thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-27 18:12:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into igor/analyzer-test-fixes

Browse Source
This commit is contained in:
Igor Nikonov 2023-04-12 10:10:15 +00:00
commit 4f2f5f9cad
585 changed files with 8289 additions and 4115 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
.clang-tidy
View File

@ -110,6 +110,7 @@ Checks: '*,
-misc-const-correctness,
-misc-no-recursion,
-misc-non-private-member-variables-in-classes,
-misc-confusable-identifiers, # useful but slooow
-modernize-avoid-c-arrays,
-modernize-concat-nested-namespaces,
@ -148,19 +149,6 @@ Checks: '*,
-readability-use-anyofallof,
-zirkon-*,
-misc-*, # temporarily disabled due to being too slow
# also disable checks in other categories which are aliases of checks in misc-*:
# https://releases.llvm.org/15.0.0/tools/clang/tools/extra/docs/clang-tidy/checks/list.html
-cert-dcl54-cpp, # alias of misc-new-delete-overloads
-hicpp-new-delete-operators, # alias of misc-new-delete-overloads
-cert-fio38-c, # alias of misc-non-copyable-objects
-cert-dcl03-c, # alias of misc-static-assert
-hicpp-static-assert, # alias of misc-static-assert
-cert-err09-cpp, # alias of misc-throw-by-value-catch-by-reference
-cert-err61-cpp, # alias of misc-throw-by-value-catch-by-reference
-cppcoreguidelines-c-copy-assignment-signature, # alias of misc-unconventional-assign-operator
-cppcoreguidelines-non-private-member-variables-in-classes, # alias of misc-non-private-member-variables-in-classes
'
WarningsAsErrors: '*'

7
.github/workflows/backport_branches.yml vendored
View File

@ -349,6 +349,13 @@ jobs:
with:
clear-repository: true
submodules: true
- name: Apply sparse checkout for contrib # in order to check that it doesn't break build
run: |
rm -rf "$GITHUB_WORKSPACE/contrib" && echo 'removed'
git -C "$GITHUB_WORKSPACE" checkout . && echo 'restored'
"$GITHUB_WORKSPACE/contrib/update-submodules.sh" && echo 'OK'
du -hs "$GITHUB_WORKSPACE/contrib" ||:
find "$GITHUB_WORKSPACE/contrib" -type f | wc -l ||:
- name: Build
run: |
sudo rm -fr "$TEMP_PATH"

7
.github/workflows/master.yml vendored
View File

@ -487,6 +487,13 @@ jobs:
with:
clear-repository: true
submodules: true
- name: Apply sparse checkout for contrib # in order to check that it doesn't break build
run: |
rm -rf "$GITHUB_WORKSPACE/contrib" && echo 'removed'
git -C "$GITHUB_WORKSPACE" checkout . && echo 'restored'
"$GITHUB_WORKSPACE/contrib/update-submodules.sh" && echo 'OK'
du -hs "$GITHUB_WORKSPACE/contrib" ||:
find "$GITHUB_WORKSPACE/contrib" -type f | wc -l ||:
- name: Build
run: |
sudo rm -fr "$TEMP_PATH"

7
.github/workflows/pull_request.yml vendored
View File

@ -550,6 +550,13 @@ jobs:
with:
clear-repository: true
submodules: true
- name: Apply sparse checkout for contrib # in order to check that it doesn't break build
run: |
rm -rf "$GITHUB_WORKSPACE/contrib" && echo 'removed'
git -C "$GITHUB_WORKSPACE" checkout . && echo 'restored'
"$GITHUB_WORKSPACE/contrib/update-submodules.sh" && echo 'OK'
du -hs "$GITHUB_WORKSPACE/contrib" ||:
find "$GITHUB_WORKSPACE/contrib" -type f | wc -l ||:
- name: Build
run: |
sudo rm -fr "$TEMP_PATH"

7
.github/workflows/release_branches.yml vendored
View File

@ -406,6 +406,13 @@ jobs:
with:
clear-repository: true
submodules: true
- name: Apply sparse checkout for contrib # in order to check that it doesn't break build
run: |
rm -rf "$GITHUB_WORKSPACE/contrib" && echo 'removed'
git -C "$GITHUB_WORKSPACE" checkout . && echo 'restored'
"$GITHUB_WORKSPACE/contrib/update-submodules.sh" && echo 'OK'
du -hs "$GITHUB_WORKSPACE/contrib" ||:
find "$GITHUB_WORKSPACE/contrib" -type f | wc -l ||:
- name: Build
run: |
sudo rm -fr "$TEMP_PATH"

2
README.md
View File

@ -1,4 +1,4 @@
[![ClickHouse — open source distributed column-oriented DBMS](https://github.com/ClickHouse/clickhouse-presentations/raw/master/images/logo-400x240.png)](https://clickhouse.com)
[<img alt="ClickHouse — open source distributed column-oriented DBMS" width="400px" src="https://clickhouse.com/images/ch_gh_logo_rounded.png" />](https://clickhouse.com?utm_source=github)
ClickHouse® is an open-source column-oriented database management system that allows generating analytical data reports in real-time.

2
base/base/find_symbols.h
View File

@ -36,7 +36,7 @@
namespace detail
{
template <char ...chars> constexpr bool is_in(char x) { return ((x == chars) || ...); }
template <char ...chars> constexpr bool is_in(char x) { return ((x == chars) || ...); } // NOLINT(misc-redundant-expression)
#if defined(__SSE2__)
template <char s0>

6
base/base/wide_integer_impl.h
View File

@ -155,13 +155,13 @@ struct common_type<wide::integer<Bits, Signed>, Arithmetic>
std::is_floating_point_v<Arithmetic>,
Arithmetic,
std::conditional_t<
sizeof(Arithmetic) < Bits * sizeof(long),
sizeof(Arithmetic) * 8 < Bits,
wide::integer<Bits, Signed>,
std::conditional_t<
Bits * sizeof(long) < sizeof(Arithmetic),
Bits < sizeof(Arithmetic) * 8,
Arithmetic,
std::conditional_t<
Bits * sizeof(long) == sizeof(Arithmetic) && (std::is_same_v<Signed, signed> || std::is_signed_v<Arithmetic>),
Bits == sizeof(Arithmetic) * 8 && (std::is_same_v<Signed, signed> || std::is_signed_v<Arithmetic>),
Arithmetic,
wide::integer<Bits, Signed>>>>>;
};

2
contrib/cctz vendored

@ -1 +1 @@
Subproject commit 7c78edd52b4d65acc103c2f195818ffcabe6fe0d
Subproject commit 5e05432420f9692418e2e12aff09859e420b14a2

2
contrib/krb5 vendored

@ -1 +1 @@
Subproject commit 9453aec0d50e5aff9b189051611b321b40935d02
Subproject commit b56ce6ba690e1f320df1a64afa34980c3e462617

19
contrib/krb5-cmake/CMakeLists.txt
View File

@ -15,10 +15,6 @@ if(NOT AWK_PROGRAM)
message(FATAL_ERROR "You need the awk program to build ClickHouse with krb5 enabled.")
endif()
if (NOT (ENABLE_OPENSSL OR ENABLE_OPENSSL_DYNAMIC))
add_compile_definitions(USE_BORINGSSL=1)
endif ()
set(KRB5_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/krb5/src")
set(KRB5_ET_BIN_DIR "${CMAKE_CURRENT_BINARY_DIR}/include_private")
@ -162,6 +158,11 @@ set(ALL_SRCS
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/kdf.c"
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/cmac.c"
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/des/des_keys.c"
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/des/f_parity.c"
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/enc_provider/rc4.c"
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/hash_provider/hash_md4.c"
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/md4/md4.c"
"${KRB5_SOURCE_DIR}/lib/crypto/krb/prng.c"
"${KRB5_SOURCE_DIR}/lib/crypto/krb/enc_dk_cmac.c"
# "${KRB5_SOURCE_DIR}/lib/crypto/krb/crc32.c"
@ -226,7 +227,6 @@ set(ALL_SRCS
# "${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/des.c"
"${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/rc4.c"
"${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/des3.c"
#"${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/camellia.c"
"${KRB5_SOURCE_DIR}/lib/crypto/openssl/cmac.c"
"${KRB5_SOURCE_DIR}/lib/crypto/openssl/sha256.c"
"${KRB5_SOURCE_DIR}/lib/crypto/openssl/hmac.c"
@ -474,6 +474,14 @@ set(ALL_SRCS
"${KRB5_SOURCE_DIR}/lib/krb5/krb5_libinit.c"
)
if (NOT (ENABLE_OPENSSL OR ENABLE_OPENSSL_DYNAMIC))
add_compile_definitions(USE_BORINGSSL=1)
else()
set(ALL_SRCS ${ALL_SRCS}
"${KRB5_SOURCE_DIR}/lib/crypto/openssl/enc_provider/camellia.c"
)
endif()
add_custom_command(
OUTPUT "${CMAKE_CURRENT_BINARY_DIR}/compile_et"
COMMAND /bin/sh
@ -673,6 +681,7 @@ target_include_directories(_krb5 PRIVATE
"${KRB5_SOURCE_DIR}/lib/gssapi/krb5"
"${KRB5_SOURCE_DIR}/lib/gssapi/spnego"
"${KRB5_SOURCE_DIR}/util/et"
"${KRB5_SOURCE_DIR}/lib/crypto/builtin/md4"
"${KRB5_SOURCE_DIR}/lib/crypto/openssl"
"${KRB5_SOURCE_DIR}/lib/crypto/krb"
"${KRB5_SOURCE_DIR}/util/profile"

19
contrib/sparse-checkout/setup-sparse-checkout.sh Executable file
View File

@ -0,0 +1,19 @@
#!/bin/sh
set -e
git config submodule."contrib/llvm-project".update '!../sparse-checkout/update-llvm-project.sh'
git config submodule."contrib/croaring".update '!../sparse-checkout/update-croaring.sh'
git config submodule."contrib/aws".update '!../sparse-checkout/update-aws.sh'
git config submodule."contrib/openssl".update '!../sparse-checkout/update-openssl.sh'
git config submodule."contrib/boringssl".update '!../sparse-checkout/update-boringssl.sh'
git config submodule."contrib/arrow".update '!../sparse-checkout/update-arrow.sh'
git config submodule."contrib/grpc".update '!../sparse-checkout/update-grpc.sh'
git config submodule."contrib/orc".update '!../sparse-checkout/update-orc.sh'
git config submodule."contrib/h3".update '!../sparse-checkout/update-h3.sh'
git config submodule."contrib/icu".update '!../sparse-checkout/update-icu.sh'
git config submodule."contrib/boost".update '!../sparse-checkout/update-boost.sh'
git config submodule."contrib/aws-s2n-tls".update '!../sparse-checkout/update-aws-s2n-tls.sh'
git config submodule."contrib/protobuf".update '!../sparse-checkout/update-protobuf.sh'
git config submodule."contrib/libxml2".update '!../sparse-checkout/update-libxml2.sh'
git config submodule."contrib/brotli".update '!../sparse-checkout/update-brotli.sh'

12
contrib/sparse-checkout/update-arrow.sh Executable file
View File

@ -0,0 +1,12 @@
#!/bin/sh
echo "Using sparse checkout for arrow"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/*/*' >> $FILES_TO_CHECKOUT
echo '/cpp/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

13
contrib/sparse-checkout/update-aws-s2n-tls.sh Executable file
View File

@ -0,0 +1,13 @@
#!/bin/sh
echo "Using sparse checkout for aws-s2n-tls"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/test/*' >> $FILES_TO_CHECKOUT
echo '!/docs/*' >> $FILES_TO_CHECKOUT
echo '!/compliance/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

13
contrib/sparse-checkout/update-aws.sh Executable file
View File

@ -0,0 +1,13 @@
#!/bin/sh
echo "Using sparse checkout for aws"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/*/*' >> $FILES_TO_CHECKOUT
echo '/aws-cpp-sdk-core/*' >> $FILES_TO_CHECKOUT
echo '/aws-cpp-sdk-s3/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

85
contrib/sparse-checkout/update-boost.sh Executable file
View File

@ -0,0 +1,85 @@
#!/bin/sh
echo "Using sparse checkout for boost"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/*/*' >> $FILES_TO_CHECKOUT
echo '/boost/*' > $FILES_TO_CHECKOUT
echo '!/boost/*/*' >> $FILES_TO_CHECKOUT
echo '/boost/algorithm/*' >> $FILES_TO_CHECKOUT
echo '/boost/any/*' >> $FILES_TO_CHECKOUT
echo '/boost/atomic/*' >> $FILES_TO_CHECKOUT
echo '/boost/assert/*' >> $FILES_TO_CHECKOUT
echo '/boost/bind/*' >> $FILES_TO_CHECKOUT
echo '/boost/concept/*' >> $FILES_TO_CHECKOUT
echo '/boost/config/*' >> $FILES_TO_CHECKOUT
echo '/boost/container/*' >> $FILES_TO_CHECKOUT
echo '/boost/container_hash/*' >> $FILES_TO_CHECKOUT
echo '/boost/context/*' >> $FILES_TO_CHECKOUT
echo '/boost/convert/*' >> $FILES_TO_CHECKOUT
echo '/boost/coroutine/*' >> $FILES_TO_CHECKOUT
echo '/boost/core/*' >> $FILES_TO_CHECKOUT
echo '/boost/detail/*' >> $FILES_TO_CHECKOUT
echo '/boost/dynamic_bitset/*' >> $FILES_TO_CHECKOUT
echo '/boost/exception/*' >> $FILES_TO_CHECKOUT
echo '/boost/filesystem/*' >> $FILES_TO_CHECKOUT
echo '/boost/functional/*' >> $FILES_TO_CHECKOUT
echo '/boost/function/*' >> $FILES_TO_CHECKOUT
echo '/boost/geometry/*' >> $FILES_TO_CHECKOUT
echo '/boost/graph/*' >> $FILES_TO_CHECKOUT
echo '/boost/heap/*' >> $FILES_TO_CHECKOUT
echo '/boost/integer/*' >> $FILES_TO_CHECKOUT
echo '/boost/intrusive/*' >> $FILES_TO_CHECKOUT
echo '/boost/iostreams/*' >> $FILES_TO_CHECKOUT
echo '/boost/io/*' >> $FILES_TO_CHECKOUT
echo '/boost/iterator/*' >> $FILES_TO_CHECKOUT
echo '/boost/math/*' >> $FILES_TO_CHECKOUT
echo '/boost/move/*' >> $FILES_TO_CHECKOUT
echo '/boost/mpl/*' >> $FILES_TO_CHECKOUT
echo '/boost/multi_index/*' >> $FILES_TO_CHECKOUT
echo '/boost/multiprecision/*' >> $FILES_TO_CHECKOUT
echo '/boost/numeric/*' >> $FILES_TO_CHECKOUT
echo '/boost/predef/*' >> $FILES_TO_CHECKOUT
echo '/boost/preprocessor/*' >> $FILES_TO_CHECKOUT
echo '/boost/program_options/*' >> $FILES_TO_CHECKOUT
echo '/boost/range/*' >> $FILES_TO_CHECKOUT
echo '/boost/regex/*' >> $FILES_TO_CHECKOUT
echo '/boost/smart_ptr/*' >> $FILES_TO_CHECKOUT
echo '/boost/type_index/*' >> $FILES_TO_CHECKOUT
echo '/boost/type_traits/*' >> $FILES_TO_CHECKOUT
echo '/boost/system/*' >> $FILES_TO_CHECKOUT
echo '/boost/tti/*' >> $FILES_TO_CHECKOUT
echo '/boost/utility/*' >> $FILES_TO_CHECKOUT
echo '/boost/lexical_cast/*' >> $FILES_TO_CHECKOUT
echo '/boost/optional/*' >> $FILES_TO_CHECKOUT
echo '/boost/property_map/*' >> $FILES_TO_CHECKOUT
echo '/boost/pending/*' >> $FILES_TO_CHECKOUT
echo '/boost/multi_array/*' >> $FILES_TO_CHECKOUT
echo '/boost/tuple/*' >> $FILES_TO_CHECKOUT
echo '/boost/icl/*' >> $FILES_TO_CHECKOUT
echo '/boost/unordered/*' >> $FILES_TO_CHECKOUT
echo '/boost/typeof/*' >> $FILES_TO_CHECKOUT
echo '/boost/parameter/*' >> $FILES_TO_CHECKOUT
echo '/boost/mp11/*' >> $FILES_TO_CHECKOUT
echo '/boost/archive/*' >> $FILES_TO_CHECKOUT
echo '/boost/function_types/*' >> $FILES_TO_CHECKOUT
echo '/boost/serialization/*' >> $FILES_TO_CHECKOUT
echo '/boost/fusion/*' >> $FILES_TO_CHECKOUT
echo '/boost/variant/*' >> $FILES_TO_CHECKOUT
echo '/boost/format/*' >> $FILES_TO_CHECKOUT
echo '/boost/locale/*' >> $FILES_TO_CHECKOUT
echo '/boost/random/*' >> $FILES_TO_CHECKOUT
echo '/boost/spirit/*' >> $FILES_TO_CHECKOUT
echo '/boost/uuid/*' >> $FILES_TO_CHECKOUT
echo '/boost/xpressive/*' >> $FILES_TO_CHECKOUT
echo '/boost/asio/*' >> $FILES_TO_CHECKOUT
echo '/boost/circular_buffer/*' >> $FILES_TO_CHECKOUT
echo '/boost/proto/*' >> $FILES_TO_CHECKOUT
echo '/boost/qvm/*' >> $FILES_TO_CHECKOUT
echo '/boost/property_tree/*' >> $FILES_TO_CHECKOUT
echo '/libs/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

