Merge branch 'master' into starts_ends_with_utf8

2024-11-22 07:31:57 +00:00 · 2023-08-08 16:18:04 +08:00 · 2023-08-08 16:18:04 +08:00 · d15ae5e120
commit d15ae5e120
parent 041af6899d 8812cb3cc1
571 changed files with 12765 additions and 3083 deletions
--- a/.gitmodules
+++ b/.gitmodules
@ -331,6 +331,10 @@
 [submodule "contrib/liburing"]
 	path = contrib/liburing
 	url = https://github.com/axboe/liburing
+[submodule "contrib/libarchive"]
+	path = contrib/libarchive
+	url = https://github.com/libarchive/libarchive.git
+	ignore = dirty
 [submodule "contrib/libfiu"]
 	path = contrib/libfiu
 	url = https://github.com/ClickHouse/libfiu.git
--- a/README.md
+++ b/README.md
@ -23,11 +23,8 @@ curl https://clickhouse.com/ | sh

 ## Upcoming Events

-* [**v23.7 Release Webinar**](https://clickhouse.com/company/events/v23-7-community-release-call?utm_source=github&utm_medium=social&utm_campaign=release-webinar-2023-07) - Jul 27 - 23.7 is rapidly approaching. Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release.
-* [**ClickHouse Meetup in Boston**](https://www.meetup.com/clickhouse-boston-user-group/events/293913596) - Jul 18
-* [**ClickHouse Meetup in NYC**](https://www.meetup.com/clickhouse-new-york-user-group/events/293913441) - Jul 19
-* [**ClickHouse Meetup in Toronto**](https://www.meetup.com/clickhouse-toronto-user-group/events/294183127) - Jul 20
-* [**ClickHouse Meetup in Singapore**](https://www.meetup.com/clickhouse-singapore-meetup-group/events/294428050/) - Jul 27
+* [**v23.8 Community Call**](https://clickhouse.com/company/events/v23-8-community-release-call?utm_source=github&utm_medium=social&utm_campaign=release-webinar-2023-08) - Aug 31 - 23.8 is rapidly approaching. Original creator, co-founder, and CTO of ClickHouse Alexey Milovidov will walk us through the highlights of the release.
+* [**ClickHouse & AI - A Meetup in San Francisco**](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/294472987) - Aug 8
 * [**ClickHouse Meetup in Paris**](https://www.meetup.com/clickhouse-france-user-group/events/294283460) - Sep 12

 Also, keep an eye out for upcoming meetups around the world. Somewhere else you want us to be? Please feel free to reach out to tyler <at> clickhouse <dot> com.
--- a/contrib/CMakeLists.txt
+++ b/contrib/CMakeLists.txt
@ -92,6 +92,7 @@ add_contrib (google-protobuf-cmake google-protobuf)
 add_contrib (openldap-cmake openldap)
 add_contrib (grpc-cmake grpc)
 add_contrib (msgpack-c-cmake msgpack-c)
+add_contrib (libarchive-cmake libarchive)

 add_contrib (corrosion-cmake corrosion)

--- a/contrib/libarchive
+++ b/contrib/libarchive
@ -0,0 +1 @@
+Subproject commit ee45796171324519f0c0bfd012018dd099296336
--- a/contrib/libarchive-cmake/CMakeLists.txt
+++ b/contrib/libarchive-cmake/CMakeLists.txt
@ -0,0 +1,172 @@
+set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/libarchive")
+
+set(SRCS 
+    "${LIBRARY_DIR}/libarchive/archive_acl.c"
+    "${LIBRARY_DIR}/libarchive/archive_blake2sp_ref.c"
+    "${LIBRARY_DIR}/libarchive/archive_blake2s_ref.c"
+    "${LIBRARY_DIR}/libarchive/archive_check_magic.c"
+    "${LIBRARY_DIR}/libarchive/archive_cmdline.c"
+    "${LIBRARY_DIR}/libarchive/archive_cryptor.c"
+    "${LIBRARY_DIR}/libarchive/archive_digest.c"
+    "${LIBRARY_DIR}/libarchive/archive_disk_acl_darwin.c"
+    "${LIBRARY_DIR}/libarchive/archive_disk_acl_freebsd.c"
+    "${LIBRARY_DIR}/libarchive/archive_disk_acl_linux.c"
+    "${LIBRARY_DIR}/libarchive/archive_disk_acl_sunos.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry_copy_bhfi.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry_copy_stat.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry_link_resolver.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry_sparse.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry_stat.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry_strmode.c"
+    "${LIBRARY_DIR}/libarchive/archive_entry_xattr.c"
+    "${LIBRARY_DIR}/libarchive/archive_getdate.c"
+    "${LIBRARY_DIR}/libarchive/archive_hmac.c"
+    "${LIBRARY_DIR}/libarchive/archive_match.c"
+    "${LIBRARY_DIR}/libarchive/archive_options.c"
+    "${LIBRARY_DIR}/libarchive/archive_pack_dev.c"
+    "${LIBRARY_DIR}/libarchive/archive_pathmatch.c"
+    "${LIBRARY_DIR}/libarchive/archive_ppmd7.c"
+    "${LIBRARY_DIR}/libarchive/archive_ppmd8.c"
+    "${LIBRARY_DIR}/libarchive/archive_random.c"
+    "${LIBRARY_DIR}/libarchive/archive_rb.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_add_passphrase.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_append_filter.c"
+    "${LIBRARY_DIR}/libarchive/archive_read.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_data_into_fd.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_disk_entry_from_file.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_disk_posix.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_disk_set_standard_lookup.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_disk_windows.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_extract2.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_extract.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_open_fd.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_open_file.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_open_filename.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_open_memory.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_set_format.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_set_options.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_all.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_by_code.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_bzip2.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_compress.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_grzip.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_gzip.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_lrzip.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_lz4.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_lzop.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_none.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_program.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_rpm.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_uu.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_xz.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_filter_zstd.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_7zip.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_all.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_ar.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_by_code.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_cab.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_cpio.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_empty.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_iso9660.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_lha.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_mtree.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_rar5.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_rar.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_raw.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_tar.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_warc.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_xar.c"
+    "${LIBRARY_DIR}/libarchive/archive_read_support_format_zip.c"
+    "${LIBRARY_DIR}/libarchive/archive_string.c"
+    "${LIBRARY_DIR}/libarchive/archive_string_sprintf.c"
+    "${LIBRARY_DIR}/libarchive/archive_util.c"
+    "${LIBRARY_DIR}/libarchive/archive_version_details.c"
+    "${LIBRARY_DIR}/libarchive/archive_virtual.c"
+    "${LIBRARY_DIR}/libarchive/archive_windows.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_b64encode.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_by_name.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_bzip2.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_compress.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_grzip.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_gzip.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_lrzip.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_lz4.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_lzop.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_none.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_program.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_uuencode.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_xz.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_add_filter_zstd.c"
+    "${LIBRARY_DIR}/libarchive/archive_write.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_disk_posix.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_disk_set_standard_lookup.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_disk_windows.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_open_fd.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_open_file.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_open_filename.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_open_memory.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_7zip.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_ar.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_by_name.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_cpio_binary.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_cpio.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_cpio_newc.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_cpio_odc.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_filter_by_ext.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_gnutar.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_iso9660.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_mtree.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_pax.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_raw.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_shar.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_ustar.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_v7tar.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_warc.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_xar.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_format_zip.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_options.c"
+    "${LIBRARY_DIR}/libarchive/archive_write_set_passphrase.c"
+    "${LIBRARY_DIR}/libarchive/filter_fork_posix.c"
+    "${LIBRARY_DIR}/libarchive/filter_fork_windows.c"
+    "${LIBRARY_DIR}/libarchive/xxhash.c"
+)
+
+add_library(_libarchive ${SRCS})
+target_include_directories(_libarchive PUBLIC 
+    ${CMAKE_CURRENT_SOURCE_DIR}
+    "${LIBRARY_DIR}/libarchive"
+)
+
+target_compile_definitions(_libarchive PUBLIC
+    HAVE_CONFIG_H
+)
+
+target_compile_options(_libarchive PRIVATE "-Wno-reserved-macro-identifier")
+
+if (TARGET ch_contrib::xz)
+    target_compile_definitions(_libarchive PUBLIC HAVE_LZMA_H=1)
+    target_link_libraries(_libarchive PRIVATE ch_contrib::xz)
+endif()
+
+if (TARGET ch_contrib::zlib)
+    target_compile_definitions(_libarchive PUBLIC HAVE_ZLIB_H=1)
+    target_link_libraries(_libarchive PRIVATE ch_contrib::zlib)
+endif()
+
+if (OS_LINUX)
+    target_compile_definitions(
+        _libarchive PUBLIC
+            MAJOR_IN_SYSMACROS=1
+            HAVE_LINUX_FS_H=1
+            HAVE_STRUCT_STAT_ST_MTIM_TV_NSEC=1
+            HAVE_LINUX_TYPES_H=1
+            HAVE_SYS_STATFS_H=1
+            HAVE_FUTIMESAT=1
+            HAVE_ICONV=1
+    )
+endif()
+
+add_library(ch_contrib::libarchive ALIAS _libarchive)
--- a/contrib/libarchive-cmake/config.h
+++ b/contrib/libarchive-cmake/config.h
--- a/contrib/libmetrohash/src/platform.h
+++ b/contrib/libmetrohash/src/platform.h
@ -17,7 +17,8 @@
 #ifndef METROHASH_PLATFORM_H
 #define METROHASH_PLATFORM_H

-#include <stdint.h>
+#include <bit>
+#include <cstdint>
 #include <cstring>

 // rotate right idiom recognized by most compilers
@ -33,6 +34,11 @@ inline static uint64_t read_u64(const void * const ptr)
    // so we use memcpy() which is the most portable. clang & gcc usually translates `memcpy()` into a single `load` instruction
    // when hardware supports it, so using memcpy() is efficient too.
    memcpy(&result, ptr, sizeof(result));
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+    result = std::byteswap(result);
+#endif
+
    return result;
 }

@ -40,6 +46,11 @@ inline static uint64_t read_u32(const void * const ptr)
 {
    uint32_t result;
    memcpy(&result, ptr, sizeof(result));
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+    result = std::byteswap(result);
+#endif
+
    return result;
 }

@ -47,6 +58,11 @@ inline static uint64_t read_u16(const void * const ptr)
 {
    uint16_t result;
    memcpy(&result, ptr, sizeof(result));
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+    result = std::byteswap(result);
+#endif
+
    return result;
 }

--- a/docker/keeper/Dockerfile
+++ b/docker/keeper/Dockerfile
@ -32,7 +32,7 @@ RUN arch=${TARGETARCH:-amd64} \
    esac

 ARG REPOSITORY="https://s3.amazonaws.com/clickhouse-builds/22.4/31c367d3cd3aefd316778601ff6565119fe36682/package_release"
-ARG VERSION="23.7.1.2470"
+ARG VERSION="23.7.3.14"
 ARG PACKAGES="clickhouse-keeper"

