Merge branch 'master' into update-libcxx-to-15

base/base/ReplxxLineReader.cpp

@@ -151,7 +151,7 @@ public:
     {
         size_t dot_pos = path.rfind('.');
         if (dot_pos != std::string::npos)
-            fd = ::mkstemps(path.data(), path.size() - dot_pos);
+            fd = ::mkstemps(path.data(), static_cast<int>(path.size() - dot_pos));
         else
             fd = ::mkstemp(path.data());
 
@@ -408,7 +408,7 @@ ReplxxLineReader::ReplxxLineReader(
             // In a simplest case use simple comment.
             commented_line = fmt::format("-- {}", state.text());
         }
-        rx.set_state(replxx::Replxx::State(commented_line.c_str(), commented_line.size()));
+        rx.set_state(replxx::Replxx::State(commented_line.c_str(), static_cast<int>(commented_line.size())));
 
         return rx.invoke(Replxx::ACTION::COMMIT_LINE, code);
     };
@@ -480,7 +480,7 @@ void ReplxxLineReader::openEditor()
         if (executeCommand(argv) == 0)
         {
             const std::string & new_query = readFile(editor_file.getPath());
-            rx.set_state(replxx::Replxx::State(new_query.c_str(), new_query.size()));
+            rx.set_state(replxx::Replxx::State(new_query.c_str(), static_cast<int>(new_query.size())));
         }
     }
     catch (const std::runtime_error & e)
@@ -526,7 +526,7 @@ void ReplxxLineReader::openInteractiveHistorySearch()
         {
             std::string new_query = readFile(output_file.getPath());
             rightTrim(new_query);
-            rx.set_state(replxx::Replxx::State(new_query.c_str(), new_query.size()));
+            rx.set_state(replxx::Replxx::State(new_query.c_str(), static_cast<int>(new_query.size())));
         }
     }
     catch (const std::runtime_error & e)

base/base/StringRef.h

@@ -265,7 +265,7 @@ inline size_t hashLessThan16(const char * data, size_t size)
 
 struct CRC32Hash
 {
-    size_t operator() (StringRef x) const
+    unsigned operator() (StringRef x) const
     {
         const char * pos = x.data;
         size_t size = x.size;
@@ -275,22 +275,22 @@ struct CRC32Hash
 
         if (size < 8)
         {
-            return hashLessThan8(x.data, x.size);
+            return static_cast<unsigned>(hashLessThan8(x.data, x.size));
         }
 
         const char * end = pos + size;
-        size_t res = -1ULL;
+        unsigned res = -1U;
 
         do
         {
             UInt64 word = unalignedLoad<UInt64>(pos);
-            res = CRC_INT(res, word);
+            res = static_cast<unsigned>(CRC_INT(res, word));
 
             pos += 8;
         } while (pos + 8 < end);
 
         UInt64 word = unalignedLoad<UInt64>(end - 8);    /// I'm not sure if this is normal.
-        res = CRC_INT(res, word);
+        res = static_cast<unsigned>(CRC_INT(res, word));
 
         return res;
     }
@@ -302,7 +302,7 @@ struct StringRefHash : CRC32Hash {};
 
 struct CRC32Hash
 {
-    size_t operator() (StringRef /* x */) const
+    unsigned operator() (StringRef /* x */) const
     {
        throw std::logic_error{"Not implemented CRC32Hash without SSE"};
     }

base/base/itoa.h

@@ -122,7 +122,7 @@ QuotientAndRemainder<N> static inline split(UnsignedOfSize<N> value)
     constexpr DivisionBy10PowN<N> division;
 
     UnsignedOfSize<N> quotient = (division.multiplier * (UnsignedOfSize<2 * N>(value) + division.add)) >> division.shift;
-    UnsignedOfSize<N / 2> remainder = value - quotient * pow10<UnsignedOfSize<N / 2>>(N);
+    UnsignedOfSize<N / 2> remainder = static_cast<UnsignedOfSize<N / 2>>(value - quotient * pow10<UnsignedOfSize<N / 2>>(N));
 
     return {quotient, remainder};
 }

base/base/safeExit.cpp

@@ -1,10 +1,8 @@
 #if defined(OS_LINUX)
 #    include <sys/syscall.h>
 #endif
-#include <cstdlib>
 #include <unistd.h>
 #include <base/safeExit.h>
-#include <base/defines.h>
 
 [[noreturn]] void safeExit(int code)
 {

base/base/wide_integer_impl.h

@@ -227,6 +227,8 @@ struct integer<Bits, Signed>::_impl
     template <typename T>
     __attribute__((no_sanitize("undefined"))) constexpr static auto to_Integral(T f) noexcept
     {
+        /// NOTE: this can be called with DB::Decimal, and in this case, result
+        /// will be wrong
         if constexpr (std::is_signed_v<T>)
             return static_cast<int64_t>(f);
         else

cmake/ld.lld.in

@@ -3,15 +3,15 @@
 # This is a workaround for bug in llvm/clang,
 # that does not produce .debug_aranges with LTO
 #
-# NOTE: this is a temporary solution, that should be removed once [1] will be
-# resolved.
+# NOTE: this is a temporary solution, that should be removed after upgrading to
+# clang-16/llvm-16.
 #
-#   [1]: https://discourse.llvm.org/t/clang-does-not-produce-full-debug-aranges-section-with-thinlto/64898/8
+# Refs: https://reviews.llvm.org/D133092
 
 # NOTE: only -flto=thin is supported.
 # NOTE: it is not possible to check was there -gdwarf-aranges initially or not.
 if [[ "$*" =~ -plugin-opt=thinlto ]]; then
-    exec "@LLD_PATH@" -mllvm -generate-arange-section "$@"
+    exec "@LLD_PATH@" -plugin-opt=-generate-arange-section "$@"
 else
     exec "@LLD_PATH@" "$@"
 fi

cmake/tools.cmake

@@ -117,7 +117,7 @@ endif()
 # Archiver
 
 if (COMPILER_GCC)
-    find_program (LLVM_AR_PATH NAMES "llvm-ar" "llvm-ar-14" "llvm-ar-13" "llvm-ar-12")
+    find_program (LLVM_AR_PATH NAMES "llvm-ar" "llvm-ar-15" "llvm-ar-14" "llvm-ar-13" "llvm-ar-12")
 else ()
     find_program (LLVM_AR_PATH NAMES "llvm-ar-${COMPILER_VERSION_MAJOR}" "llvm-ar")
 endif ()
@@ -131,7 +131,7 @@ message(STATUS "Using archiver: ${CMAKE_AR}")
 # Ranlib
 
 if (COMPILER_GCC)
-    find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib" "llvm-ranlib-14" "llvm-ranlib-13" "llvm-ranlib-12")
+    find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib" "llvm-ranlib-15" "llvm-ranlib-14" "llvm-ranlib-13" "llvm-ranlib-12")
 else ()
     find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib-${COMPILER_VERSION_MAJOR}" "llvm-ranlib")
 endif ()
@@ -145,7 +145,7 @@ message(STATUS "Using ranlib: ${CMAKE_RANLIB}")
 # Install Name Tool
 
 if (COMPILER_GCC)
-    find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool" "llvm-install-name-tool-14" "llvm-install-name-tool-13" "llvm-install-name-tool-12")
+    find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool" "llvm-install-name-tool-15" "llvm-install-name-tool-14" "llvm-install-name-tool-13" "llvm-install-name-tool-12")
 else ()
     find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool-${COMPILER_VERSION_MAJOR}" "llvm-install-name-tool")
 endif ()
@@ -159,7 +159,7 @@ message(STATUS "Using install-name-tool: ${CMAKE_INSTALL_NAME_TOOL}")
 # Objcopy
 
 if (COMPILER_GCC)
-    find_program (OBJCOPY_PATH NAMES "llvm-objcopy" "llvm-objcopy-14" "llvm-objcopy-13" "llvm-objcopy-12" "objcopy")
+    find_program (OBJCOPY_PATH NAMES "llvm-objcopy" "llvm-objcopy-15" "llvm-objcopy-14" "llvm-objcopy-13" "llvm-objcopy-12" "objcopy")
 else ()
     find_program (OBJCOPY_PATH NAMES "llvm-objcopy-${COMPILER_VERSION_MAJOR}" "llvm-objcopy" "objcopy")
 endif ()
@@ -173,7 +173,7 @@ endif ()
 # Strip
 
 if (COMPILER_GCC)
-    find_program (STRIP_PATH NAMES "llvm-strip" "llvm-strip-14" "llvm-strip-13" "llvm-strip-12" "strip")
+    find_program (STRIP_PATH NAMES "llvm-strip" "llvm-strip-15" "llvm-strip-14" "llvm-strip-13" "llvm-strip-12" "strip")
 else ()
     find_program (STRIP_PATH NAMES "llvm-strip-${COMPILER_VERSION_MAJOR}" "llvm-strip" "strip")
 endif ()

cmake/warnings.cmake

@@ -27,7 +27,6 @@ if (COMPILER_CLANG)
     no_warning(sign-conversion)
     no_warning(implicit-int-conversion)
     no_warning(implicit-int-float-conversion)
-    no_warning(shorten-64-to-32)
     no_warning(ctad-maybe-unsupported) # clang 9+, linux-only
     no_warning(disabled-macro-expansion)
     no_warning(documentation-unknown-command)

contrib/CMakeLists.txt

@@ -114,6 +114,7 @@ if (ENABLE_TESTS)
 endif()
 
 add_contrib (llvm-project-cmake llvm-project)
+add_contrib (libfuzzer-cmake llvm-project)
 add_contrib (libxml2-cmake libxml2)
 add_contrib (aws-s3-cmake
     aws

contrib/libfuzzer-cmake/CMakeLists.txt

@@ -0,0 +1,35 @@
+set(COMPILER_RT_FUZZER_SRC_DIR "${ClickHouse_SOURCE_DIR}/contrib/llvm-project/compiler-rt/lib/fuzzer")
+
+set(FUZZER_SRCS
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerCrossOver.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerDataFlowTrace.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerDriver.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerExtFunctionsDlsym.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerExtFunctionsWeak.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerExtFunctionsWindows.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerExtraCounters.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerExtraCountersDarwin.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerExtraCountersWindows.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerFork.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerIO.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerIOPosix.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerIOWindows.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerLoop.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerMerge.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerMutate.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerSHA1.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerTracePC.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerUtil.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerUtilDarwin.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerUtilFuchsia.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerUtilLinux.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerUtilPosix.cpp"
+    "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerUtilWindows.cpp"
+)
+
+add_library(_fuzzer_no_main STATIC ${FUZZER_SRCS})
+add_library(ch_contrib::fuzzer_no_main ALIAS _fuzzer_no_main)
+
+add_library(_fuzzer STATIC ${FUZZER_SRCS} "${COMPILER_RT_FUZZER_SRC_DIR}/FuzzerMain.cpp")
+add_library(ch_contrib::fuzzer ALIAS _fuzzer)
+

docker/test/stress/run.sh

@@ -47,7 +47,6 @@ function install_packages()
 
 function configure()
 {
-    export ZOOKEEPER_FAULT_INJECTION=1
     # install test configs
     export USE_DATABASE_ORDINARY=1
     export EXPORT_S3_STORAGE_POLICIES=1
@@ -203,6 +202,7 @@ quit
 
 install_packages package_folder
 
+export ZOOKEEPER_FAULT_INJECTION=1
 configure
 
 azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --debug /azurite_log &
@@ -243,6 +243,7 @@ stop
 
 # Let's enable S3 storage by default
 export USE_S3_STORAGE_FOR_MERGE_TREE=1
+export ZOOKEEPER_FAULT_INJECTION=1
 configure
 
 # But we still need default disk because some tables loaded only into it
@@ -375,6 +376,8 @@ else
     install_packages previous_release_package_folder
 
     # Start server from previous release
+    # Previous version may not be ready for fault injections
+    export ZOOKEEPER_FAULT_INJECTION=0
     configure
 
     # Avoid "Setting s3_check_objects_after_upload is neither a builtin setting..."
@@ -422,6 +425,7 @@ else
     # Start new server
     mv package_folder/clickhouse /usr/bin/
     mv package_folder/clickhouse.debug /usr/lib/debug/usr/bin/clickhouse.debug
+    export ZOOKEEPER_FAULT_INJECTION=1
     configure
     start 500
     clickhouse-client --query "SELECT 'Backward compatibility check: Server successfully started', 'OK'" >> /test_output/test_results.tsv \

docs/en/development/architecture.md

@@ -49,27 +49,13 @@ When we calculate some function over columns in a block, we add another column w
 
 Blocks are created for every processed chunk of data. Note that for the same type of calculation, the column names and types remain the same for different blocks, and only column data changes. It is better to split block data from the block header because small block sizes have a high overhead of temporary strings for copying shared_ptrs and column names.
 