14
contrib/sparse-checkout/update-boringssl.sh Executable file
View File

@ -0,0 +1,14 @@
#!/bin/sh
echo "Using sparse checkout for boringsll"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/fuzz/*' >> $FILES_TO_CHECKOUT
echo '!/crypto/cipher_extra/test/*' >> $FILES_TO_CHECKOUT
echo '!/third_party/wycheproof_testvectors/*' >> $FILES_TO_CHECKOUT
echo '!/third_party/googletest/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

12
contrib/sparse-checkout/update-brotli.sh Executable file
View File

@ -0,0 +1,12 @@
#!/bin/sh
echo "Using sparse checkout for brotli"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/*/*' >> $FILES_TO_CHECKOUT
echo '/c/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

12
contrib/sparse-checkout/update-croaring.sh Executable file
View File

@ -0,0 +1,12 @@
#!/bin/sh
echo "Using sparse checkout for croaring"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/benchmarks/*' >> $FILES_TO_CHECKOUT
echo '!/tests/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

22
contrib/sparse-checkout/update-grpc.sh Executable file
View File

@ -0,0 +1,22 @@
#!/bin/sh
echo "Using sparse checkout for grpc"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/test/*' >> $FILES_TO_CHECKOUT
echo '/test/build/*' >> $FILES_TO_CHECKOUT
echo '!/tools/*' >> $FILES_TO_CHECKOUT
echo '/tools/codegen/*' >> $FILES_TO_CHECKOUT
echo '!/examples/*' >> $FILES_TO_CHECKOUT
echo '!/doc/*' >> $FILES_TO_CHECKOUT
# FIXME why do we need csharp?
#echo '!/src/csharp/*' >> $FILES_TO_CHECKOUT
echo '!/src/python/*' >> $FILES_TO_CHECKOUT
echo '!/src/objective-c/*' >> $FILES_TO_CHECKOUT
echo '!/src/php/*' >> $FILES_TO_CHECKOUT
echo '!/src/ruby/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

12
contrib/sparse-checkout/update-h3.sh Executable file
View File

@ -0,0 +1,12 @@
#!/bin/sh
echo "Using sparse checkout for h3"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/tests/*' >> $FILES_TO_CHECKOUT
echo '!/website/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

12
contrib/sparse-checkout/update-icu.sh Executable file
View File

@ -0,0 +1,12 @@
#!/bin/sh
echo "Using sparse checkout for icu"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/*/*' >> $FILES_TO_CHECKOUT
echo '/icu4c/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

16
contrib/sparse-checkout/update-libxml2.sh Executable file
View File

@ -0,0 +1,16 @@
#!/bin/sh
echo "Using sparse checkout for libxml2"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/result/*' >> $FILES_TO_CHECKOUT
echo '!/test/*' >> $FILES_TO_CHECKOUT
echo '!/doc/*' >> $FILES_TO_CHECKOUT
echo '!/os400/*' >> $FILES_TO_CHECKOUT
echo '!/fuzz/*' >> $FILES_TO_CHECKOUT
echo '!/python/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

27
contrib/sparse-checkout/update-llvm-project.sh Executable file
View File

@ -0,0 +1,27 @@
#!/bin/sh
echo "Using sparse checkout for llvm-project"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/*/*' >> $FILES_TO_CHECKOUT
echo '/llvm/*' >> $FILES_TO_CHECKOUT
echo '!/llvm/*/*' >> $FILES_TO_CHECKOUT
echo '/llvm/cmake/*' >> $FILES_TO_CHECKOUT
echo '/llvm/projects/*' >> $FILES_TO_CHECKOUT
echo '/llvm/include/*' >> $FILES_TO_CHECKOUT
echo '/llvm/lib/*' >> $FILES_TO_CHECKOUT
echo '/llvm/utils/TableGen/*' >> $FILES_TO_CHECKOUT
echo '/libcxxabi/*' >> $FILES_TO_CHECKOUT
echo '!/libcxxabi/test/*' >> $FILES_TO_CHECKOUT
echo '/libcxx/*' >> $FILES_TO_CHECKOUT
echo '!/libcxx/test/*' >> $FILES_TO_CHECKOUT
echo '/libunwind/*' >> $FILES_TO_CHECKOUT
echo '!/libunwind/test/*' >> $FILES_TO_CHECKOUT
echo '/compiler-rt/*' >> $FILES_TO_CHECKOUT
echo '!/compiler-rt/test/*' >> $FILES_TO_CHECKOUT
echo '/cmake/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

15
contrib/sparse-checkout/update-openssl.sh Executable file
View File

@ -0,0 +1,15 @@
#!/bin/sh
echo "Using sparse checkout for openssl"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/fuzz/*' >> $FILES_TO_CHECKOUT
echo '!/test/*' >> $FILES_TO_CHECKOUT
echo '!/doc/*' >> $FILES_TO_CHECKOUT
echo '!/providers/*' >> $FILES_TO_CHECKOUT
echo '!/apps/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

13
contrib/sparse-checkout/update-orc.sh Executable file
View File

@ -0,0 +1,13 @@
#!/bin/sh
echo "Using sparse checkout for orc"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '/*' > $FILES_TO_CHECKOUT
echo '!/*/*' >> $FILES_TO_CHECKOUT
echo '/c++/*' >> $FILES_TO_CHECKOUT
echo '/proto/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

13
contrib/sparse-checkout/update-protobuf.sh Executable file
View File

@ -0,0 +1,13 @@
#!/bin/sh
echo "Using sparse checkout for protobuf"
FILES_TO_CHECKOUT=$(git rev-parse --git-dir)/info/sparse-checkout
echo '!/*' > $FILES_TO_CHECKOUT
echo '/*/*' >> $FILES_TO_CHECKOUT
echo '/src/*' >> $FILES_TO_CHECKOUT
echo '/cmake/*' >> $FILES_TO_CHECKOUT
git config core.sparsecheckout true
git checkout $1
git read-tree -mu HEAD

11
contrib/update-submodules.sh vendored Executable file
View File

@ -0,0 +1,11 @@
#!/bin/sh
set -e
WORKDIR=$(dirname "$0")
WORKDIR=$(readlink -f "${WORKDIR}")
"$WORKDIR/sparse-checkout/setup-sparse-checkout.sh"
git submodule init
git submodule sync
git submodule update --depth=1

8
docs/en/development/developer-instruction.md
View File

@ -39,9 +39,15 @@ Next, you need to download the source files onto your working machine. This is c
In the command line terminal run:
git clone --recursive --shallow-submodules git@github.com:your_github_username/ClickHouse.git
git clone --shallow-submodules git@github.com:your_github_username/ClickHouse.git
cd ClickHouse
Or (if you'd like to use sparse checkout for submodules and avoid checking out unneeded files):
git clone git@github.com:your_github_username/ClickHouse.git
cd ClickHouse
./contrib/update-submodules.sh
Note: please, substitute *your_github_username* with what is appropriate!
This command will create a directory `ClickHouse` containing the working copy of the project.

1
docs/en/engines/database-engines/postgresql.md
View File

@ -140,3 +140,4 @@ DESCRIBE TABLE test_database.test_table;
## Related content
- Blog: [ClickHouse and PostgreSQL - a match made in data heaven - part 1](https://clickhouse.com/blog/migrating-data-between-clickhouse-postgres)
- Blog: [ClickHouse and PostgreSQL - a Match Made in Data Heaven - part 2](https://clickhouse.com/blog/migrating-data-between-clickhouse-postgres-part-2)

2
docs/en/engines/table-engines/integrations/postgresql.md
View File

@ -177,4 +177,6 @@ CREATE TABLE pg_table_schema_with_dots (a UInt32)
- [Using PostgreSQL as a dictionary source](../../../sql-reference/dictionaries/index.md#dictionary-sources#dicts-external_dicts_dict_sources-postgresql)
## Related content
- Blog: [ClickHouse and PostgreSQL - a match made in data heaven - part 1](https://clickhouse.com/blog/migrating-data-between-clickhouse-postgres)
- Blog: [ClickHouse and PostgreSQL - a Match Made in Data Heaven - part 2](https://clickhouse.com/blog/migrating-data-between-clickhouse-postgres-part-2)

4
docs/en/engines/table-engines/mergetree-family/aggregatingmergetree.md
View File

