.
|
||||
:::
|
||||
|
||||
Syntax:
|
||||
@ -24,40 +24,40 @@ CREATE [ROW] POLICY [IF NOT EXISTS | OR REPLACE] policy_name1 [ON CLUSTER cluste
|
||||
|
||||
## USING Clause
|
||||
|
||||
Allows to specify a condition to filter rows. An user will see a row if the condition is calculated to non-zero for the row.
|
||||
Allows specifying a condition to filter rows. A user will see a row if the condition is calculated to non-zero for the row.
|
||||
|
||||
## TO Clause
|
||||
|
||||
In the section `TO` you can provide a list of users and roles this policy should work for. For example, `CREATE ROW POLICY ... TO accountant, john@localhost`.
|
||||
In the `TO` section you can provide a list of users and roles this policy should work for. For example, `CREATE ROW POLICY ... TO accountant, john@localhost`.
|
||||
|
||||
Keyword `ALL` means all the ClickHouse users including current user. Keyword `ALL EXCEPT` allow to exclude some users from the all users list, for example, `CREATE ROW POLICY ... TO ALL EXCEPT accountant, john@localhost`
|
||||
Keyword `ALL` means all the ClickHouse users, including current user. Keyword `ALL EXCEPT` allows excluding some users from the all users list, for example, `CREATE ROW POLICY ... TO ALL EXCEPT accountant, john@localhost`
|
||||
|
||||
:::note
|
||||
If there are no row policies defined for a table then any user can `SELECT` all the row from the table. Defining one or more row policies for the table makes the access to the table depending on the row policies no matter if those row policies are defined for the current user or not. For example, the following policy
|
||||
If there are no row policies defined for a table, then any user can `SELECT` all the rows from the table. Defining one or more row policies for the table makes access to the table dependent on the row policies, no matter if those row policies are defined for the current user or not. For example, the following policy:
|
||||
|
||||
`CREATE ROW POLICY pol1 ON mydb.table1 USING b=1 TO mira, peter`
|
||||
|
||||
forbids the users `mira` and `peter` to see the rows with `b != 1`, and any non-mentioned user (e.g., the user `paul`) will see no rows from `mydb.table1` at all.
|
||||
forbids the users `mira` and `peter` from seeing the rows with `b != 1`, and any non-mentioned user (e.g., the user `paul`) will see no rows from `mydb.table1` at all.
|
||||
|
||||
If that's not desirable it can't be fixed by adding one more row policy, like the following:
|
||||
If that's not desirable, it can be fixed by adding one more row policy, like the following:
|
||||
|
||||
`CREATE ROW POLICY pol2 ON mydb.table1 USING 1 TO ALL EXCEPT mira, peter`
|
||||
:::
|
||||
|
||||
## AS Clause
|
||||
|
||||
It's allowed to have more than one policy enabled on the same table for the same user at the one time. So we need a way to combine the conditions from multiple policies.
|
||||
It's allowed to have more than one policy enabled on the same table for the same user at one time. So we need a way to combine the conditions from multiple policies.
|
||||
|
||||
By default policies are combined using the boolean `OR` operator. For example, the following policies
|
||||
By default, policies are combined using the boolean `OR` operator. For example, the following policies:
|
||||
|
||||
``` sql
|
||||
CREATE ROW POLICY pol1 ON mydb.table1 USING b=1 TO mira, peter
|
||||
CREATE ROW POLICY pol2 ON mydb.table1 USING c=2 TO peter, antonio
|
||||
```
|
||||
|
||||
enables the user `peter` to see rows with either `b=1` or `c=2`.
|
||||
enable the user `peter` to see rows with either `b=1` or `c=2`.
|
||||
|
||||
The `AS` clause specifies how policies should be combined with other policies. Policies can be either permissive or restrictive. By default policies are permissive, which means they are combined using the boolean `OR` operator.
|
||||
The `AS` clause specifies how policies should be combined with other policies. Policies can be either permissive or restrictive. By default, policies are permissive, which means they are combined using the boolean `OR` operator.
|
||||
|
||||
A policy can be defined as restrictive as an alternative. Restrictive policies are combined using the boolean `AND` operator.
|
||||
|
||||
@ -68,25 +68,25 @@ row_is_visible = (one or more of the permissive policies' conditions are non-zer
|
||||
(all of the restrictive policies's conditions are non-zero)
|
||||
```
|
||||
|
||||
For example, the following policies
|
||||
For example, the following policies:
|
||||
|
||||
``` sql
|
||||
CREATE ROW POLICY pol1 ON mydb.table1 USING b=1 TO mira, peter
|
||||
CREATE ROW POLICY pol2 ON mydb.table1 USING c=2 AS RESTRICTIVE TO peter, antonio
|
||||
```
|
||||
|
||||
enables the user `peter` to see rows only if both `b=1` AND `c=2`.
|
||||
enable the user `peter` to see rows only if both `b=1` AND `c=2`.
|
||||
|
||||
Database policies are combined with table policies.
|
||||
|
||||
For example, the following policies
|
||||
For example, the following policies:
|
||||
|
||||
``` sql
|
||||
CREATE ROW POLICY pol1 ON mydb.* USING b=1 TO mira, peter
|
||||
CREATE ROW POLICY pol2 ON mydb.table1 USING c=2 AS RESTRICTIVE TO peter, antonio
|
||||
```
|
||||
|
||||
enables the user `peter` to see table1 rows only if both `b=1` AND `c=2`, although
|
||||
enable the user `peter` to see table1 rows only if both `b=1` AND `c=2`, although
|
||||
any other table in mydb would have only `b=1` policy applied for the user.
|
||||
|
||||
|
||||
|
||||
@ -10,7 +10,7 @@ title: The Lightweight DELETE Statement
|
||||
The lightweight `DELETE` statement removes rows from the table `[db.]table` that match the expression `expr`. It is only available for the *MergeTree table engine family.
|
||||
|
||||
``` sql
|
||||
DELETE FROM [db.]table [ON CLUSTER cluster] WHERE expr;
|
||||
DELETE FROM [db.]table [ON CLUSTER cluster] [IN PARTITION partition_expr] WHERE expr;
|
||||
```
|
||||
|
||||
It is called "lightweight `DELETE`" to contrast it to the [ALTER table DELETE](/en/sql-reference/statements/alter/delete) command, which is a heavyweight process.
|
||||
|
||||
@ -136,7 +136,13 @@ The compiled expression cache is enabled/disabled with the query/user/profile-le
|
||||
|
||||
## DROP QUERY CACHE
|
||||
|
||||
```sql
|
||||
SYSTEM DROP QUERY CACHE;
|
||||
SYSTEM DROP QUERY CACHE TAG '<tag>'
|
||||
````
|
||||
|
||||
Clears the [query cache](../../operations/query-cache.md).
|
||||
If a tag is specified, only query cache entries with the specified tag are deleted.
|
||||
|
||||
## DROP FORMAT SCHEMA CACHE {#system-drop-schema-format}
|
||||
|
||||
|
||||
@ -6,35 +6,37 @@ sidebar_label: iceberg
|
||||
|
||||
# iceberg Table Function
|
||||
|
||||
Provides a read-only table-like interface to Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3.
|
||||
Provides a read-only table-like interface to Apache [Iceberg](https://iceberg.apache.org/) tables in Amazon S3, Azure or locally stored.
|
||||
|
||||
## Syntax
|
||||
|
||||
``` sql
|
||||
iceberg(url [,aws_access_key_id, aws_secret_access_key] [,format] [,structure])
|
||||
icebergS3(url [, NOSIGN | access_key_id, secret_access_key, [session_token]] [,format] [,compression_method])
|
||||
icebergS3(named_collection[, option=value [,..]])
|
||||
|
||||
icebergAzure(connection_string|storage_account_url, container_name, blobpath, [,account_name], [,account_key] [,format] [,compression_method])
|
||||
icebergAzure(named_collection[, option=value [,..]])
|
||||
|
||||
icebergLocal(path_to_table, [,format] [,compression_method])
|
||||
icebergLocal(named_collection[, option=value [,..]])
|
||||
```
|
||||
|
||||
## Arguments
|
||||
|
||||
- `url` — Bucket url with the path to an existing Iceberg table in S3.
|
||||
- `aws_access_key_id`, `aws_secret_access_key` - Long-term credentials for the [AWS](https://aws.amazon.com/) account user. You can use these to authenticate your requests. These parameters are optional. If credentials are not specified, they are used from the ClickHouse configuration. For more information see [Using S3 for Data Storage](/docs/en/engines/table-engines/mergetree-family/mergetree.md/#table_engine-mergetree-s3).
|
||||
- `format` — The [format](/docs/en/interfaces/formats.md/#formats) of the file. By default `Parquet` is used.
|
||||
- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
|
||||
|
||||
Engine parameters can be specified using [Named Collections](/docs/en/operations/named-collections.md).
|
||||
Description of the arguments coincides with description of arguments in table functions `s3`, `azureBlobStorage` and `file` correspondingly.
|
||||
`format` stands for the format of data files in the Iceberg table.
|
||||
|
||||
**Returned value**
|
||||
|
||||
A table with the specified structure for reading data in the specified Iceberg table in S3.
|
||||
A table with the specified structure for reading data in the specified Iceberg table.
|
||||
|
||||
**Example**
|
||||
|
||||
```sql
|
||||
SELECT * FROM iceberg('http://test.s3.amazonaws.com/clickhouse-bucket/test_table', 'test', 'test')
|
||||
SELECT * FROM icebergS3('http://test.s3.amazonaws.com/clickhouse-bucket/test_table', 'test', 'test')
|
||||
```
|
||||
|
||||
:::important
|
||||
ClickHouse currently supports reading v1 (v2 support is coming soon!) of the Iceberg format via the `iceberg` table function and `Iceberg` table engine.
|
||||
ClickHouse currently supports reading v1 and v2 of the Iceberg format via the `icebergS3`, `icebergAzure` and `icebergLocal` table functions and `IcebergS3`, `icebergAzure` ans `icebergLocal` table engines.
|
||||
:::
|
||||
|
||||
## Defining a named collection
|
||||
@ -56,10 +58,14 @@ Here is an example of configuring a named collection for storing the URL and cre
|
||||
```
|
||||
|
||||
```sql
|
||||
SELECT * FROM iceberg(iceberg_conf, filename = 'test_table')
|
||||
DESCRIBE iceberg(iceberg_conf, filename = 'test_table')
|
||||
SELECT * FROM icebergS3(iceberg_conf, filename = 'test_table')
|
||||
DESCRIBE icebergS3(iceberg_conf, filename = 'test_table')
|
||||
```
|
||||
|
||||
**Aliases**
|
||||
|
||||
Table function `iceberg` is an alias to `icebergS3` now.
|
||||
|
||||
**See Also**
|
||||
|
||||
- [Iceberg engine](/docs/en/engines/table-engines/integrations/iceberg.md)
|
||||
|
||||
@ -54,6 +54,7 @@ Character `|` inside patterns is used to specify failover addresses. They are it
|
||||
- `_file` — Resource name of the `URL`. Type: `LowCardinalty(String)`.
|
||||
- `_size` — Size of the resource in bytes. Type: `Nullable(UInt64)`. If the size is unknown, the value is `NULL`.
|
||||
- `_time` — Last modified time of the file. Type: `Nullable(DateTime)`. If the time is unknown, the value is `NULL`.
|
||||
- `_headers` - HTTP response headers. Type: `Map(LowCardinality(String), LowCardinality(String))`.