-## Block Streams {#block-streams}
+## Processors
 
-Block streams are for processing data. We use streams of blocks to read data from somewhere, perform data transformations, or write data to somewhere. `IBlockInputStream` has the `read` method to fetch the next block while available. `IBlockOutputStream` has the `write` method to push the block somewhere.
-
-Streams are responsible for:
-
-1.  Reading or writing to a table. The table just returns a stream for reading or writing blocks.
-2.  Implementing data formats. For example, if you want to output data to a terminal in `Pretty` format, you create a block output stream where you push blocks, and it formats them.
-3.  Performing data transformations. Let’s say you have `IBlockInputStream` and want to create a filtered stream. You create `FilterBlockInputStream` and initialize it with your stream. Then when you pull a block from `FilterBlockInputStream`, it pulls a block from your stream, filters it, and returns the filtered block to you. Query execution pipelines are represented this way.
-
-There are more sophisticated transformations. For example, when you pull from `AggregatingBlockInputStream`, it reads all data from its source, aggregates it, and then returns a stream of aggregated data for you. Another example: `UnionBlockInputStream` accepts many input sources in the constructor and also a number of threads. It launches multiple threads and reads from multiple sources in parallel.
-
-> Block streams use the “pull” approach to control flow: when you pull a block from the first stream, it consequently pulls the required blocks from nested streams, and the entire execution pipeline will work. Neither “pull” nor “push” is the best solution, because control flow is implicit, and that limits the implementation of various features like simultaneous execution of multiple queries (merging many pipelines together). This limitation could be overcome with coroutines or just running extra threads that wait for each other. We may have more possibilities if we make control flow explicit: if we locate the logic for passing data from one calculation unit to another outside of those calculation units. Read this [article](http://journal.stuffwithstuff.com/2013/01/13/iteration-inside-and-out/) for more thoughts.
-
-We should note that the query execution pipeline creates temporary data at each step. We try to keep block size small enough so that temporary data fits in the CPU cache. With that assumption, writing and reading temporary data is almost free in comparison with other calculations. We could consider an alternative, which is to fuse many operations in the pipeline together. It could make the pipeline as short as possible and remove much of the temporary data, which could be an advantage, but it also has drawbacks. For example, a split pipeline makes it easy to implement caching intermediate data, stealing intermediate data from similar queries running at the same time, and merging pipelines for similar queries.
+See the description at [https://github.com/ClickHouse/ClickHouse/blob/master/src/Processors/IProcessor.h](https://github.com/ClickHouse/ClickHouse/blob/master/src/Processors/IProcessor.h).
 
 ## Formats {#formats}
 
-Data formats are implemented with block streams. There are “presentational” formats only suitable for the output of data to the client, such as `Pretty` format, which provides only `IBlockOutputStream`. And there are input/output formats, such as `TabSeparated` or `JSONEachRow`.
-
-There are also row streams: `IRowInputStream` and `IRowOutputStream`. They allow you to pull/push data by individual rows, not by blocks. And they are only needed to simplify the implementation of row-oriented formats. The wrappers `BlockInputStreamFromRowInputStream` and `BlockOutputStreamFromRowOutputStream` allow you to convert row-oriented streams to regular block-oriented streams.
+Data formats are implemented with processors.
 
 ## I/O {#io}
 

docs/en/engines/table-engines/mergetree-family/mergetree.md

@@ -419,6 +419,8 @@ Supported data types: `Int*`, `UInt*`, `Float*`, `Enum`, `Date`, `DateTime`, `St
 
 For `Map` data type client can specify if index should be created for keys or values using [mapKeys](../../../sql-reference/functions/tuple-map-functions.md#mapkeys) or [mapValues](../../../sql-reference/functions/tuple-map-functions.md#mapvalues) function.
 
+There are also special-purpose and experimental indexes to support approximate nearest neighbor (ANN) queries. See [here](annindexes.md) for details.
+
 The following functions can use the filter: [equals](../../../sql-reference/functions/comparison-functions.md), [notEquals](../../../sql-reference/functions/comparison-functions.md), [in](../../../sql-reference/functions/in-functions), [notIn](../../../sql-reference/functions/in-functions), [has](../../../sql-reference/functions/array-functions#hasarr-elem), [hasAny](../../../sql-reference/functions/array-functions#hasany), [hasAll](../../../sql-reference/functions/array-functions#hasall).
 
 Example of index creation for `Map` data type

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

@@ -271,11 +271,7 @@ Result:
 The return type of `toStartOf*`, `toLastDayOfMonth`, `toMonday`, `timeSlot` functions described below is determined by the configuration parameter [enable_extended_results_for_datetime_functions](../../operations/settings/settings#enable-extended-results-for-datetime-functions) which is `0` by default.
 
 Behavior for
-* `enable_extended_results_for_datetime_functions = 0`: Functions `toStartOfYear`, `toStartOfISOYear`, `toStartOfQuarter`, `toStartOfMonth`, `toStartOfWeek`, `toLastDayOfMonth`, `toMonday` return `Date` or `DateTime`. Functions `toStartOfDay`, `toStartOfHour`, `toStartOfFifteenMinutes`, `toStartOfTenMinutes`, `toStartOfFiveMinutes`, `toStartOfMinute`, `timeSlot` return `DateTime`. Though these functions can take values of the extended types `Date32` and `DateTime64` as an argument, passing them a time outside the normal range (year 1970 to 2149 for `Date` / 2106 for `DateTime`) will produce wrong results. In case argument is out of normal range:
-  * If the argument is smaller than 1970, the result will be calculated from the argument `1970-01-01 (00:00:00)` instead.
-  * If the return type is `DateTime` and the argument is larger than `2106-02-07 08:28:15`, the result will be calculated from the argument `2106-02-07 08:28:15` instead.
-  * If the return type is `Date` and the argument is larger than `2149-06-06`, the result will be calculated from the argument `2149-06-06` instead.
-  *  If `toLastDayOfMonth` is called with an argument greater then `2149-05-31`, the result will be calculated from the argument `2149-05-31` instead.
+* `enable_extended_results_for_datetime_functions = 0`: Functions `toStartOfYear`, `toStartOfISOYear`, `toStartOfQuarter`, `toStartOfMonth`, `toStartOfWeek`, `toLastDayOfMonth`, `toMonday` return `Date` or `DateTime`. Functions `toStartOfDay`, `toStartOfHour`, `toStartOfFifteenMinutes`, `toStartOfTenMinutes`, `toStartOfFiveMinutes`, `toStartOfMinute`, `timeSlot` return `DateTime`. Though these functions can take values of the extended types `Date32` and `DateTime64` as an argument, passing them a time outside the normal range (year 1970 to 2149 for `Date` / 2106 for `DateTime`) will produce wrong results.
 * `enable_extended_results_for_datetime_functions = 1`:
   * Functions `toStartOfYear`, `toStartOfISOYear`, `toStartOfQuarter`, `toStartOfMonth`, `toStartOfWeek`, `toLastDayOfMonth`, `toMonday` return `Date` or `DateTime` if their argument is a `Date` or `DateTime`, and they return `Date32` or `DateTime64` if their argument is a `Date32` or `DateTime64`.
   * Functions `toStartOfDay`, `toStartOfHour`, `toStartOfFifteenMinutes`, `toStartOfTenMinutes`, `toStartOfFiveMinutes`, `toStartOfMinute`, `timeSlot` return `DateTime` if their argument is a `Date` or `DateTime`, and they return `DateTime64` if their argument is a `Date32` or `DateTime64`.
@@ -302,25 +298,22 @@ Returns the date.
 Rounds down a date or date with time to the first day of the month.
 Returns the date.
 
-## toLastDayOfMonth
-
-Rounds up a date or date with time to the last day of the month.
-Returns the date.
+:::note
+The behavior of parsing incorrect dates is implementation specific. ClickHouse may return zero date, throw an exception or do “natural” overflow.
+:::
 
 If `toLastDayOfMonth` is called with an argument of type `Date` greater then 2149-05-31, the result will be calculated from the argument 2149-05-31 instead.
 
 ## toMonday
 
 Rounds down a date or date with time to the nearest Monday.
-As a special case, date arguments `1970-01-01`, `1970-01-02`, `1970-01-03` and `1970-01-04` return date `1970-01-01`.
 Returns the date.
 
 ## toStartOfWeek(t\[,mode\])
 
 Rounds down a date or date with time to the nearest Sunday or Monday by mode.
 Returns the date.
-As a special case, date arguments `1970-01-01`, `1970-01-02`, `1970-01-03` and `1970-01-04` (and `1970-01-05` if `mode` is `1`) return date `1970-01-01`.
-The `mode` argument works exactly like the mode argument to toWeek(). For the single-argument syntax, a mode value of 0 is used.
+The mode argument works exactly like the mode argument to toWeek(). For the single-argument syntax, a mode value of 0 is used.
 
 ## toStartOfDay
 
@@ -671,9 +664,9 @@ Aliases: `dateDiff`, `DATE_DIFF`.
     - `quarter`
     - `year`
 
--   `startdate` — The first time value to subtract (the subtrahend). [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
+-   `startdate` — The first time value to subtract (the subtrahend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
 
--   `enddate` — The second time value to subtract from (the minuend). [Date](../../sql-reference/data-types/date.md) or [DateTime](../../sql-reference/data-types/datetime.md).
+-   `enddate` — The second time value to subtract from (the minuend). [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
 
 -   `timezone` — [Timezone name](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (optional). If specified, it is applied to both `startdate` and `enddate`. If not specified, timezones of `startdate` and `enddate` are used. If they are not the same, the result is unspecified. [String](../../sql-reference/data-types/string.md).
 
@@ -1075,7 +1068,7 @@ Example:
 SELECT timeSlots(toDateTime('2012-01-01 12:20:00'), toUInt32(600));
 SELECT timeSlots(toDateTime('1980-12-12 21:01:02', 'UTC'), toUInt32(600), 299);
 SELECT timeSlots(toDateTime64('1980-12-12 21:01:02.1234', 4, 'UTC'), toDecimal64(600.1, 1), toDecimal64(299, 0));
-```
+``` 
 ``` text
 ┌─timeSlots(toDateTime('2012-01-01 12:20:00'), toUInt32(600))─┐
 │ ['2012-01-01 12:00:00','2012-01-01 12:30:00']               │
@@ -1163,7 +1156,7 @@ dateName(date_part, date)
 **Arguments**
 
 -   `date_part` — Date part. Possible values: 'year', 'quarter', 'month', 'week', 'dayofyear', 'day', 'weekday', 'hour', 'minute', 'second'. [String](../../sql-reference/data-types/string.md).
--   `date` — Date. [Date](../../sql-reference/data-types/date.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
+-   `date` — Date. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) or [DateTime64](../../sql-reference/data-types/datetime64.md).
 -   `timezone` — Timezone. Optional. [String](../../sql-reference/data-types/string.md).
 
 **Returned value**

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

@@ -571,7 +571,7 @@ Example:
 
 ``` sql
 SELECT
-    transform(domain(Referer), ['yandex.ru', 'google.ru', 'vk.com'], ['www.yandex', 'example.com']) AS s,
+    transform(domain(Referer), ['yandex.ru', 'google.ru', 'vkontakte.ru'], ['www.yandex', 'example.com', 'vk.com']) AS s,
     count() AS c
 FROM test.hits
 GROUP BY domain(Referer)

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

@@ -1,21 +0,0 @@
----
-slug: /en/sql-reference/statements/misc
-toc_hidden: true
-sidebar_position: 70
----
-
-# Miscellaneous Statements
-
--   [ATTACH](../../sql-reference/statements/attach.md)
--   [CHECK TABLE](../../sql-reference/statements/check-table.md)
--   [DESCRIBE TABLE](../../sql-reference/statements/describe-table.md)
--   [DETACH](../../sql-reference/statements/detach.md)
--   [DROP](../../sql-reference/statements/drop.md)
--   [EXISTS](../../sql-reference/statements/exists.md)
--   [KILL](../../sql-reference/statements/kill.md)
--   [OPTIMIZE](../../sql-reference/statements/optimize.md)
--   [RENAME](../../sql-reference/statements/rename.md)
--   [SET](../../sql-reference/statements/set.md)
--   [SET ROLE](../../sql-reference/statements/set-role.md)
--   [TRUNCATE](../../sql-reference/statements/truncate.md)
--   [USE](../../sql-reference/statements/use.md)

docs/ru/sql-reference/data-types/date.md

@@ -6,7 +6,7 @@ sidebar_label: Date
 
 # Date {#data-type-date}
 
-Дата. Хранится в двух байтах в виде (беззнакового) числа дней, прошедших от 1970-01-01. Позволяет хранить значения от чуть больше, чем начала unix-эпохи до верхнего порога, определяющегося константой на этапе компиляции (сейчас - до 2149 года, последний полностью поддерживаемый год - 2148).
+Дата. Хранится в двух байтах в виде (беззнакового) числа дней, прошедших от 1970-01-01. Позволяет хранить значения от чуть больше, чем начала unix-эпохи до верхнего порога, определяющегося константой на этапе компиляции (сейчас - до 2106 года, последний полностью поддерживаемый год - 2105).
 