@ -122,3 +122,7 @@ FROM test.mv_visits
GROUP BY StartDate
ORDER BY StartDate;
```
## Related Content
- Blog: [Using Aggregate Combinators in ClickHouse](https://clickhouse.com/blog/aggregate-functions-combinators-in-clickhouse-for-arrays-maps-and-states)

4
docs/en/engines/table-engines/mergetree-family/invertedindexes.md
View File

@ -191,3 +191,7 @@ is performance. In practice, users often search for multiple terms at once. For
'%big%'` can be evaluated directly using an inverted index by forming the union of the row id lists for terms "little" and "big". This also
means that the parameter `GRANULARITY` supplied to index creation has no meaning (it may be removed from the syntax in the future).
:::
## Related Content
- Blog: [Introducing Inverted Indices in ClickHouse](https://clickhouse.com/blog/clickhouse-search-with-inverted-indices)

13
docs/en/engines/table-engines/mergetree-family/replication.md
View File

@ -8,11 +8,18 @@ sidebar_label: Data Replication
:::note
In ClickHouse Cloud replication is managed for you. Please create your tables without adding arguments. For example, in the text below you would replace:
```sql
ENGINE = ReplicatedReplacingMergeTree(
'/clickhouse/tables/{shard}/table_name',
'{replica}',
ver
)
```
ENGINE = ReplicatedReplacingMergeTree('/clickhouse/tables/{shard}/table_name', '{replica}', ver)
```
with:
```
```sql
ENGINE = ReplicatedReplacingMergeTree
```
:::

4
docs/en/engines/table-engines/mergetree-family/summingmergetree.md
View File

@ -186,3 +186,7 @@ ARRAY JOIN
When requesting data, use the [sumMap(key, value)](../../../sql-reference/aggregate-functions/reference/summap.md) function for aggregation of `Map`.
For nested data structure, you do not need to specify its columns in the tuple of columns for summation.
## Related Content
- Blog: [Using Aggregate Combinators in ClickHouse](https://clickhouse.com/blog/aggregate-functions-combinators-in-clickhouse-for-arrays-maps-and-states)

4
docs/en/engines/table-engines/special/keepermap.md
View File

@ -112,3 +112,7 @@ If setting `keeper_map_strict_mode` is set to `true`, fetching and updating data
```sql
ALTER TABLE keeper_map_table UPDATE v1 = v1 * 10 + 2 WHERE key LIKE 'some%' AND v3 > 3.1;
```
## Related content
- Blog: [Building a Real-time Analytics Apps with ClickHouse and Hex](https://clickhouse.com/blog/building-real-time-applications-with-clickhouse-and-hex-notebook-keeper-engine)

8
docs/en/getting-started/example-datasets/github.md
View File

@ -2499,7 +2499,9 @@ LIMIT 20
We welcome exact and improved solutions here.
# Related Content
## Related Content
- [Git commits and our community](https://clickhouse.com/blog/clickhouse-git-community-commits)
- [Window and array functions for Git commit sequences](https://clickhouse.com/blog/clickhouse-window-array-functions-git-commits)
- Blog: [Git commits and our community](https://clickhouse.com/blog/clickhouse-git-community-commits)
- Blog: [Window and array functions for Git commit sequences](https://clickhouse.com/blog/clickhouse-window-array-functions-git-commits)
- Blog: [Building a Real-time Analytics Apps with ClickHouse and Hex](https://clickhouse.com/blog/building-real-time-applications-with-clickhouse-and-hex-notebook-keeper-engine)
- Blog: [A Story of Open-source GitHub Activity using ClickHouse + Grafana](https://clickhouse.com/blog/introduction-to-clickhouse-and-grafana-webinar)

188
docs/en/interfaces/formats.md
View File

@ -78,7 +78,7 @@ The supported formats are:
| [Null](#null) | ✗ | ✔ |
| [XML](#xml) | ✗ | ✔ |
| [CapnProto](#capnproto) | ✔ | ✔ |
| [LineAsString](#lineasstring) | ✔ | ✗ |
| [LineAsString](#lineasstring) | ✔ | ✔ |
| [Regexp](#data-format-regexp) | ✔ | ✗ |
| [RawBLOB](#rawblob) | ✔ | ✔ |
| [MsgPack](#msgpack) | ✔ | ✔ |
@ -1235,8 +1235,8 @@ For output it uses the following correspondence between ClickHouse types and BSO
| ClickHouse type | BSON Type |
|-----------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------|
| [Bool](/docs/en/sql-reference/data-types/boolean.md) | `\x08` boolean |
| [Int8/UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `\x10` int32 |
| [Int16UInt16](/docs/en/sql-reference/data-types/int-uint.md) | `\x10` int32 |
| [Int8/UInt8](/docs/en/sql-reference/data-types/int-uint.md)/[Enum8](/docs/en/sql-reference/data-types/enum.md) | `\x10` int32 |
| [Int16/UInt16](/docs/en/sql-reference/data-types/int-uint.md)/[Enum16](/docs/en/sql-reference/data-types/enum.md) | `\x10` int32 |
| [Int32](/docs/en/sql-reference/data-types/int-uint.md) | `\x10` int32 |
| [UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `\x12` int64 |
| [Int64/UInt64](/docs/en/sql-reference/data-types/int-uint.md) | `\x12` int64 |
@ -1255,30 +1255,30 @@ For output it uses the following correspondence between ClickHouse types and BSO
| [Array](/docs/en/sql-reference/data-types/array.md) | `\x04` array |
| [Tuple](/docs/en/sql-reference/data-types/tuple.md) | `\x04` array |
| [Named Tuple](/docs/en/sql-reference/data-types/tuple.md) | `\x03` document |
| [Map](/docs/en/sql-reference/data-types/map.md) (with String keys) | `\x03` document |
| [Map](/docs/en/sql-reference/data-types/map.md) | `\x03` document |
| [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md) | `\x10` int32 |
| [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) | `\x05` binary, `\x00` binary subtype |
For input it uses the following correspondence between BSON types and ClickHouse types:
| BSON Type | ClickHouse Type |
|------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `\x01` double | [Float32/Float64](/docs/en/sql-reference/data-types/float.md) |
| `\x02` string | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x03` document | [Map](/docs/en/sql-reference/data-types/map.md)/[Named Tuple](/docs/en/sql-reference/data-types/tuple.md) |
| `\x04` array | [Array](/docs/en/sql-reference/data-types/array.md)/[Tuple](/docs/en/sql-reference/data-types/tuple.md) |
| `\x05` binary, `\x00` binary subtype | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)/[IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) |
| `\x05` binary, `\x02` old binary subtype | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x05` binary, `\x03` old uuid subtype | [UUID](/docs/en/sql-reference/data-types/uuid.md) |
| `\x05` binary, `\x04` uuid subtype | [UUID](/docs/en/sql-reference/data-types/uuid.md) |
| `\x07` ObjectId | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x08` boolean | [Bool](/docs/en/sql-reference/data-types/boolean.md) |
| `\x09` datetime | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
| `\x0A` null value | [NULL](/docs/en/sql-reference/data-types/nullable.md) |
| `\x0D` JavaScript code | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x0E` symbol | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x10` int32 | [Int32/UInt32](/docs/en/sql-reference/data-types/int-uint.md)/[Decimal32](/docs/en/sql-reference/data-types/decimal.md)/[IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md) |
| `\x12` int64 | [Int64/UInt64](/docs/en/sql-reference/data-types/int-uint.md)/[Decimal64](/docs/en/sql-reference/data-types/decimal.md)/[DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
| BSON Type | ClickHouse Type |
|------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `\x01` double | [Float32/Float64](/docs/en/sql-reference/data-types/float.md) |
| `\x02` string | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x03` document | [Map](/docs/en/sql-reference/data-types/map.md)/[Named Tuple](/docs/en/sql-reference/data-types/tuple.md) |
| `\x04` array | [Array](/docs/en/sql-reference/data-types/array.md)/[Tuple](/docs/en/sql-reference/data-types/tuple.md) |
| `\x05` binary, `\x00` binary subtype | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md)/[IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) |
| `\x05` binary, `\x02` old binary subtype | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x05` binary, `\x03` old uuid subtype | [UUID](/docs/en/sql-reference/data-types/uuid.md) |
| `\x05` binary, `\x04` uuid subtype | [UUID](/docs/en/sql-reference/data-types/uuid.md) |
| `\x07` ObjectId | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x08` boolean | [Bool](/docs/en/sql-reference/data-types/boolean.md) |
| `\x09` datetime | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
| `\x0A` null value | [NULL](/docs/en/sql-reference/data-types/nullable.md) |
| `\x0D` JavaScript code | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x0E` symbol | [String](/docs/en/sql-reference/data-types/string.md)/[FixedString](/docs/en/sql-reference/data-types/fixedstring.md) |
| `\x10` int32 | [Int32/UInt32](/docs/en/sql-reference/data-types/int-uint.md)/[Decimal32](/docs/en/sql-reference/data-types/decimal.md)/[IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md)/[Enum8/Enum16](/docs/en/sql-reference/data-types/enum.md) |
| `\x12` int64 | [Int64/UInt64](/docs/en/sql-reference/data-types/int-uint.md)/[Decimal64](/docs/en/sql-reference/data-types/decimal.md)/[DateTime64](/docs/en/sql-reference/data-types/datetime64.md) |
Other BSON types are not supported. Also, it performs conversion between different integer types (for example, you can insert BSON int32 value into ClickHouse UInt8).
Big integers and decimals (Int128/UInt128/Int256/UInt256/Decimal128/Decimal256) can be parsed from BSON Binary value with `\x00` binary subtype. In this case this format will validate that the size of binary data equals the size of expected value.
@ -1877,6 +1877,13 @@ Column names must:
Output Avro file compression and sync interval can be configured with [output_format_avro_codec](/docs/en/operations/settings/settings-formats.md/#output_format_avro_codec) and [output_format_avro_sync_interval](/docs/en/operations/settings/settings-formats.md/#output_format_avro_sync_interval) respectively.
### Example Data {#example-data-avro}
Using the ClickHouse [DESCRIBE](/docs/en/sql-reference/statements/describe-table) function, you can quickly view the inferred format of an Avro file like the following example. This example includes the URL of a publicly accessible Avro file in the ClickHouse S3 public bucket:
``` DESCRIBE url('https://clickhouse-public-datasets.s3.eu-central-1.amazonaws.com/hits.avro','Avro');
```
## AvroConfluent {#data-format-avro-confluent}
AvroConfluent supports decoding single-object Avro messages commonly used with [Kafka](https://kafka.apache.org/) and [Confluent Schema Registry](https://docs.confluent.io/current/schema-registry/index.html).
@ -1936,30 +1943,31 @@ Setting `format_avro_schema_registry_url` needs to be configured in `users.xml`
The table below shows supported data types and how they match ClickHouse [data types](/docs/en/sql-reference/data-types/index.md) in `INSERT` and `SELECT` queries.
| Parquet data type (`INSERT`) | ClickHouse data type | Parquet data type (`SELECT`) |
|----------------------------------------------------|-----------------------------------------------------------------|------------------------------|
| `BOOL` | [Bool](/docs/en/sql-reference/data-types/boolean.md) | `BOOL` |
| `UINT8`, `BOOL` | [UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `UINT8` |
| `INT8` | [Int8](/docs/en/sql-reference/data-types/int-uint.md) | `INT8` |
| `UINT16` | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) | `UINT16` |
| `INT16` | [Int16](/docs/en/sql-reference/data-types/int-uint.md) | `INT16` |
| `UINT32` | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `UINT32` |
| `INT32` | [Int32](/docs/en/sql-reference/data-types/int-uint.md) | `INT32` |
| `UINT64` | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) | `UINT64` |
| `INT64` | [Int64](/docs/en/sql-reference/data-types/int-uint.md) | `INT64` |
| `FLOAT` | [Float32](/docs/en/sql-reference/data-types/float.md) | `FLOAT` |
| `DOUBLE` | [Float64](/docs/en/sql-reference/data-types/float.md) | `DOUBLE` |
| `DATE` | [Date32](/docs/en/sql-reference/data-types/date.md) | `DATE` |
| `TIME (ms)` | [DateTime](/docs/en/sql-reference/data-types/datetime.md) | `UINT32` |
| `TIMESTAMP`, `TIME (us, ns)` | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) | `TIMESTAMP` |
| `STRING`, `BINARY` | [String](/docs/en/sql-reference/data-types/string.md) | `BINARY` |
| `STRING`, `BINARY`, `FIXED_LENGTH_BYTE_ARRAY` | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `FIXED_LENGTH_BYTE_ARRAY` |
| `DECIMAL` | [Decimal](/docs/en/sql-reference/data-types/decimal.md) | `DECIMAL` |
| `LIST` | [Array](/docs/en/sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](/docs/en/sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](/docs/en/sql-reference/data-types/map.md) | `MAP` |
| `UINT32` | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md) | `UINT32` |
| `FIXED_LENGTH_BYTE_ARRAY` | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) | `FIXED_LENGTH_BYTE_ARRAY` |
| Parquet data type (`INSERT`) | ClickHouse data type | Parquet data type (`SELECT`) |
|-----------------------------------------------|------------------------------------------------------------------------------------------------------------|-------------------------------|
| `BOOL` | [Bool](/docs/en/sql-reference/data-types/boolean.md) | `BOOL` |
| `UINT8`, `BOOL` | [UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `UINT8` |
| `INT8` | [Int8](/docs/en/sql-reference/data-types/int-uint.md)/[Enum8](/docs/en/sql-reference/data-types/enum.md) | `INT8` |
| `UINT16` | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) | `UINT16` |
| `INT16` | [Int16](/docs/en/sql-reference/data-types/int-uint.md)/[Enum16](/docs/en/sql-reference/data-types/enum.md) | `INT16` |
| `UINT32` | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `UINT32` |
| `INT32` | [Int32](/docs/en/sql-reference/data-types/int-uint.md) | `INT32` |
| `UINT64` | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) | `UINT64` |
| `INT64` | [Int64](/docs/en/sql-reference/data-types/int-uint.md) | `INT64` |
| `FLOAT` | [Float32](/docs/en/sql-reference/data-types/float.md) | `FLOAT` |
| `DOUBLE` | [Float64](/docs/en/sql-reference/data-types/float.md) | `DOUBLE` |
| `DATE` | [Date32](/docs/en/sql-reference/data-types/date.md) | `DATE` |
| `TIME (ms)` | [DateTime](/docs/en/sql-reference/data-types/datetime.md) | `UINT32` |
| `TIMESTAMP`, `TIME (us, ns)` | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) | `TIMESTAMP` |
| `STRING`, `BINARY` | [String](/docs/en/sql-reference/data-types/string.md) | `BINARY` |
| `STRING`, `BINARY`, `FIXED_LENGTH_BYTE_ARRAY` | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `FIXED_LENGTH_BYTE_ARRAY` |
| `DECIMAL` | [Decimal](/docs/en/sql-reference/data-types/decimal.md) | `DECIMAL` |
| `LIST` | [Array](/docs/en/sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](/docs/en/sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](/docs/en/sql-reference/data-types/map.md) | `MAP` |
| `UINT32` | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md) | `UINT32` |
| `FIXED_LENGTH_BYTE_ARRAY`, `BINARY` | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) | `FIXED_LENGTH_BYTE_ARRAY` |
| `FIXED_LENGTH_BYTE_ARRAY`, `BINARY` | [Int128/UInt128/Int256/UInt256](/docs/en/sql-reference/data-types/int-uint.md) | `FIXED_LENGTH_BYTE_ARRAY` |
Arrays can be nested and can have a value of the `Nullable` type as an argument. `Tuple` and `Map` types also can be nested.
@ -2005,31 +2013,32 @@ To exchange data with Hadoop, you can use [HDFS table engine](/docs/en/engines/t
The table below shows supported data types and how they match ClickHouse [data types](/docs/en/sql-reference/data-types/index.md) in `INSERT` and `SELECT` queries.
| Arrow data type (`INSERT`) | ClickHouse data type | Arrow data type (`SELECT`) |
|-----------------------------------------|-----------------------------------------------------------------|----------------------------|
| `BOOL` | [Bool](/docs/en/sql-reference/data-types/boolean.md) | `BOOL` |
| `UINT8`, `BOOL` | [UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `UINT8` |
| `INT8` | [Int8](/docs/en/sql-reference/data-types/int-uint.md) | `INT8` |
| `UINT16` | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) | `UINT16` |
| `INT16` | [Int16](/docs/en/sql-reference/data-types/int-uint.md) | `INT16` |
| `UINT32` | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `UINT32` |
| `INT32` | [Int32](/docs/en/sql-reference/data-types/int-uint.md) | `INT32` |
| `UINT64` | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) | `UINT64` |
| `INT64` | [Int64](/docs/en/sql-reference/data-types/int-uint.md) | `INT64` |
| `FLOAT`, `HALF_FLOAT` | [Float32](/docs/en/sql-reference/data-types/float.md) | `FLOAT32` |
| `DOUBLE` | [Float64](/docs/en/sql-reference/data-types/float.md) | `FLOAT64` |
| `DATE32` | [Date32](/docs/en/sql-reference/data-types/date32.md) | `UINT16` |
| `DATE64` | [DateTime](/docs/en/sql-reference/data-types/datetime.md) | `UINT32` |
| `TIMESTAMP`, `TIME32`, `TIME64` | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) | `UINT32` |
| `STRING`, `BINARY` | [String](/docs/en/sql-reference/data-types/string.md) | `BINARY` |
| `STRING`, `BINARY`, `FIXED_SIZE_BINARY` | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `FIXED_SIZE_BINARY` |
| `DECIMAL` | [Decimal](/docs/en/sql-reference/data-types/decimal.md) | `DECIMAL` |
| `DECIMAL256` | [Decimal256](/docs/en/sql-reference/data-types/decimal.md) | `DECIMAL256` |
| `LIST` | [Array](/docs/en/sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](/docs/en/sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](/docs/en/sql-reference/data-types/map.md) | `MAP` |
| `UINT32` | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md) | `UINT32` |
| `FIXED_SIZE_BINARY`, `BINARY` | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) | `FIXED_SIZE_BINARY` |
| Arrow data type (`INSERT`) | ClickHouse data type | Arrow data type (`SELECT`) |
|-----------------------------------------|------------------------------------------------------------------------------------------------------------|----------------------------|
| `BOOL` | [Bool](/docs/en/sql-reference/data-types/boolean.md) | `BOOL` |
| `UINT8`, `BOOL` | [UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `UINT8` |
| `INT8` | [Int8](/docs/en/sql-reference/data-types/int-uint.md)/[Enum8](/docs/en/sql-reference/data-types/enum.md) | `INT8` |
| `UINT16` | [UInt16](/docs/en/sql-reference/data-types/int-uint.md) | `UINT16` |
| `INT16` | [Int16](/docs/en/sql-reference/data-types/int-uint.md)/[Enum16](/docs/en/sql-reference/data-types/enum.md) | `INT16` |
| `UINT32` | [UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `UINT32` |
| `INT32` | [Int32](/docs/en/sql-reference/data-types/int-uint.md) | `INT32` |
| `UINT64` | [UInt64](/docs/en/sql-reference/data-types/int-uint.md) | `UINT64` |
| `INT64` | [Int64](/docs/en/sql-reference/data-types/int-uint.md) | `INT64` |
| `FLOAT`, `HALF_FLOAT` | [Float32](/docs/en/sql-reference/data-types/float.md) | `FLOAT32` |
| `DOUBLE` | [Float64](/docs/en/sql-reference/data-types/float.md) | `FLOAT64` |
| `DATE32` | [Date32](/docs/en/sql-reference/data-types/date32.md) | `UINT16` |
| `DATE64` | [DateTime](/docs/en/sql-reference/data-types/datetime.md) | `UINT32` |
| `TIMESTAMP`, `TIME32`, `TIME64` | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) | `UINT32` |
| `STRING`, `BINARY` | [String](/docs/en/sql-reference/data-types/string.md) | `BINARY` |
| `STRING`, `BINARY`, `FIXED_SIZE_BINARY` | [FixedString](/docs/en/sql-reference/data-types/fixedstring.md) | `FIXED_SIZE_BINARY` |
| `DECIMAL` | [Decimal](/docs/en/sql-reference/data-types/decimal.md) | `DECIMAL` |
| `DECIMAL256` | [Decimal256](/docs/en/sql-reference/data-types/decimal.md) | `DECIMAL256` |
| `LIST` | [Array](/docs/en/sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](/docs/en/sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](/docs/en/sql-reference/data-types/map.md) | `MAP` |
| `UINT32` | [IPv4](/docs/en/sql-reference/data-types/domains/ipv4.md) | `UINT32` |
| `FIXED_SIZE_BINARY`, `BINARY` | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) | `FIXED_SIZE_BINARY` |
| `FIXED_SIZE_BINARY`, `BINARY` | [Int128/UInt128/Int256/UInt256](/docs/en/sql-reference/data-types/int-uint.md) | `FIXED_SIZE_BINARY` |
Arrays can be nested and can have a value of the `Nullable` type as an argument. `Tuple` and `Map` types also can be nested.
@ -2078,23 +2087,26 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Arrow" > {filenam
The table below shows supported data types and how they match ClickHouse [data types](/docs/en/sql-reference/data-types/index.md) in `INSERT` and `SELECT` queries.
| ORC data type (`INSERT`) | ClickHouse data type | ORC data type (`SELECT`) |
|---------------------------------------|---------------------------------------------------------------|--------------------------|
| `Boolean` | [UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `Boolean` |
| `Tinyint` | [Int8](/docs/en/sql-reference/data-types/int-uint.md) | `Tinyint` |
| `Smallint` | [Int16](/docs/en/sql-reference/data-types/int-uint.md) | `Smallint` |
| `Int` | [Int32](/docs/en/sql-reference/data-types/int-uint.md) | `Int` |
| `Bigint` | [Int64](/docs/en/sql-reference/data-types/int-uint.md) | `Bigint` |
| `Float` | [Float32](/docs/en/sql-reference/data-types/float.md) | `Float` |
| `Double` | [Float64](/docs/en/sql-reference/data-types/float.md) | `Double` |
| `Decimal` | [Decimal](/docs/en/sql-reference/data-types/decimal.md) | `Decimal` |
| `Date` | [Date32](/docs/en/sql-reference/data-types/date32.md) | `Date` |
| `Timestamp` | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) | `Timestamp` |
| `String`, `Char`, `Varchar`, `Binary` | [String](/docs/en/sql-reference/data-types/string.md) | `Binary` |
| `List` | [Array](/docs/en/sql-reference/data-types/array.md) | `List` |
| `Struct` | [Tuple](/docs/en/sql-reference/data-types/tuple.md) | `Struct` |
| `Map` | [Map](/docs/en/sql-reference/data-types/map.md) | `Map` |
| `-` | [IPv4](/docs/en/sql-reference/data-types/int-uint.md) | `Int` |
| ORC data type (`INSERT`) | ClickHouse data type | ORC data type (`SELECT`) |
|---------------------------------------|-------------------------------------------------------------------------------------------------------------------|--------------------------|
| `Boolean` | [UInt8](/docs/en/sql-reference/data-types/int-uint.md) | `Boolean` |
| `Tinyint` | [Int8/UInt8](/docs/en/sql-reference/data-types/int-uint.md)/[Enum8](/docs/en/sql-reference/data-types/enum.md) | `Tinyint` |
| `Smallint` | [Int16/UInt16](/docs/en/sql-reference/data-types/int-uint.md)/[Enum16](/docs/en/sql-reference/data-types/enum.md) | `Smallint` |
| `Int` | [Int32/UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `Int` |
| `Bigint` | [Int64/UInt32](/docs/en/sql-reference/data-types/int-uint.md) | `Bigint` |
| `Float` | [Float32](/docs/en/sql-reference/data-types/float.md) | `Float` |
| `Double` | [Float64](/docs/en/sql-reference/data-types/float.md) | `Double` |
| `Decimal` | [Decimal](/docs/en/sql-reference/data-types/decimal.md) | `Decimal` |
| `Date` | [Date32](/docs/en/sql-reference/data-types/date32.md) | `Date` |
| `Timestamp` | [DateTime64](/docs/en/sql-reference/data-types/datetime64.md) | `Timestamp` |
| `String`, `Char`, `Varchar`, `Binary` | [String](/docs/en/sql-reference/data-types/string.md) | `Binary` |
| `List` | [Array](/docs/en/sql-reference/data-types/array.md) | `List` |
| `Struct` | [Tuple](/docs/en/sql-reference/data-types/tuple.md) | `Struct` |
| `Map` | [Map](/docs/en/sql-reference/data-types/map.md) | `Map` |
| `Int` | [IPv4](/docs/en/sql-reference/data-types/int-uint.md) | `Int` |
| `Binary` | [IPv6](/docs/en/sql-reference/data-types/domains/ipv6.md) | `Binary` |
| `Binary` | [Int128/UInt128/Int256/UInt256](/docs/en/sql-reference/data-types/int-uint.md) | `Binary` |
| `Binary` | [Decimal256](/docs/en/sql-reference/data-types/decimal.md) | `Binary` |
Other types are not supported.

4
docs/en/operations/opentelemetry.md
View File

@ -61,3 +61,7 @@ FROM system.opentelemetry_span_log
```
In case of any errors, the part of the log data for which the error has occurred will be silently lost. Check the server log for error messages if the data does not arrive.
## Related Content
- Blog: [Building an Observability Solution with ClickHouse - Part 2 - Traces](https://clickhouse.com/blog/storing-traces-and-spans-open-telemetry-in-clickhouse)