 # user/group precreated explicitly with fixed uid/gid on purpose.
--- a/docker/packager/README.md
+++ b/docker/packager/README.md
@ -6,7 +6,7 @@ Usage:
 Build deb package with `clang-14` in `debug` mode:
 ```
 $ mkdir deb/test_output
-$ ./packager --output-dir deb/test_output/ --package-type deb --compiler=clang-14 --build-type=debug
+$ ./packager --output-dir deb/test_output/ --package-type deb --compiler=clang-14 --debug-build
 $ ls -l deb/test_output
 -rw-r--r-- 1 root root      3730 clickhouse-client_22.2.2+debug_all.deb
 -rw-r--r-- 1 root root  84221888 clickhouse-common-static_22.2.2+debug_amd64.deb
--- a/docker/packager/packager
+++ b/docker/packager/packager
@ -112,12 +112,12 @@ def run_docker_image_with_env(
    subprocess.check_call(cmd, shell=True)


-def is_release_build(build_type: str, package_type: str, sanitizer: str) -> bool:
-    return build_type == "" and package_type == "deb" and sanitizer == ""
+def is_release_build(debug_build: bool, package_type: str, sanitizer: str) -> bool:
+    return not debug_build and package_type == "deb" and sanitizer == ""


 def parse_env_variables(
-    build_type: str,
+    debug_build: bool,
    compiler: str,
    sanitizer: str,
    package_type: str,
@ -240,7 +240,7 @@ def parse_env_variables(
        build_target = (
            f"{build_target} clickhouse-odbc-bridge clickhouse-library-bridge"
        )
-        if is_release_build(build_type, package_type, sanitizer):
+        if is_release_build(debug_build, package_type, sanitizer):
            cmake_flags.append("-DSPLIT_DEBUG_SYMBOLS=ON")
            result.append("WITH_PERFORMANCE=1")
            if is_cross_arm:
@ -255,8 +255,8 @@ def parse_env_variables(

    if sanitizer:
        result.append(f"SANITIZER={sanitizer}")
-    if build_type:
-        result.append(f"BUILD_TYPE={build_type.capitalize()}")
+    if debug_build:
+        result.append("BUILD_TYPE=Debug")
    else:
        result.append("BUILD_TYPE=None")

@ -361,7 +361,7 @@ def parse_args() -> argparse.Namespace:
        help="ClickHouse git repository",
    )
    parser.add_argument("--output-dir", type=dir_name, required=True)
-    parser.add_argument("--build-type", choices=("debug", ""), default="")
+    parser.add_argument("--debug-build", action="store_true")

    parser.add_argument(
        "--compiler",
@ -467,7 +467,7 @@ def main():
        build_image(image_with_version, dockerfile)

    env_prepared = parse_env_variables(
-        args.build_type,
+        args.debug_build,
        args.compiler,
        args.sanitizer,
        args.package_type,
--- a/docker/server/Dockerfile.alpine
+++ b/docker/server/Dockerfile.alpine
@ -33,7 +33,7 @@ RUN arch=${TARGETARCH:-amd64} \
 # lts / testing / prestable / etc
 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="https://packages.clickhouse.com/tgz/${REPO_CHANNEL}"
-ARG VERSION="23.7.1.2470"
+ARG VERSION="23.7.3.14"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"

 # user/group precreated explicitly with fixed uid/gid on purpose.
--- a/docker/server/Dockerfile.ubuntu
+++ b/docker/server/Dockerfile.ubuntu
@ -23,7 +23,7 @@ RUN sed -i "s|http://archive.ubuntu.com|${apt_archive}|g" /etc/apt/sources.list

 ARG REPO_CHANNEL="stable"
 ARG REPOSITORY="deb [signed-by=/usr/share/keyrings/clickhouse-keyring.gpg] https://packages.clickhouse.com/deb ${REPO_CHANNEL} main"
-ARG VERSION="23.7.1.2470"
+ARG VERSION="23.7.3.14"
 ARG PACKAGES="clickhouse-client clickhouse-server clickhouse-common-static"

 # set non-empty deb_location_url url to create a docker image
--- a/docker/test/base/Dockerfile
+++ b/docker/test/base/Dockerfile
@ -19,13 +19,13 @@ RUN apt-get update \
 # and MEMORY_LIMIT_EXCEEDED exceptions in Functional tests (total memory limit in Functional tests is ~55.24 GiB).
 # TSAN will flush shadow memory when reaching this limit.
 # It may cause false-negatives, but it's better than OOM.
-RUN echo "TSAN_OPTIONS='verbosity=1000 halt_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'" >> /etc/environment
+RUN echo "TSAN_OPTIONS='verbosity=1000 halt_on_error=1 abort_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'" >> /etc/environment
 RUN echo "UBSAN_OPTIONS='print_stacktrace=1'" >> /etc/environment
 RUN echo "MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1'" >> /etc/environment
 RUN echo "LSAN_OPTIONS='suppressions=/usr/share/clickhouse-test/config/lsan_suppressions.txt'" >> /etc/environment
 # Sanitizer options for current shell (not current, but the one that will be spawned on "docker run")
 # (but w/o verbosity for TSAN, otherwise test.reference will not match)
-ENV TSAN_OPTIONS='halt_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'
+ENV TSAN_OPTIONS='halt_on_error=1 abort_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'
 ENV UBSAN_OPTIONS='print_stacktrace=1'
 ENV MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1'

--- a/docker/test/integration/runner/Dockerfile
+++ b/docker/test/integration/runner/Dockerfile
@ -95,6 +95,7 @@ RUN python3 -m pip install --no-cache-dir \
    pytest-timeout \
    pytest-xdist \
    pytz \
+    pyyaml==5.3.1 \
    redis \
    requests-kerberos \
    tzlocal==2.1 \
@ -129,7 +130,7 @@ COPY misc/ /misc/

 # Same options as in test/base/Dockerfile
 # (in case you need to override them in tests)
-ENV TSAN_OPTIONS='halt_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'
+ENV TSAN_OPTIONS='halt_on_error=1 abort_on_error=1 history_size=7 memory_limit_mb=46080 second_deadlock_stack=1'
 ENV UBSAN_OPTIONS='print_stacktrace=1'
 ENV MSAN_OPTIONS='abort_on_error=1 poison_in_dtor=1'

--- a/docker/test/integration/runner/compose/docker_compose_hdfs.yml
+++ b/docker/test/integration/runner/compose/docker_compose_hdfs.yml
@ -12,3 +12,5 @@ services:
            - type: ${HDFS_FS:-tmpfs}
              source: ${HDFS_LOGS:-}
              target: /usr/local/hadoop/logs
+        sysctls:
+            net.ipv4.ip_local_port_range: '55000 65535'
--- a/docker/test/integration/runner/compose/docker_compose_kafka.yml
+++ b/docker/test/integration/runner/compose/docker_compose_kafka.yml
@ -31,6 +31,8 @@ services:
      - kafka_zookeeper
    security_opt:
      - label:disable
+    sysctls:
+      net.ipv4.ip_local_port_range: '55000 65535'

  schema-registry:
    image: confluentinc/cp-schema-registry:5.2.0
--- a/docker/test/integration/runner/compose/docker_compose_kerberized_hdfs.yml
+++ b/docker/test/integration/runner/compose/docker_compose_kerberized_hdfs.yml
@ -20,6 +20,8 @@ services:
    depends_on:
      - hdfskerberos
    entrypoint: /etc/bootstrap.sh -d
+    sysctls:
+      net.ipv4.ip_local_port_range: '55000 65535'

  hdfskerberos:
    image: clickhouse/kerberos-kdc:${DOCKER_KERBEROS_KDC_TAG:-latest}
@ -29,3 +31,5 @@ services:
      - ${KERBERIZED_HDFS_DIR}/../../kerberos_image_config.sh:/config.sh
      - /dev/urandom:/dev/random
    expose: [88, 749]
+    sysctls:
+      net.ipv4.ip_local_port_range: '55000 65535'
--- a/docker/test/integration/runner/compose/docker_compose_kerberized_kafka.yml
+++ b/docker/test/integration/runner/compose/docker_compose_kerberized_kafka.yml
@ -48,6 +48,8 @@ services:
      - kafka_kerberos
    security_opt:
      - label:disable
+    sysctls:
+      net.ipv4.ip_local_port_range: '55000 65535'

  kafka_kerberos:
    image: clickhouse/kerberos-kdc:${DOCKER_KERBEROS_KDC_TAG:-latest}
--- a/docker/test/integration/runner/compose/docker_compose_minio.yml
+++ b/docker/test/integration/runner/compose/docker_compose_minio.yml
@ -14,7 +14,7 @@ services:
      MINIO_ACCESS_KEY: minio
      MINIO_SECRET_KEY: minio123
      MINIO_PROMETHEUS_AUTH_TYPE: public
-    command: server --address :9001 --certs-dir /certs /data1-1
+    command: server --console-address 127.0.0.1:19001 --address :9001 --certs-dir /certs /data1-1
    depends_on:
      - proxy1
      - proxy2
--- a/docker/test/performance-comparison/config/users.d/perf-comparison-tweaks-users.xml
+++ b/docker/test/performance-comparison/config/users.d/perf-comparison-tweaks-users.xml
@ -3,7 +3,7 @@
        <default>
            <allow_introspection_functions>1</allow_introspection_functions>
            <log_queries>1</log_queries>
-            <metrics_perf_events_enabled>1</metrics_perf_events_enabled>
+            <metrics_perf_events_enabled>0</metrics_perf_events_enabled>
            <!--
                If a test takes too long by mistake, the entire test task can
                time out and the author won't get a proper message. Put some cap
--- a/docker/test/performance-comparison/perf.py
+++ b/docker/test/performance-comparison/perf.py
@ -369,6 +369,7 @@ for query_index in queries_to_run:
                        "max_execution_time": args.prewarm_max_query_seconds,
                        "query_profiler_real_time_period_ns": 10000000,
                        "query_profiler_cpu_time_period_ns": 10000000,
+                        "metrics_perf_events_enabled": 1,
                        "memory_profiler_step": "4Mi",
                    },
                )
@ -503,6 +504,7 @@ for query_index in queries_to_run:
                    settings={
                        "query_profiler_real_time_period_ns": 10000000,
                        "query_profiler_cpu_time_period_ns": 10000000,
+                        "metrics_perf_events_enabled": 1,
                    },
                )
                print(
--- a/docker/test/sqllogic/run.sh
+++ b/docker/test/sqllogic/run.sh
@ -96,5 +96,4 @@ rg -Fa "Fatal" /var/log/clickhouse-server/clickhouse-server.log ||:
 zstd < /var/log/clickhouse-server/clickhouse-server.log > /test_output/clickhouse-server.log.zst &

 # Compressed (FIXME: remove once only github actions will be left)
-rm /var/log/clickhouse-server/clickhouse-server.log
 mv /var/log/clickhouse-server/stderr.log /test_output/ ||:
--- a/docker/test/stateless/Dockerfile
+++ b/docker/test/stateless/Dockerfile
@ -41,6 +41,8 @@ RUN apt-get update -y \
            zstd \
            file \
            pv \
+            zip \
+            p7zip-full \
    && apt-get clean

 RUN pip3 install numpy scipy pandas Jinja2
--- a/docs/README.md
+++ b/docs/README.md
@ -200,8 +200,8 @@ Templates:
 - [Server Setting](_description_templates/template-server-setting.md)
 - [Database or Table engine](_description_templates/template-engine.md)
 - [System table](_description_templates/template-system-table.md)
- [Data type](_description_templates/data-type.md)
- [Statement](_description_templates/statement.md)
+- [Data type](_description_templates/template-data-type.md)
+- [Statement](_description_templates/template-statement.md)


 <a name="how-to-build-docs"/>
--- a/docs/changelogs/v23.7.2.25-stable.md
+++ b/docs/changelogs/v23.7.2.25-stable.md
@ -0,0 +1,31 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.7.2.25-stable (8dd1107b032) FIXME as compared to v23.7.1.2470-stable (a70127baecc)
+
+#### Backward Incompatible Change
+* Backported in [#52850](https://github.com/ClickHouse/ClickHouse/issues/52850): If a dynamic disk contains a name, it should be specified as `disk = disk(name = 'disk_name'`, ...) in disk function arguments. In previous version it could be specified as `disk = disk_<disk_name>(...)`, which is no longer supported. [#52820](https://github.com/ClickHouse/ClickHouse/pull/52820) ([Kseniia Sumarokova](https://github.com/kssenii)).
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#52913](https://github.com/ClickHouse/ClickHouse/issues/52913): Add `clickhouse-keeper-client` symlink to the clickhouse-server package. [#51882](https://github.com/ClickHouse/ClickHouse/pull/51882) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+
+* Fix binary arithmetic for Nullable(IPv4) [#51642](https://github.com/ClickHouse/ClickHouse/pull/51642) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* Support IPv4 and IPv6 as dictionary attributes [#51756](https://github.com/ClickHouse/ClickHouse/pull/51756) ([Yakov Olkhovskiy](https://github.com/yakov-olkhovskiy)).
+* init and destroy ares channel on demand.. [#52634](https://github.com/ClickHouse/ClickHouse/pull/52634) ([Arthur Passos](https://github.com/arthurpassos)).
+* Fix crash in function `tuple` with one sparse column argument [#52659](https://github.com/ClickHouse/ClickHouse/pull/52659) ([Anton Popov](https://github.com/CurtizJ)).
+* Fix data race in Keeper reconfiguration [#52804](https://github.com/ClickHouse/ClickHouse/pull/52804) ([Antonio Andelic](https://github.com/antonio2368)).
+* clickhouse-keeper: fix implementation of server with poll() [#52833](https://github.com/ClickHouse/ClickHouse/pull/52833) ([Andy Fiddaman](https://github.com/citrus-it)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Rename setting disable_url_encoding to enable_url_encoding and add a test [#52656](https://github.com/ClickHouse/ClickHouse/pull/52656) ([Kruglov Pavel](https://github.com/Avogar)).
+* Fix bugs and better test for SYSTEM STOP LISTEN [#52680](https://github.com/ClickHouse/ClickHouse/pull/52680) ([Nikolay Degterinsky](https://github.com/evillique)).
+* Increase min protocol version for sparse serialization [#52835](https://github.com/ClickHouse/ClickHouse/pull/52835) ([Anton Popov](https://github.com/CurtizJ)).
+* Docker improvements [#52869](https://github.com/ClickHouse/ClickHouse/pull/52869) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+
--- a/docs/changelogs/v23.7.3.14-stable.md
+++ b/docs/changelogs/v23.7.3.14-stable.md
@ -0,0 +1,23 @@
+---
+sidebar_position: 1
+sidebar_label: 2023
+---
+
+# 2023 Changelog
+
+### ClickHouse release v23.7.3.14-stable (bd9a510550c) FIXME as compared to v23.7.2.25-stable (8dd1107b032)
+
+#### Build/Testing/Packaging Improvement
+* Backported in [#53025](https://github.com/ClickHouse/ClickHouse/issues/53025): Packing inline cache into docker images sometimes causes strange special effects. Since we don't use it at all, it's good to go. [#53008](https://github.com/ClickHouse/ClickHouse/pull/53008) ([Mikhail f. Shiryaev](https://github.com/Felixoid)).
+
+#### Bug Fix (user-visible misbehavior in an official stable release)
+
+* Fix named collections on cluster 23.7 [#52687](https://github.com/ClickHouse/ClickHouse/pull/52687) ([Al Korgun](https://github.com/alkorgun)).
+* Fix password leak in show create mysql table [#52962](https://github.com/ClickHouse/ClickHouse/pull/52962) ([Duc Canh Le](https://github.com/canhld94)).
+* Fix ZstdDeflatingWriteBuffer truncating the output sometimes [#53064](https://github.com/ClickHouse/ClickHouse/pull/53064) ([Michael Kolupaev](https://github.com/al13n321)).
+
+#### NOT FOR CHANGELOG / INSIGNIFICANT
+
+* Suspicious DISTINCT crashes from sqlancer [#52636](https://github.com/ClickHouse/ClickHouse/pull/52636) ([Igor Nikonov](https://github.com/devcrafter)).
+* Fix Parquet stats for Float32 and Float64 [#53067](https://github.com/ClickHouse/ClickHouse/pull/53067) ([Michael Kolupaev](https://github.com/al13n321)).
+
--- a/docs/en/development/build.md
+++ b/docs/en/development/build.md
@ -14,6 +14,20 @@ Supported platforms:
 - PowerPC 64 LE (experimental)
 - RISC-V 64 (experimental)

+## Building in docker
+We use the docker image `clickhouse/binary-builder` for our CI builds. It contains everything necessary to build the binary and packages. There is a script `docker/packager/packager` to ease the image usage:
+
+```bash
+# define a directory for the output artifacts
+output_dir="build_results"
+# a simplest build
+./docker/packager/packager --package-type=binary --output-dir "$output_dir"
+# build debian packages
+./docker/packager/packager --package-type=deb --output-dir "$output_dir"
+# by default, debian packages use thin LTO, so we can override it to speed up the build
+CMAKE_FLAGS='-DENABLE_THINLTO=' ./docker/packager/packager --package-type=deb --output-dir "./$(git rev-parse --show-cdup)/build_results"
+```
+
 ## Building on Ubuntu

 The following tutorial is based on Ubuntu Linux.
--- a/docs/en/development/continuous-integration.md
+++ b/docs/en/development/continuous-integration.md
@ -141,6 +141,10 @@ Runs [stateful functional tests](tests.md#functional-tests). Treat them in the s
 Runs [integration tests](tests.md#integration-tests).


+## Bugfix validate check
+Checks that either a new test (functional or integration) or there some changed tests that fail with the binary built on master branch. This check is triggered when pull request has "pr-bugfix" label.
+
+
 ## Stress Test
 Runs stateless functional tests concurrently from several clients to detect
 concurrency-related errors. If it fails:
--- a/docs/en/engines/database-engines/replicated.md
+++ b/docs/en/engines/database-engines/replicated.md
@ -35,7 +35,7 @@ The [system.clusters](../../operations/system-tables/clusters.md) system table c

 When creating a new replica of the database, this replica creates tables by itself. If the replica has been unavailable for a long time and has lagged behind the replication log — it checks its local metadata with the current metadata in ZooKeeper, moves the extra tables with data to a separate non-replicated database (so as not to accidentally delete anything superfluous), creates the missing tables, updates the table names if they have been renamed. The data is replicated at the `ReplicatedMergeTree` level, i.e. if the table is not replicated, the data will not be replicated (the database is responsible only for metadata).

-[`ALTER TABLE ATTACH|FETCH|DROP|DROP DETACHED|DETACH PARTITION|PART`](../../sql-reference/statements/alter/partition.md) queries are allowed but not replicated. The database engine will only add/fetch/remove the partition/part to the current replica. However, if the table itself uses a Replicated table engine, then the data will be replicated after using `ATTACH`.
+[`ALTER TABLE FREEZE|ATTACH|FETCH|DROP|DROP DETACHED|DETACH PARTITION|PART`](../../sql-reference/statements/alter/partition.md) queries are allowed but not replicated. The database engine will only add/fetch/remove the partition/part to the current replica. However, if the table itself uses a Replicated table engine, then the data will be replicated after using `ATTACH`.

 ## Usage Example {#usage-example}

--- a/docs/en/engines/table-engines/index.md
+++ b/docs/en/engines/table-engines/index.md
@ -60,6 +60,7 @@ Engines in the family:
 - [EmbeddedRocksDB](../../engines/table-engines/integrations/embedded-rocksdb.md)
 - [RabbitMQ](../../engines/table-engines/integrations/rabbitmq.md)
 - [PostgreSQL](../../engines/table-engines/integrations/postgresql.md)
+- [S3Queue](../../engines/table-engines/integrations/s3queue.md)

 ### Special Engines {#special-engines}

--- a/docs/en/engines/table-engines/integrations/deltalake.md
+++ b/docs/en/engines/table-engines/integrations/deltalake.md
@ -22,7 +22,7 @@ CREATE TABLE deltalake
 - `url` — Bucket url with path to the existing Delta Lake table.
 - `aws_access_key_id`, `aws_secret_access_key` - Long-term credentials for the [AWS](https://aws.amazon.com/) account user.  You can use these to authenticate your requests. Parameter is optional. If credentials are not specified, they are used from the configuration file.

-Engine parameters can be specified using [Named Collections](../../../operations/named-collections.md)
+Engine parameters can be specified using [Named Collections](/docs/en/operations/named-collections.md).

 **Example**

--- a/docs/en/engines/table-engines/integrations/hudi.md
+++ b/docs/en/engines/table-engines/integrations/hudi.md
@ -22,7 +22,7 @@ CREATE TABLE hudi_table
 - `url` — Bucket url with the path to an existing Hudi table.
 - `aws_access_key_id`, `aws_secret_access_key` - Long-term credentials for the [AWS](https://aws.amazon.com/) account user.  You can use these to authenticate your requests. Parameter is optional. If credentials are not specified, they are used from the configuration file.

-Engine parameters can be specified using [Named Collections](../../../operations/named-collections.md)
+Engine parameters can be specified using [Named Collections](/docs/en/operations/named-collections.md).

 **Example**

--- a/docs/en/engines/table-engines/integrations/s3.md
+++ b/docs/en/engines/table-engines/integrations/s3.md
@ -237,7 +237,7 @@ The following settings can be set before query execution or placed into configur
 - `s3_max_get_rps` — Maximum GET requests per second rate before throttling. Default value is `0` (unlimited).
 - `s3_max_get_burst` — Max number of requests that can be issued simultaneously before hitting request per second limit. By default (`0` value) equals to `s3_max_get_rps`.
 - `s3_upload_part_size_multiply_factor` - Multiply `s3_min_upload_part_size` by this factor each time `s3_multiply_parts_count_threshold` parts were uploaded from a single write to S3. Default values is `2`.
- `s3_upload_part_size_multiply_parts_count_threshold` - Each time this number of parts was uploaded to S3 `s3_min_upload_part_size multiplied` by `s3_upload_part_size_multiply_factor`. Default value us `500`.
+- `s3_upload_part_size_multiply_parts_count_threshold` - Each time this number of parts was uploaded to S3, `s3_min_upload_part_size` is multiplied by `s3_upload_part_size_multiply_factor`. Default value is `500`.
 - `s3_max_inflight_parts_for_one_file` - Limits the number of put requests that can be run concurrently for one object. Its number should be limited. The value `0` means unlimited. Default value is `20`. Each in-flight part has a buffer with size `s3_min_upload_part_size` for the first `s3_upload_part_size_multiply_factor` parts and more when file is big enough, see `upload_part_size_multiply_factor`. With default settings one uploaded file consumes not more than `320Mb` for a file which is less than `8G`. The consumption is greater for a larger file.

 Security consideration: if malicious user can specify arbitrary S3 URLs, `s3_max_redirects` must be set to zero to avoid [SSRF](https://en.wikipedia.org/wiki/Server-side_request_forgery) attacks; or alternatively, `remote_host_filter` must be specified in server configuration.
--- a/docs/en/engines/table-engines/integrations/s3queue.md
+++ b/docs/en/engines/table-engines/integrations/s3queue.md
@ -0,0 +1,224 @@
+---
+slug: /en/engines/table-engines/integrations/s3queue
+sidebar_position: 7
+sidebar_label: S3Queue
+---
+
+# S3Queue Table Engine
+This engine provides integration with [Amazon S3](https://aws.amazon.com/s3/) ecosystem and allows streaming import. This engine is similar to the [Kafka](../../../engines/table-engines/integrations/kafka.md), [RabbitMQ](../../../engines/table-engines/integrations/rabbitmq.md) engines, but provides S3-specific features.
+
+## Create Table {#creating-a-table}
+
+``` sql
+CREATE TABLE s3_queue_engine_table (name String, value UInt32)
+    ENGINE = S3Queue(path [, NOSIGN | aws_access_key_id, aws_secret_access_key,] format, [compression])
+    [SETTINGS]
+    [mode = 'unordered',]
+    [after_processing = 'keep',]
+    [keeper_path = '',]
+    [s3queue_loading_retries = 0,]
+    [s3queue_polling_min_timeout_ms = 1000,]
+    [s3queue_polling_max_timeout_ms = 10000,]
+    [s3queue_polling_backoff_ms = 0,]
+    [s3queue_tracked_files_limit = 1000,]
+    [s3queue_tracked_file_ttl_sec = 0,]
+    [s3queue_polling_size = 50,]
+```
+
+**Engine parameters**
+
+- `path` — Bucket url with path to file. Supports following wildcards in readonly mode: `*`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings. For more information see [below](#wildcards-in-path).
+- `NOSIGN` - If this keyword is provided in place of credentials, all the requests will not be signed.
+- `format` — The [format](../../../interfaces/formats.md#formats) of the file.
+- `aws_access_key_id`, `aws_secret_access_key` - Long-term credentials for the [AWS](https://aws.amazon.com/) account user.  You can use these to authenticate your requests. Parameter is optional. If credentials are not specified, they are used from the configuration file. For more information see [Using S3 for Data Storage](../mergetree-family/mergetree.md#table_engine-mergetree-s3).
+- `compression` — Compression type. Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. Parameter is optional. By default, it will autodetect compression by file extension.
+
+**Example**
+
+```sql
+CREATE TABLE s3queue_engine_table (name String, value UInt32)
+ENGINE=S3Queue('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/*', 'CSV', 'gzip')
+SETTINGS
+    mode = 'ordred';
+```
+
+Using named collections:
+
+``` xml
+<clickhouse>
+    <named_collections>
+        <s3queue_conf>
+            <url>'https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/*</url>
+            <access_key_id>test<access_key_id>
+            <secret_access_key>test</secret_access_key>
+        </s3queue_conf>
+    </named_collections>
+</clickhouse>
+```
+
+```sql
+CREATE TABLE s3queue_engine_table (name String, value UInt32)
+ENGINE=S3Queue(s3queue_conf, format = 'CSV', compression_method = 'gzip')
+SETTINGS
+    mode = 'ordred';
+```
+
+## Settings {#s3queue-settings}
+
+### mode {#mode}
+
+Possible values:
+
+- unordered — With unordered mode, the set of all already processed files is tracked with persistent nodes in ZooKeeper.
+- ordered — With ordered mode, only the max name of the successfully consumed file, and the names of files that will be retried after unsuccessful loading attempt are being stored in ZooKeeper.
+
+Default value: `unordered`.
+
+### after_processing {#after_processing}
+
+Delete or keep file after successful processing.
+Possible values:
+
+- keep.
+- delete.
+
+Default value: `keep`.
+
+### keeper_path {#keeper_path}
+
+The path in ZooKeeper can be specified as a table engine setting or default path can be formed from the global configuration-provided path and table UUID.
+Possible values:
+
+- String.
+
+Default value: `/`.
+
+### s3queue_loading_retries {#s3queue_loading_retries}
+
+Retry file loading up to specified number of times. By default, there are no retries.
+Possible values:
+
+- Positive integer.
+
+Default value: `0`.
+
+### s3queue_polling_min_timeout_ms {#s3queue_polling_min_timeout_ms}
+
+Minimal timeout before next polling (in milliseconds).
+
+Possible values:
+
+- Positive integer.
+
+Default value: `1000`.
+
+### s3queue_polling_max_timeout_ms {#s3queue_polling_max_timeout_ms}
+
+Maximum timeout before next polling (in milliseconds).
+
+Possible values:
+
+- Positive integer.
+
+Default value: `10000`.
+
+### s3queue_polling_backoff_ms {#s3queue_polling_backoff_ms}
+
+Polling backoff (in milliseconds).
+
+Possible values:
+
+- Positive integer.
+
+Default value: `0`.
+
+### s3queue_tracked_files_limit {#s3queue_tracked_files_limit}
+
+Allows to limit the number of Zookeeper nodes if the 'unordered' mode is used, does nothing for 'ordered' mode.
+If limit reached the oldest processed files will be deleted from ZooKeeper node and processed again.
+
+Possible values:
+
+- Positive integer.
+
+Default value: `1000`.
+
+### s3queue_tracked_file_ttl_sec {#s3queue_tracked_file_ttl_sec}
+
+Maximum number of seconds to store processed files in ZooKeeper node (store forever by default) for 'unordered' mode, does nothing for 'ordered' mode.
+After the specified number of seconds, the file will be re-imported.
+
+Possible values:
+
+- Positive integer.
+
+Default value: `0`.
+
+### s3queue_polling_size {#s3queue_polling_size}
+
+Maximum files to fetch from S3 with SELECT or in background task.
+Engine takes files for processing from S3 in batches.
+We limit the batch size to increase concurrency if multiple table engines with the same `keeper_path` consume files from the same path.
+
+Possible values:
+
+- Positive integer.
+
+Default value: `50`.
+
+
+## S3-related Settings {#s3-settings}
+
+Engine supports all s3 related settings. For more information about S3 settings see [here](../../../engines/table-engines/integrations/s3.md).
+
+
+## Description {#description}
+
+`SELECT` is not particularly useful for streaming import (except for debugging), because each file can be imported only once. It is more practical to create real-time threads using [materialized views](../../../sql-reference/statements/create/view.md). To do this:
+
+1.  Use the engine to create a table for consuming from specified path in S3 and consider it a data stream.
+2.  Create a table with the desired structure.
+3.  Create a materialized view that converts data from the engine and puts it into a previously created table.
+
+When the `MATERIALIZED VIEW` joins the engine, it starts collecting data in the background.
+
+Example:
+
+``` sql
+  CREATE TABLE s3queue_engine_table (name String, value UInt32)
+    ENGINE=S3Queue('https://clickhouse-public-datasets.s3.amazonaws.com/my-test-bucket-768/*', 'CSV', 'gzip')
+    SETTINGS
+        mode = 'unordred',
+        keeper_path = '/clickhouse/s3queue/';
+
+  CREATE TABLE stats (name String, value UInt32)
+    ENGINE = MergeTree() ORDER BY name;
+
+  CREATE MATERIALIZED VIEW consumer TO stats
+    AS SELECT name, value FROM s3queue_engine_table;
+
+  SELECT * FROM stats ORDER BY name;
+```
+
+## Virtual columns {#virtual-columns}
+
+- `_path` — Path to the file.
+- `_file` — Name of the file.
+
+For more information about virtual columns see [here](../../../engines/table-engines/index.md#table_engines-virtual_columns).
+
+
+## Wildcards In Path {#wildcards-in-path}
+
+`path` argument can specify multiple files using bash-like wildcards. For being processed file should exist and match to the whole path pattern. Listing of files is determined during `SELECT` (not at `CREATE` moment).
+
+- `*` — Substitutes any number of any characters except `/` including empty string.
+- `?` — Substitutes any single character.
+- `{some_string,another_string,yet_another_one}` — Substitutes any of strings `'some_string', 'another_string', 'yet_another_one'`.
+- `{N..M}` — Substitutes any number in range from N to M including both borders. N and M can have leading zeroes e.g. `000..078`.
+
+Constructions with `{}` are similar to the [remote](../../../sql-reference/table-functions/remote.md) table function.
+
+:::note
+If the listing of files contains number ranges with leading zeros, use the construction with braces for each digit separately or use `?`.
+:::
--- a/docs/en/engines/table-engines/mergetree-family/annindexes.md
+++ b/docs/en/engines/table-engines/mergetree-family/annindexes.md
@ -193,6 +193,19 @@ index creation, `L2Distance` is used as default. Parameter `NumTrees` is the num
 specified: 100). Higher values of `NumTree` mean more accurate search results but slower index creation / query times (approximately
 linearly) as well as larger index sizes.

+`L2Distance` is also called Euclidean distance, the Euclidean distance between two points in Euclidean space is the length of a line segment between the two points.
+For example: If we have point P(p1,p2), Q(q1,q2), their distance will be d(p,q)
+![L2Distance](https://en.wikipedia.org/wiki/Euclidean_distance#/media/File:Euclidean_distance_2d.svg)
+
+`cosineDistance` also called cosine similarity is a measure of similarity between two non-zero vectors defined in an inner product space. Cosine similarity is the cosine of the angle between the vectors; that is, it is the dot product of the vectors divided by the product of their lengths. 
+![cosineDistance](https://www.tyrrell4innovation.ca/wp-content/uploads/2021/06/rsz_jenny_du_miword.png)
+
+The Euclidean distance corresponds to the L2-norm of a difference between vectors. The cosine similarity is proportional to the dot product of two vectors and inversely proportional to the product of their magnitudes.
+![compare](https://www.researchgate.net/publication/320914786/figure/fig2/AS:558221849841664@1510101868614/The-difference-between-Euclidean-distance-and-cosine-similarity.png)
+In one sentence: cosine similarity care only about the angle between them, but do not care about the "distance" we normally think.
+![L2 distance](https://www.baeldung.com/wp-content/uploads/sites/4/2020/06/4-1.png)
+![cosineDistance](https://www.baeldung.com/wp-content/uploads/sites/4/2020/06/5.png)
+
 :::note
 Indexes over columns of type `Array` will generally work faster than indexes on `Tuple` columns. All arrays **must** have same length. Use
 [CONSTRAINT](/docs/en/sql-reference/statements/create/table.md#constraints) to avoid errors. For example, `CONSTRAINT constraint_name_1
--- a/docs/en/engines/table-engines/special/buffer.md
+++ b/docs/en/engines/table-engines/special/buffer.md
@ -13,7 +13,7 @@ A recommended alternative to the Buffer Table Engine is enabling [asynchronous i
 :::