 Диапазон значений: \[1970-01-01, 2149-06-06\].
 

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

@@ -272,15 +272,9 @@ SELECT toUnixTimestamp('2017-11-05 08:07:47', 'Asia/Tokyo') AS unix_timestamp;
 
 Поведение для
 * `enable_extended_results_for_datetime_functions = 0`: Функции `toStartOf*`, `toLastDayOfMonth`, `toMonday` возвращают `Date` или `DateTime`. Функции `toStartOfDay`, `toStartOfHour`, `toStartOfFifteenMinutes`, `toStartOfTenMinutes`, `toStartOfFiveMinutes`, `toStartOfMinute`, `timeSlot` возвращают `DateTime`. Хотя эти функции могут принимать значения типа `Date32` или `DateTime64` в качестве аргумента, при обработке аргумента вне нормального диапазона значений (`1970` - `2148` для `Date` и `1970-01-01 00:00:00`-`2106-02-07 08:28:15` для `DateTime`) будет получен некорректный результат.
-В случае если значение аргумента вне нормального диапазона:
-    * `1970-01-01 (00:00:00)` будет возвращён для моментов времени до 1970 года,
-    * `2106-02-07 08:28:15` будет взят в качестве аргумента, если полученный аргумент превосходит данное значение и возвращаемый тип - `DateTime`,
-    * `2149-06-06` будет взят в качестве аргумента, если полученный аргумент превосходит данное значение и возвращаемый тип - `Date`,
-    * `2149-05-31` будет результатом функции `toLastDayOfMonth` при обработке аргумента больше `2149-05-31`.
 * `enable_extended_results_for_datetime_functions = 1`:
     * Функции `toStartOfYear`, `toStartOfISOYear`, `toStartOfQuarter`, `toStartOfMonth`, `toStartOfWeek`, `toLastDayOfMonth`, `toMonday` возвращают `Date` или `DateTime` если их аргумент `Date` или `DateTime` и они возвращают `Date32` или `DateTime64` если их аргумент `Date32` или `DateTime64`.
     * Функции `toStartOfDay`, `toStartOfHour`, `toStartOfFifteenMinutes`, `toStartOfTenMinutes`, `toStartOfFiveMinutes`, `toStartOfMinute`, `timeSlot` возвращают `DateTime` если их аргумент `Date` или `DateTime` и они возвращают `DateTime64` если их аргумент `Date32` или `DateTime64`.
-
 :::
 
 ## toStartOfYear {#tostartofyear}
@@ -321,20 +315,20 @@ SELECT toStartOfISOYear(toDate('2017-01-01')) AS ISOYear20170101;
 Округляет дату или дату-с-временем до последнего числа месяца.
 Возвращается дата.
 
-Если `toLastDayOfMonth` вызывается с аргументом типа `Date` большим чем 2149-05-31, то результат будет вычислен от аргумента 2149-05-31.
-
+:::note "Attention"
+    Возвращаемое значение для некорректных дат зависит от реализации. ClickHouse может вернуть нулевую дату, выбросить исключение, или выполнить «естественное» перетекание дат между месяцами.
+:::
+    
 ## toMonday {#tomonday}
 
 Округляет дату или дату-с-временем вниз до ближайшего понедельника.
-Частный случай: для дат `1970-01-01`, `1970-01-02`, `1970-01-03` и `1970-01-04` результатом будет `1970-01-01`.
 Возвращается дата.
 
 ## toStartOfWeek(t[,mode]) {#tostartofweek}
 
 Округляет дату или дату со временем до ближайшего воскресенья или понедельника в соответствии с mode.
 Возвращается дата.
-Частный случай: для дат `1970-01-01`, `1970-01-02`, `1970-01-03` и `1970-01-04` (и `1970-01-05`, если `mode` равен `1`) результатом будет `1970-01-01`.
-Аргумент `mode` работает точно так же, как аргумент mode [toWeek()](#toweek). Если аргумент mode опущен, то используется режим 0.
+Аргумент mode работает точно так же, как аргумент mode [toWeek()](#toweek). Если аргумент mode опущен, то используется режим 0.
 
 ## toStartOfDay {#tostartofday}
 
@@ -721,9 +715,9 @@ date_diff('unit', startdate, enddate, [timezone])
     - `quarter`
     - `year`
 
--   `startdate` — первая дата или дата со временем, которая вычитается из `enddate`. [Date](../../sql-reference/data-types/date.md) или [DateTime](../../sql-reference/data-types/datetime.md).
+-   `startdate` — первая дата или дата со временем, которая вычитается из `enddate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
 
--   `enddate` — вторая дата или дата со временем, из которой вычитается `startdate`. [Date](../../sql-reference/data-types/date.md) или [DateTime](../../sql-reference/data-types/datetime.md).
+-   `enddate` — вторая дата или дата со временем, из которой вычитается `startdate`. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
 
 -   `timezone` — [часовой пояс](../../operations/server-configuration-parameters/settings.md#server_configuration_parameters-timezone) (необязательно). Если этот аргумент указан, то он применяется как для `startdate`, так и для `enddate`. Если этот аргумент не указан, то используются часовые пояса аргументов `startdate` и `enddate`. Если часовые пояса аргументов `startdate` и `enddate` не совпадают, то результат не определен. [String](../../sql-reference/data-types/string.md).
 
@@ -975,8 +969,7 @@ SELECT now('Europe/Moscow');
 
 ## timeSlots(StartTime, Duration,\[, Size\]) {#timeslotsstarttime-duration-size}
 Для интервала, начинающегося в `StartTime` и длящегося `Duration` секунд, возвращает массив моментов времени, кратных `Size`. Параметр `Size` указывать необязательно, по умолчанию он равен 1800 секундам (30 минутам) - необязательный параметр.
-Данная функция может использоваться, например, для анализа количества просмотров страницы за соответствующую сессию.
-Аргумент `StartTime` может иметь тип `DateTime` или `DateTime64`. В случае, если используется `DateTime`, аргументы `Duration` и `Size` должны иметь тип `UInt32`; Для DateTime64 они должны быть типа `Decimal64`.
+
 Возвращает массив DateTime/DateTime64 (тип будет совпадать с типом параметра ’StartTime’). Для DateTime64 масштаб(scale) возвращаемой величины может отличаться от масштаба фргумента ’StartTime’ --- результат будет иметь наибольший масштаб среди всех данных аргументов.
 
 Пример использования:
@@ -1085,7 +1078,7 @@ dateName(date_part, date)
 **Аргументы**
 
 -   `date_part` — часть даты. Возможные значения: 'year', 'quarter', 'month', 'week', 'dayofyear', 'day', 'weekday', 'hour', 'minute', 'second'. [String](../../sql-reference/data-types/string.md).
--   `date` — дата. [Date](../../sql-reference/data-types/date.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
+-   `date` — дата. [Date](../../sql-reference/data-types/date.md), [Date32](../../sql-reference/data-types/date32.md), [DateTime](../../sql-reference/data-types/datetime.md) или [DateTime64](../../sql-reference/data-types/datetime64.md).
 -   `timezone` — часовой пояс. Необязательный аргумент. [String](../../sql-reference/data-types/string.md).
 
 **Возвращаемое значение**

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

@@ -568,7 +568,7 @@ ORDER BY c DESC
 
 ``` sql
 SELECT
-    transform(domain(Referer), ['yandex.ru', 'google.ru', 'vk.com'], ['www.yandex', 'example.com']) AS s,
+    transform(domain(Referer), ['yandex.ru', 'google.ru', 'vkontakte.ru'], ['www.yandex', 'example.com', 'vk.com']) AS s,
     count() AS c
 FROM test.hits
 GROUP BY domain(Referer)

docs/ru/sql-reference/statements/misc.md

@@ -1,21 +0,0 @@
----
-slug: /ru/sql-reference/statements/misc
-sidebar_position: 41
----
-
-# Прочие виды запросов {#prochie-vidy-zaprosov}
-
--   [ATTACH](../../sql-reference/statements/attach.md)
--   [CHECK TABLE](../../sql-reference/statements/check-table.md)
--   [DESCRIBE TABLE](../../sql-reference/statements/describe-table.md)
--   [DETACH](../../sql-reference/statements/detach.md)
--   [DROP](../../sql-reference/statements/drop.md)
--   [EXISTS](../../sql-reference/statements/exists.md)
--   [KILL](../../sql-reference/statements/kill.md)
--   [OPTIMIZE](../../sql-reference/statements/optimize.md)
--   [RENAME](../../sql-reference/statements/rename.md)
--   [SET](../../sql-reference/statements/set.md)
--   [SET ROLE](../../sql-reference/statements/set-role.md)
--   [TRUNCATE](../../sql-reference/statements/truncate.md)
--   [USE](../../sql-reference/statements/use.md)
-

docs/zh/sql-reference/data-types/date.md

@@ -3,7 +3,7 @@ slug: /zh/sql-reference/data-types/date
 ---
 # 日期 {#date}
 
-日期类型，用两个字节存储，表示从 1970-01-01 (无符号) 到当前的日期值。允许存储从 Unix 纪元开始到编译阶段定义的上限阈值常量（目前上限是2149年，但最终完全支持的年份为2148）。最小值输出为1970-01-01。
+日期类型，用两个字节存储，表示从 1970-01-01 (无符号) 到当前的日期值。允许存储从 Unix 纪元开始到编译阶段定义的上限阈值常量（目前上限是2106年，但最终完全支持的年份为2105）。最小值输出为1970-01-01。
 
 值的范围: \[1970-01-01, 2149-06-06\]。
 

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

@@ -237,7 +237,7 @@ ORDER BY c DESC
 
 ``` sql
 SELECT
-    transform(domain(Referer), ['yandex.ru', 'google.ru', 'vk.com'], ['www.yandex', 'example.com']) AS s,
+    transform(domain(Referer), ['yandex.ru', 'google.ru', 'vkontakte.ru'], ['www.yandex', 'example.com', 'vk.com']) AS s,
     count() AS c
 FROM test.hits
 GROUP BY domain(Referer)

programs/client/Client.cpp

@@ -1108,15 +1108,21 @@ void Client::processConfig()
     else
         format = config().getString("format", is_interactive ? "PrettyCompact" : "TabSeparated");
 
-    format_max_block_size = config().getInt("format_max_block_size", global_context->getSettingsRef().max_block_size);
+    format_max_block_size = config().getUInt64("format_max_block_size",
+        global_context->getSettingsRef().max_block_size);
 
     insert_format = "Values";
 
     /// Setting value from cmd arg overrides one from config
     if (global_context->getSettingsRef().max_insert_block_size.changed)
+    {
         insert_format_max_block_size = global_context->getSettingsRef().max_insert_block_size;
+    }
     else
-        insert_format_max_block_size = config().getInt("insert_format_max_block_size", global_context->getSettingsRef().max_insert_block_size);
+    {
+        insert_format_max_block_size = config().getUInt64("insert_format_max_block_size",
+            global_context->getSettingsRef().max_insert_block_size);
+    }
 