4
docs/en/operations/query-cache.md
View File

@ -124,3 +124,7 @@ Finally, entries in the query cache are not shared between users due to security
row policy on a table by running the same query as another user B for whom no such policy exists. However, if necessary, cache entries can
be marked accessible by other users (i.e. shared) by supplying setting
[query_cache_share_between_users](settings/settings.md#query-cache-share-between-users).
## Related Content
- Blog: [Introducing the ClickHouse Query Cache](https://clickhouse.com/blog/introduction-to-the-clickhouse-query-cache-and-design)

2
docs/en/operations/system-tables/replicas.md
View File

@ -50,6 +50,7 @@ last_queue_update: 2021-10-12 14:50:08
absolute_delay: 99
total_replicas: 5
active_replicas: 5
lost_part_count: 0
last_queue_update_exception:
zookeeper_exception:
replica_is_active: {'r1':1,'r2':1}
@ -90,6 +91,7 @@ The next 4 columns have a non-zero value only where there is an active session w
- `absolute_delay` (`UInt64`) - How big lag in seconds the current replica has.
- `total_replicas` (`UInt8`) - The total number of known replicas of this table.
- `active_replicas` (`UInt8`) - The number of replicas of this table that have a session in ClickHouse Keeper (i.e., the number of functioning replicas).
- `lost_part_count` (`UInt64`) - The number of data parts lost in the table by all replicas in total since table creation. Value is persisted in ClickHouse Keeper and can only increase.
- `last_queue_update_exception` (`String`) - When the queue contains broken entries. Especially important when ClickHouse breaks backward compatibility between versions and log entries written by newer versions aren't parseable by old versions.
- `zookeeper_exception` (`String`) - The last exception message, got if the error happened when fetching the info from ClickHouse Keeper.
- `replica_is_active` ([Map(String, UInt8)](../../sql-reference/data-types/map.md)) — Map between replica name and is replica active.

8
docs/en/operations/system-tables/storage_policies.md
View File

@ -11,8 +11,16 @@ Columns:
- `volume_name` ([String](../../sql-reference/data-types/string.md)) — Volume name defined in the storage policy.
- `volume_priority` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Volume order number in the configuration, the data fills the volumes according this priority, i.e. data during inserts and merges is written to volumes with a lower priority (taking into account other rules: TTL, `max_data_part_size`, `move_factor`).
- `disks` ([Array(String)](../../sql-reference/data-types/array.md)) — Disk names, defined in the storage policy.
- `volume_type` ([Enum8](../../sql-reference/data-types/enum.md)) — Type of volume. Can have one of the following values:
- `JBOD`
- `SINGLE_DISK`
- `UNKNOWN`
- `max_data_part_size` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Maximum size of a data part that can be stored on volume disks (0 — no limit).
- `move_factor` ([Float64](../../sql-reference/data-types/float.md)) — Ratio of free disk space. When the ratio exceeds the value of configuration parameter, ClickHouse start to move data to the next volume in order.
- `prefer_not_to_merge` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Value of the `prefer_not_to_merge` setting. When this setting is enabled, merging data on this volume is not allowed. This allows controlling how ClickHouse works with slow disks.
- `perform_ttl_move_on_insert` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Value of the `perform_ttl_move_on_insert` setting. — Disables TTL move on data part INSERT. By default if we insert a data part that already expired by the TTL move rule it immediately goes to a volume/disk declared in move rule. This can significantly slowdown insert in case if destination volume/disk is slow (e.g. S3).
- `load_balancing` ([Enum8](../../sql-reference/data-types/enum.md)) — Policy for disk balancing. Can have one of the following values:
- `ROUND_ROBIN`
- `LEAST_USED`
If the storage policy contains more then one volume, then information for each volume is stored in the individual row of the table.

12
docs/en/operations/utilities/clickhouse-local.md
View File

@ -6,7 +6,17 @@ sidebar_label: clickhouse-local
# clickhouse-local
The `clickhouse-local` program enables you to perform fast processing on local files, without having to deploy and configure the ClickHouse server. It accepts data that represent tables and queries them using [ClickHouse SQL dialect](../../sql-reference/index.md). `clickhouse-local` uses the same core as ClickHouse server, so it supports most of the features and the same set of formats and table engines.
## Related Content
- Blog: [Extracting, Converting, and Querying Data in Local Files using clickhouse-local](https://clickhouse.com/blog/extracting-converting-querying-local-files-with-sql-clickhouse-local)
## When to use clickhouse-local vs. ClickHouse
`clickhouse-local` is an easy-to-use version of ClickHouse that is ideal for developers who need to perform fast processing on local and remote files using SQL without having to install a full database server. With `clickhouse-local`, developers can use SQL commands (using the [ClickHouse SQL dialect](../../sql-reference/index.md)) directly from the command line, providing a simple and efficient way to access ClickHouse features without the need for a full ClickHouse installation. One of the main benefits of `clickhouse-local` is that it is already included when installing [clickhouse-client](https://clickhouse.com/docs/en/integrations/sql-clients/clickhouse-client-local). This means that developers can get started with `clickhouse-local` quickly, without the need for a complex installation process.
While `clickhouse-local` is a great tool for development and testing purposes, and for processing files, it is not suitable for serving end users or applications. In these scenarios, it is recommended to use the open-source [ClickHouse](https://clickhouse.com/docs/en/install). ClickHouse is a powerful OLAP database that is designed to handle large-scale analytical workloads. It provides fast and efficient processing of complex queries on large datasets, making it ideal for use in production environments where high-performance is critical. Additionally, ClickHouse offers a wide range of features such as replication, sharding, and high availability, which are essential for scaling up to handle large datasets and serving applications. If you need to handle larger datasets or serve end users or applications, we recommend using open-source ClickHouse instead of `clickhouse-local`.
Please read the docs below that show example use cases for `clickhouse-local`, such as [querying local CSVs](#query-data-in-a-csv-file-using-sql) or [reading a parquet file in S3](#query-data-in-a-parquet-file-in-aws-s3).
## Download clickhouse-local

5
docs/en/sql-reference/aggregate-functions/combinators.md
View File

@ -285,3 +285,8 @@ FROM people
│ [3,2] │ [11.5,12.949999809265137] │
└────────┴───────────────────────────┘
```
## Related Content
- Blog: [Using Aggregate Combinators in ClickHouse](https://clickhouse.com/blog/aggregate-functions-combinators-in-clickhouse-for-arrays-maps-and-states)

2
docs/en/sql-reference/aggregate-functions/reference/deltasumtimestamp.md
View File

@ -6,7 +6,7 @@ title: deltaSumTimestamp
Adds the difference between consecutive rows. If the difference is negative, it is ignored.
This function is primarily for [materialized views](../../../sql-reference/statements/create/view.md#materialized) that are ordered by some time bucket-aligned timestamp, for example, a `toStartOfMinute` bucket. Because the rows in such a materialized view will all have the same timestamp, it is impossible for them to be merged in the "right" order. This function keeps track of the `timestamp` of the values it's seen, so it's possible to order the states correctly during merging.
This function is primarily for [materialized views](../../../sql-reference/statements/create/view.md#materialized) that store data ordered by some time bucket-aligned timestamp, for example, a `toStartOfMinute` bucket. Because the rows in such a materialized view will all have the same timestamp, it is impossible for them to be merged in the correct order, without storing the original, unrounded timestamp value. The `deltaSumTimestamp` function keeps track of the original `timestamp` of the values it's seen, so the values (states) of the function are correctly computed during merging of parts.
To calculate the delta sum across an ordered collection you can simply use the [deltaSum](../../../sql-reference/aggregate-functions/reference/deltasum.md#agg_functions-deltasum) function.

5
docs/en/sql-reference/data-types/aggregatefunction.md
View File

@ -63,3 +63,8 @@ SELECT uniqMerge(state) FROM (SELECT uniqState(UserID) AS state FROM table GROUP
## Usage Example
See [AggregatingMergeTree](../../engines/table-engines/mergetree-family/aggregatingmergetree.md) engine description.
## Related Content
- Blog: [Using Aggregate Combinators in ClickHouse](https://clickhouse.com/blog/aggregate-functions-combinators-in-clickhouse-for-arrays-maps-and-states)

5
docs/en/sql-reference/data-types/map.md
View File

@ -108,3 +108,8 @@ Result:
- [map()](../../sql-reference/functions/tuple-map-functions.md#function-map) function
- [CAST()](../../sql-reference/functions/type-conversion-functions.md#type_conversion_function-cast) function
## Related content
- Blog: [Building an Observability Solution with ClickHouse - Part 2 - Traces](https://clickhouse.com/blog/storing-traces-and-spans-open-telemetry-in-clickhouse)

16
docs/en/sql-reference/functions/date-time-functions.md
View File

@ -645,7 +645,7 @@ For an alternative to `date\_diff`, see function `age`.
date_diff('unit', startdate, enddate, [timezone])
```
Aliases: `dateDiff`, `DATE_DIFF`.
Aliases: `dateDiff`, `DATE_DIFF`, `timestampDiff`, `timestamp_diff`, `TIMESTAMP_DIFF`.
**Arguments**
@ -1264,7 +1264,7 @@ Using replacement fields, you can define a pattern for the resulting string. “
| %d | day of the month, zero-padded (01-31) | 02 |
| %D | Short MM/DD/YY date, equivalent to %m/%d/%y | 01/02/18 |
| %e | day of the month, space-padded (1-31) | &nbsp; 2 |
| %f | fractional second from the fractional part of DateTime64 | 1234560 |
| %f | fractional second, see 'Note 1' below | 1234560 |
| %F | short YYYY-MM-DD date, equivalent to %Y-%m-%d | 2018-01-02 |
| %g | two-digit year format, aligned to ISO 8601, abbreviated from four-digit notation | 18 |
| %G | four-digit year format for ISO week number, calculated from the week-based year [defined by the ISO 8601](https://en.wikipedia.org/wiki/ISO_8601#Week_dates) standard, normally useful only with %V | 2018 |
@ -1276,16 +1276,16 @@ Using replacement fields, you can define a pattern for the resulting string. “
| %k | hour in 24h format (00-23) | 22 |
| %l | hour in 12h format (01-12) | 09 |
| %m | month as an integer number (01-12) | 01 |
| %M | minute (00-59) | 33 |
| %M | full month name (January-December), see 'Note 2' below | January |
| %n | new-line character (‘’) | |
| %p | AM or PM designation | PM |
| %Q | Quarter (1-4) | 1 |
| %r | 12-hour HH:MM AM/PM time, equivalent to %H:%M %p | 10:30 PM |
| %R | 24-hour HH:MM time, equivalent to %H:%M | 22:33 |
| %r | 12-hour HH:MM AM/PM time, equivalent to %H:%i %p | 10:30 PM |
| %R | 24-hour HH:MM time, equivalent to %H:%i | 22:33 |
| %s | second (00-59) | 44 |
| %S | second (00-59) | 44 |
| %t | horizontal-tab character (’) | |
| %T | ISO 8601 time format (HH:MM:SS), equivalent to %H:%M:%S | 22:33:44 |
| %T | ISO 8601 time format (HH:MM:SS), equivalent to %H:%i:%S | 22:33:44 |
| %u | ISO 8601 weekday as number with Monday as 1 (1-7) | 2 |
| %V | ISO 8601 week number (01-53) | 01 |
| %w | weekday as a integer number with Sunday as 0 (0-6) | 2 |
@ -1295,6 +1295,10 @@ Using replacement fields, you can define a pattern for the resulting string. “
| %z | Time offset from UTC as +HHMM or -HHMM | -0500 |
| %% | a % sign | % |
Note 1: In ClickHouse versions earlier than v23.4, `%f` prints a single zero (0) if the formatted value is a Date, Date32 or DateTime (which have no fractional seconds) or a DateTime64 with a precision of 0. The previous behavior can be restored using setting `formatdatetime_f_prints_single_zero = 1`.
Note 2: In ClickHouse versions earlier than v23.4, `%M` prints the minute (00-59) instead of the full month name (January-December). The previous behavior can be restored using setting `formatdatetime_parsedatetime_m_is_month_name = 0`.
**Example**
Query:

