Merge remote-tracking branch 'origin/master' into pr-custom-key-failover

.github/workflows/backport_branches.yml

@@ -19,6 +19,8 @@ jobs:
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
+          fetch-depth: 0 # to get version
+          filter: tree:0
       - name: Labels check
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
@@ -155,7 +157,7 @@ jobs:
 ##################################### BUILD REPORTER #######################################
 ############################################################################################
   BuilderReport:
-    if: ${{ success() || failure() }}
+    if: ${{ !failure() && !cancelled() }}
     needs:
       - RunConfig
       - BuilderDebAarch64

.github/workflows/master.yml

@@ -19,6 +19,8 @@ jobs:
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
+          fetch-depth: 0 # to get version
+          filter: tree:0
       - name: Python unit tests
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"

.github/workflows/nightly.yml

@@ -22,6 +22,8 @@ jobs:
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
+          fetch-depth: 0 # to get version
+          filter: tree:0
       - name: PrepareRunConfig
         id: runconfig
         run: |

.github/workflows/pull_request.yml

@@ -13,13 +13,6 @@ on:  # yamllint disable-line rule:truthy
       - opened
     branches:
       - master
-    paths-ignore:
-      - '**.md'
-      - 'docker/docs/**'
-      - 'docs/**'
-      - 'utils/check-style/aspell-ignore/**'
-      - 'tests/ci/docs_check.py'
-      - '.github/workflows/docs_check.yml'
 ##########################################################################################
 ##################################### SMALL CHECKS #######################################
 ##########################################################################################

.github/workflows/release_branches.yml

@@ -22,6 +22,8 @@ jobs:
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
+          fetch-depth: 0 # to get version
+          filter: tree:0
       - name: Labels check
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"
@@ -214,6 +216,7 @@ jobs:
       run_command: |
         python3 build_report_check.py "$CHECK_NAME"
   MarkReleaseReady:
+    if: ${{ !failure() && !cancelled() }}
     needs:
       - BuilderBinDarwin
       - BuilderBinDarwinAarch64

.gitmodules

@@ -360,3 +360,6 @@
 [submodule "contrib/sqids-cpp"]
 	path = contrib/sqids-cpp
 	url = https://github.com/sqids/sqids-cpp.git
+[submodule "contrib/idna"]
+	path = contrib/idna
+	url = https://github.com/ada-url/idna.git

contrib/CMakeLists.txt

@@ -154,6 +154,7 @@ add_contrib (libpqxx-cmake libpqxx)
 add_contrib (libpq-cmake libpq)
 add_contrib (nuraft-cmake NuRaft)
 add_contrib (fast_float-cmake fast_float)
+add_contrib (idna-cmake idna)
 add_contrib (datasketches-cpp-cmake datasketches-cpp)
 add_contrib (incbin-cmake incbin)
 add_contrib (sqids-cpp-cmake sqids-cpp)

contrib/azure

@@ -1 +1 @@
-Subproject commit 352ff0a61cb319ac1cc38c4058443ddf70147530
+Subproject commit a852d81f92f153e109de165ee08546741e3f2a68

contrib/azure-cmake/CMakeLists.txt

@@ -12,26 +12,20 @@ file(GLOB AZURE_SDK_CORE_SRC
     "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/*.cpp"
     "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/cryptography/*.cpp"
     "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/http/*.cpp"
-    "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/http/curl/*.hpp"
     "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/http/curl/*.cpp"
-    "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/winhttp/*.cpp"
     "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/io/*.cpp"
-    "${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/private/*.hpp"
 )
 
 file(GLOB AZURE_SDK_IDENTITY_SRC
     "${AZURE_SDK_LIBRARY_DIR}/identity/azure-identity/src/*.cpp"
-    "${AZURE_SDK_LIBRARY_DIR}/identity/azure-identity/src/private/*.hpp"
 )
 
 file(GLOB AZURE_SDK_STORAGE_COMMON_SRC
     "${AZURE_SDK_LIBRARY_DIR}/storage/azure-storage-common/src/*.cpp"
-    "${AZURE_SDK_LIBRARY_DIR}/storage/azure-storage-common/src/private/*.cpp"
 )
 
 file(GLOB AZURE_SDK_STORAGE_BLOBS_SRC
     "${AZURE_SDK_LIBRARY_DIR}/storage/azure-storage-blobs/src/*.cpp"
-    "${AZURE_SDK_LIBRARY_DIR}/storage/azure-storage-blobs/src/private/*.hpp"
 )
 
 file(GLOB AZURE_SDK_UNIFIED_SRC

contrib/boringssl

@@ -1 +1 @@
-Subproject commit 8061ac62d67953e61b793042e33baf1352e67510
+Subproject commit aa6d2f865a2eab01cf94f197e11e36b6de47b5b4

contrib/idna

@@ -0,0 +1 @@
+Subproject commit 3c8be01d42b75649f1ac9b697d0ef757eebfe667

contrib/idna-cmake/CMakeLists.txt

@@ -0,0 +1,24 @@
+option(ENABLE_IDNA "Enable idna support" ${ENABLE_LIBRARIES})
+if ((NOT ENABLE_IDNA))
+    message (STATUS "Not using idna")
+    return()
+endif()
+set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/idna")
+
+set (SRCS
+    "${LIBRARY_DIR}/src/idna.cpp"
+    "${LIBRARY_DIR}/src/mapping.cpp"
+    "${LIBRARY_DIR}/src/mapping_tables.cpp"
+    "${LIBRARY_DIR}/src/normalization.cpp"
+    "${LIBRARY_DIR}/src/normalization_tables.cpp"
+    "${LIBRARY_DIR}/src/punycode.cpp"
+    "${LIBRARY_DIR}/src/to_ascii.cpp"
+    "${LIBRARY_DIR}/src/to_unicode.cpp"
+    "${LIBRARY_DIR}/src/unicode_transcoding.cpp"
+    "${LIBRARY_DIR}/src/validity.cpp"
+)
+
+add_library (_idna ${SRCS})
+target_include_directories(_idna PUBLIC "${LIBRARY_DIR}/include")
+
+add_library (ch_contrib::idna ALIAS _idna)

contrib/llvm-project-cmake/CMakeLists.txt

@@ -11,7 +11,9 @@ option (ENABLE_EMBEDDED_COMPILER "Enable support for JIT compilation during quer
 
 option (ENABLE_DWARF_PARSER "Enable support for DWARF input format (uses LLVM library)" ${ENABLE_DWARF_PARSER_DEFAULT})
 
-if (NOT ENABLE_EMBEDDED_COMPILER AND NOT ENABLE_DWARF_PARSER)
+option (ENABLE_BLAKE3 "Enable BLAKE3 function" ${ENABLE_LIBRARIES})
+
+if (NOT ENABLE_EMBEDDED_COMPILER AND NOT ENABLE_DWARF_PARSER AND NOT ENABLE_BLAKE3)
     message(STATUS "Not using LLVM")
     return()
 endif()
@@ -26,61 +28,75 @@ set (LLVM_LIBRARY_DIRS "${ClickHouse_BINARY_DIR}/contrib/llvm-project/llvm")
 # and llvm cannot be compiled with bundled libcxx and 20 standard.
 set (CMAKE_CXX_STANDARD 14)
 
-# This list was generated by listing all LLVM libraries, compiling the binary and removing all libraries while it still compiles.
-set (REQUIRED_LLVM_LIBRARIES
-    LLVMExecutionEngine
-    LLVMRuntimeDyld
-    LLVMAsmPrinter
-    LLVMDebugInfoDWARF
-    LLVMGlobalISel
-    LLVMSelectionDAG
-    LLVMMCDisassembler
-    LLVMPasses
-    LLVMCodeGen
-    LLVMipo
-    LLVMBitWriter
-    LLVMInstrumentation
-    LLVMScalarOpts
-    LLVMAggressiveInstCombine
-    LLVMInstCombine
-    LLVMVectorize
-    LLVMTransformUtils
-    LLVMTarget
-    LLVMAnalysis
-    LLVMProfileData
-    LLVMObject
-    LLVMBitReader
-    LLVMCore
-    LLVMRemarks
-    LLVMBitstreamReader
-    LLVMMCParser
-    LLVMMC
-    LLVMBinaryFormat
-    LLVMDebugInfoCodeView
-    LLVMSupport
-    LLVMDemangle
-)
+if (ARCH_AMD64)
+    set (LLVM_TARGETS_TO_BUILD "X86" CACHE INTERNAL "")
+elseif (ARCH_AARCH64)
+    set (LLVM_TARGETS_TO_BUILD "AArch64" CACHE INTERNAL "")
+elseif (ARCH_PPC64LE)
+    set (LLVM_TARGETS_TO_BUILD "PowerPC" CACHE INTERNAL "")
+elseif (ARCH_S390X)
+    set (LLVM_TARGETS_TO_BUILD "SystemZ" CACHE INTERNAL "")
+elseif (ARCH_RISCV64)
+    set (LLVM_TARGETS_TO_BUILD "RISCV" CACHE INTERNAL "")
+endif ()
+
+
+if (NOT ENABLE_EMBEDDED_COMPILER AND NOT ENABLE_DWARF_PARSER)
+    # Only compiling blake3
+    set (REQUIRED_LLVM_LIBRARIES LLVMSupport)
+else()
+    # This list was generated by listing all LLVM libraries, compiling the binary and removing all libraries while it still compiles.
+    set (REQUIRED_LLVM_LIBRARIES
+        LLVMExecutionEngine
+        LLVMRuntimeDyld
+        LLVMAsmPrinter
+        LLVMDebugInfoDWARF
+        LLVMGlobalISel
+        LLVMSelectionDAG
+        LLVMMCDisassembler
+        LLVMPasses
+        LLVMCodeGen
+        LLVMipo
+        LLVMBitWriter
+        LLVMInstrumentation
+        LLVMScalarOpts
+        LLVMAggressiveInstCombine
+        LLVMInstCombine
+        LLVMVectorize
+        LLVMTransformUtils
+        LLVMTarget
+        LLVMAnalysis
+        LLVMProfileData
+        LLVMObject
+        LLVMBitReader
+        LLVMCore
+        LLVMRemarks
+        LLVMBitstreamReader
+        LLVMMCParser
+        LLVMMC
+        LLVMBinaryFormat
+        LLVMDebugInfoCodeView
+        LLVMSupport
+        LLVMDemangle
+    )
+
+    if (ARCH_AMD64)
+        list(APPEND REQUIRED_LLVM_LIBRARIES LLVMX86Info LLVMX86Desc LLVMX86CodeGen)
+    elseif (ARCH_AARCH64)
+        list(APPEND REQUIRED_LLVM_LIBRARIES LLVMAArch64Info LLVMAArch64Desc LLVMAArch64CodeGen)
+    elseif (ARCH_PPC64LE)
+        list(APPEND REQUIRED_LLVM_LIBRARIES LLVMPowerPCInfo LLVMPowerPCDesc LLVMPowerPCCodeGen)
+    elseif (ARCH_S390X)
+        list(APPEND REQUIRED_LLVM_LIBRARIES LLVMSystemZInfo LLVMSystemZDesc LLVMSystemZCodeGen)
+    elseif (ARCH_RISCV64)
+        list(APPEND REQUIRED_LLVM_LIBRARIES LLVMRISCVInfo LLVMRISCVDesc LLVMRISCVCodeGen)
+    endif ()
+endif()
+
 
 # Skip useless "install" instructions from CMake:
 set (LLVM_INSTALL_TOOLCHAIN_ONLY 1 CACHE INTERNAL "")
 
-if (ARCH_AMD64)
-    set (LLVM_TARGETS_TO_BUILD "X86" CACHE INTERNAL "")
-    list(APPEND REQUIRED_LLVM_LIBRARIES LLVMX86Info LLVMX86Desc LLVMX86CodeGen)
-elseif (ARCH_AARCH64)
-    set (LLVM_TARGETS_TO_BUILD "AArch64" CACHE INTERNAL "")
-    list(APPEND REQUIRED_LLVM_LIBRARIES LLVMAArch64Info LLVMAArch64Desc LLVMAArch64CodeGen)
-elseif (ARCH_PPC64LE)
-    set (LLVM_TARGETS_TO_BUILD "PowerPC" CACHE INTERNAL "")
-    list(APPEND REQUIRED_LLVM_LIBRARIES LLVMPowerPCInfo LLVMPowerPCDesc LLVMPowerPCCodeGen)
-elseif (ARCH_S390X)
-    set (LLVM_TARGETS_TO_BUILD "SystemZ" CACHE INTERNAL "")
-    list(APPEND REQUIRED_LLVM_LIBRARIES LLVMSystemZInfo LLVMSystemZDesc LLVMSystemZCodeGen)
-elseif (ARCH_RISCV64)
-    set (LLVM_TARGETS_TO_BUILD "RISCV" CACHE INTERNAL "")
-    list(APPEND REQUIRED_LLVM_LIBRARIES LLVMRISCVInfo LLVMRISCVDesc LLVMRISCVCodeGen)
-endif ()
-
 message (STATUS "LLVM TARGETS TO BUILD ${LLVM_TARGETS_TO_BUILD}")
 
 set (CMAKE_INSTALL_RPATH "ON") # Do not adjust RPATH in llvm, since then it will not be able to find libcxx/libcxxabi/libunwind

docker/test/stateless/run.sh

@@ -216,11 +216,11 @@ export -f run_tests
 if [ "$NUM_TRIES" -gt "1" ]; then
     # We don't run tests with Ordinary database in PRs, only in master.
     # So run new/changed tests with Ordinary at least once in flaky check.
-    timeout "$MAX_RUN_TIME" bash -c 'NUM_TRIES=1; USE_DATABASE_ORDINARY=1; run_tests' \
+    timeout_with_logging "$MAX_RUN_TIME" bash -c 'NUM_TRIES=1; USE_DATABASE_ORDINARY=1; run_tests' \
       | sed 's/All tests have finished//' | sed 's/No tests were run//' ||:
 fi
 
-timeout "$MAX_RUN_TIME" bash -c run_tests ||:
+timeout_with_logging "$MAX_RUN_TIME" bash -c run_tests ||:
 
 echo "Files in current directory"
 ls -la ./

docker/test/stateless/utils.lib

@@ -35,4 +35,17 @@ function fn_exists() {
     declare -F "$1" > /dev/null;
 }
 
+function timeout_with_logging() {
+    local exit_code=0
+
+    timeout "${@}" || exit_code="${?}"
+
+    if [[ "${exit_code}" -eq "124" ]]
+    then
+      echo "The command 'timeout ${*}' has been killed by timeout"
+    fi
+
+    return $exit_code
+}
+
 # vi: ft=bash

docs/en/development/style.md

@@ -489,7 +489,7 @@ When using functions with response codes or `errno`, always check the result and
 
 ``` cpp
 if (0 != close(fd))
-    throwFromErrno("Cannot close file " + file_name, ErrorCodes::CANNOT_CLOSE_FILE);
+    throw ErrnoException(ErrorCodes::CANNOT_CLOSE_FILE, "Cannot close file {}", file_name);
 ```
 
 You can use assert to check invariant in code.

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

@@ -67,7 +67,6 @@ Engines in the family:
 Engines in the family:
 
 - [Distributed](../../engines/table-engines/special/distributed.md#distributed)
-- [MaterializedView](../../engines/table-engines/special/materializedview.md#materializedview)
 - [Dictionary](../../engines/table-engines/special/dictionary.md#dictionary)
 - [Merge](../../engines/table-engines/special/merge.md#merge)
 - [File](../../engines/table-engines/special/file.md#file)

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

@@ -212,5 +212,5 @@ ORDER BY key ASC
 ```
 
 ### More information on Joins
-- [`join_algorithm` setting](/docs/en/operations/settings/settings.md#settings-join_algorithm)
+- [`join_algorithm` setting](/docs/en/operations/settings/settings.md#join_algorithm)
 - [JOIN clause](/docs/en/sql-reference/statements/select/join.md)

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

@@ -236,7 +236,7 @@ libhdfs3 support HDFS namenode HA.
 
 ## Storage Settings {#storage-settings}
 
-- [hdfs_truncate_on_insert](/docs/en/operations/settings/settings.md#hdfs-truncate-on-insert) - allows to truncate file before insert into it. Disabled by default.
+- [hdfs_truncate_on_insert](/docs/en/operations/settings/settings.md#hdfs_truncate_on_insert) - allows to truncate file before insert into it. Disabled by default.
 - [hdfs_create_multiple_files](/docs/en/operations/settings/settings.md#hdfs_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
 - [hdfs_skip_empty_files](/docs/en/operations/settings/settings.md#hdfs_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
 

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

@@ -54,7 +54,7 @@ Optional parameters:
 
 - `kafka_schema` — Parameter that must be used if the format requires a schema definition. For example, [Cap’n Proto](https://capnproto.org/) requires the path to the schema file and the name of the root `schema.capnp:Message` object.
 - `kafka_num_consumers` — The number of consumers per table. Specify more consumers if the throughput of one consumer is insufficient. The total number of consumers should not exceed the number of partitions in the topic, since only one consumer can be assigned per partition, and must not be greater than the number of physical cores on the server where ClickHouse is deployed. Default: `1`.
-- `kafka_max_block_size` — The maximum batch size (in messages) for poll. Default: [max_insert_block_size](../../../operations/settings/settings.md#setting-max_insert_block_size).
+- `kafka_max_block_size` — The maximum batch size (in messages) for poll. Default: [max_insert_block_size](../../../operations/settings/settings.md#max_insert_block_size).
 - `kafka_skip_broken_messages` — Kafka message parser tolerance to schema-incompatible messages per block. If `kafka_skip_broken_messages = N` then the engine skips *N* Kafka messages that cannot be parsed (a message equals a row of data). Default: `0`.
 - `kafka_commit_every_batch` — Commit every consumed and handled batch instead of a single commit after writing a whole block. Default: `0`.
 - `kafka_client_id` — Client identifier. Empty by default.
@@ -151,7 +151,7 @@ Example:
 
   SELECT level, sum(total) FROM daily GROUP BY level;
 ```
-To improve performance, received messages are grouped into blocks the size of [max_insert_block_size](../../../operations/settings/settings.md#settings-max_insert_block_size). If the block wasn’t formed within [stream_flush_interval_ms](../../../operations/settings/settings.md/#stream-flush-interval-ms) milliseconds, the data will be flushed to the table regardless of the completeness of the block.
+To improve performance, received messages are grouped into blocks the size of [max_insert_block_size](../../../operations/settings/settings.md#max_insert_block_size). If the block wasn’t formed within [stream_flush_interval_ms](../../../operations/settings/settings.md/#stream-flush-interval-ms) milliseconds, the data will be flushed to the table regardless of the completeness of the block.
 