|
||||
|
||||
## Hive-style partitioning {#hive-style-partitioning}
|
||||
|
||||
|
||||
@ -22,18 +22,26 @@ grep -q sse4_2 /proc/cpuinfo && echo "SSE 4.2 supported" || echo "SSE 4.2 not su
|
||||
|
||||
### Из deb-пакетов {#install-from-deb-packages}
|
||||
|
||||
Яндекс рекомендует использовать официальные скомпилированные `deb`-пакеты для Debian или Ubuntu. Для установки пакетов выполните:
|
||||
Рекомендуется использовать официальные скомпилированные `deb`-пакеты для Debian или Ubuntu. Для установки пакетов выполните:
|
||||
|
||||
``` bash
|
||||
sudo apt-get install -y apt-transport-https ca-certificates dirmngr
|
||||
sudo apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv 8919F6BD2B48D754
|
||||
sudo apt-get install -y apt-transport-https ca-certificates curl gnupg
|
||||
curl -fsSL 'https://packages.clickhouse.com/rpm/lts/repodata/repomd.xml.key' | sudo gpg --dearmor -o /usr/share/keyrings/clickhouse-keyring.gpg
|
||||
|
||||
echo "deb https://packages.clickhouse.com/deb stable main" | sudo tee \
|
||||
echo "deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb stable main" | sudo tee \
|
||||
/etc/apt/sources.list.d/clickhouse.list
|
||||
sudo apt-get update
|
||||
```
|
||||
|
||||
#### Установка ClickHouse server и client
|
||||
|
||||
```bash
|
||||
sudo apt-get install -y clickhouse-server clickhouse-client
|
||||
```
|
||||
|
||||
#### Запуск ClickHouse server
|
||||
|
||||
```bash
|
||||
sudo service clickhouse-server start
|
||||
clickhouse-client # or "clickhouse-client --password" if you've set up a password.
|
||||
```
|
||||
@ -55,7 +63,7 @@ clickhouse-client # or "clickhouse-client --password" if you've set up a passwor
|
||||
:::
|
||||
### Из rpm-пакетов {#from-rpm-packages}
|
||||
|
||||
Команда ClickHouse в Яндексе рекомендует использовать официальные предкомпилированные `rpm`-пакеты для CentOS, RedHat и всех остальных дистрибутивов Linux, основанных на rpm.
|
||||
Команда ClickHouse рекомендует использовать официальные предкомпилированные `rpm`-пакеты для CentOS, RedHat и всех остальных дистрибутивов Linux, основанных на rpm.
|
||||
|
||||
#### Установка официального репозитория
|
||||
|
||||
@ -102,7 +110,7 @@ sudo yum install clickhouse-server clickhouse-client
|
||||
|
||||
### Из tgz-архивов {#from-tgz-archives}
|
||||
|
||||
Команда ClickHouse в Яндексе рекомендует использовать предкомпилированные бинарники из `tgz`-архивов для всех дистрибутивов, где невозможна установка `deb`- и `rpm`- пакетов.
|
||||
Команда ClickHouse рекомендует использовать предкомпилированные бинарники из `tgz`-архивов для всех дистрибутивов, где невозможна установка `deb`- и `rpm`- пакетов.
|
||||
|
||||
Интересующую версию архивов можно скачать вручную с помощью `curl` или `wget` из репозитория https://packages.clickhouse.com/tgz/.
|
||||
После этого архивы нужно распаковать и воспользоваться скриптами установки. Пример установки самой свежей версии:
|
||||
|
||||
@ -50,7 +50,7 @@ Connection: Close
|
||||
Content-Type: text/tab-separated-values; charset=UTF-8
|
||||
X-ClickHouse-Server-Display-Name: clickhouse.ru-central1.internal
|
||||
X-ClickHouse-Query-Id: 5abe861c-239c-467f-b955-8a201abb8b7f
|
||||
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
|
||||
1
|
||||
```
|
||||
@ -367,7 +367,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
|
||||
< X-ClickHouse-Format: Template
|
||||
< X-ClickHouse-Timezone: Asia/Shanghai
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0", "elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
# HELP "Query" "Number of executing queries"
|
||||
# TYPE "Query" counter
|
||||
@ -601,7 +601,7 @@ $ curl -v -H 'XXX:xxx' 'http://localhost:8123/get_config_static_handler'
|
||||
< Content-Type: text/plain; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
* Connection #0 to host localhost left intact
|
||||
<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>%
|
||||
@ -659,7 +659,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_absolute_path_static_handler'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
<html><body>Absolute Path File</body></html>
|
||||
* Connection #0 to host localhost left intact
|
||||
@ -678,7 +678,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_relative_path_static_handler'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
<html><body>Relative Path File</body></html>
|
||||
* Connection #0 to host localhost left intact
|
||||
|
||||
@ -54,29 +54,28 @@ SELECT now() as current_date_time, current_date_time + INTERVAL 4 DAY
|
||||
└─────────────────────┴───────────────────────────────┘
|
||||
```
|
||||
|
||||
Нельзя объединять интервалы различных типов. Нельзя использовать интервалы вида `4 DAY 1 HOUR`. Вместо этого выражайте интервал в единицах меньших или равных минимальной единице интервала, например, интервал «1 день и 1 час» можно выразить как `25 HOUR` или `90000 SECOND`.
|
||||
|
||||
Арифметические операции со значениями типов `Interval` не доступны, однако можно последовательно добавлять различные интервалы к значениям типов `Date` и `DateTime`. Например:
|
||||
Также можно использовать различные типы интервалов одновременно:
|
||||
|
||||
``` sql
|
||||
SELECT now() AS current_date_time, current_date_time + INTERVAL 4 DAY + INTERVAL 3 HOUR
|
||||
SELECT now() AS current_date_time, current_date_time + (INTERVAL 4 DAY + INTERVAL 3 HOUR)
|
||||
```
|
||||
|
||||
``` text
|
||||
┌───current_date_time─┬─plus(plus(now(), toIntervalDay(4)), toIntervalHour(3))─┐
|
||||
│ 2019-10-23 11:16:28 │ 2019-10-27 14:16:28 │
|
||||
└─────────────────────┴────────────────────────────────────────────────────────┘
|
||||
┌───current_date_time─┬─plus(current_date_time, plus(toIntervalDay(4), toIntervalHour(3)))─┐
|
||||
│ 2024-08-08 18:31:39 │ 2024-08-12 21:31:39 │
|
||||
└─────────────────────┴────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
Следующий запрос приведёт к генерированию исключения:
|
||||
И сравнивать значения из разными интервалами:
|
||||
|
||||
``` sql
|
||||
select now() AS current_date_time, current_date_time + (INTERVAL 4 DAY + INTERVAL 3 HOUR)
|
||||
SELECT toIntervalMicrosecond(3600000000) = toIntervalHour(1);
|
||||
```
|
||||
|
||||
``` text
|
||||
Received exception from server (version 19.14.1):
|
||||
Code: 43. DB::Exception: Received from localhost:9000. DB::Exception: Wrong argument types for function plus: if one argument is Interval, then another must be Date or DateTime..
|
||||
┌─less(toIntervalMicrosecond(179999999), toIntervalMinute(3))─┐
|
||||
│ 1 │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Смотрите также {#smotrite-takzhe}
|
||||
|
||||
@ -124,6 +124,40 @@ SELECT hex(sipHash128('foo', '\x01', 3));
|
||||
└──────────────────────────────────┘
|
||||
```
|
||||
|
||||
## ripeMD160
|
||||
|
||||
Генерирует [RIPEMD-160](https://en.wikipedia.org/wiki/RIPEMD) хеш строки.
|
||||
|
||||
**Синтаксис**
|
||||
|
||||
```sql
|
||||
ripeMD160(input)
|
||||
```
|
||||
|
||||
**Аргументы**
|
||||
|
||||
- `input`: Строка [String](../data-types/string.md)
|
||||
|
||||
**Возвращаемое значение**
|
||||
|
||||
- [UInt256](../data-types/int-uint.md), где 160-битный хеш RIPEMD-160 хранится в первых 20 байтах. Оставшиеся 12 байт заполняются нулями.
|
||||
|
||||
**Пример**
|
||||
|
||||
Используйте функцию [hex](../functions/encoding-functions.md#hex) для представления результата в виде строки с шестнадцатеричной кодировкой
|
||||
|
||||
Запрос:
|
||||
|
||||
```sql
|
||||
SELECT hex(ripeMD160('The quick brown fox jumps over the lazy dog'));
|
||||
```
|
||||
Результат:
|
||||
```response
|
||||
┌─hex(ripeMD160('The quick brown fox jumps over the lazy dog'))─┐
|
||||
│ 37F332F68DB77BD9D7EDD4969571AD671CF9DD3B │
|
||||
└───────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## cityHash64 {#cityhash64}
|
||||
|
||||
Генерирует 64-х битное значение [CityHash](https://github.com/google/cityhash).