49
docs/en/sql-reference/functions/hash-functions.md
View File

@ -441,11 +441,11 @@ SELECT farmHash64(array('e','x','a'), 'mple', 10, toDateTime('2019-06-15 23:00:0
## javaHash
Calculates JavaHash from a [string](http://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/String.java#l1452),
[Byte](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Byte.java#l405),
[Short](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Short.java#l410),
[Integer](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Integer.java#l959),
[Long](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Long.java#l1060).
Calculates JavaHash from a [string](http://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/String.java#l1452),
[Byte](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Byte.java#l405),
[Short](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Short.java#l410),
[Integer](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Integer.java#l959),
[Long](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Long.java#l1060).
This hash function is neither fast nor having a good quality. The only reason to use it is when this algorithm is already used in another system and you have to calculate exactly the same result.
Note that Java only support calculating signed integers hash, so if you want to calculate unsigned integers hash you must cast it to proper signed ClickHouse types.
@ -660,6 +660,45 @@ Result:
└──────────────────────┴─────────────────────┘
```
## kafkaMurmurHash
Calculates a 32-bit [MurmurHash2](https://github.com/aappleby/smhasher) hash value using the same hash seed as [Kafka](https://github.com/apache/kafka/blob/461c5cfe056db0951d9b74f5adc45973670404d7/clients/src/main/java/org/apache/kafka/common/utils/Utils.java#L482) and without the highest bit to be compatible with [Default Partitioner](https://github.com/apache/kafka/blob/139f7709bd3f5926901a21e55043388728ccca78/clients/src/main/java/org/apache/kafka/clients/producer/internals/BuiltInPartitioner.java#L328).
**Syntax**
```sql
MurmurHash(par1, ...)
```
**Arguments**
- `par1, ...` — A variable number of parameters that can be any of the [supported data types](/docs/en/sql-reference/data-types/index.md/#data_types).
**Returned value**
- Calculated hash value.
Type: [UInt32](/docs/en/sql-reference/data-types/int-uint.md).
**Example**
Query:
```sql
SELECT
kafkaMurmurHash('foobar') AS res1,
kafkaMurmurHash(array('e','x','a'), 'mple', 10, toDateTime('2019-06-15 23:00:00')) AS res2
```
Result:
```response
┌───────res1─┬─────res2─┐
│ 1357151166 │ 85479775 │
└────────────┴──────────┘
```
## murmurHash3_32, murmurHash3_64
Produces a [MurmurHash3](https://github.com/aappleby/smhasher) hash value.

9
docs/en/sql-reference/functions/rounding-functions.md
View File

@ -194,7 +194,14 @@ Accepts a number. If the number is less than one, it returns 0. Otherwise, it ro
## roundAge(num)
Accepts a number. If the number is less than 18, it returns 0. Otherwise, it rounds the number down to a number from the set: 18, 25, 35, 45, 55.
Accepts a number. If the number is
- smaller than 1, it returns 0,
- between 1 and 17, it returns 17,
- between 18 and 24, it returns 18,
- between 25 and 34, it returns 25,
- between 35 and 44, it returns 35,
- between 45 and 54, it returns 45,
- larger than 55, it returns 55.
## roundDown(num, arr)

9
docs/en/sql-reference/functions/string-replace-functions.md
View File

@ -13,17 +13,18 @@ Functions for [searching](../../sql-reference/functions/string-search-functions.
## replaceOne(haystack, pattern, replacement)
Replaces the first occurrence of the substring ‘pattern’ (if it exists) in ‘haystack’ by the ‘replacement’ string.
‘pattern’ and ‘replacement’ must be constants.
## replaceAll(haystack, pattern, replacement), replace(haystack, pattern, replacement)
Replaces all occurrences of the substring ‘pattern’ in ‘haystack’ by the ‘replacement’ string.
Alias: `replace`.
## replaceRegexpOne(haystack, pattern, replacement)
Replaces the first occurrence of the substring matching the regular expression ‘pattern’ in ‘haystack‘ by the ‘replacement‘ string.
‘pattern‘ must be a constant [re2 regular expression](https://github.com/google/re2/wiki/Syntax).
‘replacement’ must be a plain constant string or a constant string containing substitutions `\0-\9`.
‘pattern‘ must be a [re2 regular expression](https://github.com/google/re2/wiki/Syntax).
‘replacement’ must be a plain string or a string containing substitutions `\0-\9`.
Substitutions `\1-\9` correspond to the 1st to 9th capturing group (submatch), substitution `\0` corresponds to the entire match.
To use a verbatim `\` character in the ‘pattern‘ or ‘replacement‘ string, escape it using `\`.
Also keep in mind that string literals require an extra escaping.
@ -88,6 +89,8 @@ SELECT replaceRegexpAll('Hello, World!', '^', 'here: ') AS res
└─────────────────────┘
```
Alias: `REGEXP_REPLACE`.
## regexpQuoteMeta(s)
The function adds a backslash before some predefined characters in the string.

1
docs/en/sql-reference/functions/type-conversion-functions.md
View File

@ -1245,7 +1245,6 @@ Returns DateTime values parsed from input string according to a MySQL style form
**Supported format specifiers**
All format specifiers listed in [formatDateTime](/docs/en/sql-reference/functions/date-time-functions.md#date_time_functions-formatDateTime) except:
- %f: fractional second
- %Q: Quarter (1-4)
**Example**

4
docs/en/sql-reference/statements/alter/delete.md
View File

@ -28,3 +28,7 @@ The synchronicity of the query processing is defined by the [mutations_sync](/do
- [Mutations](/docs/en/sql-reference/statements/alter/index.md#mutations)
- [Synchronicity of ALTER Queries](/docs/en/sql-reference/statements/alter/index.md#synchronicity-of-alter-queries)
- [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting
## Related content
- Blog: [Handling Updates and Deletes in ClickHouse](https://clickhouse.com/blog/handling-updates-and-deletes-in-clickhouse)

4
docs/en/sql-reference/statements/alter/index.md
View File

@ -61,3 +61,7 @@ For all `ALTER` queries, if `alter_sync = 2` and some replicas are not active fo
:::
For `ALTER TABLE ... UPDATE|DELETE` queries the synchronicity is defined by the [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting.
## Related content
- Blog: [Handling Updates and Deletes in ClickHouse](https://clickhouse.com/blog/handling-updates-and-deletes-in-clickhouse)

5
docs/en/sql-reference/statements/alter/update.md
View File

@ -27,3 +27,8 @@ The synchronicity of the query processing is defined by the [mutations_sync](/do
- [Mutations](/docs/en/sql-reference/statements/alter/index.md#mutations)
- [Synchronicity of ALTER Queries](/docs/en/sql-reference/statements/alter/index.md#synchronicity-of-alter-queries)
- [mutations_sync](/docs/en/operations/settings/settings.md/#mutations_sync) setting
## Related content
- Blog: [Handling Updates and Deletes in ClickHouse](https://clickhouse.com/blog/handling-updates-and-deletes-in-clickhouse)

1
docs/en/sql-reference/statements/create/view.md
View File

@ -364,3 +364,4 @@ The window view is useful in the following scenarios:
## Related Content
- Blog: [Working with time series data in ClickHouse](https://clickhouse.com/blog/working-with-time-series-data-and-functions-ClickHouse)
- Blog: [Building an Observability Solution with ClickHouse - Part 2 - Traces](https://clickhouse.com/blog/storing-traces-and-spans-open-telemetry-in-clickhouse)

4
docs/en/sql-reference/statements/delete.md
View File

@ -55,3 +55,7 @@ With the described implementation now we can see what can negatively affect 'DEL
- Table having a very large number of data parts
- Having a lot of data in Compact parts—in a Compact part, all columns are stored in one file.
## Related content
- Blog: [Handling Updates and Deletes in ClickHouse](https://clickhouse.com/blog/handling-updates-and-deletes-in-clickhouse)

4
docs/en/sql-reference/statements/drop.md
View File

@ -22,6 +22,10 @@ DROP DATABASE [IF EXISTS] db [ON CLUSTER cluster] [SYNC]
Deletes the table.
:::tip
Also see [UNDROP TABLE](/docs/en/sql-reference/statements/undrop.md)
:::
Syntax:
``` sql

4
docs/en/sql-reference/statements/select/join.md
View File

@ -18,6 +18,10 @@ FROM <left_table>
Expressions from `ON` clause and columns from `USING` clause are called “join keys”. Unless otherwise stated, join produces a [Cartesian product](https://en.wikipedia.org/wiki/Cartesian_product) from rows with matching “join keys”, which might produce results with much more rows than the source tables.
## Related Content
- Blog: [ClickHouse: A Blazingly Fast DBMS with Full SQL Join Support - Part 1](https://clickhouse.com/blog/clickhouse-fully-supports-joins)
## Supported Types of JOIN
All standard [SQL JOIN](https://en.wikipedia.org/wiki/Join_(SQL)) types are supported:

99
docs/en/sql-reference/statements/undrop.md Normal file
View File

@ -0,0 +1,99 @@
---
slug: /en/sql-reference/statements/undrop
sidebar_label: UNDROP
---
# UNDROP TABLE
Cancels the dropping of the table.
Beginning with ClickHouse version 23.3 it is possible to UNDROP a table in an Atomic database
within `database_atomic_delay_before_drop_table_sec` (8 minutes by default) of issuing the DROP TABLE statement. Dropped tables are listed in
a system table called `system.dropped_tables`.
If you have a materialized view without a `TO` clause associated with the dropped table, then you will also have to UNDROP the inner table of that view.
:::note
UNDROP TABLE is experimental. To use it add this setting:
```sql
set allow_experimental_undrop_table_query = 1;
```
:::
:::tip
Also see [DROP TABLE](/docs/en/sql-reference/statements/drop.md)
:::
Syntax:
``` sql
UNDROP TABLE [db.]name [UUID '<uuid>'] [ON CLUSTER cluster]
```
**Example**
``` sql
set allow_experimental_undrop_table_query = 1;
```
```sql
CREATE TABLE undropMe
(
`id` UInt8
)
ENGINE = MergeTree
ORDER BY id
```
```sql
DROP TABLE undropMe
```
```sql
SELECT *
FROM system.dropped_tables
FORMAT Vertical
```
```response
Row 1:
──────
index: 0
database: default
table: undropMe
uuid: aa696a1a-1d70-4e60-a841-4c80827706cc
engine: MergeTree
metadata_dropped_path: /var/lib/clickhouse/metadata_dropped/default.undropMe.aa696a1a-1d70-4e60-a841-4c80827706cc.sql
table_dropped_time: 2023-04-05 14:12:12
1 row in set. Elapsed: 0.001 sec.
```
```sql
UNDROP TABLE undropMe
```
```response
Ok.
```
```sql
SELECT *
FROM system.dropped_tables
FORMAT Vertical
```
```response
Ok.
0 rows in set. Elapsed: 0.001 sec.
```
```sql
DESCRIBE TABLE undropMe
FORMAT Vertical
```
```response
Row 1:
──────
name: id
type: UInt8
default_type:
default_expression:
comment:
codec_expression:
ttl_expression:
```

30
docs/en/sql-reference/syntax.md
View File

@ -14,7 +14,7 @@ The `INSERT` query uses both parsers:
INSERT INTO t VALUES (1, 'Hello, world'), (2, 'abc'), (3, 'def')
```
The `INSERT INTO t VALUES` fragment is parsed by the full parser, and the data `(1, 'Hello, world'), (2, 'abc'), (3, 'def')` is parsed by the fast stream parser. You can also turn on the full parser for the data by using the [input_format_values_interpret_expressions](../operations/settings/settings-formats.md#settings-input_format_values_interpret_expressions) setting. When `input_format_values_interpret_expressions = 1`, ClickHouse first tries to parse values with the fast stream parser. If it fails, ClickHouse tries to use the full parser for the data, treating it like an SQL [expression](#syntax-expressions).
The `INSERT INTO t VALUES` fragment is parsed by the full parser, and the data `(1, 'Hello, world'), (2, 'abc'), (3, 'def')` is parsed by the fast stream parser. You can also turn on the full parser for the data by using the [input_format_values_interpret_expressions](../operations/settings/settings-formats.md#input_format_values_interpret_expressions) setting. When `input_format_values_interpret_expressions = 1`, ClickHouse first tries to parse values with the fast stream parser. If it fails, ClickHouse tries to use the full parser for the data, treating it like an SQL [expression](#expressions).
Data can have any format. When a query is received, the server calculates no more than [max_query_size](../operations/settings/settings.md#settings-max_query_size) bytes of the request in RAM (by default, 1 MB), and the rest is stream parsed.
It allows for avoiding issues with large `INSERT` queries.
@ -45,7 +45,7 @@ You can check whether a data type name is case-sensitive in the [system.data_typ
In contrast to standard SQL, all other keywords (including functions names) are **case-sensitive**.
Keywords are not reserved; they are treated as such only in the corresponding context. If you use [identifiers](#syntax-identifiers) with the same name as the keywords, enclose them into double-quotes or backticks. For example, the query `SELECT "FROM" FROM table_name` is valid if the table `table_name` has column with the name `"FROM"`.
Keywords are not reserved; they are treated as such only in the corresponding context. If you use [identifiers](#identifiers) with the same name as the keywords, enclose them into double-quotes or backticks. For example, the query `SELECT "FROM" FROM table_name` is valid if the table `table_name` has column with the name `"FROM"`.
## Identifiers
@ -54,7 +54,7 @@ Identifiers are:
- Cluster, database, table, partition, and column names.
- Functions.
- Data types.
- [Expression aliases](#syntax-expression_aliases).
- [Expression aliases](#expression_aliases).
Identifiers can be quoted or non-quoted. The latter is preferred.
@ -108,7 +108,7 @@ Depending on the data format (input or output), `NULL` may have a different repr
There are many nuances to processing `NULL`. For example, if at least one of the arguments of a comparison operation is `NULL`, the result of this operation is also `NULL`. The same is true for multiplication, addition, and other operations. For more information, read the documentation for each operation.
In queries, you can check `NULL` using the [IS NULL](../sql-reference/operators/index.md#operator-is-null) and [IS NOT NULL](../sql-reference/operators/index.md) operators and the related functions `isNull` and `isNotNull`.
In queries, you can check `NULL` using the [IS NULL](../sql-reference/operators/index.md#is-null) and [IS NOT NULL](../sql-reference/operators/index.md#is-not-null) operators and the related functions `isNull` and `isNotNull`.
### Heredoc
@ -149,7 +149,7 @@ For example, the following SQL defines parameters named `a`, `b`, `c` and `d` -
SET param_a = 13;
SET param_b = 'str';
SET param_c = '2022-08-04 18:30:53';
SET param_d = {'10': [11, 12], '13': [14, 15]}';
SET param_d = {'10': [11, 12], '13': [14, 15]};
SELECT
{a: UInt32},
@ -166,7 +166,7 @@ Result:
If you are using `clickhouse-client`, the parameters are specified as `--param_name=value`. For example, the following parameter has the name `message` and it is retrieved as a `String`:
```sql
```bash
clickhouse-client --param_message='hello' --query="SELECT {message: String}"
```
@ -190,7 +190,7 @@ Query parameters are not general text substitutions which can be used in arbitra
## Functions
Function calls are written like an identifier with a list of arguments (possibly empty) in round brackets. In contrast to standard SQL, the brackets are required, even for an empty argument list. Example: `now()`.
There are regular and aggregate functions (see the section “Aggregate functions”). Some aggregate functions can contain two lists of arguments in brackets. Example: `quantile (0.9) (x)`. These aggregate functions are called “parametric” functions, and the arguments in the first list are called “parameters”. The syntax of aggregate functions without parameters is the same as for regular functions.
There are regular and aggregate functions (see the section [Aggregate functions](/docs/en/sql-reference/aggregate-functions/index.md)). Some aggregate functions can contain two lists of arguments in brackets. Example: `quantile (0.9) (x)`. These aggregate functions are called “parametric” functions, and the arguments in the first list are called “parameters”. The syntax of aggregate functions without parameters is the same as for regular functions.
## Operators
@ -199,7 +199,7 @@ For example, the expression `1 + 2 * 3 + 4` is transformed to `plus(plus(1, mult
## Data Types and Database Table Engines
Data types and table engines in the `CREATE` query are written the same way as identifiers or functions. In other words, they may or may not contain an argument list in brackets. For more information, see the sections “Data types,” “Table engines,” and “CREATE”.
Data types and table engines in the `CREATE` query are written the same way as identifiers or functions. In other words, they may or may not contain an argument list in brackets. For more information, see the sections [Data types](/docs/en/sql-reference/data-types/index.md), [Table engines](/docs/en/engines/table-engines/index.md), and [CREATE](/docs/en/sql-reference/statements/create/index.md).
## Expression Aliases
@ -211,17 +211,17 @@ expr AS alias
- `AS` — The keyword for defining aliases. You can define the alias for a table name or a column name in a `SELECT` clause without using the `AS` keyword.
For example, `SELECT table_name_alias.column_name FROM table_name table_name_alias`.
For example, `SELECT table_name_alias.column_name FROM table_name table_name_alias`.
In the [CAST](./functions/type-conversion-functions.md#type_conversion_function-cast) function, the `AS` keyword has another meaning. See the description of the function.
In the [CAST](./functions/type-conversion-functions.md#castx-t) function, the `AS` keyword has another meaning. See the description of the function.
- `expr` — Any expression supported by ClickHouse.
For example, `SELECT column_name * 2 AS double FROM some_table`.
For example, `SELECT column_name * 2 AS double FROM some_table`.
- `alias` — Name for `expr`. Aliases should comply with the [identifiers](#syntax-identifiers) syntax.
- `alias` — Name for `expr`. Aliases should comply with the [identifiers](#identifiers) syntax.
For example, `SELECT "table t".column_name FROM table_name AS "table t"`.
For example, `SELECT "table t".column_name FROM table_name AS "table t"`.
### Notes on Usage
@ -254,11 +254,11 @@ Received exception from server (version 18.14.17):
Code: 184. DB::Exception: Received from localhost:9000, 127.0.0.1. DB::Exception: Aggregate function sum(b) is found inside another aggregate function in query.
```
In this example, we declared table `t` with column `b`. Then, when selecting data, we defined the `sum(b) AS b` alias. As aliases are global, ClickHouse substituted the literal `b` in the expression `argMax(a, b)` with the expression `sum(b)`. This substitution caused the exception. You can change this default behavior by setting [prefer_column_name_to_alias](../operations/settings/settings.md#prefer_column_name_to_alias) to `1`.
In this example, we declared table `t` with column `b`. Then, when selecting data, we defined the `sum(b) AS b` alias. As aliases are global, ClickHouse substituted the literal `b` in the expression `argMax(a, b)` with the expression `sum(b)`. This substitution caused the exception. You can change this default behavior by setting [prefer_column_name_to_alias](../operations/settings/settings.md#prefer-column-name-to-alias) to `1`.
## Asterisk
In a `SELECT` query, an asterisk can replace the expression. For more information, see the section “SELECT”.
In a `SELECT` query, an asterisk can replace the expression. For more information, see the section [SELECT](/docs/en/sql-reference/statements/select/index.md#asterisk).
## Expressions