 ``` sql
-Buffer(database, table, num_layers, min_time, max_time, min_rows, max_rows, min_bytes, max_bytes)
+Buffer(database, table, num_layers, min_time, max_time, min_rows, max_rows, min_bytes, max_bytes [,flush_time [,flush_rows [,flush_bytes]]])
 ```

 ### Engine parameters:
--- a/docs/en/interfaces/formats.md
+++ b/docs/en/interfaces/formats.md
@ -2131,7 +2131,6 @@ To exchange data with Hadoop, you can use [HDFS table engine](/docs/en/engines/t

 - [output_format_parquet_row_group_size](/docs/en/operations/settings/settings-formats.md/#output_format_parquet_row_group_size) - row group size in rows while data output. Default value - `1000000`.
 - [output_format_parquet_string_as_string](/docs/en/operations/settings/settings-formats.md/#output_format_parquet_string_as_string) - use Parquet String type instead of Binary for String columns. Default value - `false`.
- [input_format_parquet_import_nested](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_import_nested) - allow inserting array of structs into [Nested](/docs/en/sql-reference/data-types/nested-data-structures/index.md) table in Parquet input format. Default value - `false`.
 - [input_format_parquet_case_insensitive_column_matching](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_case_insensitive_column_matching) - ignore case when matching Parquet columns with ClickHouse columns. Default value - `false`.
 - [input_format_parquet_allow_missing_columns](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_allow_missing_columns) - allow missing columns while reading Parquet data. Default value - `false`.
 - [input_format_parquet_skip_columns_with_unsupported_types_in_schema_inference](/docs/en/operations/settings/settings-formats.md/#input_format_parquet_skip_columns_with_unsupported_types_in_schema_inference) - allow skipping columns with unsupported types while schema inference for Parquet format. Default value - `false`.
@ -2336,7 +2335,6 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Arrow" > {filenam

 - [output_format_arrow_low_cardinality_as_dictionary](/docs/en/operations/settings/settings-formats.md/#output_format_arrow_low_cardinality_as_dictionary) - enable output ClickHouse LowCardinality type as Dictionary Arrow type. Default value - `false`.
 - [output_format_arrow_string_as_string](/docs/en/operations/settings/settings-formats.md/#output_format_arrow_string_as_string) - use Arrow String type instead of Binary for String columns. Default value - `false`.
- [input_format_arrow_import_nested](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_import_nested) - allow inserting array of structs into Nested table in Arrow input format. Default value - `false`.
 - [input_format_arrow_case_insensitive_column_matching](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_case_insensitive_column_matching) - ignore case when matching Arrow columns with ClickHouse columns. Default value - `false`.
 - [input_format_arrow_allow_missing_columns](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_allow_missing_columns) - allow missing columns while reading Arrow data. Default value - `false`.
 - [input_format_arrow_skip_columns_with_unsupported_types_in_schema_inference](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_skip_columns_with_unsupported_types_in_schema_inference) - allow skipping columns with unsupported types while schema inference for Arrow format. Default value - `false`.
@ -2402,7 +2400,6 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT ORC" > {filename.

 - [output_format_arrow_string_as_string](/docs/en/operations/settings/settings-formats.md/#output_format_arrow_string_as_string) - use Arrow String type instead of Binary for String columns. Default value - `false`.
 - [output_format_orc_compression_method](/docs/en/operations/settings/settings-formats.md/#output_format_orc_compression_method) - compression method used in output ORC format. Default value - `none`.
- [input_format_arrow_import_nested](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_import_nested) - allow inserting array of structs into Nested table in Arrow input format. Default value - `false`.
 - [input_format_arrow_case_insensitive_column_matching](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_case_insensitive_column_matching) - ignore case when matching Arrow columns with ClickHouse columns. Default value - `false`.
 - [input_format_arrow_allow_missing_columns](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_allow_missing_columns) - allow missing columns while reading Arrow data. Default value - `false`.
 - [input_format_arrow_skip_columns_with_unsupported_types_in_schema_inference](/docs/en/operations/settings/settings-formats.md/#input_format_arrow_skip_columns_with_unsupported_types_in_schema_inference) - allow skipping columns with unsupported types while schema inference for Arrow format. Default value - `false`.
--- a/docs/en/operations/backup.md
+++ b/docs/en/operations/backup.md
@ -84,6 +84,7 @@ The BACKUP and RESTORE statements take a list of DATABASE and TABLE names, a des
    - `password` for the file on disk
    - `base_backup`: the destination of the previous backup of this source.  For example, `Disk('backups', '1.zip')`
    - `structure_only`: if enabled, allows to only backup or restore the CREATE statements without the data of tables
+    - `storage_policy`: storage policy for the tables being restored. See [Using Multiple Block Devices for Data Storage](../engines/table-engines/mergetree-family/mergetree.md#table_engine-mergetree-multiple-volumes). This setting is only applicable to the `RESTORE` command. The specified storage policy applies only to tables with an engine from the `MergeTree` family.
    - `s3_storage_class`: the storage class used for S3 backup. For example, `STANDARD`

 ### Usage examples
--- a/docs/en/operations/settings/query-complexity.md
+++ b/docs/en/operations/settings/query-complexity.md
@ -298,7 +298,7 @@ Default value: `THROW`.
 - [JOIN clause](../../sql-reference/statements/select/join.md#select-join)
 - [Join table engine](../../engines/table-engines/special/join.md)

-## max_partitions_per_insert_block {#max-partitions-per-insert-block}
+## max_partitions_per_insert_block {#settings-max_partitions_per_insert_block}

 Limits the maximum number of partitions in a single inserted block.

@ -309,9 +309,18 @@ Default value: 100.

 **Details**

-When inserting data, ClickHouse calculates the number of partitions in the inserted block. If the number of partitions is more than `max_partitions_per_insert_block`, ClickHouse throws an exception with the following text:
+When inserting data, ClickHouse calculates the number of partitions in the inserted block. If the number of partitions is more than `max_partitions_per_insert_block`, ClickHouse either logs a warning or throws an exception based on `throw_on_max_partitions_per_insert_block`. Exceptions have the following text:

-> “Too many partitions for single INSERT block (more than” + toString(max_parts) + “). The limit is controlled by ‘max_partitions_per_insert_block’ setting. A large number of partitions is a common misconception. It will lead to severe negative performance impact, including slow server startup, slow INSERT queries and slow SELECT queries. Recommended total number of partitions for a table is under 1000..10000. Please note, that partitioning is not intended to speed up SELECT queries (ORDER BY key is sufficient to make range queries fast). Partitions are intended for data manipulation (DROP PARTITION, etc).”
+> “Too many partitions for a single INSERT block (`partitions_count` partitions, limit is ” + toString(max_partitions) + “). The limit is controlled by the ‘max_partitions_per_insert_block’ setting. A large number of partitions is a common misconception. It will lead to severe negative performance impact, including slow server startup, slow INSERT queries and slow SELECT queries. Recommended total number of partitions for a table is under 1000..10000. Please note, that partitioning is not intended to speed up SELECT queries (ORDER BY key is sufficient to make range queries fast). Partitions are intended for data manipulation (DROP PARTITION, etc).”
+
+## throw_on_max_partitions_per_insert_block {#settings-throw_on_max_partition_per_insert_block}
+
+Allows you to control behaviour when `max_partitions_per_insert_block` is reached.
+
+- `true`  - When an insert block reaches `max_partitions_per_insert_block`, an exception is raised.
+- `false` - Logs a warning when `max_partitions_per_insert_block` is reached.
+
+Default value: `true`

 ## max_temporary_data_on_disk_size_for_user {#settings_max_temporary_data_on_disk_size_for_user}

--- a/docs/en/operations/settings/settings-formats.md
+++ b/docs/en/operations/settings/settings-formats.md
@ -1112,17 +1112,6 @@ Default value: 1.

 ## Arrow format settings {#arrow-format-settings}

-### input_format_arrow_import_nested {#input_format_arrow_import_nested}
-
-Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/index.md) columns as an array of structs in [Arrow](../../interfaces/formats.md/#data_types-matching-arrow) input format.
-
-Possible values:
-
- 0 — Data can not be inserted into `Nested` columns as an array of structs.
- 1 — Data can be inserted into `Nested` columns as an array of structs.
-
-Default value: `0`.
-
 ### input_format_arrow_case_insensitive_column_matching {#input_format_arrow_case_insensitive_column_matching}

 Ignore case when matching Arrow column names with ClickHouse column names.
@ -1172,17 +1161,6 @@ Default value: `lz4_frame`.

 ## ORC format settings {#orc-format-settings}

-### input_format_orc_import_nested {#input_format_orc_import_nested}
-
-Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/index.md) columns as an array of structs in [ORC](../../interfaces/formats.md/#data-format-orc) input format.
-
-Possible values:
-
- 0 — Data can not be inserted into `Nested` columns as an array of structs.
- 1 — Data can be inserted into `Nested` columns as an array of structs.
-
-Default value: `0`.
-
 ### input_format_orc_row_batch_size {#input_format_orc_row_batch_size}

 Batch size when reading ORC stripes.
@ -1221,17 +1199,6 @@ Default value: `none`.

 ## Parquet format settings {#parquet-format-settings}

-### input_format_parquet_import_nested {#input_format_parquet_import_nested}
-
-Enables or disables the ability to insert the data into [Nested](../../sql-reference/data-types/nested-data-structures/index.md) columns as an array of structs in [Parquet](../../interfaces/formats.md/#data-format-parquet) input format.
-
-Possible values:
-
- 0 — Data can not be inserted into `Nested` columns as an array of structs.
- 1 — Data can be inserted into `Nested` columns as an array of structs.
-
-Default value: `0`.
-
 ### input_format_parquet_case_insensitive_column_matching {#input_format_parquet_case_insensitive_column_matching}

 Ignore case when matching Parquet column names with ClickHouse column names.
--- a/docs/en/operations/settings/settings.md
+++ b/docs/en/operations/settings/settings.md
@ -4578,3 +4578,39 @@ Type: Int64

 Default: 0

+## rewrite_count_distinct_if_with_count_distinct_implementation
+
+Allows you to rewrite `countDistcintIf` with [count_distinct_implementation](#settings-count_distinct_implementation) setting.
+
+Possible values:
+
+- true — Allow.
+- false — Disallow.
+
+Default value: `false`.
+
+## precise_float_parsing {#precise_float_parsing}
+
+Switches [Float32/Float64](../../sql-reference/data-types/float.md) parsing algorithms:
+* If the value is `1`, then precise method is used. It is slower than fast method, but it always returns a number that is the closest machine representable number to the input.
+* Otherwise, fast method is used (default). It usually returns the same value as precise, but in rare cases result may differ by one or two least significant digits.
+
+Possible values: `0`, `1`.
+
+Default value: `0`.
+
+Example:
+
+```sql
+SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 0;
+
+┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
+│  1.7090999999999998 │       15008753.000000002 │
+└─────────────────────┴──────────────────────────┘
+
+SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 1;
+
+┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
+│              1.7091 │                 15008753 │
+└─────────────────────┴──────────────────────────┘
+```
--- a/docs/en/operations/utilities/clickhouse-keeper-client.md
+++ b/docs/en/operations/utilities/clickhouse-keeper-client.md
@ -11,7 +11,7 @@ A client application to interact with clickhouse-keeper by its native protocol.

 -   `-q QUERY`, `--query=QUERY` — Query to execute. If this parameter is not passed, `clickhouse-keeper-client` will start in interactive mode.
 -   `-h HOST`, `--host=HOST` — Server host. Default value: `localhost`.
-   `-p N`, `--port=N` — Server port. Default value: 2181
+-   `-p N`, `--port=N` — Server port. Default value: 9181
 -   `--connection-timeout=TIMEOUT` — Set connection timeout in seconds. Default value: 10s.
 -   `--session-timeout=TIMEOUT` — Set session timeout in seconds. Default value: 10s.
 -   `--operation-timeout=TIMEOUT` — Set operation timeout in seconds. Default value: 10s.
@ -21,8 +21,8 @@ A client application to interact with clickhouse-keeper by its native protocol.
 ## Example {#clickhouse-keeper-client-example}