|
||||
|
||||
@ -280,7 +280,7 @@ SYSTEM START REPLICATION QUEUES [ON CLUSTER cluster_name] [[db.]replicated_merge
|
||||
Ждет когда таблица семейства `ReplicatedMergeTree` будет синхронизирована с другими репликами в кластере, но не более `receive_timeout` секунд:
|
||||
|
||||
``` sql
|
||||
SYSTEM SYNC REPLICA [db.]replicated_merge_tree_family_table_name [STRICT | LIGHTWEIGHT [FROM 'srcReplica1'[, 'srcReplica2'[, ...]]] | PULL]
|
||||
SYSTEM SYNC REPLICA [ON CLUSTER cluster_name] [db.]replicated_merge_tree_family_table_name [STRICT | LIGHTWEIGHT [FROM 'srcReplica1'[, 'srcReplica2'[, ...]]] | PULL]
|
||||
```
|
||||
|
||||
После выполнения этого запроса таблица `[db.]replicated_merge_tree_family_table_name` загружает команды из общего реплицированного лога в свою собственную очередь репликации. Затем запрос ждет, пока реплика не обработает все загруженные команды. Поддерживаются следующие модификаторы:
|
||||
|
||||
@ -53,7 +53,7 @@ Connection: Close
|
||||
Content-Type: text/tab-separated-values; charset=UTF-8
|
||||
X-ClickHouse-Server-Display-Name: clickhouse.ru-central1.internal
|
||||
X-ClickHouse-Query-Id: 5abe861c-239c-467f-b955-8a201abb8b7f
|
||||
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","real_time_microseconds":"0"}
|
||||
|
||||
1
|
||||
```
|
||||
@ -363,7 +363,7 @@ $ curl -v 'http://localhost:8123/predefined_query'
|
||||
< X-ClickHouse-Format: Template
|
||||
< X-ClickHouse-Timezone: Asia/Shanghai
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
# HELP "Query" "Number of executing queries"
|
||||
# TYPE "Query" counter
|
||||
@ -524,7 +524,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/hi'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334", "real_time_microseconds":"0"}
|
||||
<
|
||||
* Connection #0 to host localhost left intact
|
||||
Say Hi!%
|
||||
@ -564,7 +564,7 @@ $ curl -v -H 'XXX:xxx' 'http://localhost:8123/get_config_static_handler'
|
||||
< Content-Type: text/plain; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","real_time_microseconds":"0"}
|
||||
<
|
||||
* Connection #0 to host localhost left intact
|
||||
<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>%
|
||||
@ -616,7 +616,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_absolute_path_static_handler'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","real_time_microseconds":"0"}
|
||||
<
|
||||
<html><body>Absolute Path File</body></html>
|
||||
* Connection #0 to host localhost left intact
|
||||
@ -635,7 +635,7 @@ $ curl -vv -H 'XXX:xxx' 'http://localhost:8123/get_relative_path_static_handler'
|
||||
< Content-Type: text/html; charset=UTF-8
|
||||
< Transfer-Encoding: chunked
|
||||
< Keep-Alive: timeout=10
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334"}
|
||||
< X-ClickHouse-Summary: {"read_rows":"0","read_bytes":"0","written_rows":"0","written_bytes":"0","total_rows_to_read":"0","elapsed_ns":"662334","real_time_microseconds":"0"}
|
||||
<
|
||||
<html><body>Relative Path File</body></html>
|
||||
* Connection #0 to host localhost left intact
|
||||
|
||||
@ -1157,7 +1157,7 @@ SELECT toModifiedJulianDayOrNull('2020-01-01');
|
||||
|
||||
## fromModifiedJulianDay {#frommodifiedjulianday}
|
||||
|
||||
将 [Modified Julian Day](https://en.wikipedia.org/wiki/Julian_day#Variants) 数字转换为 `YYYY-MM-DD` 文本格式的 [Proleptic Gregorian calendar](https://en.wikipedia.org/wiki/Proleptic_Gregorian_calendar) 日期。该函数支持从 `-678941` 到 `2973119` 的天数（分别代表 0000-01-01 和 9999-12-31）。如果天数超出支持范围，则会引发异常。
|
||||
将 [Modified Julian Day](https://en.wikipedia.org/wiki/Julian_day#Variants) 数字转换为 `YYYY-MM-DD` 文本格式的 [Proleptic Gregorian calendar](https://en.wikipedia.org/wiki/Proleptic_Gregorian_calendar) 日期。该函数支持从 `-678941` 到 `2973483` 的天数（分别代表 0000-01-01 和 9999-12-31）。如果天数超出支持范围，则会引发异常。
|
||||
|
||||
**语法**
|
||||
|
||||
|
||||
@ -677,4 +677,122 @@ void GetAllChildrenNumberCommand::execute(const ASTKeeperQuery * query, KeeperCl
|
||||
std::cout << totalNumChildren << "\n";
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
|
||||
class CPMVOperation
|
||||
{
|
||||
constexpr static UInt64 kTryLimit = 1000;
|
||||
|
||||
public:
|
||||
CPMVOperation(String src_, String dest_, bool remove_src_, KeeperClient * client_)
|
||||
: src(std::move(src_)), dest(std::move(dest_)), remove_src(remove_src_), client(client_)
|
||||
{
|
||||
}
|
||||
|
||||
bool isTryLimitReached() const { return failed_tries_count >= kTryLimit; }
|
||||
|
||||
bool isCompleted() const { return is_completed; }
|
||||
|
||||
void perform()
|
||||
{
|
||||
Coordination::Stat src_stat;
|
||||
String data = client->zookeeper->get(src, &src_stat);
|
||||
|
||||
Coordination::Requests ops{
|
||||
zkutil::makeCheckRequest(src, src_stat.version),
|
||||
zkutil::makeCreateRequest(dest, data, zkutil::CreateMode::Persistent), // Do we need to copy ACLs here?
|
||||
};
|
||||
|
||||
if (remove_src)
|
||||
ops.push_back(zkutil::makeRemoveRequest(src, src_stat.version));
|
||||
|
||||
Coordination::Responses responses;
|
||||
auto code = client->zookeeper->tryMulti(ops, responses);
|
||||
|
||||
switch (code)
|
||||
{
|
||||
case Coordination::Error::ZOK: {
|
||||
is_completed = true;
|
||||
return;
|
||||
}
|
||||
case Coordination::Error::ZBADVERSION: {
|
||||
++failed_tries_count;
|
||||
|
||||
if (isTryLimitReached())
|
||||
zkutil::KeeperMultiException::check(code, ops, responses);
|
||||
|
||||
return;
|
||||
}
|
||||
default:
|
||||
zkutil::KeeperMultiException::check(code, ops, responses);
|
||||
}
|
||||
|
||||
throw Exception(ErrorCodes::LOGICAL_ERROR, "Unreachable");
|
||||
}
|
||||
|
||||
private:
|
||||
String src;
|
||||
String dest;
|
||||
bool remove_src = false;
|
||||
KeeperClient * client = nullptr;
|
||||
|
||||
bool is_completed = false;
|
||||
uint64_t failed_tries_count = 0;
|
||||
};
|
||||
|
||||
}
|
||||
|
||||
bool CPCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, [[maybe_unused]] Expected & expected) const
|
||||
{
|
||||
String src_path;
|
||||
if (!parseKeeperPath(pos, expected, src_path))
|
||||
return false;
|
||||
node->args.push_back(std::move(src_path));
|
||||
|
||||
String to_path;
|
||||
if (!parseKeeperPath(pos, expected, to_path))
|
||||
return false;
|
||||
node->args.push_back(std::move(to_path));
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
void CPCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) const
|
||||
{
|
||||
auto src = client->getAbsolutePath(query->args[0].safeGet<String>());
|
||||
auto dest = client->getAbsolutePath(query->args[1].safeGet<String>());
|
||||
|
||||
CPMVOperation operation(std::move(src), std::move(dest), /*remove_src_=*/false, /*client_=*/client);
|
||||
|
||||
while (!operation.isTryLimitReached() && !operation.isCompleted())
|
||||
operation.perform();
|
||||
}
|
||||
|
||||
bool MVCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
|
||||
{
|
||||
String src_path;
|
||||
if (!parseKeeperPath(pos, expected, src_path))
|
||||
return false;
|
||||
node->args.push_back(std::move(src_path));
|
||||
|
||||
String to_path;
|
||||
if (!parseKeeperPath(pos, expected, to_path))
|
||||
return false;
|
||||
node->args.push_back(std::move(to_path));
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
void MVCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) const
|
||||
{
|
||||
auto src = client->getAbsolutePath(query->args[0].safeGet<String>());
|
||||
auto dest = client->getAbsolutePath(query->args[1].safeGet<String>());
|
||||
|
||||
CPMVOperation operation(std::move(src), std::move(dest), /*remove_src_=*/true, /*client_=*/client);
|
||||
|
||||
while (!operation.isTryLimitReached() && !operation.isCompleted())
|
||||
operation.perform();
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@ -266,4 +266,32 @@ class GetAllChildrenNumberCommand : public IKeeperClientCommand
|
||||
}
|
||||
};
|
||||
|
||||
class CPCommand : public IKeeperClientCommand
|
||||
{
|
||||
String getName() const override { return "cp"; }
|
||||
|
||||
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 "{} <src> <dest> -- Copies 'src' node to 'dest' path.";
|
||||
}
|
||||
};
|
||||
|
||||
class MVCommand : public IKeeperClientCommand
|
||||
{
|
||||
String getName() const override { return "mv"; }
|
||||
|
||||
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 "{} <src> <dest> -- Moves 'src' node to the 'dest' path.";
|
||||
}
|
||||
};
|
||||
|
||||
}
|
||||
|
||||
@ -212,6 +212,8 @@ void KeeperClient::initialize(Poco::Util::Application & /* self */)
|
||||
std::make_shared<FourLetterWordCommand>(),
|
||||
std::make_shared<GetDirectChildrenNumberCommand>(),
|
||||
std::make_shared<GetAllChildrenNumberCommand>(),
|
||||
std::make_shared<CPCommand>(),
|
||||
std::make_shared<MVCommand>(),
|
||||
});
|
||||
|
||||
String home_path;
|
||||
|
||||
@ -978,6 +978,7 @@ try
|
||||
/** Explicitly destroy Context. It is more convenient than in destructor of Server, because logger is still available.
|
||||
* At this moment, no one could own shared part of Context.
|
||||
*/
|
||||
global_context->resetSharedContext();
|
||||
global_context.reset();
|
||||
shared_context.reset();
|
||||
LOG_DEBUG(log, "Destroyed global context.");
|
||||
|
||||
@ -120,7 +120,7 @@ void RoleCache::collectEnabledRoles(EnabledRoles & enabled_roles, SubscriptionsO
|
||||
SubscriptionsOnRoles new_subscriptions_on_roles;
|
||||
new_subscriptions_on_roles.reserve(subscriptions_on_roles.size());
|
||||
|
||||
auto get_role_function = [this, &subscriptions_on_roles](const UUID & id) TSA_NO_THREAD_SAFETY_ANALYSIS { return getRole(id, subscriptions_on_roles); };
|
||||
auto get_role_function = [this, &new_subscriptions_on_roles](const UUID & id) TSA_NO_THREAD_SAFETY_ANALYSIS { return getRole(id, new_subscriptions_on_roles); };
|
||||
|
||||
for (const auto & current_role : enabled_roles.params.current_roles)
|
||||
collectRoles(*new_info, skip_ids, get_role_function, current_role, true, false);
|
||||
|
||||
@ -68,7 +68,10 @@ public:
|
||||
if (data().isEqualTo(to.data()))
|
||||
counter += to.counter;
|
||||
else if (!data().has() || counter < to.counter)
|
||||
{
|
||||
data().set(to.data(), arena);
|
||||
counter = to.counter - counter;
|
||||
}
|
||||
else
|
||||
counter -= to.counter;
|
||||
}
|
||||
|
||||
@ -209,7 +209,7 @@ std::map<std::pair<TypeIndex, String>, NodeToSubcolumnTransformer> node_transfor
|
||||
},
|
||||
};
|
||||
|
||||
std::tuple<FunctionNode *, ColumnNode *, TableNode *> getTypedNodesForOptimization(const QueryTreeNodePtr & node)
|
||||
std::tuple<FunctionNode *, ColumnNode *, TableNode *> getTypedNodesForOptimization(const QueryTreeNodePtr & node, const ContextPtr & context)
|
||||
{
|
||||
auto * function_node = node->as<FunctionNode>();
|
||||
if (!function_node)
|
||||
@ -232,6 +232,12 @@ std::tuple<FunctionNode *, ColumnNode *, TableNode *> getTypedNodesForOptimizati
|
||||
const auto & storage_snapshot = table_node->getStorageSnapshot();
|
||||
auto column = first_argument_column_node->getColumn();
|
||||
|
||||
/// If view source is set we cannot optimize because it doesn't support moving functions to subcolumns.
|
||||
/// The storage is replaced to the view source but it happens only after building a query tree and applying passes.