     ClientInfo & client_info = global_context->getClientInfo();
     client_info.setInitialQuery();

programs/client/clickhouse-client.xml

@@ -19,7 +19,6 @@
             {host}
             {port}
             {user}
-            {database}
             {display_name}
         Terminal colors: https://misc.flogisoft.com/bash/tip_colors_and_formatting
         See also: https://wiki.hackzine.org/development/misc/readline-color-prompt.html

programs/copier/ZooKeeperStaff.h

@@ -47,8 +47,8 @@ public:
     WrappingUInt32 epoch;
     WrappingUInt32 counter;
     explicit Zxid(UInt64 _zxid)
-            : epoch(_zxid >> 32)
-            , counter(_zxid)
+            : epoch(static_cast<UInt32>(_zxid >> 32))
+            , counter(static_cast<UInt32>(_zxid))
     {}
 
     bool operator<=(const Zxid & other) const

programs/disks/DisksApp.cpp

@@ -57,7 +57,7 @@ void DisksApp::addOptions(
         ("config-file,C", po::value<String>(), "Set config file")
         ("disk", po::value<String>(), "Set disk name")
         ("command_name", po::value<String>(), "Name for command to do")
-        ("send-logs", "Send logs")
+        ("save-logs", "Save logs to a file")
         ("log-level", po::value<String>(), "Logging level")
         ;
 
@@ -82,10 +82,10 @@ void DisksApp::processOptions()
         config().setString("config-file", options["config-file"].as<String>());
     if (options.count("disk"))
         config().setString("disk", options["disk"].as<String>());
-    if (options.count("send-logs"))
-        config().setBool("send-logs", true);
+    if (options.count("save-logs"))
+        config().setBool("save-logs", true);
     if (options.count("log-level"))
-        Poco::Logger::root().setLevel(options["log-level"].as<std::string>());
+        config().setString("log-level", options["log-level"].as<String>());
 }
 
 void DisksApp::init(std::vector<String> & common_arguments)
@@ -149,15 +149,6 @@ void DisksApp::parseAndCheckOptions(
 
 int DisksApp::main(const std::vector<String> & /*args*/)
 {
-    if (config().has("send-logs"))
-    {
-        auto log_level = config().getString("log-level", "trace");
-        Poco::Logger::root().setLevel(Poco::Logger::parseLevel(log_level));
-
-        auto log_path = config().getString("logger.clickhouse-disks", "/var/log/clickhouse-server/clickhouse-disks.log");
-        Poco::Logger::root().setChannel(Poco::AutoPtr<Poco::FileChannel>(new Poco::FileChannel(log_path)));
-    }
-
     if (config().has("config-file") || fs::exists(getDefaultConfigFileName()))
     {
         String config_path = config().getString("config-file", getDefaultConfigFileName());
@@ -171,6 +162,20 @@ int DisksApp::main(const std::vector<String> & /*args*/)
         throw Exception(ErrorCodes::BAD_ARGUMENTS, "No config-file specifiged");
     }
 
+    if (config().has("save-logs"))
+    {
+        auto log_level = config().getString("log-level", "trace");
+        Poco::Logger::root().setLevel(Poco::Logger::parseLevel(log_level));
+
+        auto log_path = config().getString("logger.clickhouse-disks", "/var/log/clickhouse-server/clickhouse-disks.log");
+        Poco::Logger::root().setChannel(Poco::AutoPtr<Poco::FileChannel>(new Poco::FileChannel(log_path)));
+    }
+    else
+    {
+        auto log_level = config().getString("log-level", "none");
+        Poco::Logger::root().setLevel(Poco::Logger::parseLevel(log_level));
+    }
+
     registerDisks();
     registerFormats();
 

programs/install/Install.cpp

@@ -893,7 +893,7 @@ namespace
         if (fs::exists(pid_file))
         {
             ReadBufferFromFile in(pid_file.string());
-            UInt64 pid;
+            Int32 pid;
             if (tryReadIntText(pid, in))
             {
                 fmt::print("{} file exists and contains pid = {}.\n", pid_file.string(), pid);
@@ -982,9 +982,9 @@ namespace
         return 0;
     }
 
-    UInt64 isRunning(const fs::path & pid_file)
+    int isRunning(const fs::path & pid_file)
     {
-        UInt64 pid = 0;
+        int pid = 0;
 
         if (fs::exists(pid_file))
         {
@@ -1057,7 +1057,7 @@ namespace
         if (force && do_not_kill)
             throw Exception(ErrorCodes::BAD_ARGUMENTS, "Specified flags are incompatible");
 
-        UInt64 pid = isRunning(pid_file);
+        int pid = isRunning(pid_file);
 
         if (!pid)
             return 0;

programs/keeper/CMakeLists.txt

@@ -45,6 +45,7 @@ if (BUILD_STANDALONE_KEEPER)
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Coordination/KeeperLogStore.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Coordination/KeeperServer.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Coordination/KeeperSnapshotManager.cpp
+        ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Coordination/KeeperSnapshotManagerS3.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Coordination/KeeperStateMachine.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Coordination/KeeperStateManager.cpp
         ${CMAKE_CURRENT_SOURCE_DIR}/../../src/Coordination/KeeperStorage.cpp

programs/keeper/Keeper.cpp

@@ -68,12 +68,12 @@ namespace ErrorCodes
 namespace
 {
 
-int waitServersToFinish(std::vector<DB::ProtocolServerAdapter> & servers, size_t seconds_to_wait)
+size_t waitServersToFinish(std::vector<DB::ProtocolServerAdapter> & servers, size_t seconds_to_wait)
 {
-    const int sleep_max_ms = 1000 * seconds_to_wait;
-    const int sleep_one_ms = 100;
-    int sleep_current_ms = 0;
-    int current_connections = 0;
+    const size_t sleep_max_ms = 1000 * seconds_to_wait;
+    const size_t sleep_one_ms = 100;
+    size_t sleep_current_ms = 0;
+    size_t current_connections = 0;
     for (;;)
     {
         current_connections = 0;
@@ -441,7 +441,7 @@ int Keeper::main(const std::vector<std::string> & /*args*/)
         main_config_reloader.reset();
 
         LOG_DEBUG(log, "Waiting for current connections to Keeper to finish.");
-        int current_connections = 0;
+        size_t current_connections = 0;
         for (auto & server : *servers)
         {
             server.stop();

programs/local/LocalServer.cpp

@@ -546,9 +546,14 @@ void LocalServer::processConfig()
 
     /// Setting value from cmd arg overrides one from config
     if (global_context->getSettingsRef().max_insert_block_size.changed)
+    {
         insert_format_max_block_size = global_context->getSettingsRef().max_insert_block_size;
+    }
     else
-        insert_format_max_block_size = config().getInt("insert_format_max_block_size", global_context->getSettingsRef().max_insert_block_size);
+    {
+        insert_format_max_block_size = config().getUInt64("insert_format_max_block_size",
+            global_context->getSettingsRef().max_insert_block_size);
+    }
 
     /// Sets external authenticators config (LDAP, Kerberos).
     global_context->setExternalAuthenticatorsConfig(config());

programs/obfuscator/Obfuscator.cpp

@@ -279,7 +279,7 @@ Float transformFloatMantissa(Float x, UInt64 seed)
     constexpr size_t mantissa_num_bits = std::is_same_v<Float, Float32> ? 23 : 52;
 
     UInt x_uint = bit_cast<UInt>(x);
-    x_uint = feistelNetwork(x_uint, mantissa_num_bits, seed);
+    x_uint = static_cast<UInt>(feistelNetwork(x_uint, mantissa_num_bits, seed));
     return bit_cast<Float>(x_uint);
 }
 
@@ -511,13 +511,13 @@ public:
         for (size_t i = 0; i < size; ++i)
         {
             UInt32 src_datetime = src_data[i];
-            UInt32 src_date = date_lut.toDate(src_datetime);
+            UInt32 src_date = static_cast<UInt32>(date_lut.toDate(src_datetime));
 
             Int32 src_diff = src_datetime - src_prev_value;
-            Int32 res_diff = transformSigned(src_diff, seed);
+            Int32 res_diff = static_cast<Int32>(transformSigned(src_diff, seed));
 
             UInt32 new_datetime = res_prev_value + res_diff;
-            UInt32 new_time = new_datetime - date_lut.toDate(new_datetime);
+            UInt32 new_time = new_datetime - static_cast<UInt32>(date_lut.toDate(new_datetime));
             res_data[i] = src_date + new_time;
 
             src_prev_value = src_datetime;

programs/odbc-bridge/ColumnInfoHandler.cpp

@@ -183,7 +183,10 @@ void ODBCColumnsInfoHandler::handleRequest(HTTPServerRequest & request, HTTPServ
         if (columns.empty())
             throw Exception("Columns definition was not returned", ErrorCodes::LOGICAL_ERROR);
 
-        WriteBufferFromHTTPServerResponse out(response, request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD, keep_alive_timeout);
+        WriteBufferFromHTTPServerResponse out(
+            response,
+            request.getMethod() == Poco::Net::HTTPRequest::HTTP_HEAD,
+            keep_alive_timeout);
         try
         {
             writeStringBinary(columns.toString(), out);

programs/odbc-bridge/ODBCBlockInputStream.cpp

@@ -139,7 +139,7 @@ void ODBCSource::insertValue(
             readDateTimeText(time, in, assert_cast<const DataTypeDateTime *>(data_type.get())->getTimeZone());
             if (time < 0)
                 time = 0;
-            assert_cast<ColumnUInt32 &>(column).insertValue(time);
+            assert_cast<ColumnUInt32 &>(column).insertValue(static_cast<UInt32>(time));
             break;
         }
         case ValueType::vtDateTime64:

programs/server/Server.cpp

@@ -228,12 +228,12 @@ catch (...)
             path));
 }
 
-int waitServersToFinish(std::vector<DB::ProtocolServerAdapter> & servers, size_t seconds_to_wait)
+size_t waitServersToFinish(std::vector<DB::ProtocolServerAdapter> & servers, size_t seconds_to_wait)
 {
-    const int sleep_max_ms = 1000 * seconds_to_wait;
-    const int sleep_one_ms = 100;
-    int sleep_current_ms = 0;
-    int current_connections = 0;
+    const size_t sleep_max_ms = 1000 * seconds_to_wait;
+    const size_t sleep_one_ms = 100;
+    size_t sleep_current_ms = 0;
+    size_t current_connections = 0;
     for (;;)
     {
         current_connections = 0;
@@ -933,7 +933,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
         else
         {
             rlim_t old = rlim.rlim_cur;
-            rlim.rlim_cur = config().getUInt("max_open_files", rlim.rlim_max);
+            rlim.rlim_cur = config().getUInt("max_open_files", static_cast<unsigned>(rlim.rlim_max));
             int rc = setrlimit(RLIMIT_NOFILE, &rlim);
             if (rc != 0)
                 LOG_WARNING(log, "Cannot set max number of file descriptors to {}. Try to specify max_open_files according to your system limits. error: {}", rlim.rlim_cur, errnoToString());
@@ -1507,7 +1507,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
         if (!servers_to_start_before_tables.empty())
         {
             LOG_DEBUG(log, "Waiting for current connections to servers for tables to finish.");
-            int current_connections = 0;
+            size_t current_connections = 0;
             for (auto & server : servers_to_start_before_tables)
             {
                 server.stop();
@@ -1793,7 +1793,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
 
             is_cancelled = true;
 
-            int current_connections = 0;
+            size_t current_connections = 0;
             {
                 std::lock_guard lock(servers_lock);
                 for (auto & server : servers)

src/Access/Common/AllowedClientHosts.cpp

@@ -236,7 +236,7 @@ void AllowedClientHosts::IPSubnet::set(const IPAddress & prefix_, const IPAddres
 
 void AllowedClientHosts::IPSubnet::set(const IPAddress & prefix_, size_t num_prefix_bits)
 {
-    set(prefix_, IPAddress(num_prefix_bits, prefix_.family()));
+    set(prefix_, IPAddress(static_cast<unsigned>(num_prefix_bits), prefix_.family()));
 }
 
 void AllowedClientHosts::IPSubnet::set(const IPAddress & address)

src/Access/LDAPClient.cpp

@@ -254,7 +254,7 @@ bool LDAPClient::openConnection()
 #endif
 
     {
-        const int search_timeout = params.search_timeout.count();
+        const int search_timeout = static_cast<int>(params.search_timeout.count());
         diag(ldap_set_option(handle, LDAP_OPT_TIMELIMIT, &search_timeout));
     }
 

src/AggregateFunctions/AggregateFunctionGroupBitmap.h

@@ -45,7 +45,8 @@ public:
 
     void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
     {
-        assert_cast<ColumnVector<T> &>(to).getData().push_back(this->data(place).rbs.size());
+        assert_cast<ColumnVector<T> &>(to).getData().push_back(
+            static_cast<T>(this->data(place).rbs.size()));
     }
 };
 