 ```bash
-./clickhouse-keeper-client -h localhost:2181 --connection-timeout 30 --session-timeout 30 --operation-timeout 30
-Connected to ZooKeeper at [::1]:2181 with session_id 137
+./clickhouse-keeper-client -h localhost:9181 --connection-timeout 30 --session-timeout 30 --operation-timeout 30
+Connected to ZooKeeper at [::1]:9181 with session_id 137
 / :) ls
 keeper foo bar
 / :) cd keeper
@ -51,7 +51,3 @@ keeper foo bar
 -   `rmr <path>` -- Recursively deletes path. Confirmation required
 -   `flwc <command>` -- Executes four-letter-word command
 -   `help` -- Prints this message
-   `get_stat [path]` -- Returns the node's stat (default `.`)
-   `find_super_nodes <threshold> [path]` -- Finds nodes with number of children larger than some threshold for the given path (default `.`)
-   `delete_stable_backups` -- Deletes ClickHouse nodes used for backups that are now inactive
-   `find_big_family [path] [n]` -- Returns the top n nodes with the biggest family in the subtree (default path = `.` and n = 10)
--- a/docs/en/operations/utilities/clickhouse-local.md
+++ b/docs/en/operations/utilities/clickhouse-local.md
@ -34,7 +34,13 @@ The binary you just downloaded can run all sorts of ClickHouse tools and utiliti

 A common use of `clickhouse-local` is to run ad-hoc queries on files: where you don't have to insert the data into a table. `clickhouse-local` can stream the data from a file into a temporary table and execute your SQL.

-If the file is sitting on the same machine as `clickhouse-local`, use the `file` table engine. The following `reviews.tsv` file contains a sampling of Amazon product reviews:
+If the file is sitting on the same machine as `clickhouse-local`, you can simple specify the file to load. The following `reviews.tsv` file contains a sampling of Amazon product reviews:
+
+```bash
+./clickhouse local -q "SELECT * FROM 'reviews.tsv'"
+```
+
+This command is a shortcut of:

 ```bash
 ./clickhouse local -q "SELECT * FROM file('reviews.tsv')"
--- a/docs/en/sql-reference/statements/alter/index.md
+++ b/docs/en/sql-reference/statements/alter/index.md
@ -36,6 +36,8 @@ These `ALTER` statements modify entities related to role-based access control:

 [ALTER TABLE ... MODIFY COMMENT](/docs/en/sql-reference/statements/alter/comment.md) statement adds, modifies, or removes comments to the table, regardless if it was set before or not.

+[ALTER NAMED COLLECTION](/docs/en/sql-reference/statements/alter/named-collection.md) statement modifies [Named Collections](/docs/en/operations/named-collections.md).
+
 ## Mutations

 `ALTER` queries that are intended to manipulate table data are implemented with a mechanism called “mutations”, most notably [ALTER TABLE … DELETE](/docs/en/sql-reference/statements/alter/delete.md) and [ALTER TABLE … UPDATE](/docs/en/sql-reference/statements/alter/update.md). They are asynchronous background processes similar to merges in [MergeTree](/docs/en/engines/table-engines/mergetree-family/index.md) tables that to produce new “mutated” versions of parts.
--- a/docs/en/sql-reference/statements/alter/named-collection.md
+++ b/docs/en/sql-reference/statements/alter/named-collection.md
@ -0,0 +1,30 @@
+---
+slug: /en/sql-reference/statements/alter/named-collection
+sidebar_label: NAMED COLLECTION
+---
+
+# ALTER NAMED COLLECTION
+
+This query intends to modify already existing named collections.
+
+**Syntax**
+
+```sql
+ALTER NAMED COLLECTION [IF EXISTS] name [ON CLUSTER cluster]
+[ SET
+key_name1 = 'some value',
+key_name2 = 'some value',
+key_name3 = 'some value',
+... ] |
+[ DELETE key_name4, key_name5, ... ]
+```
+
+**Example**
+
+```sql
+CREATE NAMED COLLECTION foobar AS a = '1', b = '2';
+
+ALTER NAMED COLLECTION foobar SET a = '2', c = '3';
+
+ALTER NAMED COLLECTION foobar DELETE b;
+```
--- a/docs/en/sql-reference/statements/create/index.md
+++ b/docs/en/sql-reference/statements/create/index.md
@ -8,13 +8,14 @@ sidebar_label: CREATE

 Create queries make a new entity of one of the following kinds:

- [DATABASE](../../../sql-reference/statements/create/database.md)
- [TABLE](../../../sql-reference/statements/create/table.md)
- [VIEW](../../../sql-reference/statements/create/view.md)
- [DICTIONARY](../../../sql-reference/statements/create/dictionary.md)
- [FUNCTION](../../../sql-reference/statements/create/function.md)
- [USER](../../../sql-reference/statements/create/user.md)
- [ROLE](../../../sql-reference/statements/create/role.md)
- [ROW POLICY](../../../sql-reference/statements/create/row-policy.md)
- [QUOTA](../../../sql-reference/statements/create/quota.md)
- [SETTINGS PROFILE](../../../sql-reference/statements/create/settings-profile.md)
+- [DATABASE](/docs/en/sql-reference/statements/create/database.md)
+- [TABLE](/docs/en/sql-reference/statements/create/table.md)
+- [VIEW](/docs/en/sql-reference/statements/create/view.md)
+- [DICTIONARY](/docs/en/sql-reference/statements/create/dictionary.md)
+- [FUNCTION](/docs/en/sql-reference/statements/create/function.md)
+- [USER](/docs/en/sql-reference/statements/create/user.md)
+- [ROLE](/docs/en/sql-reference/statements/create/role.md)
+- [ROW POLICY](/docs/en/sql-reference/statements/create/row-policy.md)
+- [QUOTA](/docs/en/sql-reference/statements/create/quota.md)
+- [SETTINGS PROFILE](/docs/en/sql-reference/statements/create/settings-profile.md)
+- [NAMED COLLECTION](/docs/en/sql-reference/statements/create/named-collection.md)
--- a/docs/en/sql-reference/statements/create/named-collection.md
+++ b/docs/en/sql-reference/statements/create/named-collection.md
@ -0,0 +1,34 @@
+---
+slug: /en/sql-reference/statements/create/named-collection
+sidebar_label: NAMED COLLECTION
+---
+
+# CREATE NAMED COLLECTION
+
+Creates a new named collection.
+
+**Syntax**
+
+```sql
+CREATE NAMED COLLECTION [IF NOT EXISTS] name [ON CLUSTER cluster] AS
+key_name1 = 'some value',
+key_name2 = 'some value',
+key_name3 = 'some value',
+...
+```
+
+**Example**
+
+```sql
+CREATE NAMED COLLECTION foobar AS a = '1', b = '2';
+```
+
+**Related statements**
+
+- [CREATE NAMED COLLECTION](https://clickhouse.com/docs/en/sql-reference/statements/alter/named-collection)
+- [DROP NAMED COLLECTION](https://clickhouse.com/docs/en/sql-reference/statements/drop#drop-function)
+
+
+**See Also**
+
+- [Named collections guide](/docs/en/operations/named-collections.md)
--- a/docs/en/sql-reference/statements/drop.md
+++ b/docs/en/sql-reference/statements/drop.md
@ -119,3 +119,20 @@ DROP FUNCTION [IF EXISTS] function_name [on CLUSTER cluster]
 CREATE FUNCTION linear_equation AS (x, k, b) -> k*x + b;
 DROP FUNCTION linear_equation;
 ```
+
+## DROP NAMED COLLECTION
+
+Deletes a named collection.
+
+**Syntax**
+
+``` sql
+DROP NAMED COLLECTION [IF EXISTS] name [on CLUSTER cluster]
+```
+
+**Example**
+
+``` sql
+CREATE NAMED COLLECTION foobar AS a = '1', b = '2';
+DROP NAMED COLLECTION foobar;
+```
--- a/docs/en/sql-reference/statements/system.md
+++ b/docs/en/sql-reference/statements/system.md
@ -314,6 +314,22 @@ Provides possibility to start background fetch tasks from replication queues whi
 SYSTEM START REPLICATION QUEUES [ON CLUSTER cluster_name] [[db.]replicated_merge_tree_family_table_name]
 ```

+### STOP PULLING REPLICATION LOG
+
+Stops loading new entries from replication log to replication queue in a `ReplicatedMergeTree` table.
+
+``` sql
+SYSTEM STOP PULLING REPLICATION LOG [ON CLUSTER cluster_name] [[db.]replicated_merge_tree_family_table_name]
+```
+
+### START PULLING REPLICATION LOG
+
+Cancels `SYSTEM STOP PULLING REPLICATION LOG`.
+
+``` sql
+SYSTEM START PULLING REPLICATION LOG [ON CLUSTER cluster_name] [[db.]replicated_merge_tree_family_table_name]
+```
+
 ### SYNC REPLICA

 Wait until a `ReplicatedMergeTree` table will be synced with other replicas in a cluster, but no more than `receive_timeout` seconds.
--- a/docs/en/sql-reference/table-functions/azureBlobStorageCluster.md
+++ b/docs/en/sql-reference/table-functions/azureBlobStorageCluster.md
@ -0,0 +1,47 @@
+---
+slug: /en/sql-reference/table-functions/azureBlobStorageCluster
+sidebar_position: 55
+sidebar_label: azureBlobStorageCluster
+title: "azureBlobStorageCluster Table Function"
+---
+
+Allows processing files from [Azure Blob Storage](https://azure.microsoft.com/en-us/products/storage/blobs) in parallel from many nodes in a specified cluster. On initiator it creates a connection to all nodes in the cluster, discloses asterisks in S3 file path, and dispatches each file dynamically. On the worker node it asks the initiator about the next task to process and processes it. This is repeated until all tasks are finished.
+This table function is similar to the [s3Cluster function](../../sql-reference/table-functions/s3Cluster.md).
+
+**Syntax**
+
+``` sql
+azureBlobStorageCluster(cluster_name, connection_string|storage_account_url, container_name, blobpath, [account_name, account_key, format, compression, 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.
+- `connection_string|storage_account_url` — connection_string includes account name & key ([Create connection string](https://learn.microsoft.com/en-us/azure/storage/common/storage-configure-connection-string?toc=%2Fazure%2Fstorage%2Fblobs%2Ftoc.json&bc=%2Fazure%2Fstorage%2Fblobs%2Fbreadcrumb%2Ftoc.json#configure-a-connection-string-for-an-azure-storage-account)) or you could also provide the storage account url here and account name & account key as separate parameters (see parameters account_name & account_key)
+- `container_name` - Container name
+- `blobpath` - file path. Supports following wildcards in readonly mode: `*`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc'`, `'def'` — strings.
+- `account_name` - if storage_account_url is used, then account name can be specified here
+- `account_key` - if storage_account_url is used, then account key can be specified here
+- `format` — The [format](../../interfaces/formats.md#formats) of the file.
+- `compression` — Supported values: `none`, `gzip/gz`, `brotli/br`, `xz/LZMA`, `zstd/zst`. By default, it will autodetect compression by file extension. (same as setting to `auto`).
+- `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.
+
+**Returned value**
+
+A table with the specified structure for reading or writing data in the specified file.
+
+**Examples**
+
+Select the count for the file `test_cluster_*.csv`, using all the nodes in the `cluster_simple` cluster:
+
+``` sql
+SELECT count(*) from azureBlobStorageCluster(
+        'cluster_simple', 'http://azurite1:10000/devstoreaccount1', 'test_container', 'test_cluster_count.csv', 'devstoreaccount1',
+        'Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==', 'CSV',
+        'auto', 'key UInt64')
+```
+
+**See Also**
+
+- [AzureBlobStorage engine](../../engines/table-engines/integrations/azureBlobStorage.md)
+- [azureBlobStorage table function](../../sql-reference/table-functions/azureBlobStorage.md)
--- a/docs/en/sql-reference/table-functions/cluster.md
+++ b/docs/en/sql-reference/table-functions/cluster.md
@ -16,14 +16,14 @@ All available clusters are listed in the [system.clusters](../../operations/syst
 **Syntax**

 ``` sql
-cluster('cluster_name', db.table[, sharding_key])
-cluster('cluster_name', db, table[, sharding_key])
-clusterAllReplicas('cluster_name', db.table[, sharding_key])
-clusterAllReplicas('cluster_name', db, table[, sharding_key])
+cluster(['cluster_name', db.table, sharding_key])
+cluster(['cluster_name', db, table, sharding_key])
+clusterAllReplicas(['cluster_name', db.table, sharding_key])
+clusterAllReplicas(['cluster_name', db, table, sharding_key])
 ```
 **Arguments**

- `cluster_name` – Name of a cluster that is used to build a set of addresses and connection parameters to remote and local servers.
+- `cluster_name` – Name of a cluster that is used to build a set of addresses and connection parameters to remote and local servers, set `default` if not specified.
 - `db.table` or `db`, `table` - Name of a database and a table.
 - `sharding_key` - A sharding key. Optional. Needs to be specified if the cluster has more than one shard.

--- a/docs/en/sql-reference/table-functions/file.md
+++ b/docs/en/sql-reference/table-functions/file.md
@ -13,16 +13,18 @@ The `file` function can be used in `SELECT` and `INSERT` queries to read from or
 **Syntax**

 ``` sql
-file(path [,format] [,structure] [,compression])
+file([path_to_archive ::] path [,format] [,structure] [,compression])
 ```

 **Parameters**

 - `path` — The relative path to the file from [user_files_path](/docs/en/operations/server-configuration-parameters/settings.md#server_configuration_parameters-user_files_path). Path to file support following globs in read-only mode: `*`, `?`, `{abc,def}` and `{N..M}` where `N`, `M` — numbers, `'abc', 'def'` — strings.
+- `path_to_archive` - The relative path to zip/tar/7z archive. Path to archive support the same globs as `path`.
 - `format` — The [format](/docs/en/interfaces/formats.md#formats) of the file.
 - `structure` — Structure of the table. Format: `'column1_name column1_type, column2_name column2_type, ...'`.
 - `compression` — The existing compression type when used in a `SELECT` query, or the desired compression type when used in an `INSERT` query.  The supported compression types are `gz`, `br`, `xz`, `zst`, `lz4`, and `bz2`.

+
 **Returned value**

 A table with the specified structure for reading or writing data in the specified file.
@ -128,6 +130,11 @@ file('test.csv', 'CSV', 'column1 UInt32, column2 UInt32, column3 UInt32');
 └─────────┴─────────┴─────────┘
 ```

+Getting data from table in table.csv, located in archive1.zip or/and archive2.zip
+``` sql
+SELECT * FROM file('user_files/archives/archive{1..2}.zip :: table.csv');
+```
+
 ## Globs in Path

 Multiple path components can have globs. For being processed file must exist and match to the whole path pattern (not only suffix or prefix).
--- a/docs/en/sql-reference/table-functions/iceberg.md
+++ b/docs/en/sql-reference/table-functions/iceberg.md
@ -21,7 +21,7 @@ iceberg(url [,aws_access_key_id, aws_secret_access_key] [,format] [,structure])
 - `format` — The [format](/docs/en/interfaces/formats.md/#formats) of the file. By default `Parquet` is used.
 - `structure` — Structure of the table. Format `'column1_name column1_type, column2_name column2_type, ...'`.

-Engine parameters can be specified using [Named Collections](../../operations/named-collections.md)
+Engine parameters can be specified using [Named Collections](/docs/en/operations/named-collections.md).

 **Returned value**

--- a/docs/en/sql-reference/table-functions/remote.md
+++ b/docs/en/sql-reference/table-functions/remote.md
@ -13,10 +13,10 @@ Both functions can be used in `SELECT` and `INSERT` queries.
 ## Syntax

 ``` sql
-remote('addresses_expr', db, table[, 'user'[, 'password'], sharding_key])
-remote('addresses_expr', db.table[, 'user'[, 'password'], sharding_key])
-remoteSecure('addresses_expr', db, table[, 'user'[, 'password'], sharding_key])
-remoteSecure('addresses_expr', db.table[, 'user'[, 'password'], sharding_key])
+remote('addresses_expr', [db, table, 'user'[, 'password'], sharding_key])
+remote('addresses_expr', [db.table, 'user'[, 'password'], sharding_key])
+remoteSecure('addresses_expr', [db, table, 'user'[, 'password'], sharding_key])
+remoteSecure('addresses_expr', [db.table, 'user'[, 'password'], sharding_key])
 ```

 ## Parameters
@ -29,6 +29,8 @@ remoteSecure('addresses_expr', db.table[, 'user'[, 'password'], sharding_key])

    The port is required for an IPv6 address.

+    If only specify this parameter, `db` and `table` will use `system.one` by default.
+
    Type: [String](../../sql-reference/data-types/string.md).