|
||||
auto view_source = context->getViewSource();
|
||||
if (view_source && view_source->getStorageID().getFullNameNotQuoted() == storage->getStorageID().getFullNameNotQuoted())
|
||||
return {};
|
||||
|
||||
if (!storage->supportsOptimizationToSubcolumns() || storage->isVirtualColumn(column.name, storage_snapshot->metadata))
|
||||
return {};
|
||||
|
||||
@ -266,7 +272,7 @@ public:
|
||||
return;
|
||||
}
|
||||
|
||||
auto [function_node, first_argument_node, table_node] = getTypedNodesForOptimization(node);
|
||||
auto [function_node, first_argument_node, table_node] = getTypedNodesForOptimization(node, getContext());
|
||||
if (function_node && first_argument_node && table_node)
|
||||
{
|
||||
enterImpl(*function_node, *first_argument_node, *table_node);
|
||||
@ -416,7 +422,7 @@ public:
|
||||
if (!getSettings().optimize_functions_to_subcolumns)
|
||||
return;
|
||||
|
||||
auto [function_node, first_argument_column_node, table_node] = getTypedNodesForOptimization(node);
|
||||
auto [function_node, first_argument_column_node, table_node] = getTypedNodesForOptimization(node, getContext());
|
||||
if (!function_node || !first_argument_column_node || !table_node)
|
||||
return;
|
||||
|
||||
|
||||
@ -692,7 +692,7 @@ QueryTreeNodePtr IdentifierResolver::tryResolveIdentifierFromStorage(
|
||||
result_column_node = it->second;
|
||||
}
|
||||
/// Check if it's a dynamic subcolumn
|
||||
else
|
||||
else if (table_expression_data.supports_subcolumns)
|
||||
{
|
||||
auto [column_name, dynamic_subcolumn_name] = Nested::splitName(identifier_full_name);
|
||||
auto jt = table_expression_data.column_name_to_column_node.find(column_name);
|
||||
|
||||
@ -4379,7 +4379,10 @@ void QueryAnalyzer::initializeTableExpressionData(const QueryTreeNodePtr & table
|
||||
|
||||
auto get_column_options = GetColumnsOptions(GetColumnsOptions::All).withExtendedObjects().withVirtuals();
|
||||
if (storage_snapshot->storage.supportsSubcolumns())
|
||||
{
|
||||
get_column_options.withSubcolumns();
|
||||
table_expression_data.supports_subcolumns = true;
|
||||
}
|
||||
|
||||
auto column_names_and_types = storage_snapshot->getColumns(get_column_options);
|
||||
table_expression_data.column_names_and_types = NamesAndTypes(column_names_and_types.begin(), column_names_and_types.end());
|
||||
|
||||
@ -36,6 +36,7 @@ struct AnalysisTableExpressionData
|
||||
std::string database_name;
|
||||
std::string table_name;
|
||||
bool should_qualify_columns = true;
|
||||
bool supports_subcolumns = false;
|
||||
NamesAndTypes column_names_and_types;
|
||||
ColumnNameToColumnNodeMap column_name_to_column_node;
|
||||
std::unordered_set<std::string> subcolumn_names; /// Subset columns that are subcolumns of other columns
|
||||
|
||||
@ -100,6 +100,7 @@ protected:
|
||||
auto buf = BuilderRWBufferFromHTTP(getPingURI())
|
||||
.withConnectionGroup(HTTPConnectionGroupType::STORAGE)
|
||||
.withTimeouts(getHTTPTimeouts())
|
||||
.withSettings(getContext()->getReadSettings())
|
||||
.create(credentials);
|
||||
|
||||
return checkString(PING_OK_ANSWER, *buf);
|
||||
@ -206,6 +207,7 @@ protected:
|
||||
.withConnectionGroup(HTTPConnectionGroupType::STORAGE)
|
||||
.withMethod(Poco::Net::HTTPRequest::HTTP_POST)
|
||||
.withTimeouts(getHTTPTimeouts())
|
||||
.withSettings(getContext()->getReadSettings())
|
||||
.create(credentials);
|
||||
|
||||
bool res = false;
|
||||
@ -232,6 +234,7 @@ protected:
|
||||
.withConnectionGroup(HTTPConnectionGroupType::STORAGE)
|
||||
.withMethod(Poco::Net::HTTPRequest::HTTP_POST)
|
||||
.withTimeouts(getHTTPTimeouts())
|
||||
.withSettings(getContext()->getReadSettings())
|
||||
.create(credentials);
|
||||
|
||||
std::string character;
|
||||
|
||||
@ -111,6 +111,7 @@ add_headers_and_sources(dbms Storages/ObjectStorage)
|
||||
add_headers_and_sources(dbms Storages/ObjectStorage/Azure)
|
||||
add_headers_and_sources(dbms Storages/ObjectStorage/S3)
|
||||
add_headers_and_sources(dbms Storages/ObjectStorage/HDFS)
|
||||
add_headers_and_sources(dbms Storages/ObjectStorage/Local)
|
||||
add_headers_and_sources(dbms Storages/ObjectStorage/DataLakes)
|
||||
add_headers_and_sources(dbms Common/NamedCollections)
|
||||
|
||||
|
||||
@ -34,6 +34,7 @@
|
||||
#include <Parsers/Access/ASTCreateUserQuery.h>
|
||||
#include <Parsers/Access/ASTAuthenticationData.h>
|
||||
#include <Parsers/ASTDropQuery.h>
|
||||
#include <Parsers/ASTExplainQuery.h>
|
||||
#include <Parsers/ASTSelectQuery.h>
|
||||
#include <Parsers/ASTSetQuery.h>
|
||||
#include <Parsers/ASTUseQuery.h>
|
||||
@ -2111,6 +2112,15 @@ MultiQueryProcessingStage ClientBase::analyzeMultiQueryText(
|
||||
// - Other formats (e.g. FORMAT CSV) are arbitrarily more complex and tricky to parse. For example, we may be unable to distinguish if the semicolon
|
||||
// is part of the data or ends the statement. In this case, we simply assume that the end of the INSERT statement is determined by \n\n (two newlines).
|
||||
auto * insert_ast = parsed_query->as<ASTInsertQuery>();
|
||||
// We also consider the INSERT query in EXPLAIN queries (same as normal INSERT queries)
|
||||
if (!insert_ast)
|
||||
{
|
||||
auto * explain_ast = parsed_query->as<ASTExplainQuery>();
|
||||
if (explain_ast && explain_ast->getExplainedQuery())
|
||||
{
|
||||
insert_ast = explain_ast->getExplainedQuery()->as<ASTInsertQuery>();
|
||||
}
|
||||
}
|
||||
const char * query_to_execute_end = this_query_end;
|
||||
if (insert_ast && insert_ast->data)
|
||||
{
|
||||
|
||||
@ -145,6 +145,9 @@ void Connection::connect(const ConnectionTimeouts & timeouts)
|
||||
/// work we need to pass host name separately. It will be send into TLS Hello packet to let
|
||||
/// the server know which host we want to talk with (single IP can process requests for multiple hosts using SNI).
|
||||
static_cast<Poco::Net::SecureStreamSocket*>(socket.get())->setPeerHostName(host);
|
||||
/// we want to postpone SSL handshake until first read or write operation
|
||||
/// so any errors during negotiation would be properly processed
|
||||
static_cast<Poco::Net::SecureStreamSocket*>(socket.get())->setLazyHandshake(true);
|
||||
#else
|
||||
throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "tcp_secure protocol is disabled because poco library was built without NetSSL support.");
|
||||
#endif
|
||||
|
||||
@ -299,13 +299,14 @@ ReplxxLineReader::ReplxxLineReader(
|
||||
Patterns delimiters_,
|
||||
const char word_break_characters_[],
|
||||
replxx::Replxx::highlighter_callback_t highlighter_,
|
||||
[[ maybe_unused ]] std::istream & input_stream_,
|
||||
[[ maybe_unused ]] std::ostream & output_stream_,
|
||||
[[ maybe_unused ]] int in_fd_,
|
||||
[[ maybe_unused ]] int out_fd_,
|
||||
[[ maybe_unused ]] int err_fd_
|
||||
std::istream & input_stream_,
|
||||
std::ostream & output_stream_,
|
||||
int in_fd_,
|
||||
int out_fd_,
|
||||
int err_fd_
|
||||
)
|
||||
: LineReader(history_file_path_, multiline_, std::move(extenders_), std::move(delimiters_), input_stream_, output_stream_, in_fd_)
|
||||
, rx(input_stream_, output_stream_, in_fd_, out_fd_, err_fd_)
|
||||
, highlighter(std::move(highlighter_))
|
||||
, word_break_characters(word_break_characters_)
|
||||
, editor(getEditor())
|
||||
@ -516,7 +517,7 @@ void ReplxxLineReader::addToHistory(const String & line)
|
||||
rx.history_add(line);
|
||||
|
||||
// flush changes to the disk
|
||||
if (!rx.history_save(history_file_path))
|
||||
if (history_file_fd >= 0 && !rx.history_save(history_file_path))
|
||||
rx.print("Saving history failed: %s\n", errnoToString().c_str());
|
||||
|
||||
if (history_file_fd >= 0 && locked && 0 != flock(history_file_fd, LOCK_UN))
|
||||
|
||||
@ -300,7 +300,7 @@ void ColumnDynamic::get(size_t n, Field & res) const
|
||||
auto value_data = shared_variant.getDataAt(variant_col.offsetAt(n));
|
||||
ReadBufferFromMemory buf(value_data.data, value_data.size);
|
||||
auto type = decodeDataType(buf);
|
||||
getVariantSerialization(type)->deserializeBinary(res, buf, getFormatSettings());
|
||||
type->getDefaultSerialization()->deserializeBinary(res, buf, getFormatSettings());
|
||||
}
|
||||
|
||||
|
||||
@ -736,8 +736,7 @@ StringRef ColumnDynamic::serializeValueIntoArena(size_t n, Arena & arena, const
|
||||
{
|
||||
const auto & variant_type = assert_cast<const DataTypeVariant &>(*variant_info.variant_type).getVariant(discr);
|
||||
encodeDataType(variant_type, buf);
|
||||
getVariantSerialization(variant_type, variant_info.variant_names[discr])
|
||||
->serializeBinary(variant_col.getVariantByGlobalDiscriminator(discr), variant_col.offsetAt(n), buf, getFormatSettings());
|
||||
variant_type->getDefaultSerialization()->serializeBinary(variant_col.getVariantByGlobalDiscriminator(discr), variant_col.offsetAt(n), buf, getFormatSettings());
|
||||
type_and_value = buf.str();
|
||||
}
|
||||
|
||||
@ -870,7 +869,7 @@ int ColumnDynamic::doCompareAt(size_t n, size_t m, const IColumn & rhs, int nan_
|
||||
/// We have both values serialized in binary format, so we need to
|
||||
/// create temporary column, insert both values into it and compare.
|
||||
auto tmp_column = left_data_type->createColumn();
|
||||
const auto & serialization = getVariantSerialization(left_data_type, left_data_type_name);
|
||||
const auto & serialization = left_data_type->getDefaultSerialization();
|
||||
serialization->deserializeBinary(*tmp_column, buf_left, getFormatSettings());
|
||||
serialization->deserializeBinary(*tmp_column, buf_right, getFormatSettings());
|
||||
return tmp_column->compareAt(0, 1, *tmp_column, nan_direction_hint);
|
||||
@ -892,7 +891,7 @@ int ColumnDynamic::doCompareAt(size_t n, size_t m, const IColumn & rhs, int nan_
|
||||
/// We have left value serialized in binary format, we need to
|
||||
/// create temporary column, insert the value into it and compare.
|
||||
auto tmp_column = left_data_type->createColumn();
|
||||
getVariantSerialization(left_data_type, left_data_type_name)->deserializeBinary(*tmp_column, buf_left, getFormatSettings());
|
||||
left_data_type->getDefaultSerialization()->deserializeBinary(*tmp_column, buf_left, getFormatSettings());
|
||||
return tmp_column->compareAt(0, right_variant.offsetAt(m), right_variant.getVariantByGlobalDiscriminator(right_discr), nan_direction_hint);
|
||||
}
|
||||
/// Check if only right value is in shared data.
|
||||
@ -912,7 +911,7 @@ int ColumnDynamic::doCompareAt(size_t n, size_t m, const IColumn & rhs, int nan_
|
||||
/// We have right value serialized in binary format, we need to
|
||||
/// create temporary column, insert the value into it and compare.
|
||||
auto tmp_column = right_data_type->createColumn();
|
||||
getVariantSerialization(right_data_type, right_data_type_name)->deserializeBinary(*tmp_column, buf_right, getFormatSettings());
|
||||
right_data_type->getDefaultSerialization()->deserializeBinary(*tmp_column, buf_right, getFormatSettings());
|
||||
return left_variant.getVariantByGlobalDiscriminator(left_discr).compareAt(left_variant.offsetAt(n), 0, *tmp_column, nan_direction_hint);
|
||||
}
|
||||
/// Otherwise both values are regular variants.