@@ -142,7 +143,8 @@ public:
 
     void insertResultInto(AggregateDataPtr __restrict place, IColumn & to, Arena *) const override
     {
-        assert_cast<ColumnVector<T> &>(to).getData().push_back(this->data(place).rbs.size());
+        assert_cast<ColumnVector<T> &>(to).getData().push_back(
+            static_cast<T>(this->data(place).rbs.size()));
     }
 };
 

src/AggregateFunctions/AggregateFunctionGroupBitmapData.h

@@ -426,7 +426,7 @@ public:
             return 0;
 
         if (isSmall())
-            return small.find(x) != small.end();
+            return small.find(static_cast<T>(x)) != small.end();
         else
             return rb->contains(static_cast<Value>(x));
     }

src/AggregateFunctions/AggregateFunctionHistogram.h

@@ -136,8 +136,8 @@ private:
 
         for (size_t i = 0; i <= size; ++i)
         {
-            previous[i] = i - 1;
-            next[i] = i + 1;
+            previous[i] = static_cast<UInt32>(i - 1);
+            next[i] = static_cast<UInt32>(i + 1);
         }
 
         next[size] = 0;
@@ -157,7 +157,7 @@ private:
         auto quality = [&](UInt32 i) { return points[next[i]].mean - points[i].mean; };
 
         for (size_t i = 0; i + 1 < size; ++i)
-            queue.push({quality(i), i});
+            queue.push({quality(static_cast<UInt32>(i)), i});
 
         while (new_size > max_bins && !queue.empty())
         {
@@ -217,7 +217,7 @@ private:
                 points[left] = points[right];
             }
         }
-        size = left + 1;
+        size = static_cast<UInt32>(left + 1);
     }
 
 public:

src/AggregateFunctions/AggregateFunctionMinMaxAny.h

@@ -540,7 +540,7 @@ public:
     /// Assuming to.has()
     void changeImpl(StringRef value, Arena * arena)
     {
-        Int32 value_size = value.size;
+        Int32 value_size = static_cast<Int32>(value.size);
 
         if (value_size <= MAX_SMALL_STRING_SIZE)
         {
@@ -555,7 +555,7 @@ public:
             if (capacity < value_size)
             {
                 /// Don't free large_data here.
-                capacity = roundUpToPowerOfTwoOrZero(value_size);
+                capacity = static_cast<Int32>(roundUpToPowerOfTwoOrZero(value_size));
                 large_data = arena->alloc(capacity);
             }
 

src/AggregateFunctions/AggregateFunctionQuantile.cpp

@@ -46,7 +46,7 @@ AggregateFunctionPtr createAggregateFunctionQuantile(
     if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
 
     if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
-    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
+    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<UInt128, true>>(argument_types, params);
     if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
     if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
 

src/AggregateFunctions/AggregateFunctionQuantileDeterministic.cpp

@@ -40,7 +40,7 @@ AggregateFunctionPtr createAggregateFunctionQuantile(
     if (which.idx == TypeIndex::DateTime) return std::make_shared<Function<DataTypeDateTime::FieldType, false>>(argument_types, params);
 
     if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
-    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
+    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<UInt128, true>>(argument_types, params);
     if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
     if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
 

src/AggregateFunctions/AggregateFunctionQuantileExact.cpp

@@ -47,7 +47,7 @@ AggregateFunctionPtr createAggregateFunctionQuantile(
     if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
 
     if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
-    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
+    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<UInt128, true>>(argument_types, params);
     if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
     if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
 

src/AggregateFunctions/AggregateFunctionQuantileExactWeighted.cpp

@@ -46,7 +46,7 @@ AggregateFunctionPtr createAggregateFunctionQuantile(
     if (which.idx == TypeIndex::DateTime64) return std::make_shared<Function<DateTime64, false>>(argument_types, params);
 
     if (which.idx == TypeIndex::Int128) return std::make_shared<Function<Int128, true>>(argument_types, params);
-    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<Int128, true>>(argument_types, params);
+    if (which.idx == TypeIndex::UInt128) return std::make_shared<Function<UInt128, true>>(argument_types, params);
     if (which.idx == TypeIndex::Int256) return std::make_shared<Function<Int256, true>>(argument_types, params);
     if (which.idx == TypeIndex::UInt256) return std::make_shared<Function<UInt256, true>>(argument_types, params);
 

src/AggregateFunctions/AggregateFunctionRetention.h

@@ -44,7 +44,7 @@ struct AggregateFunctionRetentionData
 
     void serialize(WriteBuffer & buf) const
     {
-        UInt32 event_value = events.to_ulong();
+        UInt32 event_value = static_cast<UInt32>(events.to_ulong());
         writeBinary(event_value, buf);
     }
 

src/AggregateFunctions/AggregateFunctionSequenceMatch.h

@@ -272,7 +272,7 @@ private:
 
                     actions.emplace_back(PatternActionType::SpecificEvent, event_number - 1);
                     dfa_states.back().transition = DFATransition::SpecificEvent;
-                    dfa_states.back().event = event_number - 1;
+                    dfa_states.back().event = static_cast<uint32_t>(event_number - 1);
                     dfa_states.emplace_back();
                     conditions_in_pattern.set(event_number - 1);
                 }

src/AggregateFunctions/AggregateFunctionSequenceNextNode.h

@@ -226,7 +226,7 @@ public:
         for (UInt8 i = 0; i < events_size; ++i)
             if (assert_cast<const ColumnVector<UInt8> *>(columns[min_required_args + i])->getData()[row_num])
                 node->events_bitset.set(i);
-        node->event_time = timestamp;
+        node->event_time = static_cast<DataTypeDateTime::FieldType>(timestamp);
 
         node->can_be_base = assert_cast<const ColumnVector<UInt8> *>(columns[base_cond_column_idx])->getData()[row_num];
 
@@ -365,7 +365,7 @@ public:
     /// The first matched event is 0x00000001, the second one is 0x00000002, the third one is 0x00000004, and so on.
     UInt32 getNextNodeIndex(Data & data) const
     {
-        const UInt32 unmatched_idx = data.value.size();
+        const UInt32 unmatched_idx = static_cast<UInt32>(data.value.size());
 
         if (data.value.size() <= events_size)
             return unmatched_idx;

src/AggregateFunctions/AggregateFunctionSparkbar.h

@@ -165,7 +165,7 @@ private:
             {
                 for (size_t i = 0; i <= diff_x; ++i)
                 {
-                    auto it = data.points.find(min_x_local + i);
+                    auto it = data.points.find(static_cast<X>(min_x_local + i));
                     bool found = it != data.points.end();
                     value += getBar(found ? std::round(((it->getMapped() - min_y) / diff_y) * 7) + 1 : 0.0);
                 }
@@ -173,7 +173,7 @@ private:
             else
             {
                 for (size_t i = 0; i <= diff_x; ++i)
-                    value += getBar(data.points.has(min_x_local + i) ? 1 : 0);
+                    value += getBar(data.points.has(min_x_local + static_cast<X>(i)) ? 1 : 0);
             }
         }
         else
@@ -202,7 +202,7 @@ private:
                 if (i == bound.first) // is bound
                 {
                     Float64 proportion = bound.second - bound.first;
-                    auto it = data.points.find(min_x_local + i);
+                    auto it = data.points.find(min_x_local + static_cast<X>(i));
                     bool found = (it != data.points.end());
                     if (found && proportion > 0)
                         new_y = new_y.value_or(0) + it->getMapped() * proportion;
@@ -229,7 +229,7 @@ private:
                 }
                 else
                 {
-                    auto it = data.points.find(min_x_local + i);
+                    auto it = data.points.find(min_x_local + static_cast<X>(i));
                     if (it != data.points.end())
                         new_y = new_y.value_or(0) + it->getMapped();
                 }
@@ -267,8 +267,8 @@ public:
         if (params.size() == 3)
         {
             specified_min_max_x = true;
-            min_x = params.at(1).safeGet<X>();
-            max_x = params.at(2).safeGet<X>();
+            min_x = static_cast<X>(params.at(1).safeGet<X>());
+            max_x = static_cast<X>(params.at(2).safeGet<X>());
         }
         else
         {

src/AggregateFunctions/AggregateFunctionUniq.h

@@ -175,8 +175,9 @@ struct OneAdder
         {
             if constexpr (!std::is_same_v<T, String>)
             {
+                using ValueType = typename decltype(data.set)::value_type;
                 const auto & value = assert_cast<const ColumnVector<T> &>(column).getElement(row_num);
-                data.set.insert(AggregateFunctionUniqTraits<T>::hash(value));
+                data.set.insert(static_cast<ValueType>(AggregateFunctionUniqTraits<T>::hash(value)));
             }
             else
             {

src/AggregateFunctions/AggregateFunctionUniqCombined.h

@@ -43,7 +43,7 @@ namespace detail
     {
         static Ret hash(UInt128 x)
         {
-            return sipHash64(x);
+            return static_cast<Ret>(sipHash64(x));
         }
     };
 

src/AggregateFunctions/AggregateFunctionWelchTTest.cpp

@@ -40,7 +40,15 @@ struct WelchTTestData : public TTestMoments<Float64>
         Float64 denominator_x = sx2 * sx2 / (nx * nx * (nx - 1));
         Float64 denominator_y = sy2 * sy2 / (ny * ny * (ny - 1));
 
-        return numerator / (denominator_x + denominator_y);
+        auto result = numerator / (denominator_x + denominator_y);
+
+        if (result <= 0 || std::isinf(result) || isNaN(result))
+            throw Exception(
+                ErrorCodes::BAD_ARGUMENTS,
+                "Cannot calculate p_value, because the t-distribution \
+                has inappropriate value of degrees of freedom (={}). It should be > 0", result);
+
+        return result;
     }
 
     std::tuple<Float64, Float64> getResult() const

src/AggregateFunctions/IAggregateFunction.cpp

@@ -53,9 +53,12 @@ String IAggregateFunction::getDescription() const
 
 bool IAggregateFunction::haveEqualArgumentTypes(const IAggregateFunction & rhs) const
 {
-    return std::equal(argument_types.begin(), argument_types.end(),
-                      rhs.argument_types.begin(), rhs.argument_types.end(),
-                      [](const auto & t1, const auto & t2) { return t1->equals(*t2); });
+    return std::equal(
+        argument_types.begin(),
+        argument_types.end(),
+        rhs.argument_types.begin(),
+        rhs.argument_types.end(),
+        [](const auto & t1, const auto & t2) { return t1->equals(*t2); });
 }
 
 bool IAggregateFunction::haveSameStateRepresentation(const IAggregateFunction & rhs) const
@@ -67,11 +70,7 @@ bool IAggregateFunction::haveSameStateRepresentation(const IAggregateFunction &
 
 bool IAggregateFunction::haveSameStateRepresentationImpl(const IAggregateFunction & rhs) const
 {
-    bool res = getName() == rhs.getName()
-        && parameters == rhs.parameters
-        && haveEqualArgumentTypes(rhs);
-    assert(res == (getStateType()->getName() == rhs.getStateType()->getName()));
-    return res;
+    return getStateType()->equals(*rhs.getStateType());
 }
 
 }

src/AggregateFunctions/ReservoirSamplerDeterministic.h

@@ -84,7 +84,7 @@ public:
         if (isNaN(v))
             return;
 
-        UInt32 hash = intHash64(determinator);
+        UInt32 hash = static_cast<UInt32>(intHash64(determinator));
         insertImpl(v, hash);
         sorted = false;
         ++total_values;

src/AggregateFunctions/UniquesHashSet.h

@@ -118,7 +118,7 @@ private:
 
     HashValue hash(Value key) const
     {
-        return Hash()(key);
+        return static_cast<HashValue>(Hash()(key));
     }
 