 - `db` — Database name. Type: [String](../../sql-reference/data-types/string.md).
--- a/docs/ru/engines/table-engines/special/buffer.md
+++ b/docs/ru/engines/table-engines/special/buffer.md
@ -9,7 +9,7 @@ sidebar_label: Buffer
 Буферизует записываемые данные в оперативке, периодически сбрасывая их в другую таблицу. При чтении, производится чтение данных одновременно из буфера и из другой таблицы.

 ``` sql
-Buffer(database, table, num_layers, min_time, max_time, min_rows, max_rows, min_bytes, max_bytes)
+Buffer(database, table, num_layers, min_time, max_time, min_rows, max_rows, min_bytes, max_bytes [,flush_time [,flush_rows [,flush_bytes]]])
 ```

 Параметры движка:
--- a/docs/ru/interfaces/formats.md
+++ b/docs/ru/interfaces/formats.md
@ -1353,8 +1353,6 @@ ClickHouse поддерживает настраиваемую точность
 $ cat {filename} | clickhouse-client --query="INSERT INTO {some_table} FORMAT Parquet"
 ```

-Чтобы вставить данные в колонки типа [Nested](../sql-reference/data-types/nested-data-structures/nested.md) в виде массива структур, нужно включить настройку [input_format_parquet_import_nested](../operations/settings/settings.md#input_format_parquet_import_nested).
-
 Чтобы получить данные из таблицы ClickHouse и сохранить их в файл формата Parquet, используйте команду следующего вида:

 ``` bash
@ -1413,8 +1411,6 @@ ClickHouse поддерживает настраиваемую точность
 $ cat filename.arrow | clickhouse-client --query="INSERT INTO some_table FORMAT Arrow"
 ```

-Чтобы вставить данные в колонки типа [Nested](../sql-reference/data-types/nested-data-structures/nested.md) в виде массива структур, нужно включить настройку [input_format_arrow_import_nested](../operations/settings/settings.md#input_format_arrow_import_nested).
-
 ### Вывод данных {#selecting-data-arrow}

 Чтобы получить данные из таблицы ClickHouse и сохранить их в файл формата Arrow, используйте команду следующего вида:
@ -1471,8 +1467,6 @@ ClickHouse поддерживает настраиваемую точность
 $ cat filename.orc | clickhouse-client --query="INSERT INTO some_table FORMAT ORC"
 ```

-Чтобы вставить данные в колонки типа [Nested](../sql-reference/data-types/nested-data-structures/nested.md) в виде массива структур, нужно включить настройку [input_format_orc_import_nested](../operations/settings/settings.md#input_format_orc_import_nested).
-
 ### Вывод данных {#selecting-data-2}

 Чтобы получить данные из таблицы ClickHouse и сохранить их в файл формата ORC, используйте команду следующего вида:
--- a/docs/ru/operations/optimizing-performance/profile-guided-optimization.md
+++ b/docs/ru/operations/optimizing-performance/profile-guided-optimization.md
@ -0,0 +1 @@
+../../../en/operations/optimizing-performance/profile-guided-optimization.md
--- a/docs/ru/operations/settings/query-complexity.md
+++ b/docs/ru/operations/settings/query-complexity.md
@ -311,9 +311,18 @@ FORMAT Null;

 **Подробности**

-При вставке данных, ClickHouse вычисляет количество партиций во вставленном блоке. Если число партиций больше, чем `max_partitions_per_insert_block`, ClickHouse генерирует исключение со следующим текстом:
+При вставке данных ClickHouse проверяет количество партиций во вставляемом блоке. Если количество разделов превышает число `max_partitions_per_insert_block`, ClickHouse либо логирует предупреждение, либо выбрасывает исключение в зависимости от значения `throw_on_max_partitions_per_insert_block`.  Исключения имеют следующий текст:

-> «Too many partitions for single INSERT block (more than» + toString(max_parts) + «). The limit is controlled by ‘max_partitions_per_insert_block’ setting. Large number of partitions is a common misconception. It will lead to severe negative performance impact, including slow server startup, slow INSERT queries and slow SELECT queries. Recommended total number of partitions for a table is under 1000..10000. Please note, that partitioning is not intended to speed up SELECT queries (ORDER BY key is sufficient to make range queries fast). Partitions are intended for data manipulation (DROP PARTITION, etc).»
+> “Too many partitions for a single INSERT block (`partitions_count` partitions, limit is ” + toString(max_partitions) + “). The limit is controlled by the ‘max_partitions_per_insert_block’ setting. A large number of partitions is a common misconception. It will lead to severe negative performance impact, including slow server startup, slow INSERT queries and slow SELECT queries. Recommended total number of partitions for a table is under 1000..10000. Please note, that partitioning is not intended to speed up SELECT queries (ORDER BY key is sufficient to make range queries fast). Partitions are intended for data manipulation (DROP PARTITION, etc).”
+
+## throw_on_max_partitions_per_insert_block {#settings-throw_on_max_partition_per_insert_block}
+
+Позволяет контролировать поведение при достижении `max_partitions_per_insert_block`
+
+- `true`  - Когда вставляемый блок достигает `max_partitions_per_insert_block`, возникает исключение.
+- `false` - Записывает предупреждение при достижении `max_partitions_per_insert_block`.
+
+Значение по умолчанию: `true`

 ## max_sessions_for_user {#max-sessions-per-user}

--- a/docs/ru/operations/settings/settings.md
+++ b/docs/ru/operations/settings/settings.md
@ -238,39 +238,6 @@ ClickHouse применяет настройку в тех случаях, ко

 В случае превышения `input_format_allow_errors_ratio` ClickHouse генерирует исключение.

-## input_format_parquet_import_nested {#input_format_parquet_import_nested}
-
-Включает или отключает возможность вставки данных в колонки типа [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) в виде массива структур  в формате ввода [Parquet](../../interfaces/formats.md#data-format-parquet).
-
-Возможные значения:
-
-   0 — данные не могут быть вставлены в колонки типа `Nested` в виде массива структур.
-   0 — данные могут быть вставлены в колонки типа `Nested` в виде массива структур.
-
-Значение по умолчанию: `0`.
-
-## input_format_arrow_import_nested {#input_format_arrow_import_nested}
-
-Включает или отключает возможность вставки данных в колонки типа [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) в виде массива структур в формате ввода [Arrow](../../interfaces/formats.md#data_types-matching-arrow).
-
-Возможные значения:
-
-   0 — данные не могут быть вставлены в колонки типа `Nested` в виде массива структур.
-   0 — данные могут быть вставлены в колонки типа `Nested` в виде массива структур.
-
-Значение по умолчанию: `0`.
-
-## input_format_orc_import_nested {#input_format_orc_import_nested}
-
-Включает или отключает возможность вставки данных в колонки типа [Nested](../../sql-reference/data-types/nested-data-structures/nested.md) в виде массива структур в формате ввода [ORC](../../interfaces/formats.md#data-format-orc).
-
-Возможные значения:
-
-   0 — данные не могут быть вставлены в колонки типа `Nested` в виде массива структур.
-   0 — данные могут быть вставлены в колонки типа `Nested` в виде массива структур.
-
-Значение по умолчанию: `0`.
-
 ## input_format_values_interpret_expressions {#settings-input_format_values_interpret_expressions}

 Включает или отключает парсер SQL, если потоковый парсер не может проанализировать данные. Этот параметр используется только для формата [Values](../../interfaces/formats.md#data-format-values) при вставке данных. Дополнительные сведения о парсерах читайте в разделе [Синтаксис](../../sql-reference/syntax.md).
@ -4213,3 +4180,29 @@ SELECT *, timezone() FROM test_tz WHERE d = '2000-01-01 00:00:00' SETTINGS sessi
 - Запрос: `SELECT * FROM file('sample.csv')`

 Если чтение и обработка `sample.csv` прошли успешно, файл будет переименован в `processed_sample_1683473210851438.csv`.
+
+## precise_float_parsing {#precise_float_parsing}
+
+Позволяет выбрать алгоритм, используемый при парсинге [Float32/Float64](../../sql-reference/data-types/float.md):
+* Если установлено значение `1`, то используется точный метод. Он более медленный, но всегда возвращает число, наиболее близкое к входному значению.
+* В противном случае используется быстрый метод (поведение по умолчанию). Обычно результат его работы совпадает с результатом, полученным точным методом, однако в редких случаях он может отличаться на 1 или 2 наименее значимых цифры.
+
+Возможные значения: `0`, `1`.
+
+Значение по умолчанию: `0`.
+
+Пример:
+
+```sql
+SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 0;
+
+┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
+│  1.7090999999999998 │       15008753.000000002 │
+└─────────────────────┴──────────────────────────┘
+
+SELECT toFloat64('1.7091'), toFloat64('1.5008753E7') SETTINGS precise_float_parsing = 1;
+
+┌─toFloat64('1.7091')─┬─toFloat64('1.5008753E7')─┐
+│              1.7091 │                 15008753 │
+└─────────────────────┴──────────────────────────┘
+```
--- a/docs/zh/engines/table-engines/special/buffer.md
+++ b/docs/zh/engines/table-engines/special/buffer.md
@ -5,7 +5,7 @@ slug: /zh/engines/table-engines/special/buffer

 缓冲数据写入 RAM 中，周期性地将数据刷新到另一个表。在读取操作时，同时从缓冲区和另一个表读取数据。

-    Buffer(database, table, num_layers, min_time, max_time, min_rows, max_rows, min_bytes, max_bytes)
+    Buffer(database, table, num_layers, min_time, max_time, min_rows, max_rows, min_bytes, max_bytes [,flush_time [,flush_rows [,flush_bytes]]])

 引擎的参数：database，table - 要刷新数据的表。可以使用返回字符串的常量表达式而不是数据库名称。 num_layers - 并行层数。在物理上，该表将表示为 num_layers 个独立缓冲区。建议值为16。min_time，max_time，min_rows，max_rows，min_bytes，max_bytes - 从缓冲区刷新数据的条件。

--- a/docs/zh/operations/optimizing-performance/profile-guided-optimization.md
+++ b/docs/zh/operations/optimizing-performance/profile-guided-optimization.md
@ -0,0 +1 @@
+../../../en/operations/optimizing-performance/profile-guided-optimization.md
--- a/packages/clickhouse-server.yaml
+++ b/packages/clickhouse-server.yaml
@ -55,6 +55,9 @@ contents:
 - src: clickhouse
  dst: /usr/bin/clickhouse-keeper
  type: symlink
+- src: clickhouse
+  dst: /usr/bin/clickhouse-keeper-client
+  type: symlink
 - src: root/usr/bin/clickhouse-report
  dst: /usr/bin/clickhouse-report
 - src: root/usr/bin/clickhouse-server
--- a/programs/keeper-client/Commands.cpp
+++ b/programs/keeper-client/Commands.cpp
@ -1,6 +1,5 @@

 #include "Commands.h"
-#include <queue>
 #include "KeeperClient.h"


@ -25,18 +24,8 @@ void LSCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) con
    else
        path = client->cwd;

-    auto children = client->zookeeper->getChildren(path);
-    std::sort(children.begin(), children.end());
-
-    bool need_space = false;
-    for (const auto & child : children)
-    {
-        if (std::exchange(need_space, true))
-            std::cout << " ";
-
-        std::cout << child;
-    }
-
+    for (const auto & child : client->zookeeper->getChildren(path))
+        std::cout << child << " ";
    std::cout << "\n";
 }

@ -88,7 +77,7 @@ void SetCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) co
        client->zookeeper->set(
            client->getAbsolutePath(query->args[0].safeGet<String>()),
            query->args[1].safeGet<String>(),
-            static_cast<Int32>(query->args[2].safeGet<Int64>()));
+            static_cast<Int32>(query->args[2].get<Int32>()));
 }

 bool CreateCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
@ -141,173 +130,6 @@ void GetCommand::execute(const ASTKeeperQuery * query, KeeperClient * client) co
    std::cout << client->zookeeper->get(client->getAbsolutePath(query->args[0].safeGet<String>())) << "\n";
 }

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

 bool FourLetterWordCommand::parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const
--- a/programs/keeper-client/Commands.h
+++ b/programs/keeper-client/Commands.h
@ -21,12 +21,6 @@ public:
    virtual String getName() const = 0;

    virtual ~IKeeperClientCommand() = default;
-
-    String generateHelpString() const
-    {
-        return fmt::vformat(getHelpMessage(), fmt::make_format_args(getName()));
-    }
-
 };

 using Command = std::shared_ptr<IKeeperClientCommand>;
@ -40,7 +34,7 @@ class LSCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} [path] -- Lists the nodes for the given path (default: cwd)"; }
+    String getHelpMessage() const override { return "ls [path] -- Lists the nodes for the given path (default: cwd)"; }
 };

 class CDCommand : public IKeeperClientCommand
@ -51,7 +45,7 @@ class CDCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} [path] -- Change the working path (default `.`)"; }
+    String getHelpMessage() const override { return "cd [path] -- Change the working path (default `.`)"; }
 };

 class SetCommand : public IKeeperClientCommand
@ -64,7 +58,7 @@ class SetCommand : public IKeeperClientCommand

    String getHelpMessage() const override
    {
-        return "{} <path> <value> [version] -- Updates the node's value. Only update if version matches (default: -1)";
+        return "set <path> <value> [version] -- Updates the node's value. Only update if version matches (default: -1)";
    }
 };

@ -76,7 +70,7 @@ class CreateCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} <path> <value> -- Creates new node"; }
+    String getHelpMessage() const override { return "create <path> <value> -- Creates new node"; }
 };

 class GetCommand : public IKeeperClientCommand
@ -87,63 +81,9 @@ class GetCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} <path> -- Returns the node's value"; }
+    String getHelpMessage() const override { return "get <path> -- Returns the node's value"; }
 };

-class GetStatCommand : public IKeeperClientCommand
-{
-    String getName() const override { return "get_stat"; }
-
-    bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
-
-    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
-
-    String getHelpMessage() const override { return "{} [path] -- Returns the node's stat (default `.`)"; }
-};
-
-class FindSuperNodes : public IKeeperClientCommand
-{
-    String getName() const override { return "find_super_nodes"; }
-
-    bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
-
-    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
-
-    String getHelpMessage() const override
-    {
-        return "{} <threshold> [path] -- Finds nodes with number of children larger than some threshold for the given path (default `.`)";
-    }
-};
-
-class DeleteStableBackups : public IKeeperClientCommand
-{
-    String getName() const override { return "delete_stable_backups"; }
-
-    bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
-
-    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
-
-    String getHelpMessage() const override
-    {
-        return "{} -- Deletes ClickHouse nodes used for backups that are now inactive";
-    }
-};
-
-class FindBigFamily : public IKeeperClientCommand
-{
-    String getName() const override { return "find_big_family"; }
-
-    bool parse(IParser::Pos & pos, std::shared_ptr<ASTKeeperQuery> & node, Expected & expected) const override;
-
-    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;
-
-    String getHelpMessage() const override
-    {
-        return "{} [path] [n] -- Returns the top n nodes with the biggest family in the subtree (default path = `.` and n = 10)";
-    }
-};
-
-
 class RMCommand : public IKeeperClientCommand
 {
    String getName() const override { return "rm"; }
@ -152,7 +92,7 @@ class RMCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} <path> -- Remove the node"; }
+    String getHelpMessage() const override { return "remove <path> -- Remove the node"; }
 };

 class RMRCommand : public IKeeperClientCommand
@ -163,7 +103,7 @@ class RMRCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} <path> -- Recursively deletes path. Confirmation required"; }
+    String getHelpMessage() const override { return "rmr <path> -- Recursively deletes path. Confirmation required"; }
 };

 class HelpCommand : public IKeeperClientCommand
@ -174,7 +114,7 @@ class HelpCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} -- Prints this message"; }
+    String getHelpMessage() const override { return "help -- Prints this message"; }
 };

 class FourLetterWordCommand : public IKeeperClientCommand
@ -185,7 +125,7 @@ class FourLetterWordCommand : public IKeeperClientCommand

    void execute(const ASTKeeperQuery * query, KeeperClient * client) const override;

-    String getHelpMessage() const override { return "{} <command> -- Executes four-letter-word command"; }
+    String getHelpMessage() const override { return "flwc <command> -- Executes four-letter-word command"; }
 };

 }
--- a/programs/keeper-client/KeeperClient.cpp
+++ b/programs/keeper-client/KeeperClient.cpp
@ -131,7 +131,7 @@ void KeeperClient::defineOptions(Poco::Util::OptionSet & options)
            .binding("host"));

    options.addOption(
-        Poco::Util::Option("port", "p", "server port. default `2181`")
+        Poco::Util::Option("port", "p", "server port. default `9181`")
            .argument("<port>")
            .binding("port"));

@ -177,10 +177,6 @@ void KeeperClient::initialize(Poco::Util::Application & /* self */)
        std::make_shared<SetCommand>(),
        std::make_shared<CreateCommand>(),
        std::make_shared<GetCommand>(),
-        std::make_shared<GetStatCommand>(),
-        std::make_shared<FindSuperNodes>(),
-        std::make_shared<DeleteStableBackups>(),
-        std::make_shared<FindBigFamily>(),
        std::make_shared<RMCommand>(),
        std::make_shared<RMRCommand>(),
        std::make_shared<HelpCommand>(),
@ -270,8 +266,16 @@ void KeeperClient::runInteractive()

    LineReader::Patterns query_extenders = {"\\"};
    LineReader::Patterns query_delimiters = {};
+    char word_break_characters[] = " \t\v\f\a\b\r\n/";

-    ReplxxLineReader lr(suggest, history_file, false, query_extenders, query_delimiters, {});
+    ReplxxLineReader lr(
+        suggest,
+        history_file,
+        /* multiline= */ false,
+        query_extenders,
+        query_delimiters,
+        word_break_characters,
+        /* highlighter_= */ {});
    lr.enableBracketedPaste();

    while (true)
@ -303,7 +307,7 @@ int KeeperClient::main(const std::vector<String> & /* args */)
    }

    auto host = config().getString("host", "localhost");
-    auto port = config().getString("port", "2181");
+    auto port = config().getString("port", "9181");
    zk_args.hosts = {host + ":" + port};
    zk_args.connection_timeout_ms = config().getInt("connection-timeout", 10) * 1000;
    zk_args.session_timeout_ms = config().getInt("session-timeout", 10) * 1000;
--- a/programs/keeper-client/Parser.cpp
+++ b/programs/keeper-client/Parser.cpp
@ -58,7 +58,6 @@ bool KeeperParser::parseImpl(Pos & pos, ASTPtr & node, Expected & expected)
        return false;