13
docs/en/sql-reference/table-functions/executable.md
View File

@ -20,7 +20,7 @@ A key advantage between ordinary UDF functions and the `executable` table functi
The `executable` table function requires three parameters and accepts an optional list of input queries:
```sql
executable(script_name, format, structure, [input_query...])
executable(script_name, format, structure, [input_query...] [,SETTINGS ...])
```
- `script_name`: the file name of the script. saved in the `user_scripts` folder (the default folder of the `user_scripts_path` setting)
@ -83,6 +83,15 @@ The response looks like:
└────┴────────────┘
```
## Settings
- `send_chunk_header` - controls whether to send row count before sending a chunk of data to process. Default value is `false`.
- `pool_size` — Size of pool. If 0 is specified as `pool_size` then there is no pool size restrictions. Default value is `16`.
- `max_command_execution_time` — Maximum executable script command execution time for processing block of data. Specified in seconds. Default value is 10.
- `command_termination_timeout` — executable script should contain main read-write loop. After table function is destroyed, pipe is closed, and executable file will have `command_termination_timeout` seconds to shutdown, before ClickHouse will send SIGTERM signal to child process. Specified in seconds. Default value is 10.
- `command_read_timeout` - timeout for reading data from command stdout in milliseconds. Default value 10000.
- `command_write_timeout` - timeout for writing data to command stdin in milliseconds. Default value 10000.
## Passing Query Results to a Script
Be sure to check out the example in the `Executable` table engine on [how to pass query results to a script](../../engines/table-engines/special/executable.md#passing-query-results-to-a-script). Here is how you execute the same script in that example using the `executable` table function:
@ -94,4 +103,4 @@ SELECT * FROM executable(
'id UInt64, sentiment Float32',
(SELECT id, comment FROM hackernews WHERE id > 0 AND comment != '' LIMIT 20)
);
```
```

2
docs/en/sql-reference/table-functions/postgresql.md
View File

@ -133,4 +133,6 @@ CREATE TABLE pg_table_schema_with_dots (a UInt32)
- [Using PostgreSQL as a dictionary source](../../sql-reference/dictionaries/index.md#dictionary-sources#dicts-external_dicts_dict_sources-postgresql)
## Related content
- Blog: [ClickHouse and PostgreSQL - a match made in data heaven - part 1](https://clickhouse.com/blog/migrating-data-between-clickhouse-postgres)
- Blog: [ClickHouse and PostgreSQL - a Match Made in Data Heaven - part 2](https://clickhouse.com/blog/migrating-data-between-clickhouse-postgres-part-2)

8
docs/ru/development/developer-instruction.md
View File

@ -41,9 +41,15 @@ ClickHouse не работает и не собирается на 32-битны
Выполните в терминале:
git clone git@github.com:your_github_username/ClickHouse.git --recursive
git clone --shallow-submodules git@github.com:your_github_username/ClickHouse.git
cd ClickHouse
Или (если вы хотите использовать sparse checkout для submodules):
git clone git@github.com:your_github_username/ClickHouse.git
cd ClickHouse
./contrib/update-submodules.sh
Замените слово `your_github_username` в команде для git на имя вашего аккаунта на GitHub.
Эта команда создаст директорию ClickHouse, содержащую рабочую копию проекта.

2
docs/ru/sql-reference/aggregate-functions/reference/deltasumtimestamp.md
View File

@ -7,7 +7,7 @@ sidebar_position: 141
Суммирует разницу между последовательными строками. Если разница отрицательна — она будет проигнорирована.
Эта функция предназначена в первую очередь для [материализованных представлений](../../../sql-reference/statements/create/view.md#materialized), упорядоченных по некоторому временному бакету согласно timestamp, например, по бакету `toStartOfMinute`. Поскольку строки в таком материализованном представлении будут иметь одинаковый timestamp, невозможно объединить их в "правом" порядке. Функция отслеживает `timestamp` наблюдаемых значений, поэтому возможно правильно упорядочить состояния во время слияния.
Эта функция предназначена в первую очередь для [материализованных представлений](../../../sql-reference/statements/create/view.md#materialized), хранящих данные, упорядоченные по некоторому округленному временному интервалу, согласно timestamp, например, по бакету `toStartOfMinute`. Поскольку строки в таком материализованном представлении будут иметь одинаковый timestamp, их невозможно объединить в правильном порядке без хранения исходного, неокругленного значения timestamp. Функция `deltaSumTimestamp` отслеживает исходные `timestamp` наблюдаемых значений, поэтому значения (состояния) функции правильно вычисляются во время слияния кусков.
Чтобы вычислить разницу между упорядоченными последовательными строками, вы можете использовать функцию [deltaSum](../../../sql-reference/aggregate-functions/reference/deltasum.md#agg_functions-deltasum) вместо функции `deltaSumTimestamp`.

4
programs/client/Client.cpp
View File

@ -277,11 +277,11 @@ void Client::initialize(Poco::Util::Application & self)
*/
const char * env_user = getenv("CLICKHOUSE_USER"); // NOLINT(concurrency-mt-unsafe)
if (env_user)
if (env_user && !config().has("user"))
config().setString("user", env_user);
const char * env_password = getenv("CLICKHOUSE_PASSWORD"); // NOLINT(concurrency-mt-unsafe)
if (env_password)
if (env_password && !config().has("password"))
config().setString("password", env_password);
parseConnectionsCredentials();

21
programs/install/Install.cpp
View File

@ -375,15 +375,22 @@ int mainEntryClickHouseInstall(int argc, char ** argv)
try
{
ReadBufferFromFile in(binary_self_path.string());
WriteBufferFromFile out(main_bin_tmp_path.string());
copyData(in, out);
out.sync();
String source = binary_self_path.string();
String destination = main_bin_tmp_path.string();
if (0 != fchmod(out.getFD(), S_IRUSR | S_IRGRP | S_IROTH | S_IXUSR | S_IXGRP | S_IXOTH))
/// Try to make a hard link first, as an optimization.
/// It is possible if the source and the destination are on the same filesystems.
if (0 != link(source.c_str(), destination.c_str()))
{
ReadBufferFromFile in(binary_self_path.string());
WriteBufferFromFile out(main_bin_tmp_path.string());
copyData(in, out);
out.sync();
out.finalize();
}
if (0 != chmod(destination.c_str(), S_IRUSR | S_IRGRP | S_IROTH | S_IXUSR | S_IXGRP | S_IXOTH))
throwFromErrno(fmt::format("Cannot chmod {}", main_bin_tmp_path.string()), ErrorCodes::SYSTEM_ERROR);
out.finalize();
}
catch (const Exception & e)
{

1
programs/keeper/Keeper.cpp
View File

@ -17,7 +17,6 @@
#include <Poco/Net/TCPServerParams.h>
#include <Poco/Net/TCPServer.h>
#include <Poco/Util/HelpFormatter.h>
#include <Poco/Version.h>
#include <Poco/Environment.h>
#include <sys/stat.h>
#include <pwd.h>

2
programs/server/Server.cpp
View File

@ -981,7 +981,7 @@ try
StatusFile status{path / "status", StatusFile::write_full_info};
DB::ServerUUID::load(path / "uuid", log);
ServerUUID::load(path / "uuid", log);
/// Try to increase limit on number of open files.
{

12
src/Access/DiskAccessStorage.cpp
View File

@ -10,6 +10,7 @@
#include <Interpreters/Access/InterpreterCreateUserQuery.h>
#include <Interpreters/Access/InterpreterShowGrantsQuery.h>
#include <Common/logger_useful.h>
#include <Common/ThreadPool.h>
#include <Poco/JSON/JSON.h>
#include <Poco/JSON/Object.h>
#include <Poco/JSON/Stringifier.h>
@ -19,6 +20,7 @@
#include <base/range.h>
#include <filesystem>
#include <fstream>
#include <memory>
namespace DB
@ -317,15 +319,15 @@ void DiskAccessStorage::scheduleWriteLists(AccessEntityType type)
return; /// If the lists' writing thread is still waiting we can update `types_of_lists_to_write` easily,
/// without restarting that thread.
if (lists_writing_thread.joinable())
lists_writing_thread.join();
if (lists_writing_thread && lists_writing_thread->joinable())
lists_writing_thread->join();
/// Create the 'need_rebuild_lists.mark' file.
/// This file will be used later to find out if writing lists is successful or not.
std::ofstream out{getNeedRebuildListsMarkFilePath(directory_path)};
out.close();
lists_writing_thread = ThreadFromGlobalPool{&DiskAccessStorage::listsWritingThreadFunc, this};
lists_writing_thread = std::make_unique<ThreadFromGlobalPool>(&DiskAccessStorage::listsWritingThreadFunc, this);
lists_writing_thread_is_waiting = true;
}
@ -349,10 +351,10 @@ void DiskAccessStorage::listsWritingThreadFunc()
void DiskAccessStorage::stopListsWritingThread()
{
if (lists_writing_thread.joinable())
if (lists_writing_thread && lists_writing_thread->joinable())
{
lists_writing_thread_should_exit.notify_one();
lists_writing_thread.join();
lists_writing_thread->join();
}
}

4
src/Access/DiskAccessStorage.h
View File

@ -1,7 +1,7 @@
#pragma once
#include <Access/MemoryAccessStorage.h>
#include <Common/ThreadPool.h>
#include <Common/ThreadPool_fwd.h>
#include <boost/container/flat_set.hpp>
@ -81,7 +81,7 @@ private:
bool failed_to_write_lists TSA_GUARDED_BY(mutex) = false;
/// List files are written in a separate thread.
ThreadFromGlobalPool lists_writing_thread;
std::unique_ptr<ThreadFromGlobalPool> lists_writing_thread;
/// Signals `lists_writing_thread` to exit.
std::condition_variable lists_writing_thread_should_exit;

8
src/Access/ReplicatedAccessStorage.cpp
View File

@ -1,3 +1,4 @@
#include <memory>
#include <Access/AccessEntityIO.h>
#include <Access/MemoryAccessStorage.h>
#include <Access/ReplicatedAccessStorage.h>
@ -15,6 +16,7 @@
#include <Common/ZooKeeper/ZooKeeper.h>
#include <Common/escapeForFileName.h>
#include <Common/setThreadName.h>
#include <Common/ThreadPool.h>
#include <base/range.h>
#include <base/sleep.h>
#include <boost/range/algorithm_ext/erase.hpp>
@ -72,7 +74,7 @@ void ReplicatedAccessStorage::startWatchingThread()
{
bool prev_watching_flag = watching.exchange(true);
if (!prev_watching_flag)
watching_thread = ThreadFromGlobalPool(&ReplicatedAccessStorage::runWatchingThread, this);
watching_thread = std::make_unique<ThreadFromGlobalPool>(&ReplicatedAccessStorage::runWatchingThread, this);
}
void ReplicatedAccessStorage::stopWatchingThread()
@ -81,8 +83,8 @@ void ReplicatedAccessStorage::stopWatchingThread()
if (prev_watching_flag)
{
watched_queue->finish();
if (watching_thread.joinable())
watching_thread.join();
if (watching_thread && watching_thread->joinable())
watching_thread->join();
}
}

6
src/Access/ReplicatedAccessStorage.h
View File

@ -2,7 +2,7 @@
#include <atomic>
#include <Common/ThreadPool.h>
#include <Common/ThreadPool_fwd.h>
#include <Common/ZooKeeper/Common.h>
#include <Common/ZooKeeper/ZooKeeper.h>
#include <Common/ConcurrentBoundedQueue.h>
@ -21,7 +21,7 @@ public:
static constexpr char STORAGE_TYPE[] = "replicated";
ReplicatedAccessStorage(const String & storage_name, const String & zookeeper_path, zkutil::GetZooKeeper get_zookeeper, AccessChangesNotifier & changes_notifier_, bool allow_backup);
virtual ~ReplicatedAccessStorage() override;
~ReplicatedAccessStorage() override;
const char * getStorageType() const override { return STORAGE_TYPE; }
@ -43,7 +43,7 @@ private:
std::mutex cached_zookeeper_mutex;
std::atomic<bool> watching = false;
ThreadFromGlobalPool watching_thread;
std::unique_ptr<ThreadFromGlobalPool> watching_thread;
std::shared_ptr<ConcurrentBoundedQueue<UUID>> watched_queue;
std::optional<UUID> insertImpl(const AccessEntityPtr & entity, bool replace_if_exists, bool throw_if_exists) override;

1
src/AggregateFunctions/AggregateFunctionMaxIntersections.h
View File

@ -1,6 +1,5 @@
#pragma once
#include <Common/logger_useful.h>
#include <base/sort.h>
#include <DataTypes/DataTypesNumber.h>

1
src/AggregateFunctions/AggregateFunctionSparkbar.h
View File

@ -11,7 +11,6 @@
#include <IO/WriteHelpers.h>
#include <Columns/ColumnString.h>
#include <Common/PODArray.h>
#include <Common/logger_useful.h>
#include <IO/ReadBufferFromString.h>
#include <Common/HashTable/HashMap.h>
#include <Columns/IColumn.h>

1
src/AggregateFunctions/AggregateFunctionSumMap.h
View File

@ -18,7 +18,6 @@
#include <AggregateFunctions/IAggregateFunction.h>
#include <AggregateFunctions/FactoryHelpers.h>
#include <map>
#include <Common/logger_useful.h>
#include <Common/ClickHouseRevision.h>

2
src/AggregateFunctions/IAggregateFunction.h
View File

@ -9,7 +9,7 @@
#include <Interpreters/Context_fwd.h>
#include <base/types.h>
#include <Common/Exception.h>
#include <Common/ThreadPool.h>
#include <Common/ThreadPool_fwd.h>
#include <Core/IResolvedFunction.h>