     /// Delete all values whose hashes do not divide by 2 ^ skip_degree

src/Backups/BackupIO_S3.cpp

@@ -44,12 +44,12 @@ namespace
         S3::PocoHTTPClientConfiguration client_configuration = S3::ClientFactory::instance().createClientConfiguration(
             settings.auth_settings.region,
             context->getRemoteHostFilter(),
-            context->getGlobalContext()->getSettingsRef().s3_max_redirects,
+            static_cast<unsigned>(context->getGlobalContext()->getSettingsRef().s3_max_redirects),
             context->getGlobalContext()->getSettingsRef().enable_s3_requests_logging,
             /* for_disk_s3 = */ false);
 
         client_configuration.endpointOverride = s3_uri.endpoint;
-        client_configuration.maxConnections = context->getSettingsRef().s3_max_connections;
+        client_configuration.maxConnections = static_cast<unsigned>(context->getSettingsRef().s3_max_connections);
         /// Increase connect timeout
         client_configuration.connectTimeoutMs = 10 * 1000;
         /// Requests in backups can be extremely long, set to one hour
@@ -221,7 +221,7 @@ void BackupWriterS3::copyObjectMultipartImpl(
         part_request.SetBucket(dst_bucket);
         part_request.SetKey(dst_key);
         part_request.SetUploadId(multipart_upload_id);
-        part_request.SetPartNumber(part_number);
+        part_request.SetPartNumber(static_cast<int>(part_number));
         part_request.SetCopySourceRange(fmt::format("bytes={}-{}", position, std::min(size, position + upload_part_size) - 1));
 
         auto outcome = client->UploadPartCopy(part_request);
@@ -251,7 +251,7 @@ void BackupWriterS3::copyObjectMultipartImpl(
         for (size_t i = 0; i < part_tags.size(); ++i)
         {
             Aws::S3::Model::CompletedPart part;
-            multipart_upload.AddParts(part.WithETag(part_tags[i]).WithPartNumber(i + 1));
+            multipart_upload.AddParts(part.WithETag(part_tags[i]).WithPartNumber(static_cast<int>(i) + 1));
         }
 
         req.SetMultipartUpload(multipart_upload);

src/Backups/BackupSettings.cpp

@@ -62,7 +62,6 @@ namespace
 #define LIST_OF_BACKUP_SETTINGS(M) \
     M(String, id) \
     M(String, compression_method) \
-    M(Int64, compression_level) \
     M(String, password) \
     M(Bool, structure_only) \
     M(Bool, async) \
@@ -72,6 +71,7 @@ namespace
     M(String, host_id) \
     M(String, coordination_zk_path) \
     M(OptionalUUID, backup_uuid)
+    /// M(Int64, compression_level)
 
 BackupSettings BackupSettings::fromBackupQuery(const ASTBackupQuery & query)
 {
@@ -82,6 +82,9 @@ BackupSettings BackupSettings::fromBackupQuery(const ASTBackupQuery & query)
         const auto & settings = query.settings->as<const ASTSetQuery &>().changes;
         for (const auto & setting : settings)
         {
+            if (setting.name == "compression_level")
+                res.compression_level = static_cast<int>(SettingFieldInt64{setting.value}.value);
+            else
 #define GET_SETTINGS_FROM_BACKUP_QUERY_HELPER(TYPE, NAME) \
             if (setting.name == #NAME) \
                 res.NAME = SettingField##TYPE{setting.value}.value; \

src/Bridge/IBridge.h

@@ -43,7 +43,7 @@ private:
     std::string hostname;
     size_t port;
     std::string log_level;
-    size_t max_server_connections;
+    unsigned max_server_connections;
     size_t http_timeout;
 
     Poco::Logger * log;

src/BridgeHelper/IBridgeHelper.h

@@ -43,7 +43,7 @@ protected:
 
     virtual String serviceFileName() const = 0;
 
-    virtual size_t getDefaultPort() const = 0;
+    virtual unsigned getDefaultPort() const = 0;
 
     virtual bool startBridgeManually() const = 0;
 

src/BridgeHelper/LibraryBridgeHelper.h

@@ -23,7 +23,7 @@ protected:
 
     String serviceFileName() const override { return serviceAlias(); }
 
-    size_t getDefaultPort() const override { return DEFAULT_PORT; }
+    unsigned getDefaultPort() const override { return DEFAULT_PORT; }
 
     bool startBridgeManually() const override { return false; }
 

src/BridgeHelper/XDBCBridgeHelper.h

@@ -109,7 +109,7 @@ protected:
 
     String getName() const override { return BridgeHelperMixin::getName(); }
 
-    size_t getDefaultPort() const override { return DEFAULT_PORT; }
+    unsigned getDefaultPort() const override { return DEFAULT_PORT; }
 
     String serviceAlias() const override { return BridgeHelperMixin::serviceAlias(); }
 

src/Client/ClientBase.cpp

@@ -1,7 +1,6 @@
 #include <Client/ClientBase.h>
 
 #include <iostream>
-#include <iomanip>
 #include <filesystem>
 #include <map>
 #include <unordered_map>
@@ -9,7 +8,6 @@
 #include "config.h"
 
 #include <Common/DateLUT.h>
-#include <Common/LocalDate.h>
 #include <Common/MemoryTracker.h>
 #include <base/argsToConfig.h>
 #include <base/LineReader.h>
@@ -32,7 +30,6 @@
 #include <Common/clearPasswordFromCommandLine.h>
 #include <Common/StringUtils/StringUtils.h>
 #include <Common/filesystemHelpers.h>
-#include <Common/Config/configReadClient.h>
 #include <Common/NetException.h>
 #include <Storages/ColumnsDescription.h>
 
@@ -70,10 +67,10 @@
 #include <IO/WriteBufferFromOStream.h>
 #include <IO/CompressionMethod.h>
 #include <Client/InternalTextLogs.h>
-#include <boost/algorithm/string/replace.hpp>
 #include <IO/ForkWriteBuffer.h>
 #include <Parsers/Kusto/ParserKQLStatement.h>
 
+
 namespace fs = std::filesystem;
 using namespace std::literals;
 
@@ -340,7 +337,7 @@ ASTPtr ClientBase::parseQuery(const char *& pos, const char * end, bool allow_mu
 
 
 /// Consumes trailing semicolons and tries to consume the same-line trailing comment.
-void ClientBase::adjustQueryEnd(const char *& this_query_end, const char * all_queries_end, int max_parser_depth)
+void ClientBase::adjustQueryEnd(const char *& this_query_end, const char * all_queries_end, uint32_t max_parser_depth)
 {
     // We have to skip the trailing semicolon that might be left
     // after VALUES parsing or just after a normal semicolon-terminated query.
@@ -553,7 +550,7 @@ try
                 out_file_buf = wrapWriteBufferWithCompressionMethod(
                     std::make_unique<WriteBufferFromFile>(out_file, DBMS_DEFAULT_BUFFER_SIZE, O_WRONLY | O_EXCL | O_CREAT),
                     compression_method,
-                    compression_level
+                    static_cast<int>(compression_level)
                 );
 
                 if (query_with_output->is_into_outfile_with_stdout)
@@ -1605,6 +1602,8 @@ MultiQueryProcessingStage ClientBase::analyzeMultiQueryText(
     if (this_query_begin >= all_queries_end)
         return MultiQueryProcessingStage::QUERIES_END;
 
+    unsigned max_parser_depth = static_cast<unsigned>(global_context->getSettingsRef().max_parser_depth);
+
     // If there are only comments left until the end of file, we just
     // stop. The parser can't handle this situation because it always
     // expects that there is some query that it can parse.
@@ -1614,7 +1613,7 @@ MultiQueryProcessingStage ClientBase::analyzeMultiQueryText(
     // and it makes more sense to treat them as such.
     {
         Tokens tokens(this_query_begin, all_queries_end);
-        IParser::Pos token_iterator(tokens, global_context->getSettingsRef().max_parser_depth);
+        IParser::Pos token_iterator(tokens, max_parser_depth);
         if (!token_iterator.isValid())
             return MultiQueryProcessingStage::QUERIES_END;
     }
@@ -1635,7 +1634,7 @@ MultiQueryProcessingStage ClientBase::analyzeMultiQueryText(
         if (ignore_error)
         {
             Tokens tokens(this_query_begin, all_queries_end);
-            IParser::Pos token_iterator(tokens, global_context->getSettingsRef().max_parser_depth);
+            IParser::Pos token_iterator(tokens, max_parser_depth);
             while (token_iterator->type != TokenType::Semicolon && token_iterator.isValid())
                 ++token_iterator;
             this_query_begin = token_iterator->end;
@@ -1675,7 +1674,7 @@ MultiQueryProcessingStage ClientBase::analyzeMultiQueryText(
     // after we have processed the query. But even this guess is
     // beneficial so that we see proper trailing comments in "echo" and
     // server log.
-    adjustQueryEnd(this_query_end, all_queries_end, global_context->getSettingsRef().max_parser_depth);
+    adjustQueryEnd(this_query_end, all_queries_end, max_parser_depth);
     return MultiQueryProcessingStage::EXECUTE_QUERY;
 }
 
@@ -1869,7 +1868,9 @@ bool ClientBase::executeMultiQuery(const String & all_queries_text)
                 if (insert_ast && isSyncInsertWithData(*insert_ast, global_context))
                 {
                     this_query_end = insert_ast->end;
-                    adjustQueryEnd(this_query_end, all_queries_end, global_context->getSettingsRef().max_parser_depth);
+                    adjustQueryEnd(
+                        this_query_end, all_queries_end,
+                        static_cast<unsigned>(global_context->getSettingsRef().max_parser_depth));
                 }
 
                 // Report error.
@@ -1925,7 +1926,7 @@ bool ClientBase::processQueryText(const String & text)
 
 String ClientBase::prompt() const
 {
-    return boost::replace_all_copy(prompt_by_server_display_name, "{database}", config().getString("database", "default"));
+    return prompt_by_server_display_name;
 }
 
 
@@ -2350,7 +2351,7 @@ void ClientBase::init(int argc, char ** argv)
     if (options.count("print-profile-events"))
         config().setBool("print-profile-events", true);
     if (options.count("profile-events-delay-ms"))
-        config().setInt("profile-events-delay-ms", options["profile-events-delay-ms"].as<UInt64>());
+        config().setUInt64("profile-events-delay-ms", options["profile-events-delay-ms"].as<UInt64>());
     if (options.count("progress"))
         config().setBool("progress", true);
     if (options.count("echo"))

src/Client/ClientBase.h

@@ -72,7 +72,7 @@ protected:
     void processParsedSingleQuery(const String & full_query, const String & query_to_execute,
         ASTPtr parsed_query, std::optional<bool> echo_query_ = {}, bool report_error = false);
 
-    static void adjustQueryEnd(const char *& this_query_end, const char * all_queries_end, int max_parser_depth);
+    static void adjustQueryEnd(const char *& this_query_end, const char * all_queries_end, uint32_t max_parser_depth);
     ASTPtr parseQuery(const char *& pos, const char * end, bool allow_multi_statements) const;
     static void setupSignalHandler();
 

src/Client/HedgedConnections.cpp

@@ -338,7 +338,7 @@ HedgedConnections::ReplicaLocation HedgedConnections::getReadyReplicaLocation(As
             offset_states[location.offset].replicas[location.index].change_replica_timeout.reset();
             offset_states[location.offset].replicas[location.index].is_change_replica_timeout_expired = true;
             offset_states[location.offset].next_replica_in_process = true;
-            offsets_queue.push(location.offset);
+            offsets_queue.push(static_cast<int>(location.offset));
             ProfileEvents::increment(ProfileEvents::HedgedRequestsChangeReplica);
             startNewReplica();
         }

src/Client/HedgedConnectionsFactory.cpp

@@ -362,7 +362,7 @@ void HedgedConnectionsFactory::removeReplicaFromEpoll(int index, int fd)
     timeout_fd_to_replica_index.erase(replicas[index].change_replica_timeout.getDescriptor());
 }
 