 To stop receiving topic data or to change the conversion logic, detach the materialized view:
 

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

@@ -58,7 +58,7 @@ Optional parameters:
 - `nats_reconnect_wait` – Amount of time in milliseconds to sleep between each reconnect attempt. Default: `5000`.
 - `nats_server_list` - Server list for connection. Can be specified to connect to NATS cluster.
 - `nats_skip_broken_messages` - NATS message parser tolerance to schema-incompatible messages per block. Default: `0`. If `nats_skip_broken_messages = N` then the engine skips *N* RabbitMQ messages that cannot be parsed (a message equals a row of data).
-- `nats_max_block_size` - Number of row collected by poll(s) for flushing data from NATS. Default: [max_insert_block_size](../../../operations/settings/settings.md#setting-max_insert_block_size).
+- `nats_max_block_size` - Number of row collected by poll(s) for flushing data from NATS. Default: [max_insert_block_size](../../../operations/settings/settings.md#max_insert_block_size).
 - `nats_flush_interval_ms` - Timeout for flushing data read from NATS. Default: [stream_flush_interval_ms](../../../operations/settings/settings.md#stream-flush-interval-ms).
 - `nats_username` - NATS username.
 - `nats_password` - NATS password.

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

@@ -65,7 +65,7 @@ Optional parameters:
 - `rabbitmq_deadletter_exchange` - Specify name for a [dead letter exchange](https://www.rabbitmq.com/dlx.html). You can create another table with this exchange name and collect messages in cases when they are republished to dead letter exchange. By default dead letter exchange is not specified.
 - `rabbitmq_persistent` - If set to 1 (true), in insert query delivery mode will be set to 2 (marks messages as 'persistent'). Default: `0`.
 - `rabbitmq_skip_broken_messages` – RabbitMQ message parser tolerance to schema-incompatible messages per block. If `rabbitmq_skip_broken_messages = N` then the engine skips *N* RabbitMQ messages that cannot be parsed (a message equals a row of data). Default: `0`.
-- `rabbitmq_max_block_size` - Number of row collected before flushing data from RabbitMQ. Default: [max_insert_block_size](../../../operations/settings/settings.md#setting-max_insert_block_size).
+- `rabbitmq_max_block_size` - Number of row collected before flushing data from RabbitMQ. Default: [max_insert_block_size](../../../operations/settings/settings.md#max_insert_block_size).
 - `rabbitmq_flush_interval_ms` - Timeout for flushing data from RabbitMQ. Default: [stream_flush_interval_ms](../../../operations/settings/settings.md#stream-flush-interval-ms).
 - `rabbitmq_queue_settings_list` - allows to set RabbitMQ settings when creating a queue. Available settings: `x-max-length`, `x-max-length-bytes`, `x-message-ttl`, `x-expires`, `x-priority`, `x-max-priority`, `x-overflow`, `x-dead-letter-exchange`, `x-queue-type`. The `durable` setting is enabled automatically for the queue.
 - `rabbitmq_address` - Address for connection. Use ether this setting or `rabbitmq_host_port`.

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

@@ -222,7 +222,7 @@ CREATE TABLE table_with_asterisk (name String, value UInt32)
 
 ## Storage Settings {#storage-settings}
 
-- [s3_truncate_on_insert](/docs/en/operations/settings/settings.md#s3-truncate-on-insert) - allows to truncate file before insert into it. Disabled by default.
+- [s3_truncate_on_insert](/docs/en/operations/settings/settings.md#s3_truncate_on_insert) - allows to truncate file before insert into it. Disabled by default.
 - [s3_create_multiple_files](/docs/en/operations/settings/settings.md#s3_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
 - [s3_skip_empty_files](/docs/en/operations/settings/settings.md#s3_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
 

docs/en/engines/table-engines/mergetree-family/custom-partitioning-key.md

@@ -12,7 +12,7 @@ In most cases you do not need a partition key, and in most other cases you do no
 You should never use too granular of partitioning. Don't partition your data by client identifiers or names. Instead, make a client identifier or name the first column in the ORDER BY expression.
 :::
 
-Partitioning is available for the [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md) family tables (including [replicated](../../../engines/table-engines/mergetree-family/replication.md) tables). [Materialized views](../../../engines/table-engines/special/materializedview.md#materializedview) based on MergeTree tables support partitioning, as well.
+Partitioning is available for the [MergeTree family tables](../../../engines/table-engines/mergetree-family/mergetree.md), including [replicated tables](../../../engines/table-engines/mergetree-family/replication.md) and [materialized views](../../../sql-reference/statements/create/view.md#materialized-view).
 
 A partition is a logical combination of records in a table by a specified criterion. You can set a partition by an arbitrary criterion, such as by month, by day, or by event type. Each partition is stored separately to simplify manipulations of this data. When accessing the data, ClickHouse uses the smallest subset of partitions possible. Partitions improve performance for queries containing a partitioning key because ClickHouse will filter for that partition before selecting the parts and granules within the partition.
 

docs/en/engines/table-engines/special/distributed.md

@@ -112,7 +112,7 @@ Specifying the `sharding_key` is necessary for the following:
 For **Insert limit settings** (`..._insert`) see also:
 
 - [distributed_foreground_insert](../../../operations/settings/settings.md#distributed_foreground_insert) setting
-- [prefer_localhost_replica](../../../operations/settings/settings.md#settings-prefer-localhost-replica) setting
+- [prefer_localhost_replica](../../../operations/settings/settings.md#prefer-localhost-replica) setting
 - `bytes_to_throw_insert` handled before `bytes_to_delay_insert`, so you should not set it to the value less then `bytes_to_delay_insert`
 :::
 
@@ -198,7 +198,7 @@ The parameters `host`, `port`, and optionally `user`, `password`, `secure`, `com
 - `secure` - Whether to use a secure SSL/TLS connection. Usually also requires specifying the port (the default secure port is `9440`). The server should listen on `<tcp_port_secure>9440</tcp_port_secure>` and be configured with correct certificates.
 - `compression` - Use data compression. Default value: `true`.
 
-When specifying replicas, one of the available replicas will be selected for each of the shards when reading. You can configure the algorithm for load balancing (the preference for which replica to access) – see the [load_balancing](../../../operations/settings/settings.md#settings-load_balancing) setting. If the connection with the server is not established, there will be an attempt to connect with a short timeout. If the connection failed, the next replica will be selected, and so on for all the replicas. If the connection attempt failed for all the replicas, the attempt will be repeated the same way, several times. This works in favour of resiliency, but does not provide complete fault tolerance: a remote server might accept the connection, but might not work, or work poorly.
+When specifying replicas, one of the available replicas will be selected for each of the shards when reading. You can configure the algorithm for load balancing (the preference for which replica to access) – see the [load_balancing](../../../operations/settings/settings.md#load_balancing) setting. If the connection with the server is not established, there will be an attempt to connect with a short timeout. If the connection failed, the next replica will be selected, and so on for all the replicas. If the connection attempt failed for all the replicas, the attempt will be repeated the same way, several times. This works in favour of resiliency, but does not provide complete fault tolerance: a remote server might accept the connection, but might not work, or work poorly.
 
 You can specify just one of the shards (in this case, query processing should be called remote, rather than distributed) or up to any number of shards. In each shard, you can specify from one to any number of replicas. You can specify a different number of replicas for each shard.
 
@@ -243,7 +243,7 @@ If the server ceased to exist or had a rough restart (for example, due to a hard
 
 When querying a `Distributed` table, `SELECT` queries are sent to all shards and work regardless of how data is distributed across the shards (they can be distributed completely randomly). When you add a new shard, you do not have to transfer old data into it. Instead, you can write new data to it by using a heavier weight – the data will be distributed slightly unevenly, but queries will work correctly and efficiently.
 
-When the `max_parallel_replicas` option is enabled, query processing is parallelized across all replicas within a single shard. For more information, see the section [max_parallel_replicas](../../../operations/settings/settings.md#settings-max_parallel_replicas).
+When the `max_parallel_replicas` option is enabled, query processing is parallelized across all replicas within a single shard. For more information, see the section [max_parallel_replicas](../../../operations/settings/settings.md#max_parallel_replicas).
 
 To learn more about how distributed `in` and `global in` queries are processed, refer to [this](../../../sql-reference/operators/in.md#select-distributed-subqueries) documentation.
 

docs/en/engines/table-engines/special/file.md

@@ -101,8 +101,8 @@ For partitioning by month, use the `toYYYYMM(date_column)` expression, where `da
 
 ## Settings {#settings}
 
-- [engine_file_empty_if_not_exists](/docs/en/operations/settings/settings.md#engine-file-emptyif-not-exists) - allows to select empty data from a file that doesn't exist. Disabled by default.
+- [engine_file_empty_if_not_exists](/docs/en/operations/settings/settings.md#engine-file-empty_if-not-exists) - allows to select empty data from a file that doesn't exist. Disabled by default.
 - [engine_file_truncate_on_insert](/docs/en/operations/settings/settings.md#engine-file-truncate-on-insert) - allows to truncate file before insert into it. Disabled by default.
 - [engine_file_allow_create_multiple_files](/docs/en/operations/settings/settings.md#engine_file_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
 - [engine_file_skip_empty_files](/docs/en/operations/settings/settings.md#engine_file_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
-- [storage_file_read_method](/docs/en/operations/settings/settings.md#engine-file-emptyif-not-exists) - method of reading data from storage file, one of: `read`, `pread`, `mmap`. The mmap method does not apply to clickhouse-server (it's intended for clickhouse-local). Default value: `pread` for clickhouse-server, `mmap` for clickhouse-local.
+- [storage_file_read_method](/docs/en/operations/settings/settings.md#engine-file-empty_if-not-exists) - method of reading data from storage file, one of: `read`, `pread`, `mmap`. The mmap method does not apply to clickhouse-server (it's intended for clickhouse-local). Default value: `pread` for clickhouse-server, `mmap` for clickhouse-local.

docs/en/engines/table-engines/special/filelog.md

@@ -41,7 +41,7 @@ Optional parameters:
 
 - `poll_timeout_ms` - Timeout for single poll from log file. Default: [stream_poll_timeout_ms](../../../operations/settings/settings.md#stream_poll_timeout_ms).
 - `poll_max_batch_size` — Maximum amount of records to be polled in a single poll. Default: [max_block_size](../../../operations/settings/settings.md#setting-max_block_size).
-- `max_block_size` — The maximum batch size (in records) for poll. Default: [max_insert_block_size](../../../operations/settings/settings.md#setting-max_insert_block_size).
+- `max_block_size` — The maximum batch size (in records) for poll. Default: [max_insert_block_size](../../../operations/settings/settings.md#max_insert_block_size).
 - `max_threads` - Number of max threads to parse files, default is 0, which means the number will be max(1, physical_cpu_cores / 4).
 - `poll_directory_watch_events_backoff_init` - The initial sleep value for watch directory thread. Default: `500`.
 - `poll_directory_watch_events_backoff_max` - The max sleep value for watch directory thread. Default: `32000`.

docs/en/engines/table-engines/special/materializedview.md

@@ -1,9 +0,0 @@
----
-slug: /en/engines/table-engines/special/materializedview
-sidebar_position: 100
-sidebar_label: MaterializedView
----
-
-# MaterializedView Table Engine
-
-Used for implementing materialized views (for more information, see [CREATE VIEW](../../../sql-reference/statements/create/view.md#materialized)). For storing data, it uses a different engine that was specified when creating the view. When reading from a table, it just uses that engine.

docs/en/interfaces/http.md

@@ -167,7 +167,7 @@ For successful requests that do not return a data table, an empty response body
 
 You can use compression to reduce network traffic when transmitting a large amount of data or for creating dumps that are immediately compressed.
 
-You can use the internal ClickHouse compression format when transmitting data. The compressed data has a non-standard format, and you need `clickhouse-compressor` program to work with it. It is installed with the `clickhouse-client` package. To increase the efficiency of data insertion, you can disable server-side checksum verification by using the [http_native_compression_disable_checksumming_on_decompress](../operations/settings/settings.md#settings-http_native_compression_disable_checksumming_on_decompress) setting.
+You can use the internal ClickHouse compression format when transmitting data. The compressed data has a non-standard format, and you need `clickhouse-compressor` program to work with it. It is installed with the `clickhouse-client` package. To increase the efficiency of data insertion, you can disable server-side checksum verification by using the [http_native_compression_disable_checksumming_on_decompress](../operations/settings/settings.md#http_native_compression_disable_checksumming_on_decompress) setting.
 
 If you specify `compress=1` in the URL, the server will compress the data it sends to you. If you specify `decompress=1` in the URL, the server will decompress the data which you pass in the `POST` method.
 
@@ -183,7 +183,7 @@ You can also choose to use [HTTP compression](https://en.wikipedia.org/wiki/HTTP
 - `snappy`
 
 To send a compressed `POST` request, append the request header `Content-Encoding: compression_method`.
-In order for ClickHouse to compress the response, enable compression with [enable_http_compression](../operations/settings/settings.md#settings-enable_http_compression) setting and append `Accept-Encoding: compression_method` header to the request. You can configure the data compression level in the [http_zlib_compression_level](../operations/settings/settings.md#settings-http_zlib_compression_level) setting for all compression methods.
+In order for ClickHouse to compress the response, enable compression with [enable_http_compression](../operations/settings/settings.md#enable_http_compression) setting and append `Accept-Encoding: compression_method` header to the request. You can configure the data compression level in the [http_zlib_compression_level](../operations/settings/settings.md#http_zlib_compression_level) setting for all compression methods.
 
 :::info
 Some HTTP clients might decompress data from the server by default (with `gzip` and `deflate`) and you might get decompressed data even if you use the compression settings correctly.
@@ -285,7 +285,7 @@ For information about other parameters, see the section “SET”.
 
 Similarly, you can use ClickHouse sessions in the HTTP protocol. To do this, you need to add the `session_id` GET parameter to the request. You can use any string as the session ID. By default, the session is terminated after 60 seconds of inactivity. To change this timeout, modify the `default_session_timeout` setting in the server configuration, or add the `session_timeout` GET parameter to the request. To check the session status, use the `session_check=1` parameter. Only one query at a time can be executed within a single session.
 