#include "config.h"

141
src/Analyzer/Passes/QueryAnalysisPass.cpp
View File

@ -32,6 +32,7 @@
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <TableFunctions/TableFunctionFactory.h>
#include <Formats/FormatFactory.h>
#include <Databases/IDatabase.h>
@ -75,6 +76,7 @@
#include <Analyzer/InDepthQueryTreeVisitor.h>
#include <Analyzer/QueryTreeBuilder.h>
#include <Analyzer/IQueryTreeNode.h>
#include <Analyzer/Identifier.h>
namespace ProfileEvents
{
@ -112,6 +114,8 @@ namespace ErrorCodes
extern const int ALIAS_REQUIRED;
extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
extern const int UNKNOWN_TABLE;
extern const int ILLEGAL_COLUMN;
extern const int NUMBER_OF_COLUMNS_DOESNT_MATCH;
}
/** Query analyzer implementation overview. Please check documentation in QueryAnalysisPass.h before.
@ -6079,6 +6083,18 @@ void QueryAnalyzer::initializeTableExpressionData(const QueryTreeNodePtr & table
scope.table_expression_node_to_data.emplace(table_expression_node, std::move(table_expression_data));
}
bool findIdentifier(const FunctionNode & function)
{
for (const auto & argument : function.getArguments())
{
if (argument->as<IdentifierNode>())
return true;
if (const auto * f = argument->as<FunctionNode>(); f && findIdentifier(*f))
return true;
}
return false;
}
/// Resolve table function node in scope
void QueryAnalyzer::resolveTableFunction(QueryTreeNodePtr & table_function_node,
IdentifierResolveScope & scope,
@ -6090,12 +6106,11 @@ void QueryAnalyzer::resolveTableFunction(QueryTreeNodePtr & table_function_node,
if (!nested_table_function)
expressions_visitor.visit(table_function_node_typed.getArgumentsNode());
const auto & table_function_factory = TableFunctionFactory::instance();
const auto & table_function_name = table_function_node_typed.getTableFunctionName();
auto & scope_context = scope.context;
TableFunctionPtr table_function_ptr = table_function_factory.tryGet(table_function_name, scope_context);
TableFunctionPtr table_function_ptr = TableFunctionFactory::instance().tryGet(table_function_name, scope_context);
if (!table_function_ptr)
{
auto hints = TableFunctionFactory::instance().getHints(table_function_name);
@ -6110,17 +6125,131 @@ void QueryAnalyzer::resolveTableFunction(QueryTreeNodePtr & table_function_node,
table_function_name);
}
uint64_t use_structure_from_insertion_table_in_table_functions = scope_context->getSettingsRef().use_structure_from_insertion_table_in_table_functions;
if (!nested_table_function &&
scope_context->getSettingsRef().use_structure_from_insertion_table_in_table_functions &&
use_structure_from_insertion_table_in_table_functions &&
scope_context->hasInsertionTable() &&
table_function_ptr->needStructureHint())
{
const auto & insertion_table = scope_context->getInsertionTable();
if (!insertion_table.empty())
{
auto insertion_table_storage = DatabaseCatalog::instance().getTable(insertion_table, scope_context);
const auto & structure_hint = insertion_table_storage->getInMemoryMetadataPtr()->columns;
table_function_ptr->setStructureHint(structure_hint);
const auto & insert_structure = DatabaseCatalog::instance().getTable(insertion_table, scope_context)->getInMemoryMetadataPtr()->getColumns();
DB::ColumnsDescription structure_hint;
bool use_columns_from_insert_query = true;
/// Insert table matches columns against SELECT expression by position, so we want to map
/// insert table columns to table function columns through names from SELECT expression.
auto insert_column = insert_structure.begin();
auto insert_structure_end = insert_structure.end(); /// end iterator of the range covered by possible asterisk
auto virtual_column_names = table_function_ptr->getVirtualsToCheckBeforeUsingStructureHint();
bool asterisk = false;
const auto & expression_list = scope.scope_node->as<QueryNode &>().getProjection();
auto expression = expression_list.begin();
/// We want to go through SELECT expression list and correspond each expression to column in insert table
/// which type will be used as a hint for the file structure inference.
for (; expression != expression_list.end() && insert_column != insert_structure_end; ++expression)
{
if (auto * identifier_node = (*expression)->as<IdentifierNode>())
{
if (!virtual_column_names.contains(identifier_node->getIdentifier().getFullName()))
{
if (asterisk)
{
if (use_structure_from_insertion_table_in_table_functions == 1)
throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Asterisk cannot be mixed with column list in INSERT SELECT query.");
use_columns_from_insert_query = false;
break;
}
structure_hint.add({ identifier_node->getIdentifier().getFullName(), insert_column->type });
}
/// Once we hit asterisk we want to find end of the range covered by asterisk
/// contributing every further SELECT expression to the tail of insert structure
if (asterisk)
--insert_structure_end;
else
++insert_column;
}
else if (auto * matcher_node = (*expression)->as<MatcherNode>(); matcher_node && matcher_node->getMatcherType() == MatcherNodeType::ASTERISK)
{
if (asterisk)
{
if (use_structure_from_insertion_table_in_table_functions == 1)
throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Only one asterisk can be used in INSERT SELECT query.");
use_columns_from_insert_query = false;
break;
}
if (!structure_hint.empty())
{
if (use_structure_from_insertion_table_in_table_functions == 1)
throw Exception(ErrorCodes::ILLEGAL_COLUMN, "Asterisk cannot be mixed with column list in INSERT SELECT query.");
use_columns_from_insert_query = false;
break;
}
asterisk = true;
}
else if (auto * function = (*expression)->as<FunctionNode>())
{
if (use_structure_from_insertion_table_in_table_functions == 2 && findIdentifier(*function))
{
use_columns_from_insert_query = false;
break;
}
/// Once we hit asterisk we want to find end of the range covered by asterisk
/// contributing every further SELECT expression to the tail of insert structure
if (asterisk)
--insert_structure_end;
else
++insert_column;
}
else
{
/// Once we hit asterisk we want to find end of the range covered by asterisk
/// contributing every further SELECT expression to the tail of insert structure
if (asterisk)
--insert_structure_end;
else
++insert_column;
}
}
if (use_structure_from_insertion_table_in_table_functions == 2 && !asterisk)
{
/// For input function we should check if input format supports reading subset of columns.
if (table_function_ptr->getName() == "input")
use_columns_from_insert_query = FormatFactory::instance().checkIfFormatSupportsSubsetOfColumns(scope.context->getInsertFormat());
else
use_columns_from_insert_query = table_function_ptr->supportsReadingSubsetOfColumns();
}
if (use_columns_from_insert_query)
{
if (expression == expression_list.end())
{
/// Append tail of insert structure to the hint
if (asterisk)
{
for (; insert_column != insert_structure_end; ++insert_column)
structure_hint.add({ insert_column->name, insert_column->type });
}
if (!structure_hint.empty())
table_function_ptr->setStructureHint(structure_hint);
} else if (use_structure_from_insertion_table_in_table_functions == 1)
throw Exception(ErrorCodes::NUMBER_OF_COLUMNS_DOESNT_MATCH, "Number of columns in insert table less than required by SELECT expression.");
}
}
}

1
src/Backups/BackupCoordinationFileInfos.cpp
View File

@ -1,5 +1,6 @@
#include <Backups/BackupCoordinationFileInfos.h>
#include <Common/quoteString.h>
#include <Common/Exception.h>
namespace DB

15
src/Backups/BackupCoordinationRemote.cpp
View File

@ -771,16 +771,19 @@ bool BackupCoordinationRemote::hasConcurrentBackups(const std::atomic<size_t> &)
String existing_backup_uuid = existing_backup_path;
existing_backup_uuid.erase(0, String("backup-").size());
if (existing_backup_uuid == toString(backup_uuid))
continue;
const auto status = zk->get(root_zookeeper_path + "/" + existing_backup_path + "/stage");
if (status != Stage::COMPLETED)
String status;
if (zk->tryGet(root_zookeeper_path + "/" + existing_backup_path + "/stage", status))
{
LOG_WARNING(log, "Found a concurrent backup: {}, current backup: {}", existing_backup_uuid, toString(backup_uuid));
result = true;
return;
/// If status is not COMPLETED it could be because the backup failed, check if 'error' exists
if (status != Stage::COMPLETED && !zk->exists(root_zookeeper_path + "/" + existing_backup_path + "/error"))
{
LOG_WARNING(log, "Found a concurrent backup: {}, current backup: {}", existing_backup_uuid, toString(backup_uuid));
result = true;
return;
}
}
}

3
src/Backups/BackupEntriesCollector.cpp
View File

@ -15,6 +15,7 @@
#include <base/sleep.h>
#include <Common/escapeForFileName.h>
#include <boost/range/algorithm/copy.hpp>
#include <base/scope_guard.h>
#include <filesystem>
namespace fs = std::filesystem;
@ -490,7 +491,7 @@ std::vector<std::pair<ASTPtr, StoragePtr>> BackupEntriesCollector::findTablesInD
{
/// Database or table could be replicated - so may use ZooKeeper. We need to retry.
auto zookeeper_retries_info = global_zookeeper_retries_info;
ZooKeeperRetriesControl retries_ctl("getTablesForBackup", zookeeper_retries_info);
ZooKeeperRetriesControl retries_ctl("getTablesForBackup", zookeeper_retries_info, nullptr);
retries_ctl.retryLoop([&](){ db_tables = database->getTablesForBackup(filter_by_table_name, context); });
}
catch (Exception & e)

3
src/Backups/BackupEntryFromAppendOnlyFile.cpp
View File

@ -8,10 +8,11 @@ namespace DB
BackupEntryFromAppendOnlyFile::BackupEntryFromAppendOnlyFile(
const DiskPtr & disk_,
const String & file_path_,
const ReadSettings & settings_,
const std::optional<UInt64> & file_size_,
const std::optional<UInt128> & checksum_,
const std::shared_ptr<TemporaryFileOnDisk> & temporary_file_)
: BackupEntryFromImmutableFile(disk_, file_path_, file_size_, checksum_, temporary_file_)
: BackupEntryFromImmutableFile(disk_, file_path_, settings_, file_size_, checksum_, temporary_file_)
, limit(BackupEntryFromImmutableFile::getSize())
{
}

1
src/Backups/BackupEntryFromAppendOnlyFile.h
View File

@ -16,6 +16,7 @@ public:
BackupEntryFromAppendOnlyFile(
const DiskPtr & disk_,
const String & file_path_,
const ReadSettings & settings_,
const std::optional<UInt64> & file_size_ = {},
const std::optional<UInt128> & checksum_ = {},
const std::shared_ptr<TemporaryFileOnDisk> & temporary_file_ = {});

10
src/Backups/BackupEntryFromImmutableFile.cpp
View File

@ -11,10 +11,16 @@ namespace DB
BackupEntryFromImmutableFile::BackupEntryFromImmutableFile(
const DiskPtr & disk_,
const String & file_path_,
const ReadSettings & settings_,
const std::optional<UInt64> & file_size_,
const std::optional<UInt128> & checksum_,
const std::shared_ptr<TemporaryFileOnDisk> & temporary_file_)
: disk(disk_), file_path(file_path_), file_size(file_size_), checksum(checksum_), temporary_file_on_disk(temporary_file_)
: disk(disk_)
, file_path(file_path_)
, settings(settings_)
, file_size(file_size_)
, checksum(checksum_)
, temporary_file_on_disk(temporary_file_)
{
}
@ -30,7 +36,7 @@ UInt64 BackupEntryFromImmutableFile::getSize() const
std::unique_ptr<SeekableReadBuffer> BackupEntryFromImmutableFile::getReadBuffer() const
{
return disk->readFile(file_path);
return disk->readFile(file_path, settings);
}

3
src/Backups/BackupEntryFromImmutableFile.h
View File

@ -1,6 +1,7 @@
#pragma once
#include <Backups/IBackupEntry.h>
#include <IO/ReadSettings.h>
#include <base/defines.h>
#include <mutex>
@ -19,6 +20,7 @@ public:
BackupEntryFromImmutableFile(
const DiskPtr & disk_,
const String & file_path_,
const ReadSettings & settings_,
const std::optional<UInt64> & file_size_ = {},
const std::optional<UInt128> & checksum_ = {},
const std::shared_ptr<TemporaryFileOnDisk> & temporary_file_ = {});
@ -37,6 +39,7 @@ public:
private:
const DiskPtr disk;
const String file_path;
ReadSettings settings;
mutable std::optional<UInt64> file_size TSA_GUARDED_BY(get_file_size_mutex);
mutable std::mutex get_file_size_mutex;
const std::optional<UInt128> checksum;

1
src/Backups/BackupFileInfo.cpp
View File

@ -6,6 +6,7 @@
#include <Common/logger_useful.h>
#include <Common/scope_guard_safe.h>
#include <Common/setThreadName.h>
#include <Common/ThreadPool.h>
#include <IO/HashingReadBuffer.h>

3
src/Backups/BackupFileInfo.h
View File

@ -1,8 +1,9 @@
#pragma once
#include <Core/Types.h>
#include <Common/ThreadPool.h>
#include <Common/ThreadPool_fwd.h>
namespace Poco { class Logger; }
namespace DB
{

6
src/Backups/BackupIO.cpp
View File

@ -3,6 +3,7 @@
#include <IO/copyData.h>
#include <IO/WriteBufferFromFileBase.h>
#include <IO/SeekableReadBuffer.h>