-int HedgedConnectionsFactory::numberOfProcessingReplicas() const
+size_t HedgedConnectionsFactory::numberOfProcessingReplicas() const
 {
     if (epoll.empty())
         return 0;
@@ -381,7 +381,7 @@ HedgedConnectionsFactory::State HedgedConnectionsFactory::setBestUsableReplica(C
             && result.is_usable
             && !replicas[i].is_ready
             && (!skip_replicas_with_two_level_aggregation_incompatibility || !isTwoLevelAggregationIncompatible(&*result.entry)))
-            indexes.push_back(i);
+            indexes.push_back(static_cast<int>(i));
     }
 
     if (indexes.empty())

src/Client/HedgedConnectionsFactory.h

@@ -70,7 +70,7 @@ public:
 
     const ConnectionTimeouts & getConnectionTimeouts() const { return timeouts; }
 
-    int numberOfProcessingReplicas() const;
+    size_t numberOfProcessingReplicas() const;
 
     /// Tell Factory to not return connections with two level aggregation incompatibility.
     void skipReplicasWithTwoLevelAggregationIncompatibility() { skip_replicas_with_two_level_aggregation_incompatibility = true; }

src/Client/LocalConnection.cpp

@@ -6,8 +6,6 @@
 #include <Processors/Executors/PushingAsyncPipelineExecutor.h>
 #include <Storages/IStorage.h>
 #include <Core/Protocol.h>
-#include <DataTypes/DataTypesNumber.h>
-#include <DataTypes/DataTypeString.h>
 
 
 namespace DB

src/Client/QueryFuzzer.cpp

@@ -81,9 +81,9 @@ Field QueryFuzzer::getRandomField(int type)
     {
         static constexpr UInt64 scales[] = {0, 1, 2, 10};
         return DecimalField<Decimal64>(
-            bad_int64_values[fuzz_rand() % (sizeof(bad_int64_values)
-                / sizeof(*bad_int64_values))],
-            scales[fuzz_rand() % (sizeof(scales) / sizeof(*scales))]);
+            bad_int64_values[fuzz_rand() % (sizeof(bad_int64_values) / sizeof(*bad_int64_values))],
+            static_cast<UInt32>(scales[fuzz_rand() % (sizeof(scales) / sizeof(*scales))])
+        );
     }
     default:
         assert(false);

src/Columns/ColumnArray.cpp

@@ -277,13 +277,13 @@ void ColumnArray::updateWeakHash32(WeakHash32 & hash) const
     {
         /// This row improves hash a little bit according to integration tests.
         /// It is the same as to use previous hash value as the first element of array.
-        hash_data[i] = intHashCRC32(hash_data[i]);
+        hash_data[i] = static_cast<UInt32>(intHashCRC32(hash_data[i]));
 
         for (size_t row = prev_offset; row < offsets_data[i]; ++row)
             /// It is probably not the best way to combine hashes.
             /// But much better then xor which lead to similar hash for arrays like [1], [1, 1, 1], [1, 1, 1, 1, 1], ...
             /// Much better implementation - to add offsets as an optional argument to updateWeakHash32.
-            hash_data[i] = intHashCRC32(internal_hash_data[row], hash_data[i]);
+            hash_data[i] = static_cast<UInt32>(intHashCRC32(internal_hash_data[row], hash_data[i]));
 
         prev_offset = offsets_data[i];
     }
@@ -569,8 +569,8 @@ void ColumnArray::expand(const IColumn::Filter & mask, bool inverted)
     if (mask.size() < offsets_data.size())
         throw Exception("Mask size should be no less than data size.", ErrorCodes::LOGICAL_ERROR);
 
-    int index = mask.size() - 1;
-    int from = offsets_data.size() - 1;
+    ssize_t index = mask.size() - 1;
+    ssize_t from = offsets_data.size() - 1;
     offsets_data.resize(mask.size());
     UInt64 last_offset = offsets_data[from];
     while (index >= 0)

src/Columns/ColumnCompressed.cpp

@@ -27,8 +27,8 @@ std::shared_ptr<Memory<>> ColumnCompressed::compressBuffer(const void * data, si
     auto compressed_size = LZ4_compress_default(
         reinterpret_cast<const char *>(data),
         compressed.data(),
-        data_size,
-        max_dest_size);
+        static_cast<int>(data_size),
+        static_cast<int>(max_dest_size));
 
     if (compressed_size <= 0)
         throw Exception(ErrorCodes::CANNOT_COMPRESS, "Cannot compress column");
@@ -51,8 +51,8 @@ void ColumnCompressed::decompressBuffer(
     auto processed_size = LZ4_decompress_safe(
         reinterpret_cast<const char *>(compressed_data),
         reinterpret_cast<char *>(decompressed_data),
-        compressed_size,
-        decompressed_size);
+        static_cast<int>(compressed_size),
+        static_cast<int>(decompressed_size));
 
     if (processed_size <= 0)
         throw Exception(ErrorCodes::CANNOT_DECOMPRESS, "Cannot decompress column");

src/Columns/ColumnConst.cpp

@@ -148,7 +148,7 @@ void ColumnConst::updateWeakHash32(WeakHash32 & hash) const
     size_t data_hash = element_hash.getData()[0];
 
     for (auto & value : hash.getData())
-        value = intHashCRC32(data_hash, value);
+        value = static_cast<UInt32>(intHashCRC32(data_hash, value));
 }
 
 void ColumnConst::compareColumn(

src/Columns/ColumnDecimal.cpp

@@ -109,7 +109,7 @@ void ColumnDecimal<T>::updateWeakHash32(WeakHash32 & hash) const
 
     while (begin < end)
     {
-        *hash_data = intHashCRC32(*begin, *hash_data);
+        *hash_data = static_cast<UInt32>(intHashCRC32(*begin, *hash_data));
         ++begin;
         ++hash_data;
     }

src/Columns/ColumnFixedString.cpp

@@ -277,8 +277,8 @@ void ColumnFixedString::expand(const IColumn::Filter & mask, bool inverted)
     if (mask.size() < size())
         throw Exception("Mask size should be no less than data size.", ErrorCodes::LOGICAL_ERROR);
 
-    int index = mask.size() - 1;
-    int from = size() - 1;
+    ssize_t index = mask.size() - 1;
+    ssize_t from = size() - 1;
     chars.resize_fill(mask.size() * n, 0);
     while (index >= 0)
     {

src/Columns/ColumnLowCardinality.cpp

@@ -46,7 +46,7 @@ namespace
 
         HashMap<T, T> hash_map;
         for (auto val : index)
-            hash_map.insert({val, hash_map.size()});
+            hash_map.insert({val, static_cast<T>(hash_map.size())});
 
         auto res_col = ColumnVector<T>::create();
         auto & data = res_col->getData();
@@ -632,7 +632,7 @@ void ColumnLowCardinality::Index::convertPositions()
 
             /// TODO: Optimize with SSE?
             for (size_t i = 0; i < size; ++i)
-                new_data[i] = data[i];
+                new_data[i] = static_cast<CurIndexType>(data[i]);
 
             positions = std::move(new_positions);
             size_of_type = sizeof(IndexType);
@@ -717,7 +717,7 @@ void ColumnLowCardinality::Index::insertPositionsRange(const IColumn & column, U
                 positions_data.resize(size + limit);
 
                 for (UInt64 i = 0; i < limit; ++i)
-                    positions_data[size + i] = column_data[offset + i];
+                    positions_data[size + i] = static_cast<CurIndexType>(column_data[offset + i]);
             };
 
             callForType(std::move(copy), size_of_type);
@@ -789,7 +789,7 @@ void ColumnLowCardinality::Index::updateWeakHash(WeakHash32 & hash, WeakHash32 &
         auto size = data.size();
 
         for (size_t i = 0; i < size; ++i)
-            hash_data[i] = intHashCRC32(dict_hash_data[data[i]], hash_data[i]);
+            hash_data[i] = static_cast<UInt32>(intHashCRC32(dict_hash_data[data[i]], hash_data[i]));
     };
 
     callForType(std::move(update_weak_hash), size_of_type);

src/Columns/ColumnString.cpp

@@ -168,8 +168,8 @@ void ColumnString::expand(const IColumn::Filter & mask, bool inverted)
     /// We cannot change only offsets, because each string should end with terminating zero byte.
     /// So, we will insert one zero byte when mask value is zero.
 
-    int index = mask.size() - 1;
-    int from = offsets_data.size() - 1;
+    ssize_t index = mask.size() - 1;
+    ssize_t from = offsets_data.size() - 1;
     /// mask.size() - offsets_data.size() should be equal to the number of zeros in mask
     /// (if not, one of exceptions below will throw) and we can calculate the resulting chars size.
     UInt64 last_offset = offsets_data[from] + (mask.size() - offsets_data.size());

src/Columns/ColumnUnique.h

@@ -550,7 +550,7 @@ MutableColumnPtr ColumnUnique<ColumnType>::uniqueInsertRangeImpl(
     auto insert_key = [&](StringRef ref, ReverseIndex<UInt64, ColumnType> & cur_index) -> MutableColumnPtr
     {
         auto inserted_pos = cur_index.insert(ref);
-        positions[num_added_rows] = inserted_pos;
+        positions[num_added_rows] = static_cast<IndexType>(inserted_pos);
         if (inserted_pos == next_position)
             return update_position(next_position);
 
@@ -562,9 +562,9 @@ MutableColumnPtr ColumnUnique<ColumnType>::uniqueInsertRangeImpl(
         auto row = start + num_added_rows;
 
         if (null_map && (*null_map)[row])
-            positions[num_added_rows] = getNullValueIndex();
+            positions[num_added_rows] = static_cast<IndexType>(getNullValueIndex());
         else if (column->compareAt(getNestedTypeDefaultValueIndex(), row, *src_column, 1) == 0)
-            positions[num_added_rows] = getNestedTypeDefaultValueIndex();
+            positions[num_added_rows] = static_cast<IndexType>(getNestedTypeDefaultValueIndex());
         else
         {
             auto ref = src_column->getDataAt(row);
@@ -576,7 +576,7 @@ MutableColumnPtr ColumnUnique<ColumnType>::uniqueInsertRangeImpl(
                 if (insertion_point == reverse_index.lastInsertionPoint())
                     res = insert_key(ref, *secondary_index);
                 else
-                    positions[num_added_rows] = insertion_point;
+                    positions[num_added_rows] = static_cast<IndexType>(insertion_point);
             }
             else
                 res = insert_key(ref, reverse_index);

src/Columns/ColumnVector.cpp

@@ -84,7 +84,7 @@ void ColumnVector<T>::updateWeakHash32(WeakHash32 & hash) const
 
     while (begin < end)
     {
-        *hash_data = hashCRC32(*begin, *hash_data);
+        *hash_data = static_cast<UInt32>(hashCRC32(*begin, *hash_data));
         ++begin;
         ++hash_data;
     }

src/Columns/MaskOperations.cpp

@@ -22,8 +22,8 @@ void expandDataByMask(PaddedPODArray<T> & data, const PaddedPODArray<UInt8> & ma
     if (mask.size() < data.size())
         throw Exception("Mask size should be no less than data size.", ErrorCodes::LOGICAL_ERROR);
 
-    int from = data.size() - 1;
-    int index = mask.size() - 1;
+    ssize_t from = data.size() - 1;
+    ssize_t index = mask.size() - 1;
     data.resize(mask.size());
     while (index >= 0)
     {
@@ -317,7 +317,7 @@ int checkShortCircuitArguments(const ColumnsWithTypeAndName & arguments)
     for (size_t i = 0; i != arguments.size(); ++i)
     {
         if (checkAndGetShortCircuitArgument(arguments[i].column))
-            last_short_circuit_argument_index = i;
+            last_short_circuit_argument_index = static_cast<int>(i);
     }
 
     return last_short_circuit_argument_index;

src/Columns/tests/gtest_weak_hash_32.cpp

@@ -164,7 +164,7 @@ TEST(WeakHash32, ColumnVectorU32)
 
     for (int idx [[maybe_unused]] : {1, 2})
     {
-        for (uint64_t i = 0; i < 65536; ++i)
+        for (uint32_t i = 0; i < 65536; ++i)
             data.push_back(i << 16u);
     }
 
@@ -181,7 +181,7 @@ TEST(WeakHash32, ColumnVectorI32)
 
     for (int idx [[maybe_unused]] : {1, 2})
     {
-        for (int64_t i = -32768; i < 32768; ++i)
+        for (int32_t i = -32768; i < 32768; ++i)
             data.push_back(i << 16); //-V610
     }
 