-You can receive information about the progress of a query in `X-ClickHouse-Progress` response headers. To do this, enable [send_progress_in_http_headers](../operations/settings/settings.md#settings-send_progress_in_http_headers). Example of the header sequence:
+You can receive information about the progress of a query in `X-ClickHouse-Progress` response headers. To do this, enable [send_progress_in_http_headers](../operations/settings/settings.md#send_progress_in_http_headers). Example of the header sequence:
 
 ``` text
 X-ClickHouse-Progress: {"read_rows":"2752512","read_bytes":"240570816","total_rows_to_read":"8880128","elapsed_ns":"662334"}
@@ -496,7 +496,7 @@ Next are the configuration methods for different `type`.
 
 `query` value is a predefined query of `predefined_query_handler`, which is executed by ClickHouse when an HTTP request is matched and the result of the query is returned. It is a must configuration.
 
-The following example defines the values of [max_threads](../operations/settings/settings.md#settings-max_threads) and `max_final_threads` settings, then queries the system table to check whether these settings were set successfully.
+The following example defines the values of [max_threads](../operations/settings/settings.md#max_threads) and `max_final_threads` settings, then queries the system table to check whether these settings were set successfully.
 
 :::note
 To keep the default `handlers` such as` query`, `play`,` ping`, add the `<defaults/>` rule.
@@ -539,7 +539,7 @@ In `dynamic_query_handler`, the query is written in the form of parameter of the
 
 ClickHouse extracts and executes the value corresponding to the `query_param_name` value in the URL of the HTTP request. The default value of `query_param_name` is `/query` . It is an optional configuration. If there is no definition in the configuration file, the parameter is not passed in.
 
-To experiment with this functionality, the example defines the values of [max_threads](../operations/settings/settings.md#settings-max_threads) and `max_final_threads` and `queries` whether the settings were set successfully.
+To experiment with this functionality, the example defines the values of [max_threads](../operations/settings/settings.md#max_threads) and `max_final_threads` and `queries` whether the settings were set successfully.
 
 Example:
 

docs/en/operations/monitoring.md

@@ -64,4 +64,4 @@ You can configure ClickHouse to export metrics to [Prometheus](https://prometheu
 
 Additionally, you can monitor server availability through the HTTP API. Send the `HTTP GET` request to `/ping`. If the server is available, it responds with `200 OK`.
 
-To monitor servers in a cluster configuration, you should set the [max_replica_delay_for_distributed_queries](../operations/settings/settings.md#settings-max_replica_delay_for_distributed_queries) parameter and use the HTTP resource `/replicas_status`. A request to `/replicas_status` returns `200 OK` if the replica is available and is not delayed behind the other replicas. If a replica is delayed, it returns `503 HTTP_SERVICE_UNAVAILABLE` with information about the gap.
+To monitor servers in a cluster configuration, you should set the [max_replica_delay_for_distributed_queries](../operations/settings/settings.md#max_replica_delay_for_distributed_queries) parameter and use the HTTP resource `/replicas_status`. A request to `/replicas_status` returns `200 OK` if the replica is available and is not delayed behind the other replicas. If a replica is delayed, it returns `503 HTTP_SERVICE_UNAVAILABLE` with information about the gap.

docs/en/operations/optimizing-performance/sampling-query-profiler.md

@@ -42,7 +42,7 @@ To analyze the `trace_log` system table:
 
 - Install the `clickhouse-common-static-dbg` package. See [Install from DEB Packages](../../getting-started/install.md#install-from-deb-packages).
 
-- Allow introspection functions by the [allow_introspection_functions](../../operations/settings/settings.md#settings-allow_introspection_functions) setting.
+- Allow introspection functions by the [allow_introspection_functions](../../operations/settings/settings.md#allow_introspection_functions) setting.
 
     For security reasons, introspection functions are disabled by default.
 

docs/en/operations/query-cache.md

@@ -29,6 +29,10 @@ Transactionally inconsistent caching is traditionally provided by client tools o
 the same caching logic and configuration is often duplicated. With ClickHouse's query cache, the caching logic moves to the server side.
 This reduces maintenance effort and avoids redundancy.
 
+:::security consideration
+The cached query result is tied to the user executing it. Authorization checks are performed when the query is executed. This means that if there are any alterations to the user's role or permissions between the time the query is cached and when the cache is accessed, the result will not reflect these changes. We recommend using different users to distinguish between different levels of access, instead of actively toggling roles for a single user between queries, as this practice may lead to unexpected query results.
+:::
+
 ## Configuration Settings and Usage
 
 Setting [use_query_cache](settings/settings.md#use-query-cache) can be used to control whether a specific query or all queries of the
@@ -99,7 +103,7 @@ It is also possible to limit the cache usage of individual users using [settings
 constraints](settings/constraints-on-settings.md). More specifically, you can restrict the maximum amount of memory (in bytes) a user may
 allocate in the query cache and the maximum number of stored query results. For that, first provide configurations
 [query_cache_max_size_in_bytes](settings/settings.md#query-cache-max-size-in-bytes) and
-[query_cache_max_entries](settings/settings.md#query-cache-size-max-entries) in a user profile in `users.xml`, then make both settings
+[query_cache_max_entries](settings/settings.md#query-cache-max-entries) in a user profile in `users.xml`, then make both settings
 readonly:
 
 ``` xml
@@ -140,7 +144,7 @@ value can be specified at session, profile or query level using setting [query_c
 Entries in the query cache are compressed by default. This reduces the overall memory consumption at the cost of slower writes into / reads
 from the query cache. To disable compression, use setting [query_cache_compress_entries](settings/settings.md#query-cache-compress-entries).
 
-ClickHouse reads table data in blocks of [max_block_size](settings/settings.md#settings-max_block_size) rows. Due to filtering, aggregation,
+ClickHouse reads table data in blocks of [max_block_size](settings/settings.md#setting-max_block_size) rows. Due to filtering, aggregation,
 etc., result blocks are typically much smaller than 'max_block_size' but there are also cases where they are much bigger. Setting
 [query_cache_squash_partial_results](settings/settings.md#query-cache-squash-partial-results) (enabled by default) controls if result blocks
 are squashed (if they are tiny) or split (if they are large) into blocks of 'max_block_size' size before insertion into the query result

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

@@ -2009,7 +2009,7 @@ Data for the query cache is allocated in DRAM. If memory is scarce, make sure to
 
 ## query_thread_log {#query_thread_log}
 
-Setting for logging threads of queries received with the [log_query_threads=1](../../operations/settings/settings.md#settings-log-query-threads) setting.
+Setting for logging threads of queries received with the [log_query_threads=1](../../operations/settings/settings.md#log-query-threads) setting.
 
 Queries are logged in the [system.query_thread_log](../../operations/system-tables/query_thread_log.md#system_tables-query_thread_log) table, not in a separate file. You can change the name of the table in the `table` parameter (see below).
 
@@ -2051,7 +2051,7 @@ If the table does not exist, ClickHouse will create it. If the structure of the
 
 ## query_views_log {#query_views_log}
 
-Setting for logging views (live, materialized etc) dependant of queries received with the [log_query_views=1](../../operations/settings/settings.md#settings-log-query-views) setting.
+Setting for logging views (live, materialized etc) dependant of queries received with the [log_query_views=1](../../operations/settings/settings.md#log-query-views) setting.
 
 Queries are logged in the [system.query_views_log](../../operations/system-tables/query_views_log.md#system_tables-query_views_log) table, not in a separate file. You can change the name of the table in the `table` parameter (see below).
 
@@ -2331,7 +2331,7 @@ For the value of the `incl` attribute, see the section “[Configuration files](
 
 **See Also**
 
-- [skip_unavailable_shards](../../operations/settings/settings.md#settings-skip_unavailable_shards)
+- [skip_unavailable_shards](../../operations/settings/settings.md#skip_unavailable_shards)
 - [Cluster Discovery](../../operations/cluster-discovery.md)
 - [Replicated database engine](../../engines/database-engines/replicated.md)
 

docs/en/operations/settings/query-complexity.md

@@ -139,7 +139,7 @@ Limit on the number of bytes in the result. The same as the previous setting.
 
 What to do if the volume of the result exceeds one of the limits: ‘throw’ or ‘break’. By default, throw.
 
-Using ‘break’ is similar to using LIMIT. `Break` interrupts execution only at the block level. This means that amount of returned rows is greater than [max_result_rows](#setting-max_result_rows), multiple of [max_block_size](../../operations/settings/settings.md#setting-max_block_size) and depends on [max_threads](../../operations/settings/settings.md#settings-max_threads).
+Using ‘break’ is similar to using LIMIT. `Break` interrupts execution only at the block level. This means that amount of returned rows is greater than [max_result_rows](#setting-max_result_rows), multiple of [max_block_size](../../operations/settings/settings.md#setting-max_block_size) and depends on [max_threads](../../operations/settings/settings.md#max_threads).
 
 Example:
 

docs/en/operations/settings/settings.md

@@ -460,6 +460,12 @@ Possible values:
 
 Default value: 1048576.
 
+## http_make_head_request {#http-make-head-request}
+
+The `http_make_head_request` setting allows the execution of a `HEAD` request while reading data from HTTP to retrieve information about the file to be read, such as its size. Since it's enabled by default, it may be desirable to disable this setting in cases where the server does not support `HEAD` requests.
+
+Default value: `true`.
+
 ## table_function_remote_max_addresses {#table_function_remote_max_addresses}
 
 Sets the maximum number of addresses generated from patterns for the [remote](../../sql-reference/table-functions/remote.md) function.
@@ -1578,9 +1584,15 @@ Default value: `default`.
 
 ## allow_experimental_parallel_reading_from_replicas
 
-If true, ClickHouse will send a SELECT query to all replicas of a table (up to `max_parallel_replicas`) . It will work for any kind of MergeTree table.
+Enables or disables sending SELECT queries to all replicas of a table (up to `max_parallel_replicas`). Reading is parallelized and coordinated dynamically. It will work for any kind of MergeTree table.
 
-Default value: `false`.
+Possible values:
+
+- 0 - Disabled.
+- 1 - Enabled, silently disabled in case of failure.
+- 2 - Enabled, throws an exception in case of failure.
+
+Default value: `0`.
 
 ## compile_expressions {#compile-expressions}
 
@@ -1704,7 +1716,7 @@ Default value: `1`
 
 ## query_cache_squash_partial_results {#query-cache-squash-partial-results}
 
-Squash partial result blocks to blocks of size [max_block_size](#setting-max_block_size). Reduces performance of inserts into the [query cache](../query-cache.md) but improves the compressability of cache entries (see [query_cache_compress-entries](#query_cache_compress_entries)).
+Squash partial result blocks to blocks of size [max_block_size](#setting-max_block_size). Reduces performance of inserts into the [query cache](../query-cache.md) but improves the compressability of cache entries (see [query_cache_compress-entries](#query-cache-compress-entries)).
 
 Possible values:
 
@@ -2474,7 +2486,7 @@ See also:
 - [load_balancing](#load_balancing-round_robin)
 - [Table engine Distributed](../../engines/table-engines/special/distributed.md)
 - [distributed_replica_error_cap](#distributed_replica_error_cap)
-- [distributed_replica_error_half_life](#settings-distributed_replica_error_half_life)
+- [distributed_replica_error_half_life](#distributed_replica_error_half_life)
 
 ## distributed_background_insert_sleep_time_ms {#distributed_background_insert_sleep_time_ms}
 
@@ -4152,6 +4164,41 @@ Result:
 └─────┴─────┴───────┘
 ```
 
+## enable_order_by_all {#enable-order-by-all}
+
+Enables or disables sorting by `ALL` columns, i.e. [ORDER BY](../../sql-reference/statements/select/order-by.md)
+
+Possible values:
+
+- 0 — Disable ORDER BY ALL.
+- 1 — Enable ORDER BY ALL.
+
+Default value: `1`.
+
+**Example**
+
+Query:
+
+```sql
+CREATE TABLE TAB(C1 Int, C2 Int, ALL Int) ENGINE=Memory();
+
+INSERT INTO TAB VALUES (10, 20, 30), (20, 20, 10), (30, 10, 20);
+
+SELECT * FROM TAB ORDER BY ALL; -- returns an error that ALL is ambiguous
+
+SELECT * FROM TAB ORDER BY ALL SETTINGS enable_order_by_all;
+```
+
+Result:
+
+```text
+┌─C1─┬─C2─┬─ALL─┐
+│ 20 │ 20 │  10 │
+│ 30 │ 10 │  20 │
+│ 10 │ 20 │  30 │
+└────┴────┴─────┘
+```
+
 ## splitby_max_substrings_includes_remaining_string {#splitby_max_substrings_includes_remaining_string}
 
 Controls whether function [splitBy*()](../../sql-reference/functions/splitting-merging-functions.md) with argument `max_substrings` > 0 will include the remaining string in the last element of the result array.
@@ -4668,7 +4715,7 @@ Possible values:
 
 Default value: `false`.
 
-## rename_files_after_processing
+## rename_files_after_processing {#rename_files_after_processing}
 
 - **Type:** String
 
@@ -5087,3 +5134,25 @@ When set to `true` than for all s3 requests first two attempts are made with low
 When set to `false` than all attempts are made with identical timeouts.
 
 Default value: `true`.
+
+## max_partition_size_to_drop
+
+Restriction on dropping partitions in query time.
+
+Default value: 50 GB.
+The value 0 means that you can drop partitions without any restrictions.
+
+:::note
+This query setting overwrites its server setting equivalent, see [max_partition_size_to_drop](/docs/en/operations/server-configuration-parameters/settings.md/#max-partition-size-to-drop)
+:::
+
+## max_table_size_to_drop
+
+Restriction on deleting tables in query time.
+
+Default value: 50 GB.
+The value 0 means that you can delete all tables without any restrictions.
+
+:::note
+This query setting overwrites its server setting equivalent, see [max_table_size_to_drop](/docs/en/operations/server-configuration-parameters/settings.md/#max-table-size-to-drop)
+:::

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

@@ -78,5 +78,5 @@ is_active:               NULL
 **See Also**
 
 - [Table engine Distributed](../../engines/table-engines/special/distributed.md)
-- [distributed_replica_error_cap setting](../../operations/settings/settings.md#settings-distributed_replica_error_cap)
-- [distributed_replica_error_half_life setting](../../operations/settings/settings.md#settings-distributed_replica_error_half_life)
+- [distributed_replica_error_cap setting](../../operations/settings/settings.md#distributed_replica_error_cap)
+- [distributed_replica_error_half_life setting](../../operations/settings/settings.md#distributed_replica_error_half_life)

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

@@ -11,7 +11,7 @@ This table does not contain the ingested data for `INSERT` queries.
 
 You can change settings of queries logging in the [query_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query-log) section of the server configuration.
 
-You can disable queries logging by setting [log_queries = 0](../../operations/settings/settings.md#settings-log-queries). We do not recommend to turn off logging because information in this table is important for solving issues.
+You can disable queries logging by setting [log_queries = 0](../../operations/settings/settings.md#log-queries). We do not recommend to turn off logging because information in this table is important for solving issues.
 
 The flushing period of data is set in `flush_interval_milliseconds` parameter of the [query_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query-log) server settings section. To force flushing, use the [SYSTEM FLUSH LOGS](../../sql-reference/statements/system.md#query_language-system-flush_logs) query.
 
@@ -30,7 +30,7 @@ Each query creates one or two rows in the `query_log` table, depending on the st
 
 You can use the [log_queries_probability](../../operations/settings/settings.md#log-queries-probability) setting to reduce the number of queries, registered in the `query_log` table.
 
-You can use the [log_formatted_queries](../../operations/settings/settings.md#settings-log-formatted-queries) setting to log formatted queries to the `formatted_query` column.
+You can use the [log_formatted_queries](../../operations/settings/settings.md#log-formatted-queries) setting to log formatted queries to the `formatted_query` column.
 
 Columns:
 
@@ -101,7 +101,7 @@ Columns:
 - `revision` ([UInt32](../../sql-reference/data-types/int-uint.md)) — ClickHouse revision.
 - `ProfileEvents` ([Map(String, UInt64)](../../sql-reference/data-types/map.md)) — ProfileEvents that measure different metrics. The description of them could be found in the table [system.events](../../operations/system-tables/events.md#system_tables-events)
 - `Settings` ([Map(String, String)](../../sql-reference/data-types/map.md)) — Settings that were changed when the client ran the query. To enable logging changes to settings, set the `log_query_settings` parameter to 1.
-- `log_comment` ([String](../../sql-reference/data-types/string.md)) — Log comment. It can be set to arbitrary string no longer than [max_query_size](../../operations/settings/settings.md#settings-max_query_size). An empty string if it is not defined.
+- `log_comment` ([String](../../sql-reference/data-types/string.md)) — Log comment. It can be set to arbitrary string no longer than [max_query_size](../../operations/settings/settings.md#max_query_size). An empty string if it is not defined.
 - `thread_ids` ([Array(UInt64)](../../sql-reference/data-types/array.md)) — Thread ids that are participating in query execution. These threads may not have run simultaneously.
 - `peak_threads_usage` ([UInt64)](../../sql-reference/data-types/int-uint.md)) — Maximum count of simultaneous threads executing the query.
 - `used_aggregate_functions` ([Array(String)](../../sql-reference/data-types/array.md)) — Canonical names of `aggregate functions`, which were used during query execution.

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

@@ -8,7 +8,7 @@ Contains information about threads that execute queries, for example, thread nam
 To start logging:
 
 1.  Configure parameters in the [query_thread_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) section.
-2.  Set [log_query_threads](../../operations/settings/settings.md#settings-log-query-threads) to 1.
+2.  Set [log_query_threads](../../operations/settings/settings.md#log-query-threads) to 1.
 
 The flushing period of data is set in `flush_interval_milliseconds` parameter of the [query_thread_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_thread_log) server settings section. To force flushing, use the [SYSTEM FLUSH LOGS](../../sql-reference/statements/system.md#query_language-system-flush_logs) query.
 

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

@@ -8,7 +8,7 @@ Contains information about the dependent views executed when running a query, fo
 To start logging:
 
 1. Configure parameters in the [query_views_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_views_log) section.
-2. Set [log_query_views](../../operations/settings/settings.md#settings-log-query-views) to 1.
+2. Set [log_query_views](../../operations/settings/settings.md#log-query-views) to 1.
 
 The flushing period of data is set in `flush_interval_milliseconds` parameter of the [query_views_log](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-query_views_log) server settings section. To force flushing, use the [SYSTEM FLUSH LOGS](../../sql-reference/statements/system.md#query_language-system-flush_logs) query.
 

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

@@ -14,7 +14,7 @@ This table contains the following columns (the column type is shown in brackets)
 - `supports_sort_order` (UInt8) — Flag that indicates if table engine supports clauses `PARTITION_BY`, `PRIMARY_KEY`, `ORDER_BY` and `SAMPLE_BY`.
 - `supports_replication` (UInt8) — Flag that indicates if table engine supports [data replication](../../engines/table-engines/mergetree-family/replication.md).
 - `supports_duduplication` (UInt8) — Flag that indicates if table engine supports data deduplication.
-- `supports_parallel_insert` (UInt8) — Flag that indicates if table engine supports parallel insert (see [`max_insert_threads`](../../operations/settings/settings.md#settings-max-insert-threads) setting).
+- `supports_parallel_insert` (UInt8) — Flag that indicates if table engine supports parallel insert (see [`max_insert_threads`](../../operations/settings/settings.md#max-insert-threads) setting).
 
 Example:
 

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

@@ -29,7 +29,7 @@ Columns:
 
 - `dependencies_database` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) - Database dependencies.
 
-- `dependencies_table` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) - Table dependencies ([MaterializedView](../../engines/table-engines/special/materializedview.md) tables based on the current table).
+- `dependencies_table` ([Array](../../sql-reference/data-types/array.md)([String](../../sql-reference/data-types/string.md))) - Table dependencies ([materialized views](../../sql-reference/statements/create/view.md#materialized-view) the current table).
 
 - `create_table_query` ([String](../../sql-reference/data-types/string.md)) - The query that was used to create the table.
 
@@ -57,6 +57,8 @@ Columns:
     - If the table stores data on disk, returns used space on disk (i.e. compressed).
     - If the table stores data in memory, returns approximated number of used bytes in memory.
 
+- `total_bytes_uncompressed` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) - Total number of uncompressed bytes, if it's possible to quickly determine the exact number of bytes from the part checksums for the table on storage, otherwise `NULL` (does not take underlying storage (if any) into account).
+
 - `lifetime_rows` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) - Total number of rows INSERTed since server start (only for `Buffer` tables).
 
 - `lifetime_bytes` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) - Total number of bytes INSERTed since server start (only for `Buffer` tables).

docs/en/sql-reference/aggregate-functions/reference/count.md

@@ -28,7 +28,7 @@ In both cases the type of the returned value is [UInt64](../../../sql-reference/
 
 **Details**
 
-ClickHouse supports the `COUNT(DISTINCT ...)` syntax. The behavior of this construction depends on the [count_distinct_implementation](../../../operations/settings/settings.md#settings-count_distinct_implementation) setting. It defines which of the [uniq\*](../../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniq) functions is used to perform the operation. The default is the [uniqExact](../../../sql-reference/aggregate-functions/reference/uniqexact.md#agg_function-uniqexact) function.
+ClickHouse supports the `COUNT(DISTINCT ...)` syntax. The behavior of this construction depends on the [count_distinct_implementation](../../../operations/settings/settings.md#count_distinct_implementation) setting. It defines which of the [uniq\*](../../../sql-reference/aggregate-functions/reference/uniq.md#agg_function-uniq) functions is used to perform the operation. The default is the [uniqExact](../../../sql-reference/aggregate-functions/reference/uniqexact.md#agg_function-uniqexact) function.
 
 The `SELECT count() FROM table` query is optimized by default using metadata from MergeTree. If you need to use row-level security, disable optimization using the [optimize_trivial_count_query](../../../operations/settings/settings.md#optimize-trivial-count-query) setting.
 

docs/en/sql-reference/dictionaries/index.md

@@ -394,7 +394,7 @@ Configuration example:
 or
 