    String command_name(pos->begin, pos->end);
-    std::transform(command_name.begin(), command_name.end(), command_name.begin(), [](unsigned char c) { return std::tolower(c); });
    Command command;

    auto iter = KeeperClient::commands.find(command_name);
--- a/programs/keeper/Keeper.cpp
+++ b/programs/keeper/Keeper.cpp
@ -288,13 +288,27 @@ try
    std::string path;

    if (config().has("keeper_server.storage_path"))
+    {
        path = config().getString("keeper_server.storage_path");
+    }
+    else if (std::filesystem::is_directory(std::filesystem::path{config().getString("path", DBMS_DEFAULT_PATH)} / "coordination"))
+    {
+        throw Exception(ErrorCodes::NO_ELEMENTS_IN_CONFIG,
+                        "By default 'keeper.storage_path' could be assigned to {}, but the directory {} already exists. Please specify 'keeper.storage_path' in the keeper configuration explicitly",
+                        KEEPER_DEFAULT_PATH, String{std::filesystem::path{config().getString("path", DBMS_DEFAULT_PATH)} / "coordination"});
+    }
    else if (config().has("keeper_server.log_storage_path"))
+    {
        path = std::filesystem::path(config().getString("keeper_server.log_storage_path")).parent_path();
+    }
    else if (config().has("keeper_server.snapshot_storage_path"))
+    {
        path = std::filesystem::path(config().getString("keeper_server.snapshot_storage_path")).parent_path();
+    }
    else
-        path = std::filesystem::path{KEEPER_DEFAULT_PATH};
+    {
+        path = KEEPER_DEFAULT_PATH;
+    }

    std::filesystem::create_directories(path);

@ -330,6 +344,7 @@ try
    auto global_context = Context::createGlobal(shared_context.get());

    global_context->makeGlobalContext();
+    global_context->setApplicationType(Context::ApplicationType::KEEPER);
    global_context->setPath(path);
    global_context->setRemoteHostFilter(config());

@ -365,7 +380,7 @@ try
    }

    /// Initialize keeper RAFT. Do nothing if no keeper_server in config.
-    global_context->initializeKeeperDispatcher(/* start_async = */ true);
+    global_context->initializeKeeperDispatcher(/* start_async = */ false);
    FourLetterCommandFactory::registerCommands(*global_context->getKeeperDispatcher());

    auto config_getter = [&] () -> const Poco::Util::AbstractConfiguration &
--- a/programs/main.cpp
+++ b/programs/main.cpp
@ -466,6 +466,11 @@ int main(int argc_, char ** argv_)
    checkHarmfulEnvironmentVariables(argv_);
 #endif

+    /// This is used for testing. For example,
+    /// clickhouse-local should be able to run a simple query without throw/catch.
+    if (getenv("CLICKHOUSE_TERMINATE_ON_ANY_EXCEPTION")) // NOLINT(concurrency-mt-unsafe)
+        DB::terminate_on_any_exception = true;
+
    /// Reset new handler to default (that throws std::bad_alloc)
    /// It is needed because LLVM library clobbers it.
    std::set_new_handler(nullptr);
--- a/programs/server/Server.cpp
+++ b/programs/server/Server.cpp
@ -1650,6 +1650,7 @@ try
        database_catalog.initializeAndLoadTemporaryDatabase();
        loadMetadataSystem(global_context);
        maybeConvertSystemDatabase(global_context);
+        startupSystemTables();
        /// After attaching system databases we can initialize system log.
        global_context->initializeSystemLogs();
        global_context->setSystemZooKeeperLogAfterInitializationIfNeeded();
@ -1668,7 +1669,6 @@ try
        /// Then, load remaining databases
        loadMetadata(global_context, default_database);
        convertDatabasesEnginesIfNeed(global_context);
-        startupSystemTables();
        database_catalog.startupBackgroundCleanup();
        /// After loading validate that default database exists
        database_catalog.assertDatabaseExists(default_database);
--- a/programs/server/config.d/clusters.xml
+++ b/programs/server/config.d/clusters.xml
@ -0,0 +1 @@
+../../../tests/config/config.d/clusters.xml
--- a/rust/Cargo.lock
+++ b/rust/Cargo.lock
@ -78,6 +78,55 @@ dependencies = [
 "libc",
 ]

+[[package]]
+name = "anstream"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ca84f3628370c59db74ee214b3263d58f9aadd9b4fe7e711fd87dc452b7f163"
+dependencies = [
+ "anstyle",
+ "anstyle-parse",
+ "anstyle-query",
+ "anstyle-wincon",
+ "colorchoice",
+ "is-terminal",
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a30da5c5f2d5e72842e00bcb57657162cdabef0931f40e2deb9b4140440cecd"
+
+[[package]]
+name = "anstyle-parse"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "938874ff5980b03a87c5524b3ae5b59cf99b1d6bc836848df7bc5ada9643c333"
+dependencies = [
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle-query"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5ca11d4be1bab0c8bc8734a9aa7bf4ee8316d462a08c6ac5052f888fef5b494b"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "180abfa45703aebe0093f79badacc01b8fd4ea2e35118747e5811127f926e188"
+dependencies = [
+ "anstyle",
+ "windows-sys",
+]
+
 [[package]]
 name = "anyhow"
 version = "1.0.72"
@ -89,9 +138,9 @@ dependencies = [

 [[package]]
 name = "ariadne"
-version = "0.2.0"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "367fd0ad87307588d087544707bc5fbf4805ded96c7db922b70d368fa1cb5702"
+checksum = "72fe02fc62033df9ba41cba57ee19acf5e742511a140c7dbc3a873e19a19a1bd"
 dependencies = [
 "unicode-width",
 "yansi",
@ -142,6 +191,12 @@ version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"

+[[package]]
+name = "bitflags"
+version = "2.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "630be753d4e58660abd17930c71b647fe46c27ea6b63cc59e1e3851406972e42"
+
 [[package]]
 name = "blake3"
 version = "1.4.1"
@ -204,7 +259,7 @@ version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "23170228b96236b5a7299057ac284a321457700bc8c41a4476052f0f4ba5349d"
 dependencies = [
- "hashbrown 0.12.3",
+ "hashbrown",
 "stacker",
 ]

@ -218,6 +273,12 @@ dependencies = [
 "unicode-width",
 ]

+[[package]]
+name = "colorchoice"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
+
 [[package]]
 name = "constant_time_eq"
 version = "0.3.0"
@ -488,21 +549,36 @@ checksum = "a26ae43d7bcc3b814de94796a5e736d4029efb0ee900c12e2d54c993ad1a1e07"

 [[package]]
 name = "enum-as-inner"
-version = "0.5.1"
+version = "0.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c9720bba047d567ffc8a3cba48bf19126600e249ab7f128e9233e6376976a116"
+checksum = "5ffccbb6966c05b32ef8fbac435df276c4ae4d3dc55a8cd0eb9745e6c12f546a"
 dependencies = [
 "heck",
 "proc-macro2",
 "quote",
- "syn 1.0.109",
+ "syn 2.0.27",
 ]

 [[package]]
-name = "equivalent"
-version = "1.0.1"
+name = "errno"
+version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5443807d6dff69373d433ab9ef5378ad8df50ca6298caf15de6e52e24aaf54d5"
+checksum = "6b30f669a7961ef1631673d2766cc92f52d64f7ef354d4fe0ddfd30ed52f0f4f"
+dependencies = [
+ "errno-dragonfly",
+ "libc",
+ "windows-sys",
+]
+
+[[package]]
+name = "errno-dragonfly"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "aa68f1b12764fab894d2755d2518754e71b4fd80ecfb822714a1206c2aab39bf"
+dependencies = [
+ "cc",
+ "libc",
+]

 [[package]]
 name = "fnv"
@ -555,12 +631,6 @@ dependencies = [
 "ahash",
 ]

-[[package]]
-name = "hashbrown"
-version = "0.14.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c6201b9ff9fd90a5a3bac2e56a830d0caa509576f0e503818ee82c181b3437a"
-
 [[package]]
 name = "heck"
 version = "0.4.1"
@ -603,13 +673,14 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"

 [[package]]
-name = "indexmap"
-version = "2.0.0"
+name = "is-terminal"
+version = "0.4.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d5477fe2230a79769d8dc68e0eabf5437907c0457a5614a9e8dddb67f65eb65d"
+checksum = "cb0889898416213fab133e1d33a0e5858a48177452750691bde3666d0fdbaf8b"
 dependencies = [
- "equivalent",
- "hashbrown 0.14.0",
+ "hermit-abi",
+ "rustix",
+ "windows-sys",
 ]

 [[package]]
@ -621,6 +692,15 @@ dependencies = [
 "either",
 ]

+[[package]]
+name = "itertools"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b1c173a5686ce8bfa551b3563d0c2170bf24ca44da99c7ca4bfdab5418c3fe57"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.9"
@ -657,6 +737,12 @@ dependencies = [
 "cc",
 ]

+[[package]]
+name = "linux-raw-sys"
+version = "0.4.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57bcfdad1b858c2db7c38303a6d2ad4dfaf5eb53dfeb0910128b2c26d6158503"
+
 [[package]]
 name = "log"
 version = "0.4.19"
@ -708,7 +794,7 @@ version = "0.24.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fa52e972a9a719cecb6864fb88568781eb706bac2cd1d4f04a648542dbf78069"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
 "cfg-if",
 "libc",
 ]
@ -720,7 +806,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f346ff70e7dbfd675fe90590b92d59ef2de15a8779ae305ebcbfd3f0caf59be4"
 dependencies = [
 "autocfg",
- "bitflags",
+ "bitflags 1.3.2",
 "cfg-if",
 "libc",
 "memoffset 0.6.5",
@ -787,31 +873,55 @@ dependencies = [
 ]

 [[package]]
-name = "prql-compiler"
-version = "0.8.1"
+name = "prql-ast"
+version = "0.9.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c99b52154002ac7f286dd2293c2f8d4e30526c1d396b14deef5ada1deef3c9ff"
+checksum = "71194e75f14dbe7debdf2b5eca0812c978021a1bd23d6fe1da98b58e407e035a"
 dependencies = [
+ "enum-as-inner",
+ "semver",
+ "serde",
+ "strum",
+]
+
+[[package]]
+name = "prql-compiler"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5ff28e838b1be4227cc567a75c11caa3be25c5015f0e5fd21279c06e944ba44f"
+dependencies = [
+ "anstream",
 "anyhow",
 "ariadne",
- "chumsky",
 "csv",
 "enum-as-inner",
- "itertools",
- "lazy_static",
+ "itertools 0.11.0",
 "log",
 "once_cell",
+ "prql-ast",
+ "prql-parser",
 "regex",
 "semver",
 "serde",
 "serde_json",
- "serde_yaml",
 "sqlformat",
 "sqlparser",
 "strum",
 "strum_macros",
 ]

+[[package]]
+name = "prql-parser"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3182e2ef0465a960eb02519b18768e39123d3c3a0037a2d2934055a3ef901870"
+dependencies = [
+ "chumsky",
+ "itertools 0.11.0",
+ "prql-ast",
+ "semver",
+]
+
 [[package]]
 name = "psm"
 version = "0.1.21"
@ -858,7 +968,7 @@ version = "0.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fb5a58c1855b4b6819d59012155603f0b22ad30cad752600aadfcb695265519a"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
 ]

 [[package]]
@ -907,6 +1017,19 @@ version = "0.1.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d626bb9dae77e28219937af045c257c28bfd3f69333c512553507f5f9798cb76"

+[[package]]
+name = "rustix"
+version = "0.38.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ee020b1716f0a80e2ace9b03441a749e402e86712f15f16fe8a8f75afac732f"
+dependencies = [
+ "bitflags 2.3.3",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys",
+]
+
 [[package]]
 name = "rustversion"
 version = "1.0.14"
@ -971,19 +1094,6 @@ dependencies = [
 "serde",
 ]

-[[package]]
-name = "serde_yaml"
-version = "0.9.25"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1a49e178e4452f45cb61d0cd8cebc1b0fafd3e41929e996cef79aa3aca91f574"
-dependencies = [
- "indexmap",
- "itoa",
- "ryu",
- "serde",
- "unsafe-libyaml",
-]
-
 [[package]]
 name = "skim"
 version = "0.10.4"
@ -991,7 +1101,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e5d28de0a6cb2cdd83a076f1de9d965b973ae08b244df1aa70b432946dda0f32"
 dependencies = [
 "beef",
- "bitflags",
+ "bitflags 1.3.2",
 "chrono",
 "crossbeam",
 "defer-drop",
@ -1015,16 +1125,16 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0c12bc9199d1db8234678b7051747c07f517cdcf019262d1847b94ec8b1aee3e"
 dependencies = [
- "itertools",
+ "itertools 0.10.5",
 "nom",
 "unicode_categories",
 ]

 [[package]]
 name = "sqlparser"
-version = "0.33.0"
+version = "0.36.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "355dc4d4b6207ca8a3434fc587db0a8016130a574dbcdbfb93d7f7b5bc5b211a"
+checksum = "2eaa1e88e78d2c2460d78b7dc3f0c08dbb606ab4222f9aff36f420d36e307d87"
 dependencies = [
 "log",
 "serde",
@ -1051,24 +1161,24 @@ checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"

 [[package]]
 name = "strum"
-version = "0.24.1"
+version = "0.25.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "063e6045c0e62079840579a7e47a355ae92f60eb74daaf156fb1e84ba164e63f"
+checksum = "290d54ea6f91c969195bdbcd7442c8c2a2ba87da8bf60a7ee86a235d4bc1e125"
 dependencies = [
 "strum_macros",
 ]

 [[package]]
 name = "strum_macros"
-version = "0.24.3"
+version = "0.25.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e385be0d24f186b4ce2f9982191e7101bb737312ad61c1f2f984f34bcf85d59"
+checksum = "6069ca09d878a33f883cc06aaa9718ede171841d3832450354410b718b097232"
 dependencies = [
 "heck",
 "proc-macro2",
 "quote",
 "rustversion",
- "syn 1.0.109",
+ "syn 2.0.27",
 ]

 [[package]]
@ -1191,7 +1301,7 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5e19c6ab038babee3d50c8c12ff8b910bdb2196f62278776422f50390d8e53d8"
 dependencies = [
- "bitflags",
+ "bitflags 1.3.2",
 "lazy_static",
 "log",
 "nix 0.24.3",
@ -1223,12 +1333,6 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "39ec24b3121d976906ece63c9daad25b85969647682eee313cb5779fdd69e14e"

-[[package]]
-name = "unsafe-libyaml"
-version = "0.2.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f28467d3e1d3c6586d8f25fa243f544f5800fec42d97032474e17222c2b75cfa"
-
 [[package]]
 name = "utf8parse"
 version = "0.2.1"
@ -1368,6 +1472,15 @@ dependencies = [
 "windows-targets",
 ]

+[[package]]
+name = "windows-sys"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
+dependencies = [
+ "windows-targets",
+]
+
 [[package]]
 name = "windows-targets"
 version = "0.48.1"
--- a/rust/prql/Cargo.toml
+++ b/rust/prql/Cargo.toml
@ -1,12 +1,12 @@
 [package]
+edition = "2021"
 name = "_ch_rust_prql"
 version = "0.1.0"
-edition = "2021"

 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

 [dependencies]
-prql-compiler = "0.8.1"
+prql-compiler = "0.9.3"
 serde_json = "1.0"

 [lib]
--- a/src/Access/AccessControl.cpp
+++ b/src/Access/AccessControl.cpp
@ -6,6 +6,7 @@
 #include <Access/DiskAccessStorage.h>
 #include <Access/LDAPAccessStorage.h>
 #include <Access/ContextAccess.h>
+#include <Access/EnabledSettings.h>
 #include <Access/EnabledRolesInfo.h>
 #include <Access/RoleCache.h>
 #include <Access/RowPolicyCache.h>
@ -729,6 +730,14 @@ std::shared_ptr<const EnabledRoles> AccessControl::getEnabledRoles(
 }


+std::shared_ptr<const EnabledRolesInfo> AccessControl::getEnabledRolesInfo(
+    const std::vector<UUID> & current_roles,
+    const std::vector<UUID> & current_roles_with_admin_option) const
+{
+    return getEnabledRoles(current_roles, current_roles_with_admin_option)->getRolesInfo();
+}
+
+
 std::shared_ptr<const EnabledRowPolicies> AccessControl::getEnabledRowPolicies(const UUID & user_id, const boost::container::flat_set<UUID> & enabled_roles) const
 {
    return row_policy_cache->getEnabledRowPolicies(user_id, enabled_roles);
@ -772,6 +781,15 @@ std::shared_ptr<const EnabledSettings> AccessControl::getEnabledSettings(
    return settings_profiles_cache->getEnabledSettings(user_id, settings_from_user, enabled_roles, settings_from_enabled_roles);
 }

+std::shared_ptr<const SettingsProfilesInfo> AccessControl::getEnabledSettingsInfo(
+    const UUID & user_id,
+    const SettingsProfileElements & settings_from_user,
+    const boost::container::flat_set<UUID> & enabled_roles,
+    const SettingsProfileElements & settings_from_enabled_roles) const
+{
+    return getEnabledSettings(user_id, settings_from_user, enabled_roles, settings_from_enabled_roles)->getInfo();
+}
+
 std::shared_ptr<const SettingsProfilesInfo> AccessControl::getSettingsProfileInfo(const UUID & profile_id)
 {
    return settings_profiles_cache->getSettingsProfileInfo(profile_id);
--- a/src/Access/AccessControl.h
+++ b/src/Access/AccessControl.h
@ -29,6 +29,7 @@ class ContextAccessParams;
 struct User;
 using UserPtr = std::shared_ptr<const User>;
 class EnabledRoles;
+struct EnabledRolesInfo;
 class RoleCache;
 class EnabledRowPolicies;
 class RowPolicyCache;
@ -187,6 +188,10 @@ public:
        const std::vector<UUID> & current_roles,
        const std::vector<UUID> & current_roles_with_admin_option) const;

+    std::shared_ptr<const EnabledRolesInfo> getEnabledRolesInfo(
+        const std::vector<UUID> & current_roles,
+        const std::vector<UUID> & current_roles_with_admin_option) const;
+
    std::shared_ptr<const EnabledRowPolicies> getEnabledRowPolicies(
        const UUID & user_id,
        const boost::container::flat_set<UUID> & enabled_roles) const;
@ -209,6 +214,12 @@ public:
        const boost::container::flat_set<UUID> & enabled_roles,
        const SettingsProfileElements & settings_from_enabled_roles) const;