#include <Interpreters/Context.h>
namespace DB
@ -22,6 +23,11 @@ void IBackupReader::copyFileToDisk(const String & file_name, size_t size, DiskPt
write_buffer->finalize();
}
IBackupWriter::IBackupWriter(const ContextPtr & context_)
: read_settings(context_->getBackupReadSettings())
, has_throttling(static_cast<bool>(context_->getBackupsThrottler()))
{}
void IBackupWriter::copyDataToFile(const CreateReadBufferFunction & create_read_buffer, UInt64 offset, UInt64 size, const String & dest_file_name)
{
auto read_buffer = create_read_buffer();

14
src/Backups/BackupIO.h
View File

@ -3,6 +3,8 @@
#include <Core/Types.h>
#include <Disks/DiskType.h>
#include <Disks/IDisk.h>
#include <IO/ReadSettings.h>
#include <Interpreters/Context_fwd.h>
namespace DB
{
@ -28,6 +30,8 @@ class IBackupWriter /// BackupWriterFile, BackupWriterDisk
public:
using CreateReadBufferFunction = std::function<std::unique_ptr<SeekableReadBuffer>()>;
explicit IBackupWriter(const ContextPtr & context_);
virtual ~IBackupWriter() = default;
virtual bool fileExists(const String & file_name) = 0;
virtual UInt64 getFileSize(const String & file_name) = 0;
@ -38,7 +42,17 @@ public:
virtual DataSourceDescription getDataSourceDescription() const = 0;
virtual void copyDataToFile(const CreateReadBufferFunction & create_read_buffer, UInt64 offset, UInt64 size, const String & dest_file_name);
virtual bool supportNativeCopy(DataSourceDescription /* data_source_description */) const { return false; }
/// Copy file using native copy (optimized for S3 to use CopyObject)
///
/// NOTE: It still may fall back to copyDataToFile() if native copy is not possible:
/// - different buckets
/// - throttling had been requested
virtual void copyFileNative(DiskPtr src_disk, const String & src_file_name, UInt64 src_offset, UInt64 src_size, const String & dest_file_name);
protected:
const ReadSettings read_settings;
const bool has_throttling;
};
}

9
src/Backups/BackupIO_Disk.cpp
View File

@ -50,7 +50,10 @@ void BackupReaderDisk::copyFileToDisk(const String & file_name, size_t size, Dis
}
BackupWriterDisk::BackupWriterDisk(const DiskPtr & disk_, const String & path_) : disk(disk_), path(path_)
BackupWriterDisk::BackupWriterDisk(const DiskPtr & disk_, const String & path_, const ContextPtr & context_)
: IBackupWriter(context_)
, disk(disk_)
, path(path_)
{
}
@ -127,9 +130,9 @@ void BackupWriterDisk::copyFileNative(DiskPtr src_disk, const String & src_file_
if (!src_disk)
throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot natively copy data to disk without source disk");
if ((src_offset != 0) || (src_size != src_disk->getFileSize(src_file_name)))
if (has_throttling || (src_offset != 0) || (src_size != src_disk->getFileSize(src_file_name)))
{
auto create_read_buffer = [src_disk, src_file_name] { return src_disk->readFile(src_file_name); };
auto create_read_buffer = [this, src_disk, src_file_name] { return src_disk->readFile(src_file_name, read_settings); };
copyDataToFile(create_read_buffer, src_offset, src_size, dest_file_name);
return;
}

3
src/Backups/BackupIO_Disk.h
View File

@ -2,6 +2,7 @@
#include <filesystem>
#include <Backups/BackupIO.h>
#include <Interpreters/Context_fwd.h>
namespace DB
{
@ -30,7 +31,7 @@ private:
class BackupWriterDisk : public IBackupWriter
{
public:
BackupWriterDisk(const DiskPtr & disk_, const String & path_);
BackupWriterDisk(const DiskPtr & disk_, const String & path_, const ContextPtr & context_);
~BackupWriterDisk() override;
bool fileExists(const String & file_name) override;

8
src/Backups/BackupIO_File.cpp
View File

@ -49,7 +49,9 @@ void BackupReaderFile::copyFileToDisk(const String & file_name, size_t size, Dis
}
BackupWriterFile::BackupWriterFile(const String & path_) : path(path_)
BackupWriterFile::BackupWriterFile(const String & path_, const ContextPtr & context_)
: IBackupWriter(context_)
, path(path_)
{
}
@ -152,9 +154,9 @@ void BackupWriterFile::copyFileNative(DiskPtr src_disk, const String & src_file_
else
abs_source_path = fs::absolute(src_file_name);
if ((src_offset != 0) || (src_size != fs::file_size(abs_source_path)))
if (has_throttling || (src_offset != 0) || (src_size != fs::file_size(abs_source_path)))
{
auto create_read_buffer = [abs_source_path] { return createReadBufferFromFileBase(abs_source_path, {}); };
auto create_read_buffer = [this, abs_source_path] { return createReadBufferFromFileBase(abs_source_path, read_settings); };
copyDataToFile(create_read_buffer, src_offset, src_size, dest_file_name);
return;
}

3
src/Backups/BackupIO_File.h
View File

@ -2,6 +2,7 @@
#include <filesystem>
#include <Backups/BackupIO.h>
#include <Interpreters/Context_fwd.h>
namespace DB
{
@ -27,7 +28,7 @@ private:
class BackupWriterFile : public IBackupWriter
{
public:
explicit BackupWriterFile(const String & path_);
explicit BackupWriterFile(const String & path_, const ContextPtr & context_);
~BackupWriterFile() override;
bool fileExists(const String & file_name) override;

6
src/Backups/BackupIO_S3.cpp
View File

@ -161,9 +161,9 @@ void BackupReaderS3::copyFileToDisk(const String & file_name, size_t size, DiskP
BackupWriterS3::BackupWriterS3(
const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, const ContextPtr & context_)
: s3_uri(s3_uri_)
: IBackupWriter(context_)
, s3_uri(s3_uri_)
, client(makeS3Client(s3_uri_, access_key_id_, secret_access_key_, context_))
, read_settings(context_->getReadSettings())
, request_settings(context_->getStorageS3Settings().getSettings(s3_uri.uri.toString()).request_settings)
, log(&Poco::Logger::get("BackupWriterS3"))
{
@ -189,7 +189,7 @@ void BackupWriterS3::copyFileNative(DiskPtr src_disk, const String & src_file_na
auto objects = src_disk->getStorageObjects(src_file_name);
if (objects.size() > 1)
{
auto create_read_buffer = [src_disk, src_file_name] { return src_disk->readFile(src_file_name); };
auto create_read_buffer = [this, src_disk, src_file_name] { return src_disk->readFile(src_file_name, read_settings); };
copyDataToFile(create_read_buffer, src_offset, src_size, dest_file_name);
}
else

2
src/Backups/BackupIO_S3.h
View File

@ -7,6 +7,7 @@
#include <IO/ReadSettings.h>
#include <IO/S3Common.h>
#include <Storages/StorageS3Settings.h>
#include <Interpreters/Context_fwd.h>
namespace DB
@ -76,7 +77,6 @@ private:
S3::URI s3_uri;
std::shared_ptr<S3::Client> client;
ReadSettings read_settings;
S3Settings::RequestSettings request_settings;
Poco::Logger * log;
std::optional<bool> supports_batch_delete;

1
src/Backups/BackupUtils.h
View File

@ -1,7 +1,6 @@
#pragma once
#include <Parsers/ASTBackupQuery.h>
#include <Common/ThreadPool.h>
namespace DB

19
src/Backups/BackupsWorker.cpp
View File

@ -23,6 +23,7 @@
#include <Common/CurrentMetrics.h>
#include <Common/setThreadName.h>
#include <Common/scope_guard_safe.h>
#include <Common/ThreadPool.h>
namespace CurrentMetrics
@ -182,8 +183,8 @@ namespace
BackupsWorker::BackupsWorker(size_t num_backup_threads, size_t num_restore_threads, bool allow_concurrent_backups_, bool allow_concurrent_restores_)
: backups_thread_pool(CurrentMetrics::BackupsThreads, CurrentMetrics::BackupsThreadsActive, num_backup_threads, /* max_free_threads = */ 0, num_backup_threads)
, restores_thread_pool(CurrentMetrics::RestoreThreads, CurrentMetrics::RestoreThreadsActive, num_restore_threads, /* max_free_threads = */ 0, num_restore_threads)
: backups_thread_pool(std::make_unique<ThreadPool>(CurrentMetrics::BackupsThreads, CurrentMetrics::BackupsThreadsActive, num_backup_threads, /* max_free_threads = */ 0, num_backup_threads))
, restores_thread_pool(std::make_unique<ThreadPool>(CurrentMetrics::RestoreThreads, CurrentMetrics::RestoreThreadsActive, num_restore_threads, /* max_free_threads = */ 0, num_restore_threads))
, log(&Poco::Logger::get("BackupsWorker"))
, allow_concurrent_backups(allow_concurrent_backups_)
, allow_concurrent_restores(allow_concurrent_restores_)
@ -248,7 +249,7 @@ OperationID BackupsWorker::startMakingBackup(const ASTPtr & query, const Context
if (backup_settings.async)
{
backups_thread_pool.scheduleOrThrowOnError(
backups_thread_pool->scheduleOrThrowOnError(
[this, backup_query, backup_id, backup_name_for_logging, backup_info, backup_settings, backup_coordination, context_in_use, mutable_context]
{
doBackup(
@ -435,7 +436,7 @@ void BackupsWorker::buildFileInfosForBackupEntries(const BackupPtr & backup, con
LOG_TRACE(log, "{}", Stage::BUILDING_FILE_INFOS);
backup_coordination->setStage(Stage::BUILDING_FILE_INFOS, "");
backup_coordination->waitForStage(Stage::BUILDING_FILE_INFOS);
backup_coordination->addFileInfos(::DB::buildFileInfosForBackupEntries(backup_entries, backup->getBaseBackup(), backups_thread_pool));
backup_coordination->addFileInfos(::DB::buildFileInfosForBackupEntries(backup_entries, backup->getBaseBackup(), *backups_thread_pool));
}
@ -522,7 +523,7 @@ void BackupsWorker::writeBackupEntries(BackupMutablePtr backup, BackupEntries &&
}
};
if (always_single_threaded || !backups_thread_pool.trySchedule([job] { job(true); }))
if (always_single_threaded || !backups_thread_pool->trySchedule([job] { job(true); }))
job(false);
}
@ -581,7 +582,7 @@ OperationID BackupsWorker::startRestoring(const ASTPtr & query, ContextMutablePt
if (restore_settings.async)
{
restores_thread_pool.scheduleOrThrowOnError(
restores_thread_pool->scheduleOrThrowOnError(
[this, restore_query, restore_id, backup_name_for_logging, backup_info, restore_settings, restore_coordination, context_in_use]
{
doRestore(
@ -716,7 +717,7 @@ void BackupsWorker::doRestore(
}
/// Execute the data restoring tasks.
restoreTablesData(restore_id, backup, std::move(data_restore_tasks), restores_thread_pool);
restoreTablesData(restore_id, backup, std::move(data_restore_tasks), *restores_thread_pool);
/// We have restored everything, we need to tell other hosts (they could be waiting for it).
restore_coordination->setStage(Stage::COMPLETED, "");
@ -941,8 +942,8 @@ void BackupsWorker::shutdown()
if (has_active_backups_and_restores)
LOG_INFO(log, "Waiting for {} backups and {} restores to be finished", num_active_backups, num_active_restores);
backups_thread_pool.wait();
restores_thread_pool.wait();
backups_thread_pool->wait();
restores_thread_pool->wait();
if (has_active_backups_and_restores)
LOG_INFO(log, "All backup and restore tasks have finished");

7
src/Backups/BackupsWorker.h
View File

@ -1,7 +1,8 @@
#pragma once
#include <Backups/BackupStatus.h>
#include <Common/ThreadPool.h>
#include <Common/ThreadPool_fwd.h>
#include <Interpreters/Context_fwd.h>
#include <Core/UUID.h>
#include <Parsers/IAST_fwd.h>
#include <unordered_map>
@ -132,8 +133,8 @@ private:
void setNumFilesAndSize(const OperationID & id, size_t num_files, UInt64 total_size, size_t num_entries,
UInt64 uncompressed_size, UInt64 compressed_size, size_t num_read_files, UInt64 num_read_bytes);
ThreadPool backups_thread_pool;
ThreadPool restores_thread_pool;
std::unique_ptr<ThreadPool> backups_thread_pool;
std::unique_ptr<ThreadPool> restores_thread_pool;
std::unordered_map<OperationID, Info> infos;
std::condition_variable status_changed;

14
src/Backups/RestoreCoordinationRemote.cpp
View File

@ -279,12 +279,16 @@ bool RestoreCoordinationRemote::hasConcurrentRestores(const std::atomic<size_t>
if (existing_restore_uuid == toString(restore_uuid))
continue;
const auto status = zk->get(root_zookeeper_path + "/" + existing_restore_path + "/stage");
if (status != Stage::COMPLETED)
String status;
if (zk->tryGet(root_zookeeper_path + "/" + existing_restore_path + "/stage", status))
{
LOG_WARNING(log, "Found a concurrent restore: {}, current restore: {}", existing_restore_uuid, toString(restore_uuid));
result = true;
return;
/// If status is not COMPLETED it could be because the restore failed, check if 'error' exists
if (status != Stage::COMPLETED && !zk->exists(root_zookeeper_path + "/" + existing_restore_path + "/error"))
{
LOG_WARNING(log, "Found a concurrent restore: {}, current restore: {}", existing_restore_uuid, toString(restore_uuid));
result = true;
return;
}
}
}

2
src/Backups/WithRetries.cpp
View File

@ -20,7 +20,7 @@ WithRetries::WithRetries(Poco::Logger * log_, zkutil::GetZooKeeper get_zookeeper
WithRetries::RetriesControlHolder::RetriesControlHolder(const WithRetries * parent, const String & name)
: info(parent->global_zookeeper_retries_info)
, retries_ctl(name, info)
, retries_ctl(name, info, nullptr)
, faulty_zookeeper(parent->getFaultyZooKeeper())
{}

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