 ``` sql
-LAYOUT(HASHED_ARRAY())
+LAYOUT(HASHED_ARRAY([SHARDS 1]))
 ```
 
 ### complex_key_hashed_array
@@ -412,7 +412,7 @@ Configuration example:
 or
 
 ``` sql
-LAYOUT(COMPLEX_KEY_HASHED_ARRAY())
+LAYOUT(COMPLEX_KEY_HASHED_ARRAY([SHARDS 1]))
 ```
 
 ### range_hashed {#range_hashed}
@@ -2415,8 +2415,8 @@ clickhouse client \
     --secure \
     --password MY_PASSWORD \
     --query "
-    INSERT INTO regexp_dictionary_source_table 
-    SELECT * FROM input ('id UInt64, parent_id UInt64, regexp String, keys Array(String), values Array(String)') 
+    INSERT INTO regexp_dictionary_source_table
+    SELECT * FROM input ('id UInt64, parent_id UInt64, regexp String, keys Array(String), values Array(String)')
     FORMAT CSV" < regexp_dict.csv
 ```
 

docs/en/sql-reference/functions/array-functions.md

@@ -143,7 +143,7 @@ range([start, ] end [, step])
 **Implementation details**
 
 - All arguments `start`, `end`, `step` must be below data types: `UInt8`, `UInt16`, `UInt32`, `UInt64`,`Int8`, `Int16`, `Int32`, `Int64`, as well as elements of the returned array, which's type is a super type of all arguments.
-- An exception is thrown if query results in arrays with a total length of more than number of elements specified by the [function_range_max_elements_in_block](../../operations/settings/settings.md#settings-function_range_max_elements_in_block) setting.
+- An exception is thrown if query results in arrays with a total length of more than number of elements specified by the [function_range_max_elements_in_block](../../operations/settings/settings.md#function_range_max_elements_in_block) setting.
 - Returns Null if any argument has Nullable(Nothing) type. An exception is thrown if any argument has Null value (Nullable(T) type).
 
 **Examples**

docs/en/sql-reference/functions/date-time-functions.md

@@ -1809,6 +1809,8 @@ Alias: `dateTrunc`.
     - `quarter`
     - `year`
 
+    `unit` argument is case-insensitive.
+
 - `value` — Date and time. [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
 - `timezone` — [Timezone name](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) for the returned value (optional). If not specified, the function uses the timezone of the `value` parameter. [String](../../sql-reference/data-types/string.md).
 

docs/en/sql-reference/functions/introspection.md

@@ -16,7 +16,7 @@ For proper operation of introspection functions:
 
 - Install the `clickhouse-common-static-dbg` package.
 
-- Set the [allow_introspection_functions](../../operations/settings/settings.md#settings-allow_introspection_functions) setting to 1.
+- Set the [allow_introspection_functions](../../operations/settings/settings.md#allow_introspection_functions) setting to 1.
 
         For security reasons introspection functions are disabled by default.
 

docs/en/sql-reference/functions/other-functions.md

@@ -2831,3 +2831,92 @@ Result:
 │ SELECT a, b FROM tab WHERE (a > 3) AND (b < 3)                          │
 └─────────────────────────────────────────────────────────────────────────┘
 ```
+
+## minSampleSizeConversion
+
+Calculates minimum required sample size for an A/B test comparing conversions (proportions) in two samples.
+
+**Syntax**
+
+``` sql
+minSampleSizeConversion(baseline, mde, power, alpha)
+```
+
+Uses the formula described in [this article](https://towardsdatascience.com/required-sample-size-for-a-b-testing-6f6608dd330a). Assumes equal sizes of treatment and control groups. Returns the sample size required for one group (i.e. the sample size required for the whole experiment is twice the returned value).
+
+**Arguments**
+
+- `baseline` — Baseline conversion. [Float](../data-types/float.md).
+- `mde` — Minimum detectable effect (MDE) as percentage points (e.g. for a baseline conversion 0.25 the MDE 0.03 means an expected change to 0.25 ± 0.03). [Float](../data-types/float.md).
+- `power` — Required statistical power of a test (1 - probability of Type II error). [Float](../data-types/float.md).
+- `alpha` — Required significance level of a test (probability of Type I error). [Float](../data-types/float.md).
+
+**Returned value**
+
+A named [Tuple](../data-types/tuple.md) with 3 elements:
+
+- `"minimum_sample_size"` — Required sample size. [Float64](../data-types/float.md).
+- `"detect_range_lower"` — Lower bound of the range of values not detectable with the returned required sample size (i.e. all values less than or equal to `"detect_range_lower"` are detectable with the provided `alpha` and `power`). Calculated as `baseline - mde`. [Float64](../data-types/float.md).
+- `"detect_range_upper"` — Upper bound of the range of values not detectable with the returned required sample size (i.e. all values greater than or equal to `"detect_range_upper"` are detectable with the provided `alpha` and `power`). Calculated as `baseline + mde`. [Float64](../data-types/float.md).
+
+**Example**
+
+The following query calculates the required sample size for an A/B test with baseline conversion of 25%, MDE of 3%, significance level of 5%, and the desired statistical power of 80%:
+
+``` sql
+SELECT minSampleSizeConversion(0.25, 0.03, 0.80, 0.05) AS sample_size;
+```
+
+Result:
+
+``` text
+┌─sample_size───────────────────┐
+│ (3396.077603219163,0.22,0.28) │
+└───────────────────────────────┘
+```
+
+## minSampleSizeContinuous
+
+Calculates minimum required sample size for an A/B test comparing means of a continuous metric in two samples.
+
+**Syntax**
+
+``` sql
+minSampleSizeContinous(baseline, sigma, mde, power, alpha)
+```
+
+Alias: `minSampleSizeContinous`
+
+Uses the formula described in [this article](https://towardsdatascience.com/required-sample-size-for-a-b-testing-6f6608dd330a). Assumes equal sizes of treatment and control groups. Returns the required sample size for one group (i.e. the sample size required for the whole experiment is twice the returned value). Also assumes equal variance of the test metric in treatment and control groups.
+
+**Arguments**
+
+- `baseline` — Baseline value of a metric. [Integer](../data-types/int-uint.md) or [Float](../data-types/float.md).
+- `sigma` — Baseline standard deviation of a metric. [Integer](../data-types/int-uint.md) or [Float](../data-types/float.md).
+- `mde` — Minimum detectable effect (MDE) as percentage of the baseline value (e.g. for a baseline value 112.25 the MDE 0.03 means an expected change to 112.25 ± 112.25*0.03). [Integer](../data-types/int-uint.md) or [Float](../data-types/float.md).
+- `power` — Required statistical power of a test (1 - probability of Type II error). [Integer](../data-types/int-uint.md) or [Float](../data-types/float.md).
+- `alpha` — Required significance level of a test (probability of Type I error). [Integer](../data-types/int-uint.md) or [Float](../data-types/float.md).
+
+**Returned value**
+
+A named [Tuple](../data-types/tuple.md) with 3 elements:
+
+- `"minimum_sample_size"` — Required sample size. [Float64](../data-types/float.md).
+- `"detect_range_lower"` — Lower bound of the range of values not detectable with the returned required sample size (i.e. all values less than or equal to `"detect_range_lower"` are detectable with the provided `alpha` and `power`). Calculated as `baseline * (1 - mde)`. [Float64](../data-types/float.md).
+- `"detect_range_upper"` — Upper bound of the range of values not detectable with the returned required sample size (i.e. all values greater than or equal to `"detect_range_upper"` are detectable with the provided `alpha` and `power`). Calculated as `baseline * (1 + mde)`. [Float64](../data-types/float.md).
+
+**Example**
+
+The following query calculates the required sample size for an A/B test on a metric with baseline value of 112.25, standard deviation of 21.1, MDE of 3%, significance level of 5%, and the desired statistical power of 80%:
+
+``` sql
+SELECT minSampleSizeContinous(112.25, 21.1, 0.03, 0.80, 0.05) AS sample_size;
+```
+
+Result:
+
+``` text
+┌─sample_size───────────────────────────┐
+│ (616.2931945826209,108.8825,115.6175) │
+└───────────────────────────────────────┘
+```

docs/en/sql-reference/functions/string-functions.md

@@ -533,8 +533,8 @@ Result:
 
 ```result
 ┌─concatWithSeparator('a', '1', '2', '3', '4')─┐
-│ 1a2a3a4                           │
-└───────────────────────────────────┘
+│ 1a2a3a4                                      │
+└──────────────────────────────────────────────┘
 ```
 
 ## concatWithSeparatorAssumeInjective
@@ -1383,6 +1383,71 @@ Result:
 └──────────────────┘
 ```
 
+## punycodeEncode
+
+Returns the [Punycode](https://en.wikipedia.org/wiki/Punycode) of a string.
+The string must be UTF8-encoded, otherwise results are undefined.
+
+**Syntax**
+
+``` sql
+punycodeEncode(val)
+```
+
+**Arguments**
+
+- `val` - Input value. [String](../data-types/string.md)
+
+**Returned value**
+
+- A Punycode representation of the input value. [String](../data-types/string.md)
+
+**Example**
+
+``` sql
+select punycodeEncode('München');
+```
+
+Result:
+
+```result
+┌─punycodeEncode('München')─┐
+│ Mnchen-3ya                │
+└───────────────────────────┘
+```
+
+## punycodeDecode
+
+Returns the UTF8-encoded plaintext of a [Punycode](https://en.wikipedia.org/wiki/Punycode)-encoded string.
+
+**Syntax**
+
+``` sql
+punycodeEncode(val)
+```
+
+**Arguments**
+
+- `val` - Punycode-encoded string. [String](../data-types/string.md)
+
+**Returned value**
+
+- The plaintext of the input value. [String](../data-types/string.md)
+
+**Example**
+
+``` sql
+select punycodeDecode('Mnchen-3ya');
+```
+
+Result:
+
+```result
+┌─punycodeEncode('Mnchen-3ya')─┐
+│ München                      │
+└──────────────────────────────┘
+```
+
 ## byteHammingDistance
 
 Calculates the [hamming distance](https://en.wikipedia.org/wiki/Hamming_distance) between two byte strings.

docs/en/sql-reference/statements/alter/apply-deleted-mask.md

@@ -0,0 +1,22 @@
+---
+slug: /en/sql-reference/statements/alter/apply-deleted-mask
+sidebar_position: 46
+sidebar_label: APPLY DELETED MASK
+---
+
+# Apply mask of deleted rows
+
+``` sql
+ALTER TABLE [db].name [ON CLUSTER cluster] APPLY DELETED MASK [IN PARTITION partition_id]
+```
+
+The command applies mask created by [lightweight delete](/docs/en/sql-reference/statements/delete) and forcefully removes rows marked as deleted from disk. This command is a heavyweight mutation and it semantically equals to query ```ALTER TABLE [db].name DELETE WHERE _row_exists = 0```.
+
+:::note
+It only works for tables in the [`MergeTree`](../../../engines/table-engines/mergetree-family/mergetree.md) family (including [replicated](../../../engines/table-engines/mergetree-family/replication.md) tables).
+:::
+
+**See also**
+
+- [Lightweight deletes](/docs/en/sql-reference/statements/delete)
+- [Heavyweight deletes](/docs/en/sql-reference/statements/alter/delete.md)

docs/en/sql-reference/statements/alter/index.md

@@ -17,8 +17,9 @@ Most `ALTER TABLE` queries modify table settings or data:
 - [CONSTRAINT](/docs/en/sql-reference/statements/alter/constraint.md)
 - [TTL](/docs/en/sql-reference/statements/alter/ttl.md)
 - [STATISTIC](/docs/en/sql-reference/statements/alter/statistic.md)
+- [APPLY DELETED MASK](/docs/en/sql-reference/statements/alter/apply-deleted-mask.md)
 
-:::note    
+:::note
 Most `ALTER TABLE` queries are supported only for [\*MergeTree](/docs/en/engines/table-engines/mergetree-family/index.md) tables, as well as [Merge](/docs/en/engines/table-engines/special/merge.md) and [Distributed](/docs/en/engines/table-engines/special/distributed.md).
 :::
 
@@ -59,7 +60,7 @@ For all `ALTER` queries, you can use the [alter_sync](/docs/en/operations/settin
 
 You can specify how long (in seconds) to wait for inactive replicas to execute all `ALTER` queries with the [replication_wait_for_inactive_replica_timeout](/docs/en/operations/settings/settings.md/#replication-wait-for-inactive-replica-timeout) setting.
 