|
||||
@ -1181,13 +1180,14 @@ void ColumnDynamic::takeDynamicStructureFromSourceColumns(const Columns & source
|
||||
/// Check if the number of all dynamic types exceeds the limit.
|
||||
if (!canAddNewVariants(0, all_variants.size()))
|
||||
{
|
||||
/// Create list of variants with their sizes and sort it.
|
||||
std::vector<std::pair<size_t, DataTypePtr>> variants_with_sizes;
|
||||
/// Create a list of variants with their sizes and names and then sort it.
|
||||
std::vector<std::tuple<size_t, String, DataTypePtr>> variants_with_sizes;
|
||||
variants_with_sizes.reserve(all_variants.size());
|
||||
for (const auto & variant : all_variants)
|
||||
{
|
||||
if (variant->getName() != getSharedVariantTypeName())
|
||||
variants_with_sizes.emplace_back(total_sizes[variant->getName()], variant);
|
||||
auto variant_name = variant->getName();
|
||||
if (variant_name != getSharedVariantTypeName())
|
||||
variants_with_sizes.emplace_back(total_sizes[variant_name], variant_name, variant);
|
||||
}
|
||||
std::sort(variants_with_sizes.begin(), variants_with_sizes.end(), std::greater());
|
||||
|
||||
@ -1196,14 +1196,14 @@ void ColumnDynamic::takeDynamicStructureFromSourceColumns(const Columns & source
|
||||
result_variants.reserve(max_dynamic_types + 1); /// +1 for shared variant.
|
||||
/// Add shared variant.
|
||||
result_variants.push_back(getSharedVariantDataType());
|
||||
for (const auto & [size, variant] : variants_with_sizes)
|
||||
for (const auto & [size, variant_name, variant_type] : variants_with_sizes)
|
||||
{
|
||||
/// Add variant to the resulting variants list until we reach max_dynamic_types.
|
||||
if (canAddNewVariant(result_variants.size()))
|
||||
result_variants.push_back(variant);
|
||||
result_variants.push_back(variant_type);
|
||||
/// Add all remaining variants into shared_variants_statistics until we reach its max size.
|
||||
else if (new_statistics.shared_variants_statistics.size() < Statistics::MAX_SHARED_VARIANT_STATISTICS_SIZE)
|
||||
new_statistics.shared_variants_statistics[variant->getName()] = size;
|
||||
new_statistics.shared_variants_statistics[variant_name] = size;
|
||||
else
|
||||
break;
|
||||
}
|
||||
|
||||
@ -414,7 +414,7 @@ public:
|
||||
/// Insert value into shared variant. Also updates Variant discriminators and offsets.
|
||||
void insertValueIntoSharedVariant(const IColumn & src, const DataTypePtr & type, const String & type_name, size_t n);
|
||||
|
||||
const SerializationPtr & getVariantSerialization(const DataTypePtr & variant_type, const String & variant_name) const
|
||||
const SerializationPtr & getVariantSerialization(const DataTypePtr & variant_type, const String & variant_name)
|
||||
{
|
||||
/// Get serialization for provided data type.
|
||||
/// To avoid calling type->getDefaultSerialization() every time we use simple cache with max size.
|
||||
@ -428,7 +428,7 @@ public:
|
||||
return serialization_cache.emplace(variant_name, variant_type->getDefaultSerialization()).first->second;
|
||||
}
|
||||
|
||||
const SerializationPtr & getVariantSerialization(const DataTypePtr & variant_type) const { return getVariantSerialization(variant_type, variant_type->getName()); }
|
||||
const SerializationPtr & getVariantSerialization(const DataTypePtr & variant_type) { return getVariantSerialization(variant_type, variant_type->getName()); }
|
||||
|
||||
private:
|
||||
void createVariantInfo(const DataTypePtr & variant_type);
|
||||
@ -473,7 +473,7 @@ private:
|
||||
/// We can use serializations of different data types to serialize values into shared variant.
|
||||
/// To avoid creating the same serialization multiple times, use simple cache.
|
||||
static const size_t SERIALIZATION_CACHE_MAX_SIZE = 256;
|
||||
mutable std::unordered_map<String, SerializationPtr> serialization_cache;
|
||||
std::unordered_map<String, SerializationPtr> serialization_cache;
|
||||
};
|
||||
|
||||
void extendVariantColumn(
|
||||
|
||||
@ -127,7 +127,7 @@ std::string ColumnObject::getName() const
|
||||
{
|
||||
WriteBufferFromOwnString ss;
|
||||
ss << "Object(";
|
||||
ss << "max_dynamic_paths=" << max_dynamic_paths;
|
||||
ss << "max_dynamic_paths=" << global_max_dynamic_paths;
|
||||
ss << ", max_dynamic_types=" << max_dynamic_types;
|
||||
std::vector<String> sorted_typed_paths;
|
||||
sorted_typed_paths.reserve(typed_paths.size());
|
||||
@ -1045,9 +1045,9 @@ void ColumnObject::forEachSubcolumnRecursively(DB::IColumn::RecursiveMutableColu
|
||||
|
||||
bool ColumnObject::structureEquals(const IColumn & rhs) const
|
||||
{
|
||||
/// 2 Object columns have equal structure if they have the same typed paths and max_dynamic_paths/max_dynamic_types.
|
||||
/// 2 Object columns have equal structure if they have the same typed paths and global_max_dynamic_paths/max_dynamic_types.
|
||||
const auto * rhs_object = typeid_cast<const ColumnObject *>(&rhs);
|
||||
if (!rhs_object || typed_paths.size() != rhs_object->typed_paths.size() || max_dynamic_paths != rhs_object->max_dynamic_paths || max_dynamic_types != rhs_object->max_dynamic_types)
|
||||
if (!rhs_object || typed_paths.size() != rhs_object->typed_paths.size() || global_max_dynamic_paths != rhs_object->global_max_dynamic_paths || max_dynamic_types != rhs_object->max_dynamic_types)
|
||||
return false;
|
||||
|
||||
for (const auto & [path, column] : typed_paths)
|
||||
|
||||
@ -953,7 +953,7 @@ ColumnPtr ColumnVariant::index(const IColumn & indexes, size_t limit) const
|
||||
{
|
||||
/// If we have only NULLs, index will take no effect, just return resized column.
|
||||
if (hasOnlyNulls())
|
||||
return cloneResized(limit);
|
||||
return cloneResized(limit == 0 ? indexes.size(): limit);
|
||||
|
||||
/// Optimization when we have only one non empty variant and no NULLs.
|
||||
/// In this case local_discriminators column is filled with identical values and offsets column
|
||||
@ -1009,8 +1009,16 @@ ColumnPtr ColumnVariant::indexImpl(const PaddedPODArray<Type> & indexes, size_t
|
||||
new_variants.reserve(num_variants);
|
||||
for (size_t i = 0; i != num_variants; ++i)
|
||||
{
|
||||
size_t nested_limit = nested_perms[i].size() == variants[i]->size() ? 0 : nested_perms[i].size();
|
||||
new_variants.emplace_back(variants[i]->permute(nested_perms[i], nested_limit));
|
||||
/// Check if no values from this variant were selected.
|
||||
if (nested_perms[i].empty())
|
||||
{
|
||||
new_variants.emplace_back(variants[i]->cloneEmpty());
|
||||
}
|
||||
else
|
||||
{
|
||||
size_t nested_limit = nested_perms[i].size() == variants[i]->size() ? 0 : nested_perms[i].size();
|
||||
new_variants.emplace_back(variants[i]->permute(nested_perms[i], nested_limit));
|
||||
}
|
||||
}
|
||||
|
||||
/// We cannot use new_offsets column as an offset column, because it became invalid after variants permutation.
|
||||
|
||||
@ -197,6 +197,12 @@ public:
|
||||
cache_policy->remove(key);
|
||||
}
|
||||
|
||||
void remove(std::function<bool(const Key&, const MappedPtr &)> predicate)
|
||||
{
|
||||
std::lock_guard lock(mutex);
|
||||
cache_policy->remove(predicate);
|
||||
}
|
||||
|
||||
size_t sizeInBytes() const
|
||||
{
|
||||
std::lock_guard lock(mutex);
|
||||
|
||||
@ -75,9 +75,9 @@
|
||||
M(GlobalThread, "Number of threads in global thread pool.") \
|
||||
M(GlobalThreadActive, "Number of threads in global thread pool running a task.") \
|
||||
M(GlobalThreadScheduled, "Number of queued or active jobs in global thread pool.") \
|
||||
M(LocalThread, "Number of threads in local thread pools. The threads in local thread pools are taken from the global thread pool.") \
|
||||
M(LocalThreadActive, "Number of threads in local thread pools running a task.") \
|
||||
M(LocalThreadScheduled, "Number of queued or active jobs in local thread pools.") \
|
||||
M(LocalThread, "Obsolete. Number of threads in local thread pools. The threads in local thread pools are taken from the global thread pool.") \
|
||||
M(LocalThreadActive, "Obsolete. Number of threads in local thread pools running a task.") \
|
||||
M(LocalThreadScheduled, "Obsolete. Number of queued or active jobs in local thread pools.") \
|
||||
M(MergeTreeDataSelectExecutorThreads, "Number of threads in the MergeTreeDataSelectExecutor thread pool.") \
|
||||
M(MergeTreeDataSelectExecutorThreadsActive, "Number of threads in the MergeTreeDataSelectExecutor thread pool running a task.") \
|
||||
M(MergeTreeDataSelectExecutorThreadsScheduled, "Number of queued or active jobs in the MergeTreeDataSelectExecutor thread pool.") \
|
||||
|
||||
@ -55,6 +55,7 @@ public:
|
||||
virtual void set(const Key & key, const MappedPtr & mapped) = 0;
|
||||
|
||||
virtual void remove(const Key & key) = 0;
|
||||
virtual void remove(std::function<bool(const Key & key, const MappedPtr & mapped)> predicate) = 0;
|
||||
|
||||
virtual void clear() = 0;
|
||||
virtual std::vector<KeyMapped> dump() const = 0;
|
||||
|
||||
@ -79,6 +79,22 @@ public:
|
||||
cells.erase(it);
|
||||
}
|
||||
|
||||
void remove(std::function<bool(const Key &, const MappedPtr &)> predicate) override
|
||||
{
|
||||
for (auto it = cells.begin(); it != cells.end();)
|
||||
{
|
||||
if (predicate(it->first, it->second.value))
|
||||
{
|
||||
Cell & cell = it->second;
|
||||
current_size_in_bytes -= cell.size;
|
||||
queue.erase(cell.queue_iterator);
|
||||
it = cells.erase(it);
|
||||
}
|
||||
else
|
||||
++it;
|
||||
}
|
||||
}
|
||||
|
||||
MappedPtr get(const Key & key) override
|
||||
{
|
||||
auto it = cells.find(key);
|
||||
|
||||
@ -86,6 +86,20 @@
|
||||
M(NetworkReceiveBytes, "Total number of bytes received from network. Only ClickHouse-related network interaction is included, not by 3rd party libraries.") \
|
||||
M(NetworkSendBytes, "Total number of bytes send to network. Only ClickHouse-related network interaction is included, not by 3rd party libraries.") \
|
||||
\
|
||||
M(GlobalThreadPoolExpansions, "Counts the total number of times new threads have been added to the global thread pool. This metric indicates the frequency of expansions in the global thread pool to accommodate increased processing demands.") \
|
||||