+    std::shared_ptr<const SettingsProfilesInfo> getEnabledSettingsInfo(
+        const UUID & user_id,
+        const SettingsProfileElements & settings_from_user,
+        const boost::container::flat_set<UUID> & enabled_roles,
+        const SettingsProfileElements & settings_from_enabled_roles) const;
+
    std::shared_ptr<const SettingsProfilesInfo> getSettingsProfileInfo(const UUID & profile_id);

    const ExternalAuthenticators & getExternalAuthenticators() const;
--- a/src/Access/Common/AccessType.h
+++ b/src/Access/Common/AccessType.h
@ -168,6 +168,7 @@ enum class AccessType
    M(SYSTEM_TTL_MERGES, "SYSTEM STOP TTL MERGES, SYSTEM START TTL MERGES, STOP TTL MERGES, START TTL MERGES", TABLE, SYSTEM) \
    M(SYSTEM_FETCHES, "SYSTEM STOP FETCHES, SYSTEM START FETCHES, STOP FETCHES, START FETCHES", TABLE, SYSTEM) \
    M(SYSTEM_MOVES, "SYSTEM STOP MOVES, SYSTEM START MOVES, STOP MOVES, START MOVES", TABLE, SYSTEM) \
+    M(SYSTEM_PULLING_REPLICATION_LOG, "SYSTEM STOP PULLING REPLICATION LOG, SYSTEM START PULLING REPLICATION LOG", TABLE, SYSTEM) \
    M(SYSTEM_DISTRIBUTED_SENDS, "SYSTEM STOP DISTRIBUTED SENDS, SYSTEM START DISTRIBUTED SENDS, STOP DISTRIBUTED SENDS, START DISTRIBUTED SENDS", TABLE, SYSTEM_SENDS) \
    M(SYSTEM_REPLICATED_SENDS, "SYSTEM STOP REPLICATED SENDS, SYSTEM START REPLICATED SENDS, STOP REPLICATED SENDS, START REPLICATED SENDS", TABLE, SYSTEM_SENDS) \
    M(SYSTEM_SENDS, "SYSTEM STOP SENDS, SYSTEM START SENDS, STOP SENDS, START SENDS", GROUP, SYSTEM) \
--- a/src/Access/LDAPClient.cpp
+++ b/src/Access/LDAPClient.cpp
@ -18,7 +18,8 @@
 namespace
 {

-template <typename T, typename = std::enable_if_t<std::is_fundamental_v<std::decay_t<T>>>>
+template <typename T>
+requires std::is_fundamental_v<std::decay_t<T>>
 void updateHash(SipHash & hash, const T & value)
 {
    hash.update(value);
--- a/src/Access/tests/gtest_access_rights_ops.cpp
+++ b/src/Access/tests/gtest_access_rights_ops.cpp
@ -51,7 +51,7 @@ TEST(AccessRights, Union)
              "CREATE DICTIONARY, DROP DATABASE, DROP TABLE, DROP VIEW, DROP DICTIONARY, UNDROP TABLE, "
              "TRUNCATE, OPTIMIZE, BACKUP, CREATE ROW POLICY, ALTER ROW POLICY, DROP ROW POLICY, "
              "SHOW ROW POLICIES, SYSTEM MERGES, SYSTEM TTL MERGES, SYSTEM FETCHES, "
-              "SYSTEM MOVES, SYSTEM SENDS, SYSTEM REPLICATION QUEUES, "
+              "SYSTEM MOVES, SYSTEM PULLING REPLICATION LOG, SYSTEM SENDS, SYSTEM REPLICATION QUEUES, "
              "SYSTEM DROP REPLICA, SYSTEM SYNC REPLICA, SYSTEM RESTART REPLICA, "
              "SYSTEM RESTORE REPLICA, SYSTEM WAIT LOADING PARTS, SYSTEM SYNC DATABASE REPLICA, SYSTEM FLUSH DISTRIBUTED, dictGet ON db1.*, GRANT NAMED COLLECTION ADMIN ON db1");
 }
--- a/src/Analyzer/Passes/QueryAnalysisPass.cpp
+++ b/src/Analyzer/Passes/QueryAnalysisPass.cpp
@ -6887,13 +6887,12 @@ void QueryAnalyzer::resolveQuery(const QueryTreeNodePtr & query_node, Identifier
                scope.scope_node->formatASTForErrorMessage());
    }

-    std::erase_if(with_nodes, [](const QueryTreeNodePtr & node)
-    {
-        auto * subquery_node = node->as<QueryNode>();
-        auto * union_node = node->as<UnionNode>();
-
-        return (subquery_node && subquery_node->isCTE()) || (union_node && union_node->isCTE());
-    });
+    /** WITH section can be safely removed, because WITH section only can provide aliases to query expressions
+      * and CTE for other sections to use.
+      *
+      * Example: WITH 1 AS constant, (x -> x + 1) AS lambda, a AS (SELECT * FROM test_table);
+      */
+    query_node_typed.getWith().getNodes().clear();

    for (auto & window_node : query_node_typed.getWindow().getNodes())
    {
@ -6952,9 +6951,6 @@ void QueryAnalyzer::resolveQuery(const QueryTreeNodePtr & query_node, Identifier
                scope.scope_node->formatASTForErrorMessage());
    }

-    if (query_node_typed.hasWith())
-        resolveExpressionNodeList(query_node_typed.getWithNode(), scope, true /*allow_lambda_expression*/, false /*allow_table_expression*/);
-
    if (query_node_typed.getPrewhere())
        resolveExpressionNode(query_node_typed.getPrewhere(), scope, false /*allow_lambda_expression*/, false /*allow_table_expression*/);

@ -7123,13 +7119,6 @@ void QueryAnalyzer::resolveQuery(const QueryTreeNodePtr & query_node, Identifier
                scope.scope_node->formatASTForErrorMessage());
    }

-    /** WITH section can be safely removed, because WITH section only can provide aliases to query expressions
-      * and CTE for other sections to use.
-      *
-      * Example: WITH 1 AS constant, (x -> x + 1) AS lambda, a AS (SELECT * FROM test_table);
-      */
-    query_node_typed.getWith().getNodes().clear();
-
    /** WINDOW section can be safely removed, because WINDOW section can only provide window definition to window functions.
      *
      * Example: SELECT count(*) OVER w FROM test_table WINDOW w AS (PARTITION BY id);
--- a/src/Backups/BackupEntriesCollector.cpp
+++ b/src/Backups/BackupEntriesCollector.cpp
@ -77,10 +77,12 @@ BackupEntriesCollector::BackupEntriesCollector(
    const ASTBackupQuery::Elements & backup_query_elements_,
    const BackupSettings & backup_settings_,
    std::shared_ptr<IBackupCoordination> backup_coordination_,
+    const ReadSettings & read_settings_,
    const ContextPtr & context_)
    : backup_query_elements(backup_query_elements_)
    , backup_settings(backup_settings_)
    , backup_coordination(backup_coordination_)
+    , read_settings(read_settings_)
    , context(context_)
    , on_cluster_first_sync_timeout(context->getConfigRef().getUInt64("backups.on_cluster_first_sync_timeout", 180000))
    , consistent_metadata_snapshot_timeout(context->getConfigRef().getUInt64("backups.consistent_metadata_snapshot_timeout", 600000))
--- a/src/Backups/BackupEntriesCollector.h
+++ b/src/Backups/BackupEntriesCollector.h
@ -30,6 +30,7 @@ public:
    BackupEntriesCollector(const ASTBackupQuery::Elements & backup_query_elements_,
                           const BackupSettings & backup_settings_,
                           std::shared_ptr<IBackupCoordination> backup_coordination_,
+                           const ReadSettings & read_settings_,
                           const ContextPtr & context_);
    ~BackupEntriesCollector();

@ -40,6 +41,7 @@ public:

    const BackupSettings & getBackupSettings() const { return backup_settings; }
    std::shared_ptr<IBackupCoordination> getBackupCoordination() const { return backup_coordination; }
+    const ReadSettings & getReadSettings() const { return read_settings; }
    ContextPtr getContext() const { return context; }

    /// Adds a backup entry which will be later returned by run().
@ -93,6 +95,7 @@ private:
    const ASTBackupQuery::Elements backup_query_elements;
    const BackupSettings backup_settings;
    std::shared_ptr<IBackupCoordination> backup_coordination;
+    const ReadSettings read_settings;
    ContextPtr context;
    std::chrono::milliseconds on_cluster_first_sync_timeout;
    std::chrono::milliseconds consistent_metadata_snapshot_timeout;
--- a/src/Backups/BackupEntryFromImmutableFile.cpp
+++ b/src/Backups/BackupEntryFromImmutableFile.cpp
@ -57,7 +57,7 @@ UInt64 BackupEntryFromImmutableFile::getSize() const
    return *file_size;
 }

-UInt128 BackupEntryFromImmutableFile::getChecksum() const
+UInt128 BackupEntryFromImmutableFile::getChecksum(const ReadSettings & read_settings) const
 {
    {
        std::lock_guard lock{size_and_checksum_mutex};
@ -73,7 +73,7 @@ UInt128 BackupEntryFromImmutableFile::getChecksum() const
        }
    }

-    auto calculated_checksum = BackupEntryWithChecksumCalculation<IBackupEntry>::getChecksum();
+    auto calculated_checksum = BackupEntryWithChecksumCalculation<IBackupEntry>::getChecksum(read_settings);

    {
        std::lock_guard lock{size_and_checksum_mutex};
@ -86,13 +86,13 @@ UInt128 BackupEntryFromImmutableFile::getChecksum() const
    }
 }

-std::optional<UInt128> BackupEntryFromImmutableFile::getPartialChecksum(size_t prefix_length) const
+std::optional<UInt128> BackupEntryFromImmutableFile::getPartialChecksum(size_t prefix_length, const ReadSettings & read_settings) const
 {
    if (prefix_length == 0)
        return 0;

    if (prefix_length >= getSize())
-        return getChecksum();
+        return getChecksum(read_settings);

    /// For immutable files we don't use partial checksums.
    return std::nullopt;
--- a/src/Backups/BackupEntryFromImmutableFile.h
+++ b/src/Backups/BackupEntryFromImmutableFile.h
@ -27,8 +27,8 @@ public:
    std::unique_ptr<SeekableReadBuffer> getReadBuffer(const ReadSettings & read_settings) const override;

    UInt64 getSize() const override;
-    UInt128 getChecksum() const override;
-    std::optional<UInt128> getPartialChecksum(size_t prefix_length) const override;
+    UInt128 getChecksum(const ReadSettings & read_settings) const override;
+    std::optional<UInt128> getPartialChecksum(size_t prefix_length, const ReadSettings & read_settings) const override;

    DataSourceDescription getDataSourceDescription() const override { return data_source_description; }
    bool isEncryptedByDisk() const override { return copy_encrypted; }
--- a/src/Backups/BackupEntryFromSmallFile.cpp
+++ b/src/Backups/BackupEntryFromSmallFile.cpp
@ -11,17 +11,17 @@ namespace DB
 {
 namespace
 {
-    String readFile(const String & file_path)
+    String readFile(const String & file_path, const ReadSettings & read_settings)
    {
-        auto buf = createReadBufferFromFileBase(file_path, /* settings= */ {});
+        auto buf = createReadBufferFromFileBase(file_path, read_settings);
        String s;
        readStringUntilEOF(s, *buf);
        return s;
    }

-    String readFile(const DiskPtr & disk, const String & file_path, bool copy_encrypted)
+    String readFile(const DiskPtr & disk, const String & file_path, const ReadSettings & read_settings, bool copy_encrypted)
    {
-        auto buf = copy_encrypted ? disk->readEncryptedFile(file_path, {}) : disk->readFile(file_path);
+        auto buf = copy_encrypted ? disk->readEncryptedFile(file_path, read_settings) : disk->readFile(file_path, read_settings);
        String s;
        readStringUntilEOF(s, *buf);
        return s;
@ -29,19 +29,19 @@ namespace
 }


-BackupEntryFromSmallFile::BackupEntryFromSmallFile(const String & file_path_)
+BackupEntryFromSmallFile::BackupEntryFromSmallFile(const String & file_path_, const ReadSettings & read_settings_)
    : file_path(file_path_)
    , data_source_description(DiskLocal::getLocalDataSourceDescription(file_path_))
-    , data(readFile(file_path_))
+    , data(readFile(file_path_, read_settings_))
 {
 }

-BackupEntryFromSmallFile::BackupEntryFromSmallFile(const DiskPtr & disk_, const String & file_path_, bool copy_encrypted_)
+BackupEntryFromSmallFile::BackupEntryFromSmallFile(const DiskPtr & disk_, const String & file_path_, const ReadSettings & read_settings_, bool copy_encrypted_)
    : disk(disk_)
    , file_path(file_path_)
    , data_source_description(disk_->getDataSourceDescription())
    , copy_encrypted(copy_encrypted_ && data_source_description.is_encrypted)
-    , data(readFile(disk_, file_path, copy_encrypted))
+    , data(readFile(disk_, file_path, read_settings_, copy_encrypted))
 {
 }

--- a/src/Backups/BackupEntryFromSmallFile.h
+++ b/src/Backups/BackupEntryFromSmallFile.h
@ -13,8 +13,8 @@ using DiskPtr = std::shared_ptr<IDisk>;
 class BackupEntryFromSmallFile : public BackupEntryWithChecksumCalculation<IBackupEntry>
 {
 public:
-    explicit BackupEntryFromSmallFile(const String & file_path_);
-    BackupEntryFromSmallFile(const DiskPtr & disk_, const String & file_path_, bool copy_encrypted_ = false);
+    explicit BackupEntryFromSmallFile(const String & file_path_, const ReadSettings & read_settings_);
+    BackupEntryFromSmallFile(const DiskPtr & disk_, const String & file_path_, const ReadSettings & read_settings_, bool copy_encrypted_ = false);

    std::unique_ptr<SeekableReadBuffer> getReadBuffer(const ReadSettings &) const override;
    UInt64 getSize() const override { return data.size(); }
--- a/src/Backups/BackupEntryWithChecksumCalculation.cpp
+++ b/src/Backups/BackupEntryWithChecksumCalculation.cpp
@ -6,7 +6,7 @@ namespace DB
 {

 template <typename Base>
-UInt128 BackupEntryWithChecksumCalculation<Base>::getChecksum() const
+UInt128 BackupEntryWithChecksumCalculation<Base>::getChecksum(const ReadSettings & read_settings) const
 {
    {
        std::lock_guard lock{checksum_calculation_mutex};
@ -26,7 +26,7 @@ UInt128 BackupEntryWithChecksumCalculation<Base>::getChecksum() const
            }
            else
            {
-                auto read_buffer = this->getReadBuffer(ReadSettings{}.adjustBufferSize(size));
+                auto read_buffer = this->getReadBuffer(read_settings.adjustBufferSize(size));
                HashingReadBuffer hashing_read_buffer(*read_buffer);
                hashing_read_buffer.ignoreAll();
                calculated_checksum = hashing_read_buffer.getHash();
@ -37,23 +37,20 @@ UInt128 BackupEntryWithChecksumCalculation<Base>::getChecksum() const
 }

 template <typename Base>
-std::optional<UInt128> BackupEntryWithChecksumCalculation<Base>::getPartialChecksum(size_t prefix_length) const
+std::optional<UInt128> BackupEntryWithChecksumCalculation<Base>::getPartialChecksum(size_t prefix_length, const ReadSettings & read_settings) const
 {
    if (prefix_length == 0)
        return 0;

    size_t size = this->getSize();
    if (prefix_length >= size)
-        return this->getChecksum();
+        return this->getChecksum(read_settings);

    std::lock_guard lock{checksum_calculation_mutex};

-    ReadSettings read_settings;
-    if (calculated_checksum)
-        read_settings.adjustBufferSize(calculated_checksum ? prefix_length : size);
-
-    auto read_buffer = this->getReadBuffer(read_settings);
+    auto read_buffer = this->getReadBuffer(read_settings.adjustBufferSize(calculated_checksum ? prefix_length : size));
    HashingReadBuffer hashing_read_buffer(*read_buffer);
+
    hashing_read_buffer.ignore(prefix_length);
    auto partial_checksum = hashing_read_buffer.getHash();

--- a/src/Backups/BackupEntryWithChecksumCalculation.h
+++ b/src/Backups/BackupEntryWithChecksumCalculation.h
@ -11,8 +11,8 @@ template <typename Base>
 class BackupEntryWithChecksumCalculation : public Base
 {
 public:
-    UInt128 getChecksum() const override;
-    std::optional<UInt128> getPartialChecksum(size_t prefix_length) const override;
+    UInt128 getChecksum(const ReadSettings & read_settings) const override;
+    std::optional<UInt128> getPartialChecksum(size_t prefix_length, const ReadSettings & read_settings) const override;

 private:
    mutable std::optional<UInt128> calculated_checksum;
--- a/src/Backups/BackupEntryWrappedWith.h
+++ b/src/Backups/BackupEntryWrappedWith.h
@ -17,8 +17,8 @@ public:

    std::unique_ptr<SeekableReadBuffer> getReadBuffer(const ReadSettings & read_settings) const override { return entry->getReadBuffer(read_settings); }
    UInt64 getSize() const override { return entry->getSize(); }
-    UInt128 getChecksum() const override { return entry->getChecksum(); }
-    std::optional<UInt128> getPartialChecksum(size_t prefix_length) const override { return entry->getPartialChecksum(prefix_length); }
+    UInt128 getChecksum(const ReadSettings & read_settings) const override { return entry->getChecksum(read_settings); }
+    std::optional<UInt128> getPartialChecksum(size_t prefix_length, const ReadSettings & read_settings) const override { return entry->getPartialChecksum(prefix_length, read_settings); }
    DataSourceDescription getDataSourceDescription() const override { return entry->getDataSourceDescription(); }
    bool isEncryptedByDisk() const override { return entry->isEncryptedByDisk(); }
    bool isFromFile() const override { return entry->isFromFile(); }
--- a/src/Backups/BackupFactory.h
+++ b/src/Backups/BackupFactory.h
@ -3,6 +3,8 @@
 #include <Backups/IBackup.h>
 #include <Backups/BackupInfo.h>
 #include <Core/Types.h>
+#include <IO/ReadSettings.h>
+#include <IO/WriteSettings.h>
 #include <Parsers/IAST_fwd.h>
 #include <boost/noncopyable.hpp>
 #include <memory>
@ -37,6 +39,8 @@ public:
        std::optional<UUID> backup_uuid;
        bool deduplicate_files = true;
        bool allow_s3_native_copy = true;
+        ReadSettings read_settings;
+        WriteSettings write_settings;
    };

    static BackupFactory & instance();
--- a/src/Backups/BackupFileInfo.cpp
+++ b/src/Backups/BackupFileInfo.cpp
@ -57,12 +57,12 @@ namespace