-:::note    
+:::note
 For all `ALTER` queries, if `alter_sync = 2` and some replicas are not active for more than the time, specified in the `replication_wait_for_inactive_replica_timeout` setting, then an exception `UNFINISHED` is thrown.
 :::
 

docs/en/sql-reference/statements/optimize.md

@@ -17,7 +17,7 @@ This query tries to initialize an unscheduled merge of data parts for tables. No
 OPTIMIZE TABLE [db.]name [ON CLUSTER cluster] [PARTITION partition | PARTITION ID 'partition_id'] [FINAL] [DEDUPLICATE [BY expression]]
 ```
 
-The `OPTIMIZE` query is supported for [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) family, the [MaterializedView](../../engines/table-engines/special/materializedview.md) and the [Buffer](../../engines/table-engines/special/buffer.md) engines. Other table engines aren’t supported.
+The `OPTIMIZE` query is supported for [MergeTree](../../engines/table-engines/mergetree-family/mergetree.md) family (including [materialized views](../../sql-reference/statements/create/view.md#materialized-view)) and the [Buffer](../../engines/table-engines/special/buffer.md) engines. Other table engines aren’t supported.
 
 When `OPTIMIZE` is used with the [ReplicatedMergeTree](../../engines/table-engines/mergetree-family/replication.md) family of table engines, ClickHouse creates a task for merging and waits for execution on all replicas (if the [alter_sync](../../operations/settings/settings.md#alter-sync) setting is set to `2`) or on current replica (if the [alter_sync](../../operations/settings/settings.md#alter-sync) setting is set to `1`).
 

docs/en/sql-reference/statements/select/join.md

@@ -45,20 +45,20 @@ Additional join types available in ClickHouse:
 - `ASOF JOIN` and `LEFT ASOF JOIN`, joining sequences with a non-exact match. `ASOF JOIN` usage is described below.
 
 :::note
-When [join_algorithm](../../../operations/settings/settings.md#settings-join_algorithm) is set to `partial_merge`, `RIGHT JOIN` and `FULL JOIN` are supported only with `ALL` strictness (`SEMI`, `ANTI`, `ANY`, and `ASOF` are not supported).
+When [join_algorithm](../../../operations/settings/settings.md#join_algorithm) is set to `partial_merge`, `RIGHT JOIN` and `FULL JOIN` are supported only with `ALL` strictness (`SEMI`, `ANTI`, `ANY`, and `ASOF` are not supported).
 :::
 
 ## Settings
 
-The default join type can be overridden using [join_default_strictness](../../../operations/settings/settings.md#settings-join_default_strictness) setting.
+The default join type can be overridden using [join_default_strictness](../../../operations/settings/settings.md#join_default_strictness) setting.
 
 The behavior of ClickHouse server for `ANY JOIN` operations depends on the [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys) setting.
 
 
 **See also**
 
-- [join_algorithm](../../../operations/settings/settings.md#settings-join_algorithm)
-- [join_any_take_last_row](../../../operations/settings/settings.md#settings-join_any_take_last_row)
+- [join_algorithm](../../../operations/settings/settings.md#join_algorithm)
+- [join_any_take_last_row](../../../operations/settings/settings.md#join_any_take_last_row)
 - [join_use_nulls](../../../operations/settings/settings.md#join_use_nulls)
 - [partial_merge_join_optimizations](../../../operations/settings/settings.md#partial_merge_join_optimizations)
 - [partial_merge_join_rows_in_right_blocks](../../../operations/settings/settings.md#partial_merge_join_rows_in_right_blocks)
@@ -352,7 +352,7 @@ If you need a `JOIN` for joining with dimension tables (these are relatively sma
 
 ### Memory Limitations
 
-By default, ClickHouse uses the [hash join](https://en.wikipedia.org/wiki/Hash_join) algorithm. ClickHouse takes the right_table and creates a hash table for it in RAM. If `join_algorithm = 'auto'` is enabled, then after some threshold of memory consumption, ClickHouse falls back to [merge](https://en.wikipedia.org/wiki/Sort-merge_join) join algorithm. For `JOIN` algorithms description see the [join_algorithm](../../../operations/settings/settings.md#settings-join_algorithm) setting.
+By default, ClickHouse uses the [hash join](https://en.wikipedia.org/wiki/Hash_join) algorithm. ClickHouse takes the right_table and creates a hash table for it in RAM. If `join_algorithm = 'auto'` is enabled, then after some threshold of memory consumption, ClickHouse falls back to [merge](https://en.wikipedia.org/wiki/Sort-merge_join) join algorithm. For `JOIN` algorithms description see the [join_algorithm](../../../operations/settings/settings.md#join_algorithm) setting.
 
 If you need to restrict `JOIN` operation memory consumption use the following settings:
 

docs/en/sql-reference/statements/select/order-by.md

@@ -5,12 +5,22 @@ sidebar_label: ORDER BY
 
 # ORDER BY Clause
 
-The `ORDER BY` clause contains a list of expressions, which can each be attributed with `DESC` (descending) or `ASC` (ascending) modifier which determine the sorting direction. If the direction is not specified, `ASC` is assumed, so it’s usually omitted. The sorting direction applies to a single expression, not to the entire list. Example: `ORDER BY Visits DESC, SearchPhrase`.  Sorting is case-sensitive.
+The `ORDER BY` clause contains
 
-If you want to sort by column numbers instead of column names, enable the setting [enable_positional_arguments](../../../operations/settings/settings.md#enable-positional-arguments).
+- a list of expressions, e.g. `ORDER BY visits, search_phrase`,
+- a list of numbers referring to columns in the `SELECT` clause, e.g. `ORDER BY 2, 1`, or
+- `ALL` which means all columns of the `SELECT` clause, e.g. `ORDER BY ALL`.
 
-Rows that have identical values for the list of sorting expressions are output in an arbitrary order, which can also be non-deterministic (different each time).
-If the ORDER BY clause is omitted, the order of the rows is also undefined, and may be non-deterministic as well.
+To disable sorting by column numbers, set setting [enable_positional_arguments](../../../operations/settings/settings.md#enable-positional-arguments) = 0.
+To disable sorting by `ALL`, set setting [enable_order_by_all](../../../operations/settings/settings.md#enable-order-by-all) = 0.
+
+The `ORDER BY` clause can be attributed by a `DESC` (descending) or `ASC` (ascending) modifier which determines the sorting direction.
+Unless an explicit sort order is specified, `ASC` is used by default.
+The sorting direction applies to a single expression, not to the entire list, e.g. `ORDER BY Visits DESC, SearchPhrase`.
+Also, sorting is performed case-sensitively.
+
+Rows with identical values for a sort expressions are returned in an arbitrary and non-deterministic order.
+If the `ORDER BY` clause is omitted in a `SELECT` statement, the row order is also arbitrary and non-deterministic.
 
 ## Sorting of Special Values
 
@@ -265,8 +275,9 @@ Consider disabling `optimize_read_in_order` manually, when running queries that
 
 Optimization is supported in the following table engines:
 
-- [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md)
-- [Merge](../../../engines/table-engines/special/merge.md), [Buffer](../../../engines/table-engines/special/buffer.md), and [MaterializedView](../../../engines/table-engines/special/materializedview.md) table engines over `MergeTree`-engine tables
+- [MergeTree](../../../engines/table-engines/mergetree-family/mergetree.md) (including [materialized views](../../../sql-reference/statements/create/view.md#materialized-view)),
+- [Merge](../../../engines/table-engines/special/merge.md),
+- [Buffer](../../../engines/table-engines/special/buffer.md)
 
 In `MaterializedView`-engine tables the optimization works with views like `SELECT ... FROM merge_tree_table ORDER BY pk`. But it is not supported in the queries like `SELECT ... FROM view ORDER BY pk` if the view query does not have the `ORDER BY` clause.
 

docs/en/sql-reference/syntax.md

@@ -16,7 +16,7 @@ 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#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.
+Data can have any format. When a query is received, the server calculates no more than [max_query_size](../operations/settings/settings.md#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.
 
 When using the `Values` format in an `INSERT` query, it may seem that data is parsed the same as expressions in a `SELECT` query, but this is not true. The `Values` format is much more limited.

docs/en/sql-reference/table-functions/cluster.md

@@ -55,5 +55,5 @@ Connection settings like `host`, `port`, `user`, `password`, `compression`, `sec
 
 **See Also**
 
-- [skip_unavailable_shards](../../operations/settings/settings.md#settings-skip_unavailable_shards)
-- [load_balancing](../../operations/settings/settings.md#settings-load_balancing)
+- [skip_unavailable_shards](../../operations/settings/settings.md#skip_unavailable_shards)
+- [load_balancing](../../operations/settings/settings.md#load_balancing)

docs/en/sql-reference/table-functions/file.md

@@ -199,11 +199,11 @@ SELECT count(*) FROM file('big_dir/**/file002', 'CSV', 'name String, value UInt3
 
 ## Settings {#settings}
 
-- [engine_file_empty_if_not_exists](/docs/en/operations/settings/settings.md#engine-file-emptyif-not-exists) - allows to select empty data from a file that doesn't exist. Disabled by default.
+- [engine_file_empty_if_not_exists](/docs/en/operations/settings/settings.md#engine-file-empty_if-not-exists) - allows to select empty data from a file that doesn't exist. Disabled by default.
 - [engine_file_truncate_on_insert](/docs/en/operations/settings/settings.md#engine-file-truncate-on-insert) - allows to truncate file before insert into it. Disabled by default.
 - [engine_file_allow_create_multiple_files](/docs/en/operations/settings/settings.md#engine_file_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
 - [engine_file_skip_empty_files](/docs/en/operations/settings/settings.md#engine_file_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
-- [storage_file_read_method](/docs/en/operations/settings/settings.md#engine-file-emptyif-not-exists) - method of reading data from storage file, one of: read, pread, mmap (only for clickhouse-local). Default value: `pread` for clickhouse-server, `mmap` for clickhouse-local.
+- [storage_file_read_method](/docs/en/operations/settings/settings.md#engine-file-empty_if-not-exists) - method of reading data from storage file, one of: read, pread, mmap (only for clickhouse-local). Default value: `pread` for clickhouse-server, `mmap` for clickhouse-local.
 
 
 **See Also**

docs/en/sql-reference/table-functions/hdfs.md

@@ -100,7 +100,7 @@ FROM hdfs('hdfs://hdfs1:9000/big_dir/file{0..9}{0..9}{0..9}', 'CSV', 'name Strin
 
 ## Storage Settings {#storage-settings}
 
-- [hdfs_truncate_on_insert](/docs/en/operations/settings/settings.md#hdfs-truncate-on-insert) - allows to truncate file before insert into it. Disabled by default.
+- [hdfs_truncate_on_insert](/docs/en/operations/settings/settings.md#hdfs_truncate_on_insert) - allows to truncate file before insert into it. Disabled by default.
 - [hdfs_create_multiple_files](/docs/en/operations/settings/settings.md#hdfs_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
 - [hdfs_skip_empty_files](/docs/en/operations/settings/settings.md#hdfs_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
 - [ignore_access_denied_multidirectory_globs](/docs/en/operations/settings/settings.md#ignore_access_denied_multidirectory_globs) - allows to ignore permission denied errors for multi-directory globs.

docs/en/sql-reference/table-functions/remote.md

@@ -165,5 +165,5 @@ The following pattern types are supported.
 - `{0n..0m}` - A range of numbers with leading zeroes. This pattern preserves leading zeroes in indices. For instance, `example{01..03}-1` generates `example01-1`, `example02-1` and `example03-1`.
 - `{a|b}` - Any number of variants separated by a `|`. The pattern specifies replicas. For instance, `example01-{1|2}` generates replicas `example01-1` and `example01-2`.
 
-The query will be sent to the first healthy replica. However, for `remote` the replicas are iterated in the order currently set in the [load_balancing](../../operations/settings/settings.md#settings-load_balancing) setting.
+The query will be sent to the first healthy replica. However, for `remote` the replicas are iterated in the order currently set in the [load_balancing](../../operations/settings/settings.md#load_balancing) setting.
 The number of generated addresses is limited by [table_function_remote_max_addresses](../../operations/settings/settings.md#table_function_remote_max_addresses) setting.

docs/en/sql-reference/table-functions/s3.md

@@ -16,7 +16,7 @@ When using the `s3 table function` with [`INSERT INTO...SELECT`](../../sql-refer
 **Syntax**
 
 ``` sql
-s3(path [, NOSIGN | aws_access_key_id, aws_secret_access_key] [,format] [,structure] [,compression])
+s3(path [, NOSIGN | aws_access_key_id, aws_secret_access_key [,session_token]] [,format] [,structure] [,compression])
 ```
 
 :::tip GCS
@@ -38,6 +38,8 @@ For GCS, substitute your HMAC key and HMAC secret where you see `aws_access_key_
   :::
 
 - `NOSIGN` - If this keyword is provided in place of credentials, all the requests will not be signed.
+- `access_key_id`, `secret_access_key` — Keys that specify credentials to use with given endpoint. Optional.
+- `session_token` - Session token to use with the given keys. Optional when passing keys.
 - `format` — The [format](../../interfaces/formats.md#formats) of the file.
 - `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
 - `compression` — Parameter is optional. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. By default, it will autodetect compression by file extension.
@@ -236,7 +238,7 @@ LIMIT 5;
 
 ## Storage Settings {#storage-settings}
 
-- [s3_truncate_on_insert](/docs/en/operations/settings/settings.md#s3-truncate-on-insert) - allows to truncate file before insert into it. Disabled by default.
+- [s3_truncate_on_insert](/docs/en/operations/settings/settings.md#s3_truncate_on_insert) - allows to truncate file before insert into it. Disabled by default.
 - [s3_create_multiple_files](/docs/en/operations/settings/settings.md#s3_allow_create_multiple_files) - allows to create a new file on each insert if format has suffix. Disabled by default.
 - [s3_skip_empty_files](/docs/en/operations/settings/settings.md#s3_skip_empty_files) - allows to skip empty files while reading. Disabled by default.
 

docs/en/sql-reference/table-functions/s3Cluster.md

@@ -10,14 +10,15 @@ Allows processing files from [Amazon S3](https://aws.amazon.com/s3/) and Google
 **Syntax**
 
 ``` sql
-s3Cluster(cluster_name, source, [,access_key_id, secret_access_key] [,format] [,structure])
+s3Cluster(cluster_name, source, [,access_key_id, secret_access_key, [session_token]] [,format] [,structure])
 ```
 
 **Arguments**
 
 - `cluster_name` — Name of a cluster that is used to build a set of addresses and connection parameters to remote and local servers.
 - `source` — URL to a file or a bunch of files. Supports following wildcards in readonly mode: `*`, `**`, `?`, `{'abc','def'}` and `{N..M}` where `N`, `M` — numbers, `abc`, `def` — strings. For more information see [Wildcards In Path](../../engines/table-engines/integrations/s3.md#wildcards-in-path).
-- `access_key_id` and `secret_access_key` — Keys that specify credentials to use with given endpoint. Optional.
+- `access_key_id`, `secret_access_key` — Keys that specify credentials to use with given endpoint. Optional.
+- `session_token` - Session token to use with the given keys. Optional when passing keys.
 - `format` — The [format](../../interfaces/formats.md#formats) of the file.
 - `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
 

docs/ru/development/style.md

@@ -493,7 +493,7 @@ catch (const DB::Exception & e)
 
 ``` cpp
 if (0 != close(fd))
-    throwFromErrno("Cannot close file " + file_name, ErrorCodes::CANNOT_CLOSE_FILE);
+    throw ErrnoException(ErrorCodes::CANNOT_CLOSE_FILE, "Cannot close file {}", file_name);
 ```
 
 `assert` не используются.

docs/ru/getting-started/example-datasets/criteo.md

@@ -1,14 +1,14 @@
 ---
 slug: /ru/getting-started/example-datasets/criteo
 sidebar_position: 18
-sidebar_label: "Терабайт логов кликов от Criteo"
+sidebar_label: "Терабайтный журнал посещений сайта от Criteo"
 ---
 
-# Терабайт логов кликов от Criteo {#terabait-logov-klikov-ot-criteo}
+# Терабайтный журнал посещений сайта от Criteo {#terabaitnyi-zhurnal}
 
 Скачайте данные с http://labs.criteo.com/downloads/download-terabyte-click-logs/
 
-Создайте таблицу для импорта лога:
+Создайте таблицу для импорта журнала:
 
 ``` sql
 CREATE TABLE criteo_log (date Date, clicked UInt8, int1 Int32, int2 Int32, int3 Int32, int4 Int32, int5 Int32, int6 Int32, int7 Int32, int8 Int32, int9 Int32, int10 Int32, int11 Int32, int12 Int32, int13 Int32, cat1 String, cat2 String, cat3 String, cat4 String, cat5 String, cat6 String, cat7 String, cat8 String, cat9 String, cat10 String, cat11 String, cat12 String, cat13 String, cat14 String, cat15 String, cat16 String, cat17 String, cat18 String, cat19 String, cat20 String, cat21 String, cat22 String, cat23 String, cat24 String, cat25 String, cat26 String) ENGINE = Log
@@ -69,7 +69,7 @@ CREATE TABLE criteo
 ) ENGINE = MergeTree(date, intHash32(icat1), (date, intHash32(icat1)), 8192)
 ```
 
-Преобразуем данные из сырого лога и положим во вторую таблицу:
+Преобразуйте импортированные данные, разложив их по таблице сконвертированных данных:
 