M(GlobalThreadPoolShrinks, "Counts the total number of times the global thread pool has shrunk by removing threads. This occurs when the number of idle threads exceeds max_thread_pool_free_size, indicating adjustments in the global thread pool size in response to decreased thread utilization.") \
|
||||
M(GlobalThreadPoolThreadCreationMicroseconds, "Total time spent waiting for new threads to start.") \
|
||||
M(GlobalThreadPoolLockWaitMicroseconds, "Total time threads have spent waiting for locks in the global thread pool.") \
|
||||
M(GlobalThreadPoolJobs, "Counts the number of jobs that have been pushed to the global thread pool.") \
|
||||
M(GlobalThreadPoolJobWaitTimeMicroseconds, "Measures the elapsed time from when a job is scheduled in the thread pool to when it is picked up for execution by a worker thread. This metric helps identify delays in job processing, indicating the responsiveness of the thread pool to new tasks.") \
|
||||
M(LocalThreadPoolExpansions, "Counts the total number of times threads have been borrowed from the global thread pool to expand local thread pools.") \
|
||||
M(LocalThreadPoolShrinks, "Counts the total number of times threads have been returned to the global thread pool from local thread pools.") \
|
||||
M(LocalThreadPoolThreadCreationMicroseconds, "Total time local thread pools have spent waiting to borrow a thread from the global pool.") \
|
||||
M(LocalThreadPoolLockWaitMicroseconds, "Total time threads have spent waiting for locks in the local thread pools.") \
|
||||
M(LocalThreadPoolJobs, "Counts the number of jobs that have been pushed to the local thread pools.") \
|
||||
M(LocalThreadPoolBusyMicroseconds, "Total time threads have spent executing the actual work.") \
|
||||
M(LocalThreadPoolJobWaitTimeMicroseconds, "Measures the elapsed time from when a job is scheduled in the thread pool to when it is picked up for execution by a worker thread. This metric helps identify delays in job processing, indicating the responsiveness of the thread pool to new tasks.") \
|
||||
\
|
||||
M(DiskS3GetRequestThrottlerCount, "Number of DiskS3 GET and SELECT requests passed through throttler.") \
|
||||
M(DiskS3GetRequestThrottlerSleepMicroseconds, "Total time a query was sleeping to conform DiskS3 GET and SELECT request throttling.") \
|
||||
M(DiskS3PutRequestThrottlerCount, "Number of DiskS3 PUT, COPY, POST and LIST requests passed through throttler.") \
|
||||
|
||||
@ -34,13 +34,16 @@ bool ProgressIndication::updateProgress(const Progress & value)
|
||||
|
||||
void ProgressIndication::resetProgress()
|
||||
{
|
||||
watch.restart();
|
||||
progress.reset();
|
||||
show_progress_bar = false;
|
||||
written_progress_chars = 0;
|
||||
write_progress_on_update = false;
|
||||
{
|
||||
std::lock_guard lock(progress_mutex);
|
||||
progress.reset();
|
||||
show_progress_bar = false;
|
||||
written_progress_chars = 0;
|
||||
write_progress_on_update = false;
|
||||
}
|
||||
{
|
||||
std::lock_guard lock(profile_events_mutex);
|
||||
watch.restart();
|
||||
cpu_usage_meter.reset(getElapsedNanoseconds());
|
||||
hosts_data.clear();
|
||||
}
|
||||
@ -90,6 +93,8 @@ ProgressIndication::MemoryUsage ProgressIndication::getMemoryUsage() const
|
||||
|
||||
void ProgressIndication::writeFinalProgress()
|
||||
{
|
||||
std::lock_guard lock(progress_mutex);
|
||||
|
||||
if (progress.read_rows < 1000)
|
||||
return;
|
||||
|
||||
@ -271,6 +276,8 @@ void ProgressIndication::writeProgress(WriteBufferFromFileDescriptor & message)
|
||||
|
||||
void ProgressIndication::clearProgressOutput(WriteBufferFromFileDescriptor & message)
|
||||
{
|
||||
std::lock_guard lock(progress_mutex);
|
||||
|
||||
if (written_progress_chars)
|
||||
{
|
||||
written_progress_chars = 0;
|
||||
|
||||
@ -115,6 +115,8 @@ private:
|
||||
/// It is possible concurrent access to the following:
|
||||
/// - writeProgress() (class properties) (guarded with progress_mutex)
|
||||
/// - hosts_data/cpu_usage_meter (guarded with profile_events_mutex)
|
||||
///
|
||||
/// It is also possible to have more races if query is cancelled, so that clearProgressOutput() is called concurrently
|
||||
mutable std::mutex profile_events_mutex;
|
||||
mutable std::mutex progress_mutex;
|
||||
|
||||
|
||||
@ -95,6 +95,27 @@ public:
|
||||
cells.erase(it);
|
||||
}
|
||||
|
||||
void remove(std::function<bool(const Key &, const MappedPtr &)> predicate) override
|
||||
{
|
||||
for (auto it = cells.begin(); it != cells.end();)
|
||||
{
|
||||
if (predicate(it->first, it->second.value))
|
||||
{
|
||||
auto & cell = it->second;
|
||||
|
||||
current_size_in_bytes -= cell.size;
|
||||
if (cell.is_protected)
|
||||
current_protected_size -= cell.size;
|
||||
|
||||
auto & queue = cell.is_protected ? protected_queue : probationary_queue;
|
||||
queue.erase(cell.queue_iterator);
|
||||
it = cells.erase(it);
|
||||
}
|
||||
else
|
||||
++it;
|
||||
}
|
||||
}
|
||||
|
||||
MappedPtr get(const Key & key) override
|
||||
{
|
||||
auto it = cells.find(key);
|
||||
|
||||
@ -13,6 +13,7 @@
|
||||
#include <IO/ReadHelpers.h>
|
||||
#include <Interpreters/Context.h>
|
||||
#include <Core/Settings.h>
|
||||
#include <Poco/Environment.h>
|
||||
|
||||
#pragma clang diagnostic ignored "-Wreserved-identifier"
|
||||
|
||||
@ -371,8 +372,8 @@ try
|
||||
/// in case of double fault.
|
||||
|
||||
LOG_FATAL(log, "########## Short fault info ############");
|
||||
LOG_FATAL(log, "(version {}{}, build id: {}, git hash: {}) (from thread {}) Received signal {}",
|
||||
VERSION_STRING, VERSION_OFFICIAL, daemon ? daemon->build_id : "", GIT_HASH,
|
||||
LOG_FATAL(log, "(version {}{}, build id: {}, git hash: {}, architecture: {}) (from thread {}) Received signal {}",
|
||||
VERSION_STRING, VERSION_OFFICIAL, daemon ? daemon->build_id : "", GIT_HASH, Poco::Environment::osArchitecture(),
|
||||
thread_num, sig);
|
||||
|
||||
std::string signal_description = "Unknown signal";
|
||||
|
||||
@ -273,6 +273,25 @@ void SystemLogBase<LogElement>::startup()
|
||||
saving_thread = std::make_unique<ThreadFromGlobalPool>([this] { savingThreadFunction(); });
|
||||
}
|
||||
|
||||
template <typename LogElement>
|
||||
void SystemLogBase<LogElement>::stopFlushThread()
|
||||
{
|
||||
{
|
||||
std::lock_guard lock(thread_mutex);
|
||||
|
||||
if (!saving_thread || !saving_thread->joinable())
|
||||
return;
|
||||
|
||||
if (is_shutdown)
|
||||
return;
|
||||
|
||||
is_shutdown = true;
|
||||
queue->shutdown();
|
||||
}
|
||||
|
||||
saving_thread->join();
|
||||
}
|
||||
|
||||
template <typename LogElement>
|
||||
void SystemLogBase<LogElement>::add(LogElement element)
|
||||
{
|
||||
|
||||
@ -216,6 +216,8 @@ public:
|
||||
static consteval bool shouldTurnOffLogger() { return false; }
|
||||
|
||||
protected:
|
||||
void stopFlushThread() final;
|
||||
|
||||
std::shared_ptr<SystemLogQueue<LogElement>> queue;
|
||||
};
|
||||
}
|
||||
|
||||
@ -145,6 +145,23 @@ public:
|
||||
size_in_bytes -= sz;
|
||||
}
|
||||
|
||||
void remove(std::function<bool(const Key &, const MappedPtr &)> predicate) override
|
||||
{
|
||||
for (auto it = cache.begin(); it != cache.end();)
|
||||
{
|
||||
if (predicate(it->first, it->second))
|
||||
{
|
||||
size_t sz = weight_function(*it->second);
|
||||
if (it->first.user_id.has_value())
|
||||
Base::user_quotas->decreaseActual(*it->first.user_id, sz);
|
||||
it = cache.erase(it);
|
||||
size_in_bytes -= sz;
|
||||
}
|
||||
else
|
||||
++it;
|
||||
}
|
||||
}
|
||||
|
||||
MappedPtr get(const Key & key) override
|
||||
{
|
||||
auto it = cache.find(key);
|
||||
|
||||
@ -1,4 +1,5 @@
|
||||
#include <Common/ThreadPool.h>
|
||||
#include <Common/ProfileEvents.h>
|
||||
#include <Common/setThreadName.h>
|
||||
#include <Common/Exception.h>
|
||||
#include <Common/getNumberOfPhysicalCPUCores.h>
|
||||
@ -27,6 +28,25 @@ namespace CurrentMetrics
|
||||
extern const Metric GlobalThreadScheduled;
|
||||
}
|
||||
|
||||
namespace ProfileEvents
|
||||
{
|
||||
extern const Event GlobalThreadPoolExpansions;
|
||||
extern const Event GlobalThreadPoolShrinks;
|
||||
extern const Event GlobalThreadPoolThreadCreationMicroseconds;
|
||||
extern const Event GlobalThreadPoolLockWaitMicroseconds;
|
||||
extern const Event GlobalThreadPoolJobs;
|
||||
extern const Event GlobalThreadPoolJobWaitTimeMicroseconds;
|
||||
|
||||
extern const Event LocalThreadPoolExpansions;
|
||||
extern const Event LocalThreadPoolShrinks;
|
||||
extern const Event LocalThreadPoolThreadCreationMicroseconds;
|
||||
extern const Event LocalThreadPoolLockWaitMicroseconds;
|
||||
extern const Event LocalThreadPoolJobs;
|
||||
extern const Event LocalThreadPoolBusyMicroseconds;
|
||||
extern const Event LocalThreadPoolJobWaitTimeMicroseconds;
|
||||
|
||||
}
|
||||
|
||||
class JobWithPriority
|
||||
{
|
||||
public:
|
||||
@ -40,6 +60,7 @@ public:
|
||||
/// Call stacks of all jobs' schedulings leading to this one
|
||||
std::vector<StackTrace::FramePointers> frame_pointers;
|
||||
bool enable_job_stack_trace = false;
|
||||
Stopwatch job_create_time;
|
||||
|
||||
JobWithPriority(
|
||||
Job job_, Priority priority_, CurrentMetrics::Metric metric,
|
||||
@ -59,6 +80,13 @@ public:
|
||||
{
|
||||
return priority > rhs.priority; // Reversed for `priority_queue` max-heap to yield minimum value (i.e. highest priority) first
|
||||
}
|
||||
|
||||
UInt64 elapsedMicroseconds() const
|
||||
{
|
||||
return job_create_time.elapsedMicroseconds();
|
||||
}
|
||||
|
||||
|
||||
};
|
||||
|
||||
static constexpr auto DEFAULT_THREAD_NAME = "ThreadPool";
|
||||
@ -180,14 +208,18 @@ ReturnType ThreadPoolImpl<Thread>::scheduleImpl(Job job, Priority priority, std:
|
||||
};
|
||||
|
||||
{
|
||||
Stopwatch watch;
|
||||
std::unique_lock lock(mutex);
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolLockWaitMicroseconds : ProfileEvents::LocalThreadPoolLockWaitMicroseconds,
|
||||
watch.elapsedMicroseconds());
|
||||
|
||||
if (CannotAllocateThreadFaultInjector::injectFault())
|
||||
return on_error("fault injected");
|
||||
|
||||
auto pred = [this] { return !queue_size || scheduled_jobs < queue_size || shutdown; };
|
||||
|
||||
if (wait_microseconds) /// Check for optional. Condition is true if the optional is set and the value is zero.