    /// Calculate checksum for backup entry if it's empty.
    /// Also able to calculate additional checksum of some prefix.
-    ChecksumsForNewEntry calculateNewEntryChecksumsIfNeeded(const BackupEntryPtr & entry, size_t prefix_size)
+    ChecksumsForNewEntry calculateNewEntryChecksumsIfNeeded(const BackupEntryPtr & entry, size_t prefix_size, const ReadSettings & read_settings)
    {
        ChecksumsForNewEntry res;
        /// The partial checksum should be calculated before the full checksum to enable optimization in BackupEntryWithChecksumCalculation.
-        res.prefix_checksum = entry->getPartialChecksum(prefix_size);
-        res.full_checksum = entry->getChecksum();
+        res.prefix_checksum = entry->getPartialChecksum(prefix_size, read_settings);
+        res.full_checksum = entry->getChecksum(read_settings);
        return res;
    }

@ -93,7 +93,12 @@ String BackupFileInfo::describe() const
 }


-BackupFileInfo buildFileInfoForBackupEntry(const String & file_name, const BackupEntryPtr & backup_entry, const BackupPtr & base_backup, Poco::Logger * log)
+BackupFileInfo buildFileInfoForBackupEntry(
+    const String & file_name,
+    const BackupEntryPtr & backup_entry,
+    const BackupPtr & base_backup,
+    const ReadSettings & read_settings,
+    Poco::Logger * log)
 {
    auto adjusted_path = removeLeadingSlash(file_name);

@ -126,7 +131,7 @@ BackupFileInfo buildFileInfoForBackupEntry(const String & file_name, const Backu
        /// File with the same name but smaller size exist in previous backup
        if (check_base == CheckBackupResult::HasPrefix)
        {
-            auto checksums = calculateNewEntryChecksumsIfNeeded(backup_entry, base_backup_file_info->first);
+            auto checksums = calculateNewEntryChecksumsIfNeeded(backup_entry, base_backup_file_info->first, read_settings);
            info.checksum = checksums.full_checksum;

            /// We have prefix of this file in backup with the same checksum.
@ -146,7 +151,7 @@ BackupFileInfo buildFileInfoForBackupEntry(const String & file_name, const Backu
        {
            /// We have full file or have nothing, first of all let's get checksum
            /// of current file
-            auto checksums = calculateNewEntryChecksumsIfNeeded(backup_entry, 0);
+            auto checksums = calculateNewEntryChecksumsIfNeeded(backup_entry, 0, read_settings);
            info.checksum = checksums.full_checksum;

            if (info.checksum == base_backup_file_info->second)
@ -169,7 +174,7 @@ BackupFileInfo buildFileInfoForBackupEntry(const String & file_name, const Backu
    }
    else
    {
-        auto checksums = calculateNewEntryChecksumsIfNeeded(backup_entry, 0);
+        auto checksums = calculateNewEntryChecksumsIfNeeded(backup_entry, 0, read_settings);
        info.checksum = checksums.full_checksum;
    }

@ -188,7 +193,7 @@ BackupFileInfo buildFileInfoForBackupEntry(const String & file_name, const Backu
    return info;
 }

-BackupFileInfos buildFileInfosForBackupEntries(const BackupEntries & backup_entries, const BackupPtr & base_backup, ThreadPool & thread_pool)
+BackupFileInfos buildFileInfosForBackupEntries(const BackupEntries & backup_entries, const BackupPtr & base_backup, const ReadSettings & read_settings, ThreadPool & thread_pool)
 {
    BackupFileInfos infos;
    infos.resize(backup_entries.size());
@ -210,7 +215,7 @@ BackupFileInfos buildFileInfosForBackupEntries(const BackupEntries & backup_entr
            ++num_active_jobs;
        }

-        auto job = [&mutex, &num_active_jobs, &event, &exception, &infos, &backup_entries, &base_backup, &thread_group, i, log](bool async)
+        auto job = [&mutex, &num_active_jobs, &event, &exception, &infos, &backup_entries, &read_settings, &base_backup, &thread_group, i, log](bool async)
        {
            SCOPE_EXIT_SAFE({
                std::lock_guard lock{mutex};
@ -237,7 +242,7 @@ BackupFileInfos buildFileInfosForBackupEntries(const BackupEntries & backup_entr
                        return;
                }

-                infos[i] = buildFileInfoForBackupEntry(name, entry, base_backup, log);
+                infos[i] = buildFileInfoForBackupEntry(name, entry, base_backup, read_settings, log);
            }
            catch (...)
            {
--- a/src/Backups/BackupFileInfo.h
+++ b/src/Backups/BackupFileInfo.h
@ -13,6 +13,7 @@ class IBackupEntry;
 using BackupPtr = std::shared_ptr<const IBackup>;
 using BackupEntryPtr = std::shared_ptr<const IBackupEntry>;
 using BackupEntries = std::vector<std::pair<String, BackupEntryPtr>>;
+struct ReadSettings;


 /// Information about a file stored in a backup.
@ -66,9 +67,9 @@ struct BackupFileInfo
 using BackupFileInfos = std::vector<BackupFileInfo>;

 /// Builds a BackupFileInfo for a specified backup entry.
-BackupFileInfo buildFileInfoForBackupEntry(const String & file_name, const BackupEntryPtr & backup_entry, const BackupPtr & base_backup, Poco::Logger * log);
+BackupFileInfo buildFileInfoForBackupEntry(const String & file_name, const BackupEntryPtr & backup_entry, const BackupPtr & base_backup, const ReadSettings & read_settings, Poco::Logger * log);

 /// Builds a vector of BackupFileInfos for specified backup entries.
-BackupFileInfos buildFileInfosForBackupEntries(const BackupEntries & backup_entries, const BackupPtr & base_backup, ThreadPool & thread_pool);
+BackupFileInfos buildFileInfosForBackupEntries(const BackupEntries & backup_entries, const BackupPtr & base_backup, const ReadSettings & read_settings, ThreadPool & thread_pool);

 }
--- a/src/Backups/BackupIO_Default.cpp
+++ b/src/Backups/BackupIO_Default.cpp
@ -4,17 +4,16 @@
 #include <IO/copyData.h>
 #include <IO/WriteBufferFromFileBase.h>
 #include <IO/ReadBufferFromFileBase.h>
-#include <Interpreters/Context.h>
 #include <Common/logger_useful.h>


 namespace DB
 {

-BackupReaderDefault::BackupReaderDefault(Poco::Logger * log_, const ContextPtr & context_)
+BackupReaderDefault::BackupReaderDefault(const ReadSettings & read_settings_, const WriteSettings & write_settings_, Poco::Logger * log_)
    : log(log_)
-    , read_settings(context_->getBackupReadSettings())
-    , write_settings(context_->getWriteSettings())
+    , read_settings(read_settings_)
+    , write_settings(write_settings_)
    , write_buffer_size(DBMS_DEFAULT_BUFFER_SIZE)
 {
 }
@ -37,10 +36,10 @@ void BackupReaderDefault::copyFileToDisk(const String & path_in_backup, size_t f
    write_buffer->finalize();
 }

-BackupWriterDefault::BackupWriterDefault(Poco::Logger * log_, const ContextPtr & context_)
+BackupWriterDefault::BackupWriterDefault(const ReadSettings & read_settings_, const WriteSettings & write_settings_, Poco::Logger * log_)
    : log(log_)
-    , read_settings(context_->getBackupReadSettings())
-    , write_settings(context_->getWriteSettings())
+    , read_settings(read_settings_)
+    , write_settings(write_settings_)
    , write_buffer_size(DBMS_DEFAULT_BUFFER_SIZE)
 {
 }
--- a/src/Backups/BackupIO_Default.h
+++ b/src/Backups/BackupIO_Default.h
@ -3,7 +3,6 @@
 #include <Backups/BackupIO.h>
 #include <IO/ReadSettings.h>
 #include <IO/WriteSettings.h>
-#include <Interpreters/Context_fwd.h>


 namespace DB
@ -19,7 +18,7 @@ enum class WriteMode;
 class BackupReaderDefault : public IBackupReader
 {
 public:
-    BackupReaderDefault(Poco::Logger * log_, const ContextPtr & context_);
+    BackupReaderDefault(const ReadSettings & read_settings_, const WriteSettings & write_settings_, Poco::Logger * log_);
    ~BackupReaderDefault() override = default;

    /// The function copyFileToDisk() can be much faster than reading the file with readFile() and then writing it to some disk.
@ -46,7 +45,7 @@ protected:
 class BackupWriterDefault : public IBackupWriter
 {
 public:
-    BackupWriterDefault(Poco::Logger * log_, const ContextPtr & context_);
+    BackupWriterDefault(const ReadSettings & read_settings_, const WriteSettings & write_settings_, Poco::Logger * log_);
    ~BackupWriterDefault() override = default;

    bool fileContentsEqual(const String & file_name, const String & expected_file_contents) override;
--- a/src/Backups/BackupIO_Disk.cpp
+++ b/src/Backups/BackupIO_Disk.cpp
@ -8,8 +8,8 @@
 namespace DB
 {

-BackupReaderDisk::BackupReaderDisk(const DiskPtr & disk_, const String & root_path_, const ContextPtr & context_)
-    : BackupReaderDefault(&Poco::Logger::get("BackupReaderDisk"), context_)
+BackupReaderDisk::BackupReaderDisk(const DiskPtr & disk_, const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_)
+    : BackupReaderDefault(read_settings_, write_settings_, &Poco::Logger::get("BackupReaderDisk"))
    , disk(disk_)
    , root_path(root_path_)
    , data_source_description(disk->getDataSourceDescription())
@ -56,8 +56,8 @@ void BackupReaderDisk::copyFileToDisk(const String & path_in_backup, size_t file
 }


-BackupWriterDisk::BackupWriterDisk(const DiskPtr & disk_, const String & root_path_, const ContextPtr & context_)
-    : BackupWriterDefault(&Poco::Logger::get("BackupWriterDisk"), context_)
+BackupWriterDisk::BackupWriterDisk(const DiskPtr & disk_, const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_)
+    : BackupWriterDefault(read_settings_, write_settings_, &Poco::Logger::get("BackupWriterDisk"))
    , disk(disk_)
    , root_path(root_path_)
    , data_source_description(disk->getDataSourceDescription())
--- a/src/Backups/BackupIO_Disk.h
+++ b/src/Backups/BackupIO_Disk.h
@ -13,7 +13,7 @@ using DiskPtr = std::shared_ptr<IDisk>;
 class BackupReaderDisk : public BackupReaderDefault
 {
 public:
-    BackupReaderDisk(const DiskPtr & disk_, const String & root_path_, const ContextPtr & context_);
+    BackupReaderDisk(const DiskPtr & disk_, const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_);
    ~BackupReaderDisk() override;

    bool fileExists(const String & file_name) override;
@ -33,7 +33,7 @@ private:
 class BackupWriterDisk : public BackupWriterDefault
 {
 public:
-    BackupWriterDisk(const DiskPtr & disk_, const String & root_path_, const ContextPtr & context_);
+    BackupWriterDisk(const DiskPtr & disk_, const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_);
    ~BackupWriterDisk() override;

    bool fileExists(const String & file_name) override;
--- a/src/Backups/BackupIO_File.cpp
+++ b/src/Backups/BackupIO_File.cpp
@ -16,8 +16,8 @@ namespace ErrorCodes
    extern const int LOGICAL_ERROR;
 }

-BackupReaderFile::BackupReaderFile(const String & root_path_, const ContextPtr & context_)
-    : BackupReaderDefault(&Poco::Logger::get("BackupReaderFile"), context_)
+BackupReaderFile::BackupReaderFile(const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_)
+    : BackupReaderDefault(read_settings_, write_settings_, &Poco::Logger::get("BackupReaderFile"))
    , root_path(root_path_)
    , data_source_description(DiskLocal::getLocalDataSourceDescription(root_path))
 {
@ -74,8 +74,8 @@ void BackupReaderFile::copyFileToDisk(const String & path_in_backup, size_t file
 }


-BackupWriterFile::BackupWriterFile(const String & root_path_, const ContextPtr & context_)
-    : BackupWriterDefault(&Poco::Logger::get("BackupWriterFile"), context_)
+BackupWriterFile::BackupWriterFile(const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_)
+    : BackupWriterDefault(read_settings_, write_settings_, &Poco::Logger::get("BackupWriterFile"))
    , root_path(root_path_)
    , data_source_description(DiskLocal::getLocalDataSourceDescription(root_path))
 {
--- a/src/Backups/BackupIO_File.h
+++ b/src/Backups/BackupIO_File.h
@ -11,7 +11,7 @@ namespace DB
 class BackupReaderFile : public BackupReaderDefault
 {
 public:
-    explicit BackupReaderFile(const String & root_path_, const ContextPtr & context_);
+    explicit BackupReaderFile(const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_);

    bool fileExists(const String & file_name) override;
    UInt64 getFileSize(const String & file_name) override;
@ -29,7 +29,7 @@ private:
 class BackupWriterFile : public BackupWriterDefault
 {
 public:
-    BackupWriterFile(const String & root_path_, const ContextPtr & context_);
+    BackupWriterFile(const String & root_path_, const ReadSettings & read_settings_, const WriteSettings & write_settings_);

    bool fileExists(const String & file_name) override;
    UInt64 getFileSize(const String & file_name) override;
--- a/src/Backups/BackupIO_S3.cpp
+++ b/src/Backups/BackupIO_S3.cpp
@ -50,7 +50,7 @@ namespace
            context->getRemoteHostFilter(),
            static_cast<unsigned>(context->getGlobalContext()->getSettingsRef().s3_max_redirects),
            context->getGlobalContext()->getSettingsRef().enable_s3_requests_logging,
-            /* for_disk_s3 = */ false, /* get_request_throttler = */ {}, /* put_request_throttler = */ {});
+            /* for_disk_s3 = */ false, settings.request_settings.get_request_throttler, settings.request_settings.put_request_throttler);

        client_configuration.endpointOverride = s3_uri.endpoint;
        client_configuration.maxConnections = static_cast<unsigned>(context->getSettingsRef().s3_max_connections);
@ -101,8 +101,14 @@ namespace


 BackupReaderS3::BackupReaderS3(
-    const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const ContextPtr & context_)
-    : BackupReaderDefault(&Poco::Logger::get("BackupReaderS3"), context_)
+    const S3::URI & s3_uri_,
+    const String & access_key_id_,
+    const String & secret_access_key_,
+    bool allow_s3_native_copy,
+    const ReadSettings & read_settings_,
+    const WriteSettings & write_settings_,
+    const ContextPtr & context_)
+    : BackupReaderDefault(read_settings_, write_settings_, &Poco::Logger::get("BackupReaderS3"))
    , s3_uri(s3_uri_)
    , client(makeS3Client(s3_uri_, access_key_id_, secret_access_key_, context_))
    , request_settings(context_->getStorageS3Settings().getSettings(s3_uri.uri.toString()).request_settings)
@ -178,8 +184,15 @@ void BackupReaderS3::copyFileToDisk(const String & path_in_backup, size_t file_s


 BackupWriterS3::BackupWriterS3(
-    const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const String & storage_class_name, const ContextPtr & context_)
-    : BackupWriterDefault(&Poco::Logger::get("BackupWriterS3"), context_)
+    const S3::URI & s3_uri_,
+    const String & access_key_id_,
+    const String & secret_access_key_,
+    bool allow_s3_native_copy,
+    const String & storage_class_name,
+    const ReadSettings & read_settings_,
+    const WriteSettings & write_settings_,
+    const ContextPtr & context_)
+    : BackupWriterDefault(read_settings_, write_settings_, &Poco::Logger::get("BackupWriterS3"))
    , s3_uri(s3_uri_)
    , client(makeS3Client(s3_uri_, access_key_id_, secret_access_key_, context_))
    , request_settings(context_->getStorageS3Settings().getSettings(s3_uri.uri.toString()).request_settings)
--- a/src/Backups/BackupIO_S3.h
+++ b/src/Backups/BackupIO_S3.h
@ -17,7 +17,7 @@ namespace DB
 class BackupReaderS3 : public BackupReaderDefault
 {
 public:
-    BackupReaderS3(const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const ContextPtr & context_);
+    BackupReaderS3(const S3::URI & s3_uri_, const String & access_key_id_, const String & secret_access_key_, bool allow_s3_native_copy, const ReadSettings & read_settings_, const WriteSettings & write_settings_, const ContextPtr & context_);
    ~BackupReaderS3() override;

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

    bool fileExists(const String & file_name) override;
--- a/src/Backups/BackupSettings.cpp
+++ b/src/Backups/BackupSettings.cpp
@ -27,6 +27,7 @@ namespace ErrorCodes
    M(Bool, decrypt_files_from_encrypted_disks) \
    M(Bool, deduplicate_files) \
    M(Bool, allow_s3_native_copy) \
+    M(Bool, read_from_filesystem_cache) \
    M(UInt64, shard_num) \
    M(UInt64, replica_num) \
    M(Bool, internal) \
--- a/src/Backups/BackupSettings.h
+++ b/src/Backups/BackupSettings.h
@ -44,6 +44,10 @@ struct BackupSettings
    /// Whether native copy is allowed (optimization for cloud storages, that sometimes could have bugs)
    bool allow_s3_native_copy = true;

+    /// Allow to use the filesystem cache in passive mode - benefit from the existing cache entries,
+    /// but don't put more entries into the cache.
+    bool read_from_filesystem_cache = true;
+
    /// 1-based shard index to store in the backup. 0 means all shards.
    /// Can only be used with BACKUP ON CLUSTER.
    size_t shard_num = 0;
--- a/Show More
+++ b/Show More
				`@ -0,0 +1 @@`
				`Subproject commit ee45796171324519f0c0bfd012018dd099296336`
				`@ -0,0 +1 @@`
				`../../../en/operations/optimizing-performance/profile-guided-optimization.md`