 ``` sql
 INSERT INTO criteo SELECT date, clicked, int1, int2, int3, int4, int5, int6, int7, int8, int9, int10, int11, int12, int13, reinterpretAsUInt32(unhex(cat1)) AS icat1, reinterpretAsUInt32(unhex(cat2)) AS icat2, reinterpretAsUInt32(unhex(cat3)) AS icat3, reinterpretAsUInt32(unhex(cat4)) AS icat4, reinterpretAsUInt32(unhex(cat5)) AS icat5, reinterpretAsUInt32(unhex(cat6)) AS icat6, reinterpretAsUInt32(unhex(cat7)) AS icat7, reinterpretAsUInt32(unhex(cat8)) AS icat8, reinterpretAsUInt32(unhex(cat9)) AS icat9, reinterpretAsUInt32(unhex(cat10)) AS icat10, reinterpretAsUInt32(unhex(cat11)) AS icat11, reinterpretAsUInt32(unhex(cat12)) AS icat12, reinterpretAsUInt32(unhex(cat13)) AS icat13, reinterpretAsUInt32(unhex(cat14)) AS icat14, reinterpretAsUInt32(unhex(cat15)) AS icat15, reinterpretAsUInt32(unhex(cat16)) AS icat16, reinterpretAsUInt32(unhex(cat17)) AS icat17, reinterpretAsUInt32(unhex(cat18)) AS icat18, reinterpretAsUInt32(unhex(cat19)) AS icat19, reinterpretAsUInt32(unhex(cat20)) AS icat20, reinterpretAsUInt32(unhex(cat21)) AS icat21, reinterpretAsUInt32(unhex(cat22)) AS icat22, reinterpretAsUInt32(unhex(cat23)) AS icat23, reinterpretAsUInt32(unhex(cat24)) AS icat24, reinterpretAsUInt32(unhex(cat25)) AS icat25, reinterpretAsUInt32(unhex(cat26)) AS icat26 FROM criteo_log;

docs/ru/sql-reference/table-functions/s3.md

@@ -11,7 +11,7 @@ sidebar_label: s3
 **Синтаксис**
 
 ``` sql
-s3(path [,aws_access_key_id, aws_secret_access_key] [,format] [,structure] [,compression])
+s3(path [,access_key_id, secret_access_key [,session_token]] [,format] [,structure] [,compression])
 ```
 
 **Aргументы**

docs/ru/sql-reference/table-functions/s3Cluster.md

@@ -11,14 +11,14 @@ sidebar_label: s3Cluster
 **Синтаксис**
 
 ``` sql
-s3Cluster(cluster_name, source, [,access_key_id, secret_access_key] [,format] [,structure])
+s3Cluster(cluster_name, source, [,access_key_id, secret_access_key [,session_token]] [,format] [,structure])
 ```
 
 **Аргументы**
 
 -   `cluster_name` — имя кластера, используемое для создания набора адресов и параметров подключения к удаленным и локальным серверам.
 -   `source` — URL файла или нескольких файлов. Поддерживает следующие символы подстановки: `*`, `?`, `{'abc','def'}` и `{N..M}`, где `N`, `M` — числа, `abc`, `def` — строки. Подробнее смотрите в разделе [Символы подстановки](../../engines/table-engines/integrations/s3.md#wildcards-in-path).
--   `access_key_id` и `secret_access_key` — ключи, указывающие на учетные данные для использования с точкой приема запроса. Необязательные параметры.
+-   `access_key_id`, `secret_access_key` и `session_token` — ключи, указывающие на учетные данные для использования с точкой приема запроса. Необязательные параметры.
 -   `format` — [формат](../../interfaces/formats.md#formats) файла.
 -   `structure` — структура таблицы. Формат `'column1_name column1_type, column2_name column2_type, ...'`.
 

docs/zh/development/style.md

@@ -485,7 +485,7 @@ catch (const DB::Exception & e)
 
 ``` cpp
 if (0 != close(fd))
-    throwFromErrno("Cannot close file " + file_name, ErrorCodes::CANNOT_CLOSE_FILE);
+    throw ErrnoException(ErrorCodes::CANNOT_CLOSE_FILE, "Cannot close file {}", file_name);
 ```
 
 `不要使用断言`。

docs/zh/sql-reference/statements/select/order-by.md

@@ -61,6 +61,22 @@ sidebar_label: ORDER BY
 
 我们只建议使用 `COLLATE` 对于少量行的最终排序，因为排序与 `COLLATE` 比正常的按字节排序效率低。
 
+## ORDER BY ALL
+
+`ORDER BY ALL` 对所有选定的列进行升序排序。
+
+示例:
+
+``` sql
+SELECT a, b, c FROM t ORDER BY ALL
+```
+
+等同于：
+
+``` sql
+SELECT a, b, c FROM t ORDER BY a, b, c
+```
+
 ## 实现细节 {#implementation-details}
 
 更少的RAM使用，如果一个足够小 [LIMIT](../../../sql-reference/statements/select/limit.md) 除了指定 `ORDER BY`. 否则，所花费的内存量与用于排序的数据量成正比。 对于分布式查询处理，如果 [GROUP BY](../../../sql-reference/statements/select/group-by.md) 省略排序，在远程服务器上部分完成排序，并将结果合并到请求者服务器上。 这意味着对于分布式排序，要排序的数据量可以大于单个服务器上的内存量。

docs/zh/sql-reference/table-functions/s3.md

@@ -11,7 +11,7 @@ sidebar_label: s3
 **语法**
 
 ``` sql
-s3(path, [aws_access_key_id, aws_secret_access_key,] format, structure, [compression])
+s3(path [,access_key_id, secret_access_key [,session_token]] ,format, structure, [compression])
 ```
 
 **参数**

programs/benchmark/Benchmark.cpp

@@ -405,7 +405,7 @@ private:
             || sigaddset(&sig_set, SIGINT)
             || pthread_sigmask(SIG_BLOCK, &sig_set, nullptr))
         {
-            throwFromErrno("Cannot block signal.", ErrorCodes::CANNOT_BLOCK_SIGNAL);
+            throw ErrnoException(ErrorCodes::CANNOT_BLOCK_SIGNAL, "Cannot block signal");
         }
 
         while (true)

programs/install/Install.cpp

@@ -328,7 +328,7 @@ int mainEntryClickHouseInstall(int argc, char ** argv)
                 fs::create_symlink(binary_self_canonical_path, main_bin_path);
 
                 if (0 != chmod(binary_self_canonical_path.string().c_str(), S_IRUSR | S_IRGRP | S_IROTH | S_IXUSR | S_IXGRP | S_IXOTH))
-                    throwFromErrno(fmt::format("Cannot chmod {}", binary_self_canonical_path.string()), ErrorCodes::SYSTEM_ERROR);
+                    throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot chmod {}", binary_self_canonical_path.string());
             }
         }
         else
@@ -361,7 +361,7 @@ int mainEntryClickHouseInstall(int argc, char ** argv)
             if (already_installed)
             {
                 if (0 != chmod(main_bin_path.string().c_str(), S_IRUSR | S_IRGRP | S_IROTH | S_IXUSR | S_IXGRP | S_IXOTH))
-                    throwFromErrno(fmt::format("Cannot chmod {}", main_bin_path.string()), ErrorCodes::SYSTEM_ERROR);
+                    throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot chmod {}", main_bin_path.string());
             }
             else
             {
@@ -395,7 +395,7 @@ int mainEntryClickHouseInstall(int argc, char ** argv)
                     }
 
                     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);
+                        throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot chmod {}", main_bin_tmp_path.string());
                 }
                 catch (const Exception & e)
                 {
@@ -1122,7 +1122,7 @@ namespace
                 return 0;
             }
             else
-                throwFromErrno(fmt::format("Cannot obtain the status of pid {} with `kill`", pid), ErrorCodes::CANNOT_KILL);
+                throw ErrnoException(ErrorCodes::CANNOT_KILL, "Cannot obtain the status of pid {} with `kill`", pid);
         }
 
         if (!pid)
@@ -1143,7 +1143,7 @@ namespace
         if (0 == kill(pid, signal))
             fmt::print("Sent {} signal to process with pid {}.\n", signal_name, pid);
         else
-            throwFromErrno(fmt::format("Cannot send {} signal", signal_name), ErrorCodes::SYSTEM_ERROR);
+            throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot send {} signal", signal_name);
 
         size_t try_num = 0;
         for (; try_num < max_tries; ++try_num)

programs/local/LocalServer.cpp

@@ -43,7 +43,7 @@
 #include <Parsers/IAST.h>
 #include <Parsers/ASTInsertQuery.h>
 #include <Common/ErrorHandlers.h>
-#include <Functions/UserDefined/IUserDefinedSQLObjectsLoader.h>
+#include <Functions/UserDefined/IUserDefinedSQLObjectsStorage.h>
 #include <Functions/registerFunctions.h>
 #include <AggregateFunctions/registerAggregateFunctions.h>
 #include <TableFunctions/registerTableFunctions.h>
@@ -757,7 +757,7 @@ void LocalServer::processConfig()
         }
 
         /// For ClickHouse local if path is not set the loader will be disabled.
-        global_context->getUserDefinedSQLObjectsLoader().loadObjects();
+        global_context->getUserDefinedSQLObjectsStorage().loadObjects();
 
         LOG_DEBUG(log, "Loaded metadata.");
     }

programs/obfuscator/Obfuscator.cpp

@@ -1307,7 +1307,7 @@ try
         /// stdin must be seekable
         auto res = lseek(file->getFD(), 0, SEEK_SET);
         if (-1 == res)
-            throwFromErrno("Input must be seekable file (it will be read twice).", ErrorCodes::CANNOT_SEEK_THROUGH_FILE);
+            throw ErrnoException(ErrorCodes::CANNOT_SEEK_THROUGH_FILE, "Input must be seekable file (it will be read twice)");
 
         SingleReadBufferIterator read_buffer_iterator(std::move(file));
         schema_columns = readSchemaFromFormat(input_format, {}, read_buffer_iterator, false, context_const);
@@ -1336,7 +1336,7 @@ try
         /// stdin must be seekable
         auto res = lseek(file_in.getFD(), 0, SEEK_SET);
         if (-1 == res)
-            throwFromErrno("Input must be seekable file (it will be read twice).", ErrorCodes::CANNOT_SEEK_THROUGH_FILE);
+            throw ErrnoException(ErrorCodes::CANNOT_SEEK_THROUGH_FILE, "Input must be seekable file (it will be read twice)");
     }
 
     Obfuscator obfuscator(header, seed, markov_model_params);

programs/server/Server.cpp

@@ -67,7 +67,7 @@
 #include <Storages/Cache/registerRemoteFileMetadatas.h>
 #include <Common/NamedCollections/NamedCollectionUtils.h>
 #include <AggregateFunctions/registerAggregateFunctions.h>
-#include <Functions/UserDefined/IUserDefinedSQLObjectsLoader.h>
+#include <Functions/UserDefined/IUserDefinedSQLObjectsStorage.h>
 #include <Functions/registerFunctions.h>
 #include <TableFunctions/registerTableFunctions.h>
 #include <Formats/registerFormats.h>
@@ -1756,7 +1756,7 @@ try
         /// After loading validate that default database exists
         database_catalog.assertDatabaseExists(default_database);
         /// Load user-defined SQL functions.
-        global_context->getUserDefinedSQLObjectsLoader().loadObjects();
+        global_context->getUserDefinedSQLObjectsStorage().loadObjects();
     }
     catch (...)
     {
@@ -2128,10 +2128,9 @@ void Server::createServers(
 {
     const Settings & settings = global_context->getSettingsRef();
 
-    Poco::Timespan keep_alive_timeout(config.getUInt("keep_alive_timeout", 10), 0);
     Poco::Net::HTTPServerParams::Ptr http_params = new Poco::Net::HTTPServerParams;
     http_params->setTimeout(settings.http_receive_timeout);
-    http_params->setKeepAliveTimeout(keep_alive_timeout);
+    http_params->setKeepAliveTimeout(global_context->getServerSettings().keep_alive_timeout);
 
     Poco::Util::AbstractConfiguration::Keys protocols;
     config.keys("protocols", protocols);
@@ -2385,10 +2384,9 @@ void Server::createInterserverServers(
 {
     const Settings & settings = global_context->getSettingsRef();
 
-    Poco::Timespan keep_alive_timeout(config.getUInt("keep_alive_timeout", 10), 0);
     Poco::Net::HTTPServerParams::Ptr http_params = new Poco::Net::HTTPServerParams;
     http_params->setTimeout(settings.http_receive_timeout);
-    http_params->setKeepAliveTimeout(keep_alive_timeout);
+    http_params->setKeepAliveTimeout(global_context->getServerSettings().keep_alive_timeout);
 
     /// Now iterate over interserver_listen_hosts
     for (const auto & interserver_listen_host : interserver_listen_hosts)

programs/su/su.cpp

@@ -56,7 +56,7 @@ void setUserAndGroup(std::string arg_uid, std::string arg_gid)
             group * result{};
 
             if (0 != getgrnam_r(arg_gid.data(), &entry, buf.get(), buf_size, &result))
-                throwFromErrno(fmt::format("Cannot do 'getgrnam_r' to obtain gid from group name ({})", arg_gid), ErrorCodes::SYSTEM_ERROR);
+                throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot do 'getgrnam_r' to obtain gid from group name ({})", arg_gid);
 
             if (!result)
                 throw Exception(ErrorCodes::BAD_ARGUMENTS, "Group {} is not found in the system", arg_gid);
@@ -68,7 +68,7 @@ void setUserAndGroup(std::string arg_uid, std::string arg_gid)
             throw Exception(ErrorCodes::BAD_ARGUMENTS, "Group has id 0, but dropping privileges to gid 0 does not make sense");
 
         if (0 != setgid(gid))
-            throwFromErrno(fmt::format("Cannot do 'setgid' to user ({})", arg_gid), ErrorCodes::SYSTEM_ERROR);
+            throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot do 'setgid' to user ({})", arg_gid);
     }
 
     if (!arg_uid.empty())
@@ -81,7 +81,7 @@ void setUserAndGroup(std::string arg_uid, std::string arg_gid)
             passwd * result{};
 
             if (0 != getpwnam_r(arg_uid.data(), &entry, buf.get(), buf_size, &result))
-                throwFromErrno(fmt::format("Cannot do 'getpwnam_r' to obtain uid from user name ({})", arg_uid), ErrorCodes::SYSTEM_ERROR);
+                throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot do 'getpwnam_r' to obtain uid from user name ({})", arg_uid);
 
             if (!result)
                 throw Exception(ErrorCodes::BAD_ARGUMENTS, "User {} is not found in the system", arg_uid);
@@ -93,7 +93,7 @@ void setUserAndGroup(std::string arg_uid, std::string arg_gid)
             throw Exception(ErrorCodes::BAD_ARGUMENTS, "User has id 0, but dropping privileges to uid 0 does not make sense");
 
         if (0 != setuid(uid))
-            throwFromErrno(fmt::format("Cannot do 'setuid' to user ({})", arg_uid), ErrorCodes::SYSTEM_ERROR);
+            throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot do 'setuid' to user ({})", arg_uid);
     }
 }
 
@@ -136,7 +136,7 @@ try
 
     execvp(new_argv.front(), new_argv.data());
 