|
||||
if (wait_microseconds) /// Check for optional. Condition is true if the optional is set. Even if the value is zero.
|
||||
{
|
||||
if (!job_finished.wait_for(lock, std::chrono::microseconds(*wait_microseconds), pred))
|
||||
return on_error(fmt::format("no free thread (timeout={})", *wait_microseconds));
|
||||
@ -216,7 +248,13 @@ ReturnType ThreadPoolImpl<Thread>::scheduleImpl(Job job, Priority priority, std:
|
||||
|
||||
try
|
||||
{
|
||||
Stopwatch watch2;
|
||||
threads.front() = Thread([this, it = threads.begin()] { worker(it); });
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolThreadCreationMicroseconds : ProfileEvents::LocalThreadPoolThreadCreationMicroseconds,
|
||||
watch2.elapsedMicroseconds());
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolExpansions : ProfileEvents::LocalThreadPoolExpansions);
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
@ -239,6 +277,8 @@ ReturnType ThreadPoolImpl<Thread>::scheduleImpl(Job job, Priority priority, std:
|
||||
/// Wake up a free thread to run the new job.
|
||||
new_job_or_shutdown.notify_one();
|
||||
|
||||
ProfileEvents::increment(std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolJobs : ProfileEvents::LocalThreadPoolJobs);
|
||||
|
||||
return static_cast<ReturnType>(true);
|
||||
}
|
||||
|
||||
@ -262,7 +302,14 @@ void ThreadPoolImpl<Thread>::startNewThreadsNoLock()
|
||||
|
||||
try
|
||||
{
|
||||
Stopwatch watch;
|
||||
threads.front() = Thread([this, it = threads.begin()] { worker(it); });
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolThreadCreationMicroseconds : ProfileEvents::LocalThreadPoolThreadCreationMicroseconds,
|
||||
watch.elapsedMicroseconds());
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolExpansions : ProfileEvents::LocalThreadPoolExpansions);
|
||||
|
||||
}
|
||||
catch (...)
|
||||
{
|
||||
@ -293,7 +340,11 @@ void ThreadPoolImpl<Thread>::scheduleOrThrow(Job job, Priority priority, uint64_
|
||||
template <typename Thread>
|
||||
void ThreadPoolImpl<Thread>::wait()
|
||||
{
|
||||
Stopwatch watch;
|
||||
std::unique_lock lock(mutex);
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolLockWaitMicroseconds : ProfileEvents::LocalThreadPoolLockWaitMicroseconds,
|
||||
watch.elapsedMicroseconds());
|
||||
/// Signal here just in case.
|
||||
/// If threads are waiting on condition variables, but there are some jobs in the queue
|
||||
/// then it will prevent us from deadlock.
|
||||
@ -334,7 +385,11 @@ void ThreadPoolImpl<Thread>::finalize()
|
||||
|
||||
/// Wait for all currently running jobs to finish (we don't wait for all scheduled jobs here like the function wait() does).
|
||||
for (auto & thread : threads)
|
||||
{
|
||||
thread.join();
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolShrinks : ProfileEvents::LocalThreadPoolShrinks);
|
||||
}
|
||||
|
||||
threads.clear();
|
||||
}
|
||||
@ -391,7 +446,11 @@ void ThreadPoolImpl<Thread>::worker(typename std::list<Thread>::iterator thread_
|
||||
std::optional<JobWithPriority> job_data;
|
||||
|
||||
{
|
||||
Stopwatch watch;
|
||||
std::unique_lock lock(mutex);
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolLockWaitMicroseconds : ProfileEvents::LocalThreadPoolLockWaitMicroseconds,
|
||||
watch.elapsedMicroseconds());
|
||||
|
||||
// Finish with previous job if any
|
||||
if (job_is_done)
|
||||
@ -424,6 +483,8 @@ void ThreadPoolImpl<Thread>::worker(typename std::list<Thread>::iterator thread_
|
||||
{
|
||||
thread_it->detach();
|
||||
threads.erase(thread_it);
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolShrinks : ProfileEvents::LocalThreadPoolShrinks);
|
||||
}
|
||||
return;
|
||||
}
|
||||
@ -433,6 +494,10 @@ void ThreadPoolImpl<Thread>::worker(typename std::list<Thread>::iterator thread_
|
||||
job_data = std::move(const_cast<JobWithPriority &>(jobs.top()));
|
||||
jobs.pop();
|
||||
|
||||
ProfileEvents::increment(
|
||||
std::is_same_v<Thread, std::thread> ? ProfileEvents::GlobalThreadPoolJobWaitTimeMicroseconds : ProfileEvents::LocalThreadPoolJobWaitTimeMicroseconds,
|
||||
job_data->elapsedMicroseconds());
|
||||
|
||||
/// We don't run jobs after `shutdown` is set, but we have to properly dequeue all jobs and finish them.
|
||||
if (shutdown)
|
||||
{
|
||||
@ -459,7 +524,22 @@ void ThreadPoolImpl<Thread>::worker(typename std::list<Thread>::iterator thread_
|
||||
|
||||
CurrentMetrics::Increment metric_active_pool_threads(metric_active_threads);
|
||||
|
||||
job_data->job();
|
||||
if constexpr (!std::is_same_v<Thread, std::thread>)
|
||||
{
|
||||
Stopwatch watch;
|
||||
job_data->job();
|
||||
// This metric is less relevant for the global thread pool, as it would show large values (time while
|
||||
// a thread was used by local pools) and increment only when local pools are destroyed.
|
||||
//
|
||||
// In cases where global pool threads are used directly (without a local thread pool), distinguishing
|
||||
// them is difficult.
|
||||
ProfileEvents::increment(ProfileEvents::LocalThreadPoolBusyMicroseconds, watch.elapsedMicroseconds());
|
||||
}
|
||||
else
|
||||
{
|
||||
job_data->job();
|
||||
}
|
||||
|
||||
|
||||
if (thread_trace_context.root_span.isTraceEnabled())
|
||||
{
|
||||
|
||||
@ -131,7 +131,7 @@ private:
|
||||
bool threads_remove_themselves = true;
|
||||
const bool shutdown_on_exception = true;
|
||||
|
||||
boost::heap::priority_queue<JobWithPriority> jobs;
|
||||
boost::heap::priority_queue<JobWithPriority,boost::heap::stable<true>> jobs;
|
||||
std::list<Thread> threads;
|
||||
std::exception_ptr first_exception;
|
||||
std::stack<OnDestroyCallback> on_destroy_callbacks;
|
||||
|
||||
@ -1120,7 +1120,7 @@ class IColumn;
|
||||
M(String, column_names_for_schema_inference, "", "The list of column names to use in schema inference for formats without column names. The format: 'column1,column2,column3,...'", 0) \
|
||||
M(String, schema_inference_hints, "", "The list of column names and types to use in schema inference for formats without column names. The format: 'column_name1 column_type1, column_name2 column_type2, ...'", 0) \
|
||||
M(SchemaInferenceMode, schema_inference_mode, "default", "Mode of schema inference. 'default' - assume that all files have the same schema and schema can be inferred from any file, 'union' - files can have different schemas and the resulting schema should be the a union of schemas of all files", 0) \
|
||||
M(Bool, schema_inference_make_columns_nullable, true, "If set to true, all inferred types will be Nullable in schema inference for formats without information about nullability.", 0) \
|
||||
M(UInt64Auto, schema_inference_make_columns_nullable, 1, "If set to true, all inferred types will be Nullable in schema inference. When set to false, no columns will be converted to Nullable. When set to 'auto', ClickHouse will use information about nullability from the data.", 0) \
|
||||
M(Bool, input_format_json_read_bools_as_numbers, true, "Allow to parse bools as numbers in JSON input formats", 0) \
|
||||
M(Bool, input_format_json_read_bools_as_strings, true, "Allow to parse bools as strings in JSON input formats", 0) \
|
||||
M(Bool, input_format_json_try_infer_numbers_from_strings, false, "Try to infer numbers from string fields while schema inference", 0) \
|
||||
|
||||
@ -72,11 +72,13 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
|
||||
{"24.9",
|
||||
{
|
||||
{"input_format_try_infer_variants", false, false, "Try to infer Variant type in text formats when there is more than one possible type for column/array elements"},
|
||||
{"join_output_by_rowlist_perkey_rows_threshold", 0, 5, "The lower limit of per-key average rows in the right table to determine whether to output by row list in hash join."},
|
||||
{"create_if_not_exists", false, false, "New setting."},
|
||||
{"allow_materialized_view_with_bad_select", true, true, "Support (but not enable yet) stricter validation in CREATE MATERIALIZED VIEW"},
|
||||
}
|
||||
},
|
||||
{"24.8",
|
||||
{
|
||||
{"create_if_not_exists", false, false, "New setting."},
|
||||
{"rows_before_aggregation", true, true, "Provide exact value for rows_before_aggregation statistic, represents the number of rows read before aggregation"},
|
||||
{"restore_replace_external_table_functions_to_null", false, false, "New setting."},
|
||||
{"restore_replace_external_engines_to_null", false, false, "New setting."},
|
||||
@ -85,7 +87,6 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
|
||||
{"use_hive_partitioning", false, false, "Allows to use hive partitioning for File, URL, S3, AzureBlobStorage and HDFS engines."},
|
||||
{"allow_experimental_kafka_offsets_storage_in_keeper", false, false, "Allow the usage of experimental Kafka storage engine that stores the committed offsets in ClickHouse Keeper"},
|
||||
{"allow_archive_path_syntax", true, true, "Added new setting to allow disabling archive path syntax."},
|
||||
{"allow_materialized_view_with_bad_select", true, true, "Support (but not enable yet) stricter validation in CREATE MATERIALIZED VIEW"},
|
||||
{"query_cache_tag", "", "", "New setting for labeling query cache settings."},
|
||||
{"allow_experimental_time_series_table", false, false, "Added new setting to allow the TimeSeries table engine"},
|
||||
{"enable_analyzer", 1, 1, "Added an alias to a setting `allow_experimental_analyzer`."},
|
||||
@ -93,7 +94,6 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
|
||||
{"allow_experimental_json_type", false, false, "Add new experimental JSON type"},
|
||||
{"use_json_alias_for_old_object_type", true, false, "Use JSON type alias to create new JSON type"},
|
||||
{"type_json_skip_duplicated_paths", false, false, "Allow to skip duplicated paths during JSON parsing"},
|
||||
{"join_output_by_rowlist_perkey_rows_threshold", 0, 5, "The lower limit of per-key average rows in the right table to determine whether to output by row list in hash join."},
|
||||
{"allow_experimental_vector_similarity_index", false, false, "Added new setting to allow experimental vector similarity indexes"},