-    throwFromErrno("Cannot execvp", ErrorCodes::SYSTEM_ERROR);
+    throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot execvp");
 }
 catch (...)
 {

rust/BLAKE3/CMakeLists.txt

@@ -1,3 +0,0 @@
-clickhouse_import_crate(MANIFEST_PATH Cargo.toml)
-target_include_directories(_ch_rust_blake3 INTERFACE include)
-add_library(ch_rust::blake3 ALIAS _ch_rust_blake3)

rust/BLAKE3/Cargo.toml

@@ -1,20 +0,0 @@
-[package]
-name = "_ch_rust_blake3"
-version = "0.1.0"
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-blake3 = "1.2.0"
-libc = "0.2.132"
-
-[lib]
-crate-type = ["staticlib"]
-
-[profile.release]
-debug = true
-
-[profile.release-thinlto]
-inherits = "release"
-# BLAKE3 module requires "full" LTO (not "thin") to get additional 10% performance benefit
-lto = true

rust/BLAKE3/include/blake3.h

@@ -1,15 +0,0 @@
-#ifndef BLAKE3_H
-#define BLAKE3_H
-
-#include <cstdint>
-
-
-extern "C" {
-
-char *blake3_apply_shim(const char *begin, uint32_t _size, uint8_t *out_char_data);
-
-void blake3_free_char_pointer(char *ptr_to_free);
-
-} // extern "C"
-
-#endif /* BLAKE3_H */

rust/BLAKE3/src/lib.rs

@@ -1,31 +0,0 @@
-extern crate blake3;
-extern crate libc;
-
-use std::ffi::{CString};
-use std::slice;
-use std::os::raw::c_char;
-
-#[no_mangle]
-pub unsafe extern "C" fn blake3_apply_shim(
-    begin: *const c_char,
-    size: u32,
-    out_char_data: *mut u8,
-) -> *mut c_char {
-    if begin.is_null() {
-        let err_str = CString::new("input was a null pointer").unwrap();
-        return err_str.into_raw();
-    }
-    let input_res = slice::from_raw_parts(begin as *const u8, size as usize);
-    let mut hasher = blake3::Hasher::new();
-    hasher.update(input_res);
-    let mut reader = hasher.finalize_xof();
-
-    reader.fill(std::slice::from_raw_parts_mut(out_char_data, blake3::OUT_LEN));
-    std::ptr::null_mut()
-}
-
-// Freeing memory according to docs: https://doc.rust-lang.org/std/ffi/struct.CString.html#method.into_raw
-#[no_mangle]
-pub unsafe extern "C" fn blake3_free_char_pointer(ptr_to_free: *mut c_char) {
-    std::mem::drop(CString::from_raw(ptr_to_free));
-}

rust/CMakeLists.txt

@@ -99,6 +99,5 @@ function(add_rust_subdirectory src)
         VERBATIM)
 endfunction()
 
-add_rust_subdirectory (BLAKE3)
 add_rust_subdirectory (skim)
 add_rust_subdirectory (prql)

rust/Cargo.toml

@@ -1,7 +1,6 @@
 # workspace is required to vendor crates for all packages.
 [workspace]
 members = [
-    "BLAKE3",
     "skim",
     "prql",
 ]

src/Analyzer/Passes/QueryAnalysisPass.cpp

@@ -119,6 +119,7 @@ namespace ErrorCodes
     extern const int NUMBER_OF_COLUMNS_DOESNT_MATCH;
     extern const int FUNCTION_CANNOT_HAVE_PARAMETERS;
     extern const int SYNTAX_ERROR;
+    extern const int UNEXPECTED_EXPRESSION;
 }
 
 /** Query analyzer implementation overview. Please check documentation in QueryAnalysisPass.h first.
@@ -1209,6 +1210,8 @@ private:
 
     static void expandGroupByAll(QueryNode & query_tree_node_typed);
 
+    static void expandOrderByAll(QueryNode & query_tree_node_typed);
+
     static std::string
     rewriteAggregateFunctionNameIfNeeded(const std::string & aggregate_function_name, NullsAction action, const ContextPtr & context);
 
@@ -2312,6 +2315,35 @@ void QueryAnalyzer::expandGroupByAll(QueryNode & query_tree_node_typed)
         recursivelyCollectMaxOrdinaryExpressions(node, group_by_nodes);
 }
 
+void QueryAnalyzer::expandOrderByAll(QueryNode & query_tree_node_typed)
+{
+    auto * all_node = query_tree_node_typed.getOrderBy().getNodes()[0]->as<SortNode>();
+    if (!all_node)
+        throw Exception(ErrorCodes::LOGICAL_ERROR, "Select analyze for not sort node.");
+
+    auto & projection_nodes = query_tree_node_typed.getProjection().getNodes();
+    auto list_node = std::make_shared<ListNode>();
+    list_node->getNodes().reserve(projection_nodes.size());
+
+    for (auto & node : projection_nodes)
+    {
+        if (auto * identifier_node = node->as<IdentifierNode>(); identifier_node != nullptr)
+            if (Poco::toUpper(identifier_node->getIdentifier().getFullName()) == "ALL" || Poco::toUpper(identifier_node->getAlias()) == "ALL")
+                throw Exception(ErrorCodes::UNEXPECTED_EXPRESSION,
+                    "Cannot use ORDER BY ALL to sort a column with name 'all', please disable setting `enable_order_by_all` and try again");
+
+        if (auto * function_node = node->as<FunctionNode>(); function_node != nullptr)
+            if (Poco::toUpper(function_node->getAlias()) == "ALL")
+                throw Exception(ErrorCodes::UNEXPECTED_EXPRESSION,
+                                "Cannot use ORDER BY ALL to sort a column with name 'all', please disable setting `enable_order_by_all` and try again");
+
+        auto sort_node = std::make_shared<SortNode>(node, all_node->getSortDirection(), all_node->getNullsSortDirection());
+        list_node->getNodes().push_back(sort_node);
+    }
+
+    query_tree_node_typed.getOrderByNode() = list_node;
+}
+
 std::string QueryAnalyzer::rewriteAggregateFunctionNameIfNeeded(
     const std::string & aggregate_function_name, NullsAction action, const ContextPtr & context)
 {
@@ -6975,6 +7007,9 @@ void QueryAnalyzer::resolveQuery(const QueryTreeNodePtr & query_node, Identifier
     if (query_node_typed.hasHaving() && query_node_typed.isGroupByWithTotals() && is_rollup_or_cube)
         throw Exception(ErrorCodes::NOT_IMPLEMENTED, "WITH TOTALS and WITH ROLLUP or CUBE are not supported together in presence of HAVING");
 
+    if (settings.enable_order_by_all && query_node_typed.isOrderByAll())
+        expandOrderByAll(query_node_typed);
+
     /// Initialize aliases in query node scope
     QueryExpressionsAliasVisitor visitor(scope);
 

src/Analyzer/QueryNode.h

@@ -219,6 +219,18 @@ public:
         is_group_by_all = is_group_by_all_value;
     }
 
+    /// Returns true, if query node has ORDER BY ALL modifier, false otherwise
+    bool isOrderByAll() const
+    {
+        return is_order_by_all;
+    }
+
+    /// Set query node ORDER BY ALL modifier value
+    void setIsOrderByAll(bool is_order_by_all_value)
+    {
+        is_order_by_all = is_order_by_all_value;
+    }
+
     /// Returns true if query node WITH section is not empty, false otherwise
     bool hasWith() const
     {
@@ -590,6 +602,7 @@ private:
     bool is_group_by_with_cube = false;
     bool is_group_by_with_grouping_sets = false;
     bool is_group_by_all = false;
+    bool is_order_by_all = false;
 
     std::string cte_name;
     NamesAndTypes projection_columns;

src/Analyzer/QueryTreeBuilder.cpp

@@ -284,6 +284,7 @@ QueryTreeNodePtr QueryTreeBuilder::buildSelectExpression(const ASTPtr & select_q
     current_query_tree->setIsGroupByWithRollup(select_query_typed.group_by_with_rollup);
     current_query_tree->setIsGroupByWithGroupingSets(select_query_typed.group_by_with_grouping_sets);
     current_query_tree->setIsGroupByAll(select_query_typed.group_by_all);
+    current_query_tree->setIsOrderByAll(select_query_typed.order_by_all);
     current_query_tree->setOriginalAST(select_query);
 
     auto current_context = current_query_tree->getContext();

src/Backups/BackupEntriesCollector.cpp

@@ -43,14 +43,6 @@ namespace Stage = BackupCoordinationStage;
 
 namespace
 {
-    /// Uppercases the first character of a passed string.
-    String toUpperFirst(const String & str)
-    {
-        String res = str;
-        res[0] = std::toupper(res[0]);
-        return res;
-    }
-
     /// Outputs "table <name>" or "temporary table <name>"
     String tableNameWithTypeToString(const String & database_name, const String & table_name, bool first_upper)
     {
@@ -164,7 +156,7 @@ BackupEntries BackupEntriesCollector::run()
 
 Strings BackupEntriesCollector::setStage(const String & new_stage, const String & message)
 {
-    LOG_TRACE(log, fmt::runtime(toUpperFirst(new_stage)));
+    LOG_TRACE(log, "Setting stage: {}", new_stage);
     current_stage = new_stage;
 
     backup_coordination->setStage(new_stage, message);

src/BridgeHelper/LibraryBridgeHelper.cpp

@@ -12,7 +12,7 @@ LibraryBridgeHelper::LibraryBridgeHelper(ContextPtr context_)
     , http_timeout(context_->getGlobalContext()->getSettingsRef().http_receive_timeout.value)
     , bridge_host(config.getString("library_bridge.host", DEFAULT_HOST))
     , bridge_port(config.getUInt("library_bridge.port", DEFAULT_PORT))
-    , http_timeouts(ConnectionTimeouts::getHTTPTimeouts(context_->getSettingsRef(), {context_->getConfigRef().getUInt("keep_alive_timeout", DEFAULT_HTTP_KEEP_ALIVE_TIMEOUT), 0}))
+    , http_timeouts(ConnectionTimeouts::getHTTPTimeouts(context_->getSettingsRef(), context_->getServerSettings().keep_alive_timeout))
 {
 }
 

src/BridgeHelper/XDBCBridgeHelper.h

@@ -162,7 +162,7 @@ private:
 
     ConnectionTimeouts getHTTPTimeouts()
     {
-        return ConnectionTimeouts::getHTTPTimeouts(getContext()->getSettingsRef(), {getContext()->getConfigRef().getUInt("keep_alive_timeout", DEFAULT_HTTP_KEEP_ALIVE_TIMEOUT), 0});
+        return ConnectionTimeouts::getHTTPTimeouts(getContext()->getSettingsRef(), getContext()->getServerSettings().keep_alive_timeout);
     }
 
 protected:

src/Client/ClientBase.cpp

@@ -318,14 +318,14 @@ void ClientBase::setupSignalHandler()
     sigemptyset(&new_act.sa_mask);
 #else
     if (sigemptyset(&new_act.sa_mask))
-        throwFromErrno("Cannot set signal handler.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
 #endif
 
     if (sigaction(SIGINT, &new_act, nullptr))
-        throwFromErrno("Cannot set signal handler.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
 
     if (sigaction(SIGQUIT, &new_act, nullptr))
-        throwFromErrno("Cannot set signal handler.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+        throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler");
 }
 
 
@@ -543,16 +543,16 @@ try
         if (!pager.empty())
         {
             if (SIG_ERR == signal(SIGPIPE, SIG_IGN))
-                throwFromErrno("Cannot set signal handler for SIGPIPE.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+                throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler for SIGPIPE");
             /// We need to reset signals that had been installed in the
             /// setupSignalHandler() since terminal will send signals to both
             /// processes and so signals will be delivered to the
             /// clickhouse-client/local as well, which will be terminated when
             /// signal will be delivered second time.
             if (SIG_ERR == signal(SIGINT, SIG_IGN))
-                throwFromErrno("Cannot set signal handler for SIGINT.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+                throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler for SIGINT");
             if (SIG_ERR == signal(SIGQUIT, SIG_IGN))
-                throwFromErrno("Cannot set signal handler for SIGQUIT.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+                throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler for SIGQUIT");
 
             ShellCommand::Config config(pager);
             config.pipe_stdin_only = true;
@@ -1306,11 +1306,11 @@ void ClientBase::resetOutput()
         pager_cmd->wait();
 
         if (SIG_ERR == signal(SIGPIPE, SIG_DFL))
-            throwFromErrno("Cannot set signal handler for SIIGPIEP.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+            throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler for SIGPIPE");
         if (SIG_ERR == signal(SIGINT, SIG_DFL))
-            throwFromErrno("Cannot set signal handler for SIGINT.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+            throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler for SIGINT");
         if (SIG_ERR == signal(SIGQUIT, SIG_DFL))
-            throwFromErrno("Cannot set signal handler for SIGQUIT.", ErrorCodes::CANNOT_SET_SIGNAL_HANDLER);
+            throw ErrnoException(ErrorCodes::CANNOT_SET_SIGNAL_HANDLER, "Cannot set signal handler for SIGQUIT");
 
         setupSignalHandler();
     }

src/Common/AlignedBuffer.cpp

@@ -18,9 +18,11 @@ void AlignedBuffer::alloc(size_t size, size_t alignment)
     void * new_buf;
     int res = ::posix_memalign(&new_buf, std::max(alignment, sizeof(void*)), size);
     if (0 != res)
-        throwFromErrno(fmt::format("Cannot allocate memory (posix_memalign), size: {}, alignment: {}.",
-            ReadableSize(size), ReadableSize(alignment)),
-            ErrorCodes::CANNOT_ALLOCATE_MEMORY, res);
+        throw ErrnoException(
+            ErrorCodes::CANNOT_ALLOCATE_MEMORY,
+            "Cannot allocate memory (posix_memalign), size: {}, alignment: {}.",
+            ReadableSize(size),
+            ReadableSize(alignment));
     buf = new_buf;
 }
 

src/Common/Allocator.h

@@ -118,8 +118,11 @@ public:
             void * new_buf = ::realloc(buf, new_size);
             if (nullptr == new_buf)
             {
-                DB::throwFromErrno(
-                    fmt::format("Allocator: Cannot realloc from {} to {}.", ReadableSize(old_size), ReadableSize(new_size)), DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY);
+                throw DB::ErrnoException(
+                    DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY,
+                    "Allocator: Cannot realloc from {} to {}",
+                    ReadableSize(old_size),
+                    ReadableSize(new_size));
             }
 
             buf = new_buf;
@@ -164,7 +167,7 @@ private:
                 buf = ::malloc(size);
 
             if (nullptr == buf)
-                DB::throwFromErrno(fmt::format("Allocator: Cannot malloc {}.", ReadableSize(size)), DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY);
+                throw DB::ErrnoException(DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY, "Allocator: Cannot malloc {}.", ReadableSize(size));
         }
         else
         {
@@ -172,8 +175,8 @@ private:
             int res = posix_memalign(&buf, alignment, size);
 
             if (0 != res)
-                DB::throwFromErrno(fmt::format("Cannot allocate memory (posix_memalign) {}.", ReadableSize(size)),
-                    DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY, res);
+                throw DB::ErrnoException(
+                    DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY, "Cannot allocate memory (posix_memalign) {}.", ReadableSize(size));
 
             if constexpr (clear_memory)
                 memset(buf, 0, size);

src/Common/ArrayCache.h

@@ -179,13 +179,22 @@ private:
         {
             ptr = mmap(address_hint, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
             if (MAP_FAILED == ptr)
-                DB::throwFromErrno(fmt::format("Allocator: Cannot mmap {}.", ReadableSize(size)), DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY);
+                throw DB::ErrnoException(DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY, "Allocator: Cannot mmap {}", ReadableSize(size));
         }
 
         ~Chunk()
         {
             if (ptr && 0 != munmap(ptr, size))
-                DB::throwFromErrno(fmt::format("Allocator: Cannot munmap {}.", ReadableSize(size)), DB::ErrorCodes::CANNOT_MUNMAP);
+            {
+                try
+                {
+                    throw DB::ErrnoException(DB::ErrorCodes::CANNOT_MUNMAP, "Allocator: Cannot munmap {}", ReadableSize(size));
+                }
+                catch (DB::ErrnoException &)
+                {
+                    DB::tryLogCurrentException(__PRETTY_FUNCTION__);
+                }
+            }
         }
 
         Chunk(Chunk && other) noexcept : ptr(other.ptr), size(other.size)

src/Common/AsynchronousMetrics.cpp

@@ -797,7 +797,7 @@ void AsynchronousMetrics::update(TimePoint update_time)
 
             int64_t hz = sysconf(_SC_CLK_TCK);
             if (-1 == hz)
-                throwFromErrno("Cannot call 'sysconf' to obtain system HZ", ErrorCodes::CANNOT_SYSCONF);
+                throw ErrnoException(ErrorCodes::CANNOT_SYSCONF, "Cannot call 'sysconf' to obtain system HZ");
 
             double multiplier = 1.0 / hz / (std::chrono::duration_cast<std::chrono::nanoseconds>(time_after_previous_update).count() / 1e9);
             size_t num_cpus = 0;

src/Common/CounterInFile.h

@@ -69,13 +69,13 @@ public:
 
         int fd = ::open(path.c_str(), O_RDWR | O_CREAT | O_CLOEXEC, 0666);
         if (-1 == fd)
-            DB::throwFromErrnoWithPath("Cannot open file " + path, path, DB::ErrorCodes::CANNOT_OPEN_FILE);
+            DB::ErrnoException::throwFromPath(DB::ErrorCodes::CANNOT_OPEN_FILE, path, "Cannot open file {}", path);
 
         try
         {
             int flock_ret = flock(fd, LOCK_EX);
             if (-1 == flock_ret)
-                DB::throwFromErrnoWithPath("Cannot lock file " + path, path, DB::ErrorCodes::CANNOT_OPEN_FILE);
+                DB::ErrnoException::throwFromPath(DB::ErrorCodes::CANNOT_OPEN_FILE, path, "Cannot lock file {}", path);
 
             if (!file_doesnt_exists)
             {
@@ -145,7 +145,7 @@ public:
 
         int fd = ::open(path.c_str(), O_RDWR | O_CREAT | O_CLOEXEC, 0666);
         if (-1 == fd)
-            DB::throwFromErrnoWithPath("Cannot open file " + path, path, DB::ErrorCodes::CANNOT_OPEN_FILE);
+            DB::ErrnoException::throwFromPath(DB::ErrorCodes::CANNOT_OPEN_FILE, path, "Cannot open file {}", path);
 
         try
         {

src/Common/Epoll.cpp

@@ -19,7 +19,7 @@ Epoll::Epoll() : events_count(0)
 {
     epoll_fd = epoll_create1(0);
     if (epoll_fd == -1)
-        throwFromErrno("Cannot open epoll descriptor", DB::ErrorCodes::EPOLL_ERROR);
+        throw DB::ErrnoException(DB::ErrorCodes::EPOLL_ERROR, "Cannot open epoll descriptor");
 }
 
 Epoll::Epoll(Epoll && other) noexcept : epoll_fd(other.epoll_fd), events_count(other.events_count.load())
@@ -47,7 +47,7 @@ void Epoll::add(int fd, void * ptr, uint32_t events)
     ++events_count;
 
     if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, fd, &event) == -1)
-        throwFromErrno("Cannot add new descriptor to epoll", DB::ErrorCodes::EPOLL_ERROR);
+        throw DB::ErrnoException(DB::ErrorCodes::EPOLL_ERROR, "Cannot add new descriptor to epoll");
 }
 
 void Epoll::remove(int fd)
@@ -55,7 +55,7 @@ void Epoll::remove(int fd)
     --events_count;
 
     if (epoll_ctl(epoll_fd, EPOLL_CTL_DEL, fd, nullptr) == -1)
-        throwFromErrno("Cannot remove descriptor from epoll", DB::ErrorCodes::EPOLL_ERROR);
+        throw DB::ErrnoException(DB::ErrorCodes::EPOLL_ERROR, "Cannot remove descriptor from epoll");
 }
 
 size_t Epoll::getManyReady(int max_events, epoll_event * events_out, int timeout) const
@@ -82,7 +82,7 @@ size_t Epoll::getManyReady(int max_events, epoll_event * events_out, int timeout
                 continue;
             }
             else
-                throwFromErrno("Error in epoll_wait", DB::ErrorCodes::EPOLL_ERROR);
+                throw DB::ErrnoException(DB::ErrorCodes::EPOLL_ERROR, "Error in epoll_wait");
         }
         else
             break;

src/Common/EventFD.cpp

@@ -21,7 +21,7 @@ EventFD::EventFD()
 {
     fd = eventfd(0 /* initval */, 0 /* flags */);
     if (fd == -1)
-        throwFromErrno("Cannot create eventfd", ErrorCodes::CANNOT_PIPE);
+        throw ErrnoException(ErrorCodes::CANNOT_PIPE, "Cannot create eventfd");
 }
 
 uint64_t EventFD::read() const
@@ -33,7 +33,7 @@ uint64_t EventFD::read() const
             break;
 
         if (errno != EINTR)
-            throwFromErrno("Cannot read from eventfd", ErrorCodes::CANNOT_READ_FROM_SOCKET);
+            throw ErrnoException(ErrorCodes::CANNOT_READ_FROM_SOCKET, "Cannot read from eventfd");
     }
 
     return buf;
@@ -47,7 +47,7 @@ bool EventFD::write(uint64_t increase) const
             return false;
 
         if (errno != EINTR)
-            throwFromErrno("Cannot write to eventfd", ErrorCodes::CANNOT_WRITE_TO_SOCKET);
+            throw ErrnoException(ErrorCodes::CANNOT_WRITE_TO_SOCKET, "Cannot write to eventfd");
     }
 
     return true;

src/Common/Exception.cpp

@@ -1,25 +1,24 @@
 #include "Exception.h"
 
 #include <algorithm>
-#include <cstring>
-#include <cxxabi.h>
 #include <cstdlib>
-#include <Poco/String.h>
-#include <Common/logger_useful.h>
-#include <IO/WriteHelpers.h>
-#include <IO/ReadHelpers.h>
+#include <cstring>
+#include <filesystem>
+#include <cxxabi.h>
 #include <IO/Operators.h>
-#include <IO/ReadBufferFromString.h>
 #include <IO/ReadBufferFromFile.h>
+#include <IO/ReadBufferFromString.h>
+#include <IO/ReadHelpers.h>
+#include <IO/WriteHelpers.h>
 #include <base/demangle.h>
-#include <base/errnoToString.h>
-#include <Common/formatReadable.h>
-#include <Common/filesystemHelpers.h>
+#include <Poco/String.h>
 #include <Common/ErrorCodes.h>
+#include <Common/LockMemoryExceptionInThread.h>
 #include <Common/MemorySanitizer.h>
 #include <Common/SensitiveDataMasker.h>
-#include <Common/LockMemoryExceptionInThread.h>
-#include <filesystem>
+#include <Common/filesystemHelpers.h>
+#include <Common/formatReadable.h>
+#include <Common/logger_useful.h>
 
 #include <Common/config_version.h>
 
@@ -212,17 +211,6 @@ Exception::FramePointers Exception::getStackFramePointers() const
 thread_local bool Exception::enable_job_stack_trace = false;
 thread_local std::vector<StackTrace::FramePointers> Exception::thread_frame_pointers = {};
 
-
-void throwFromErrno(const std::string & s, int code, int the_errno)
-{
-    throw ErrnoException(s + ", " + errnoToString(the_errno), code, the_errno);
-}
-
-void throwFromErrnoWithPath(const std::string & s, const std::string & path, int code, int the_errno)
-{
-    throw ErrnoException(s + ", " + errnoToString(the_errno), code, the_errno, path);
-}
-
 static void tryLogCurrentExceptionImpl(Poco::Logger * logger, const std::string & start_of_message)
 {
     try

src/Common/Exception.h

@@ -7,9 +7,10 @@
 #include <Poco/Exception.h>
 
 #include <base/defines.h>
+#include <base/errnoToString.h>
 #include <base/scope_guard.h>
-#include <Common/StackTrace.h>
 #include <Common/LoggingFormatStringHelpers.h>
+#include <Common/StackTrace.h>
 
 #include <fmt/format.h>
 
@@ -173,12 +174,61 @@ std::string getExceptionStackTraceString(const std::exception & e);
 std::string getExceptionStackTraceString(std::exception_ptr e);
 
 
-/// Contains an additional member `saved_errno`. See the throwFromErrno function.
+/// Contains an additional member `saved_errno`
 class ErrnoException : public Exception
 {
 public:
-    ErrnoException(const std::string & msg, int code, int saved_errno_, const std::optional<std::string> & path_ = {})
-        : Exception(msg, code), saved_errno(saved_errno_), path(path_) {}
+    ErrnoException(std::string && msg, int code, int with_errno) : Exception(msg, code), saved_errno(with_errno)
+    {
+        capture_thread_frame_pointers = thread_frame_pointers;
+        addMessage(", {}", errnoToString(saved_errno));
+    }
+
+    /// Message must be a compile-time constant
+    template <typename T>
+    requires std::is_convertible_v<T, String>
+    ErrnoException(int code, T && message) : Exception(message, code), saved_errno(errno)
+    {
+        capture_thread_frame_pointers = thread_frame_pointers;
+        addMessage(", {}", errnoToString(saved_errno));
+    }
+
+    // Format message with fmt::format, like the logging functions.
+    template <typename... Args>
+    ErrnoException(int code, FormatStringHelper<Args...> fmt, Args &&... args)
+        : Exception(fmt::format(fmt.fmt_str, std::forward<Args>(args)...), code), saved_errno(errno)
+    {
+        capture_thread_frame_pointers = thread_frame_pointers;
+        message_format_string = fmt.message_format_string;
+        addMessage(", {}", errnoToString(saved_errno));
+    }
+
+    template <typename... Args>
+    [[noreturn]] static void throwWithErrno(int code, int with_errno, FormatStringHelper<Args...> fmt, Args &&... args)
+    {
+        auto e = ErrnoException(fmt::format(fmt.fmt_str, std::forward<Args>(args)...), code, with_errno);
+        e.message_format_string = fmt.message_format_string;
+        throw e;
+    }
+
+    template <typename... Args>
+    [[noreturn]] static void throwFromPath(int code, const std::string & path, FormatStringHelper<Args...> fmt, Args &&... args)
+    {
+        auto e = ErrnoException(fmt::format(fmt.fmt_str, std::forward<Args>(args)...), code, errno);
+        e.message_format_string = fmt.message_format_string;
+        e.path = path;
+        throw e;
+    }
+
+    template <typename... Args>
+    [[noreturn]] static void
+    throwFromPathWithErrno(int code, const std::string & path, int with_errno, FormatStringHelper<Args...> fmt, Args &&... args)
+    {
+        auto e = ErrnoException(fmt::format(fmt.fmt_str, std::forward<Args>(args)...), code, with_errno);
+        e.message_format_string = fmt.message_format_string;
+        e.path = path;
+        throw e;
+    }
 
     ErrnoException * clone() const override { return new ErrnoException(*this); }
     void rethrow() const override { throw *this; } // NOLINT
@@ -188,7 +238,7 @@ public:
 
 private:
     int saved_errno;
-    std::optional<std::string> path;
+    std::optional<std::string> path{};
 
     const char * name() const noexcept override { return "DB::ErrnoException"; }
     const char * className() const noexcept override { return "DB::ErrnoException"; }
@@ -233,13 +283,6 @@ private:
 
 using Exceptions = std::vector<std::exception_ptr>;
 
-
-[[noreturn]] void throwFromErrno(const std::string & s, int code, int the_errno = errno);
-/// Useful to produce some extra information about available space and inodes on device
-[[noreturn]] void throwFromErrnoWithPath(const std::string & s, const std::string & path, int code,
-                                         int the_errno = errno);
-
-
 /** Try to write an exception to the log (and forget about it).
   * Can be used in destructors in the catch-all block.
   */

src/Common/FailPoint.cpp

@@ -28,13 +28,14 @@ static struct InitFiu
 
 /// We should define different types of failpoints here. There are four types of them:
 /// - ONCE: the failpoint will only be triggered once.
-/// - REGULAR: the failpoint will always be triggered util disableFailPoint is called.
-/// - PAUSAEBLE_ONCE: the failpoint will be blocked one time when pauseFailPoint is called, util disableFailPoint is called.
-/// - PAUSAEBLE: the failpoint will be blocked every time when pauseFailPoint is called, util disableFailPoint is called.
+/// - REGULAR: the failpoint will always be triggered until disableFailPoint is called.
+/// - PAUSEABLE_ONCE: the failpoint will be blocked one time when pauseFailPoint is called, util disableFailPoint is called.
+/// - PAUSEABLE: the failpoint will be blocked every time when pauseFailPoint is called, util disableFailPoint is called.
 
 #define APPLY_FOR_FAILPOINTS(ONCE, REGULAR, PAUSEABLE_ONCE, PAUSEABLE) \
     ONCE(replicated_merge_tree_commit_zk_fail_after_op) \
     ONCE(replicated_merge_tree_insert_quorum_fail_0) \
+    REGULAR(replicated_merge_tree_commit_zk_fail_when_recovering_from_hw_fault) \
     REGULAR(use_delayed_remote_source) \
     REGULAR(cluster_discovery_faults) \
     REGULAR(check_table_query_delay_for_part) \

src/Common/FiberStack.h

@@ -46,14 +46,14 @@ public:
 
         void * vp = ::mmap(nullptr, num_bytes, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
         if (MAP_FAILED == vp)
-            DB::throwFromErrno(fmt::format("FiberStack: Cannot mmap {}.", ReadableSize(num_bytes)), DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY);
+            throw DB::ErrnoException(DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY, "FiberStack: Cannot mmap {}.", ReadableSize(num_bytes));
 
         /// TODO: make reports on illegal guard page access more clear.
         /// Currently we will see segfault and almost random stacktrace.
         if (-1 == ::mprotect(vp, page_size, PROT_NONE))
         {
             ::munmap(vp, num_bytes);
-            DB::throwFromErrno("FiberStack: cannot protect guard page", DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY);
+            throw DB::ErrnoException(DB::ErrorCodes::CANNOT_ALLOCATE_MEMORY, "FiberStack: cannot protect guard page");
         }
 
         /// Do not count guard page in memory usage.

src/Common/InterruptListener.h

@@ -58,9 +58,8 @@ private:
 public:
     InterruptListener() : active(false)
     {
-        if (sigemptyset(&sig_set)
-            || sigaddset(&sig_set, SIGINT))
-            throwFromErrno("Cannot manipulate with signal set.", ErrorCodes::CANNOT_MANIPULATE_SIGSET);
+        if (sigemptyset(&sig_set) || sigaddset(&sig_set, SIGINT))
+            throw ErrnoException(ErrorCodes::CANNOT_MANIPULATE_SIGSET, "Cannot manipulate with signal set");
 
         block();
     }
@@ -82,7 +81,7 @@ public:
             if (errno == EAGAIN)
                 return false;
             else
-                throwFromErrno("Cannot poll signal (sigtimedwait).", ErrorCodes::CANNOT_WAIT_FOR_SIGNAL);
+                throw ErrnoException(ErrorCodes::CANNOT_WAIT_FOR_SIGNAL, "Cannot poll signal (sigtimedwait)");
         }
 
         return true;
@@ -93,7 +92,7 @@ public:
         if (!active)
         {
             if (pthread_sigmask(SIG_BLOCK, &sig_set, nullptr))
-                throwFromErrno("Cannot block signal.", ErrorCodes::CANNOT_BLOCK_SIGNAL);
+                throw ErrnoException(ErrorCodes::CANNOT_BLOCK_SIGNAL, "Cannot block signal");
 
             active = true;
         }
@@ -105,7 +104,7 @@ public:
         if (active)
         {
             if (pthread_sigmask(SIG_UNBLOCK, &sig_set, nullptr))
-                throwFromErrno("Cannot unblock signal.", ErrorCodes::CANNOT_UNBLOCK_SIGNAL);
+                throw ErrnoException(ErrorCodes::CANNOT_UNBLOCK_SIGNAL, "Cannot unblock signal");
 
             active = false;
         }

src/Common/MemoryStatisticsOS.cpp

@@ -39,7 +39,8 @@ MemoryStatisticsOS::MemoryStatisticsOS()
     fd = ::open(filename, O_RDONLY | O_CLOEXEC);
 
     if (-1 == fd)
-        throwFromErrno("Cannot open file " + std::string(filename), errno == ENOENT ? ErrorCodes::FILE_DOESNT_EXIST : ErrorCodes::CANNOT_OPEN_FILE);
+        ErrnoException::throwFromPath(
+            errno == ENOENT ? ErrorCodes::FILE_DOESNT_EXIST : ErrorCodes::CANNOT_OPEN_FILE, filename, "Cannot open file {}", filename);
 }
 
 MemoryStatisticsOS::~MemoryStatisticsOS()
@@ -48,9 +49,8 @@ MemoryStatisticsOS::~MemoryStatisticsOS()
     {
         try
         {
-            throwFromErrno(
-                    "File descriptor for \"" + std::string(filename) + "\" could not be closed. "
-                    "Something seems to have gone wrong. Inspect errno.", ErrorCodes::CANNOT_CLOSE_FILE);
+            ErrnoException::throwFromPath(
+                ErrorCodes::CANNOT_CLOSE_FILE, filename, "File descriptor for '{}' could not be closed", filename);
         }
         catch (const ErrnoException &)
         {
@@ -77,7 +77,7 @@ MemoryStatisticsOS::Data MemoryStatisticsOS::get() const
             if (errno == EINTR)
                 continue;
 
-            throwFromErrno("Cannot read from file " + std::string(filename), ErrorCodes::CANNOT_READ_FROM_FILE_DESCRIPTOR);
+            ErrnoException::throwFromPath(ErrorCodes::CANNOT_READ_FROM_FILE_DESCRIPTOR, filename, "Cannot read from file {}", filename);
         }
 
         assert(res >= 0);
@@ -136,7 +136,7 @@ MemoryStatisticsOS::Data MemoryStatisticsOS::get() const
     size_t len = sizeof(struct kinfo_proc);
 
     if (-1 == ::sysctl(mib, 4, &kp, &len, nullptr, 0))
-        throwFromErrno("Cannot sysctl(kern.proc.pid." + std::to_string(self) + ")", ErrorCodes::SYSTEM_ERROR);
+        throw ErrnoException(ErrorCodes::SYSTEM_ERROR, "Cannot sysctl(kern.proc.pid.{})", std::to_string(self));
 
     if (sizeof(struct kinfo_proc) != len)
         throw DB::Exception(DB::ErrorCodes::SYSTEM_ERROR, "Kernel returns structure of {} bytes instead of expected {}",