|
||||
{"input_format_try_infer_datetimes_only_datetime64", true, false, "Allow to infer DateTime instead of DateTime64 in data formats"}
|
||||
}
|
||||
|
||||
@ -3,6 +3,7 @@
|
||||
#include <utility>
|
||||
|
||||
#include <Core/Types.h>
|
||||
#include <DataTypes/DataTypeInterval.h>
|
||||
|
||||
|
||||
namespace DB
|
||||
@ -212,6 +213,8 @@ static bool callOnIndexAndDataType(TypeIndex number, F && f, ExtraArgs && ... ar
|
||||
case TypeIndex::IPv4: return f(TypePair<DataTypeIPv4, T>(), std::forward<ExtraArgs>(args)...);
|
||||
case TypeIndex::IPv6: return f(TypePair<DataTypeIPv6, T>(), std::forward<ExtraArgs>(args)...);
|
||||
|
||||
case TypeIndex::Interval: return f(TypePair<DataTypeInterval, T>(), std::forward<ExtraArgs>(args)...);
|
||||
|
||||
default:
|
||||
break;
|
||||
}
|
||||
|
||||
@ -22,7 +22,6 @@
|
||||
#include <cstring>
|
||||
#include <unistd.h>
|
||||
#include <algorithm>
|
||||
#include <typeinfo>
|
||||
#include <iostream>
|
||||
#include <memory>
|
||||
|
||||
|
||||
@ -185,7 +185,7 @@ std::unique_ptr<IDataType::SubstreamData> DataTypeDynamic::getDynamicSubcolumnDa
|
||||
auto type = decodeDataType(buf);
|
||||
if (type->getName() == subcolumn_type_name)
|
||||
{
|
||||
dynamic_column.getVariantSerialization(subcolumn_type, subcolumn_type_name)->deserializeBinary(*subcolumn, buf, format_settings);
|
||||
subcolumn_type->getDefaultSerialization()->deserializeBinary(*subcolumn, buf, format_settings);
|
||||
null_map.push_back(0);
|
||||
}
|
||||
else
|
||||
|
||||
@ -1,10 +1,12 @@
|
||||
#include <DataTypes/DataTypeFactory.h>
|
||||
#include <DataTypes/DataTypeObject.h>
|
||||
#include <DataTypes/DataTypeObjectDeprecated.h>
|
||||
#include <DataTypes/Serializations/SerializationJSON.h>
|
||||
#include <DataTypes/Serializations/SerializationObjectTypedPath.h>
|
||||
#include <DataTypes/Serializations/SerializationObjectDynamicPath.h>
|
||||
#include <DataTypes/Serializations/SerializationSubObject.h>
|
||||
#include <Columns/ColumnObject.h>
|
||||
#include <Common/CurrentThread.h>
|
||||
|
||||
#include <Parsers/IAST.h>
|
||||
#include <Parsers/ASTLiteral.h>
|
||||
@ -513,13 +515,24 @@ static DataTypePtr createObject(const ASTPtr & arguments, const DataTypeObject::
|
||||
|
||||
static DataTypePtr createJSON(const ASTPtr & arguments)
|
||||
{
|
||||
auto context = CurrentThread::getQueryContext();
|
||||
if (!context)
|
||||
context = Context::getGlobalContextInstance();
|
||||
|
||||
if (context->getSettingsRef().use_json_alias_for_old_object_type)
|
||||
{
|
||||
if (arguments && !arguments->children.empty())
|
||||
throw Exception(ErrorCodes::BAD_ARGUMENTS, "Experimental Object type doesn't support any arguments. If you want to use new JSON type, set setting allow_experimental_json_type = 1");
|
||||
|
||||
return std::make_shared<DataTypeObjectDeprecated>("JSON", false);
|
||||
}
|
||||
|
||||
return createObject(arguments, DataTypeObject::SchemaFormat::JSON);
|
||||
}
|
||||
|
||||
void registerDataTypeJSON(DataTypeFactory & factory)
|
||||
{
|
||||
if (!Context::getGlobalContextInstance()->getSettingsRef().use_json_alias_for_old_object_type)
|
||||
factory.registerDataType("JSON", createJSON, DataTypeFactory::Case::Insensitive);
|
||||
factory.registerDataType("JSON", createJSON, DataTypeFactory::Case::Insensitive);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@ -78,10 +78,6 @@ static DataTypePtr create(const ASTPtr & arguments)
|
||||
void registerDataTypeObjectDeprecated(DataTypeFactory & factory)
|
||||
{
|
||||
factory.registerDataType("Object", create);
|
||||
if (Context::getGlobalContextInstance()->getSettingsRef().use_json_alias_for_old_object_type)
|
||||
factory.registerSimpleDataType("JSON",
|
||||
[] { return std::make_shared<DataTypeObjectDeprecated>("JSON", false); },
|
||||
DataTypeFactory::Case::Insensitive);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@ -149,6 +149,8 @@ std::unique_ptr<IDataType::SubstreamData> IDataType::getSubcolumnData(
|
||||
|
||||
ISerialization::EnumerateStreamsSettings settings;
|
||||
settings.position_independent_encoding = false;
|
||||
/// Don't enumerate dynamic subcolumns, they are handled separately.
|
||||
settings.enumerate_dynamic_streams = false;
|
||||
data.serialization->enumerateStreams(settings, callback_with_data, data);
|
||||
|
||||
if (!res && data.type->hasDynamicSubcolumnsData())
|
||||
|
||||
@ -241,6 +241,10 @@ public:
|
||||
{
|
||||
SubstreamPath path;
|
||||
bool position_independent_encoding = true;
|
||||
/// If set to false, don't enumerate dynamic subcolumns
|
||||
/// (such as dynamic types in Dynamic column or dynamic paths in JSON column).
|
||||
/// It may be needed when dynamic subcolumns are processed separately.
|
||||
bool enumerate_dynamic_streams = true;
|
||||
};
|
||||
|
||||
virtual void enumerateStreams(
|
||||
|
||||
@ -64,7 +64,7 @@ void SerializationDynamic::enumerateStreams(
|
||||
const auto * deserialize_state = data.deserialize_state ? checkAndGetState<DeserializeBinaryBulkStateDynamic>(data.deserialize_state) : nullptr;
|
||||
|
||||
/// If column is nullptr and we don't have deserialize state yet, nothing to enumerate as we don't have any variants.
|
||||
if (!column_dynamic && !deserialize_state)
|
||||
if (!settings.enumerate_dynamic_streams || (!column_dynamic && !deserialize_state))
|
||||
return;
|
||||
|
||||
const auto & variant_type = column_dynamic ? column_dynamic->getVariantInfo().variant_type : checkAndGetState<DeserializeBinaryBulkStateDynamicStructure>(deserialize_state->structure_state)->variant_type;
|
||||
@ -489,9 +489,8 @@ void SerializationDynamic::serializeBinary(const IColumn & column, size_t row_nu
|
||||
}
|
||||
|
||||
const auto & variant_type = assert_cast<const DataTypeVariant &>(*variant_info.variant_type).getVariant(global_discr);
|
||||
const auto & variant_type_name = variant_info.variant_names[global_discr];
|
||||
encodeDataType(variant_type, ostr);
|
||||
dynamic_column.getVariantSerialization(variant_type, variant_type_name)->serializeBinary(variant_column.getVariantByGlobalDiscriminator(global_discr), variant_column.offsetAt(row_num), ostr, settings);
|
||||
variant_type->getDefaultSerialization()->serializeBinary(variant_column.getVariantByGlobalDiscriminator(global_discr), variant_column.offsetAt(row_num), ostr, settings);
|
||||
}
|
||||
|
||||
template <typename ReturnType = void, typename DeserializeFunc>
|
||||
@ -629,7 +628,7 @@ static void serializeTextImpl(
|
||||
ReadBufferFromMemory buf(value.data, value.size);
|
||||
auto variant_type = decodeDataType(buf);
|
||||
auto tmp_variant_column = variant_type->createColumn();
|
||||
auto variant_serialization = dynamic_column.getVariantSerialization(variant_type);
|
||||
auto variant_serialization = variant_type->getDefaultSerialization();
|
||||
variant_serialization->deserializeBinary(*tmp_variant_column, buf, settings);
|
||||
nested_serialize(*variant_serialization, *tmp_variant_column, 0, ostr);
|
||||
}
|
||||
|
||||
@ -130,7 +130,7 @@ void SerializationObject::enumerateStreams(EnumerateStreamsSettings & settings,
|
||||
}
|
||||
|
||||
/// If column or deserialization state was provided, iterate over dynamic paths,
|
||||
if (column_object || structure_state)
|
||||
if (settings.enumerate_dynamic_streams && (column_object || structure_state))
|
||||
{
|
||||
/// Enumerate dynamic paths in sorted order for consistency.
|
||||
const auto * dynamic_paths = column_object ? &column_object->getDynamicPaths() : nullptr;
|
||||
|
||||
@ -228,6 +228,39 @@ void convertUInt64toInt64IfPossible(const DataTypes & types, TypeIndexSet & type
|
||||
}
|
||||
}
|
||||
|
||||
DataTypePtr findSmallestIntervalSuperType(const DataTypes &types, TypeIndexSet &types_set)
|
||||
{
|
||||
auto min_interval = IntervalKind::Kind::Year;
|
||||
DataTypePtr smallest_type;
|
||||
|
||||
bool is_higher_interval = false; // For Years, Quarters and Months
|
||||
|
||||
for (const auto &type : types)
|
||||
{
|
||||
if (const auto * interval_type = typeid_cast<const DataTypeInterval *>(type.get()))
|
||||
{
|
||||
auto current_interval = interval_type->getKind().kind;
|
||||
if (current_interval > IntervalKind::Kind::Week)
|
||||
is_higher_interval = true;
|
||||
if (current_interval < min_interval)
|
||||
{
|
||||
min_interval = current_interval;
|
||||
smallest_type = type;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (is_higher_interval && min_interval <= IntervalKind::Kind::Week)
|
||||
throw Exception(ErrorCodes::NO_COMMON_TYPE, "Cannot compare intervals {} and {} because the number of days in a month is not fixed", types[0]->getName(), types[1]->getName());
|
||||
|
||||
if (smallest_type)
|
||||
{
|
||||
types_set.clear();
|
||||
types_set.insert(smallest_type->getTypeId());
|
||||
}
|
||||
|
||||
return smallest_type;
|
||||
}
|
||||
}
|
||||
|
||||
template <LeastSupertypeOnError on_error>
|
||||
@ -652,6 +685,13 @@ DataTypePtr getLeastSupertype(const DataTypes & types)
|
||||
return numeric_type;
|
||||
}
|
||||
|
||||
/// For interval data types.
|
||||
{
|
||||
auto res = findSmallestIntervalSuperType(types, type_ids);
|
||||
if (res)
|
||||
return res;
|
||||
}
|
||||
|
||||
/// All other data types (UUID, AggregateFunction, Enum...) are compatible only if they are the same (checked in trivial cases).
|
||||
return throwOrReturn<on_error>(types, "", ErrorCodes::NO_COMMON_TYPE);
|
||||
}
|
||||
|
||||
@ -1,5 +1,7 @@
|
||||
#pragma once
|
||||
#include <DataTypes/IDataType.h>
|
||||
#include <DataTypes/DataTypeInterval.h>
|
||||
#include <Common/IntervalKind.h>
|
||||
|
||||
namespace DB
|
||||
{
|
||||
@ -48,4 +50,7 @@ DataTypePtr getLeastSupertypeOrString(const TypeIndexSet & types);
|
||||
|
||||
DataTypePtr tryGetLeastSupertype(const TypeIndexSet & types);
|
||||
|
||||
/// A vector that shows the conversion rates to the next Interval type starting from NanoSecond
|
||||
static std::vector<int> interval_conversions = {1, 1000, 1000, 1000, 60, 60, 24, 7, 4, 3, 4};
|
||||
|
||||
}
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user