@@ -240,7 +240,7 @@ TEST(WeakHash32, ColumnVectorU128)
             val.items[0] = i << 32u;
             val.items[1] = i << 32u;
             data.push_back(val);
-            eq_data.push_back(i);
+            eq_data.push_back(static_cast<UInt32>(i));
         }
     }
 
@@ -274,7 +274,7 @@ TEST(WeakHash32, ColumnDecimal32)
 
     for (int idx [[maybe_unused]] : {1, 2})
     {
-        for (int64_t i = -32768; i < 32768; ++i)
+        for (int32_t i = -32768; i < 32768; ++i)
             data.push_back(i << 16); //-V610
     }
 
@@ -326,7 +326,7 @@ TEST(WeakHash32, ColumnString1)
 
     for (int idx [[maybe_unused]] : {1, 2})
     {
-        for (int64_t i = 0; i < 65536; ++i)
+        for (int32_t i = 0; i < 65536; ++i)
         {
             data.push_back(i);
             auto str = std::to_string(i);
@@ -359,7 +359,7 @@ TEST(WeakHash32, ColumnString2)
     {
         size_t max_size = 3000;
         char letter = 'a';
-        for (int64_t i = 0; i < 65536; ++i)
+        for (int32_t i = 0; i < 65536; ++i)
         {
             data.push_back(i);
             size_t s = (i % max_size) + 1;
@@ -401,7 +401,7 @@ TEST(WeakHash32, ColumnString3)
         char letter = 'a';
         for (int64_t i = 0; i < 65536; ++i)
         {
-            data.push_back(i);
+            data.push_back(static_cast<UInt32>(i));
             size_t s = (i % max_size) + 1;
             std::string str(s,'\0');
             str[0] = letter;
@@ -430,7 +430,7 @@ TEST(WeakHash32, ColumnFixedString)
         char letter = 'a';
         for (int64_t i = 0; i < 65536; ++i)
         {
-            data.push_back(i);
+            data.push_back(static_cast<UInt32>(i));
             size_t s = (i % max_size) + 1;
             std::string str(s, letter);
             col->insertData(str.data(), str.size());
@@ -471,7 +471,7 @@ TEST(WeakHash32, ColumnArray)
         UInt32 cur = 0;
         for (int64_t i = 0; i < 65536; ++i)
         {
-            eq_data.push_back(i);
+            eq_data.push_back(static_cast<UInt32>(i));
             size_t s = (i % max_size) + 1;
 
             cur_off += s;
@@ -505,9 +505,9 @@ TEST(WeakHash32, ColumnArray2)
     UInt64 cur_off = 0;
     for (int idx [[maybe_unused]] : {1, 2})
     {
-        for (int64_t i = 0; i < 1000; ++i)
+        for (int32_t i = 0; i < 1000; ++i)
         {
-            for (size_t j = 0; j < 1000; ++j)
+            for (uint32_t j = 0; j < 1000; ++j)
             {
                 eq_data.push_back(i * 1000 + j);
 
@@ -556,7 +556,7 @@ TEST(WeakHash32, ColumnArrayArray)
         UInt32 cur = 1;
         for (int64_t i = 0; i < 3000; ++i)
         {
-            eq_data.push_back(i);
+            eq_data.push_back(static_cast<UInt32>(i));
             size_t s = (i % max_size) + 1;
 
             cur_off2 += s;
@@ -667,7 +667,7 @@ TEST(WeakHash32, ColumnTupleUInt64UInt64)
         {
             data1.push_back(l);
             data2.push_back(i << 32u);
-            eq.push_back(l * 65536 + i);
+            eq.push_back(static_cast<UInt32>(l * 65536 + i));
         }
     }
 
@@ -695,7 +695,7 @@ TEST(WeakHash32, ColumnTupleUInt64String)
 
         size_t max_size = 3000;
         char letter = 'a';
-        for (int64_t i = 0; i < 65536; ++i)
+        for (int32_t i = 0; i < 65536; ++i)
         {
             data1.push_back(l);
             eq.push_back(l * 65536 + i);
@@ -737,7 +737,7 @@ TEST(WeakHash32, ColumnTupleUInt64FixedString)
         for (int64_t i = 0; i < 65536; ++i)
         {
             data1.push_back(l);
-            eq.push_back(l * 65536 + i);
+            eq.push_back(static_cast<Int32>(l * 65536 + i));
 
             size_t s = (i % max_size) + 1;
             std::string str(s, letter);
@@ -778,7 +778,7 @@ TEST(WeakHash32, ColumnTupleUInt64Array)
         auto l = idx % 2;
 
         UInt32 cur = 0;
-        for (int64_t i = 0; i < 65536; ++i)
+        for (int32_t i = 0; i < 65536; ++i)
         {
             data1.push_back(l);
             eq_data.push_back(l * 65536 + i);

src/Common/CombinedCardinalityEstimator.h

@@ -65,7 +65,7 @@ public:
 private:
     using Small = SmallSet<Key, small_set_size_max>;
     using Medium = HashContainer;
-    using Large = HyperLogLogCounter<K, Hash, HashValueType, DenominatorType, BiasEstimator, mode>;
+    using Large = HyperLogLogCounter<K, Key, Hash, HashValueType, DenominatorType, BiasEstimator, mode>;
 
 public:
     CombinedCardinalityEstimator()

src/Common/DateLUTImpl.cpp

@@ -149,9 +149,9 @@ DateLUTImpl::DateLUTImpl(const std::string & time_zone_)
 
     /// Fill lookup table for years and months.
     size_t year_months_lut_index = 0;
-    size_t first_day_of_last_month = 0;
+    unsigned first_day_of_last_month = 0;
 
-    for (size_t day = 0; day < DATE_LUT_SIZE; ++day)
+    for (unsigned day = 0; day < DATE_LUT_SIZE; ++day)
     {
         const Values & values = lut[day];
 

src/Common/DateLUTImpl.h

@@ -73,7 +73,7 @@ private:
             return LUTIndex(0);
         if (index >= DATE_LUT_SIZE)
             return LUTIndex(DATE_LUT_SIZE - 1);
-        return LUTIndex{index};
+        return LUTIndex{static_cast<UInt32>(index)};
     }
 
     template <typename T>
@@ -229,12 +229,12 @@ private:
         if (t >= lut[guess].date)
         {
             if (guess + 1 >= DATE_LUT_SIZE || t < lut[guess + 1].date)
-                return LUTIndex(guess);
+                return LUTIndex(static_cast<unsigned>(guess));
 
-            return LUTIndex(guess + 1);
+            return LUTIndex(static_cast<unsigned>(guess) + 1);
         }
 
-        return LUTIndex(guess ? guess - 1 : 0);
+        return LUTIndex(guess ? static_cast<unsigned>(guess) - 1 : 0);
     }
 
     static inline LUTIndex toLUTIndex(DayNum d)
@@ -272,11 +272,11 @@ private:
         if (likely(offset_is_whole_number_of_hours_during_epoch))
         {
             if (likely(x >= 0))
-                return x / divisor * divisor;
+                return static_cast<DateOrTime>(x / divisor * divisor);
 
             /// Integer division for negative numbers rounds them towards zero (up).
             /// We will shift the number so it will be rounded towards -inf (down).
-            return (x + 1 - divisor) / divisor * divisor;
+            return static_cast<DateOrTime>((x + 1 - divisor) / divisor * divisor);
         }
 
         Time date = find(x).date;
@@ -285,7 +285,7 @@ private:
         {
             if (unlikely(res < 0))
                 return 0;
-            return res;
+            return static_cast<DateOrTime>(res);
         }
         else
             return res;
@@ -509,7 +509,7 @@ public:
         if (time >= lut[index].time_at_offset_change())
             time += lut[index].amount_of_offset_change();
 
-        unsigned res = time / 3600;
+        unsigned res = static_cast<unsigned>(time / 3600);
 
         /// In case time was changed backwards at the start of next day, we will repeat the hour 23.
         return res <= 23 ? res : 23;
@@ -548,8 +548,8 @@ public:
         {
             Time res = t % 60;
             if (likely(res >= 0))
-                return res;
-            return res + 60;
+                return static_cast<unsigned>(res);
+            return static_cast<unsigned>(res) + 60;
         }
 
         LUTIndex index = findIndex(t);
@@ -895,6 +895,19 @@ public:
         return toRelativeHourNum(lut[toLUTIndex(v)].date);
     }
 
+    /// The same formula is used for positive time (after Unix epoch) and negative time (before Unix epoch).
+    /// It’s needed for correct work of dateDiff function.
+    inline Time toStableRelativeHourNum(Time t) const
+    {
+        return (t + DATE_LUT_ADD + 86400 - offset_at_start_of_epoch) / 3600 - (DATE_LUT_ADD / 3600);
+    }
+
+    template <typename DateOrTime>
+    inline Time toStableRelativeHourNum(DateOrTime v) const
+    {
+        return toStableRelativeHourNum(lut[toLUTIndex(v)].date);
+    }
+
     inline Time toRelativeMinuteNum(Time t) const /// NOLINT
     {
         return (t + DATE_LUT_ADD) / 60 - (DATE_LUT_ADD / 60);
@@ -960,7 +973,7 @@ public:
         if constexpr (std::is_same_v<Date, DayNum>)
             return DayNum(4 + (d - 4) / days * days);
         else
-            return ExtendedDayNum(4 + (d - 4) / days * days);
+            return ExtendedDayNum(static_cast<Int32>(4 + (d - 4) / days * days));
     }
 
     template <typename Date>
@@ -970,9 +983,9 @@ public:
         if (days == 1)
             return toDate(d);
         if constexpr (std::is_same_v<Date, DayNum>)
-            return lut_saturated[toLUTIndex(ExtendedDayNum(d / days * days))].date;
+            return lut_saturated[toLUTIndex(ExtendedDayNum(static_cast<Int32>(d / days * days)))].date;
         else
-            return lut[toLUTIndex(ExtendedDayNum(d / days * days))].date;
+            return lut[toLUTIndex(ExtendedDayNum(static_cast<Int32>(d / days * days)))].date;
     }
 
     template <typename DateOrTime>
@@ -1021,7 +1034,7 @@ public:
         {
             if (unlikely(res < 0))
                 return 0;
-            return res;
+            return static_cast<DateOrTime>(res);
         }
         else
             return res;
@@ -1034,8 +1047,8 @@ public:
         if (likely(offset_is_whole_number_of_minutes_during_epoch))
         {
             if (likely(t >= 0))
-                return t / divisor * divisor;
-            return (t + 1 - divisor) / divisor * divisor;
+                return static_cast<DateOrTime>(t / divisor * divisor);
+            return static_cast<DateOrTime>((t + 1 - divisor) / divisor * divisor);
         }
 
         Time date = find(t).date;
@@ -1044,7 +1057,7 @@ public:
         {
             if (unlikely(res < 0))
                 return 0;
-            return res;
+            return static_cast<UInt32>(res);
         }
         else
             return res;
@@ -1058,7 +1071,7 @@ public:
         if (seconds % 60 == 0)
             return toStartOfMinuteInterval(t, seconds / 60);
 
-        return roundDown(t, seconds);
+        return static_cast<DateOrTime>(roundDown(t, seconds));
     }
 
     inline LUTIndex makeLUTIndex(Int16 year, UInt8 month, UInt8 day_of_month) const
@@ -1236,9 +1249,9 @@ public:
         return lut[new_index].date + time;
     }
 
-    inline NO_SANITIZE_UNDEFINED Time addWeeks(Time t, Int32 delta) const
+    inline NO_SANITIZE_UNDEFINED Time addWeeks(Time t, Int64 delta) const
     {
-        return addDays(t, static_cast<Int64>(delta) * 7);
+        return addDays(t, delta * 7);
     }
 
     inline UInt8 saturateDayOfMonth(Int16 year, UInt8 month, UInt8 day_of_month) const
@@ -1318,9 +1331,9 @@ public:
     }
 
     template <typename DateOrTime>
-    inline auto addQuarters(DateOrTime d, Int32 delta) const
+    inline auto addQuarters(DateOrTime d, Int64 delta) const
     {
-        return addMonths(d, static_cast<Int64>(delta) * 3);
+        return addMonths(d, delta * 3);
     }
 
     template <typename DateOrTime>

src/Common/Dwarf.h

@@ -218,7 +218,7 @@ private:
         // Offset from start to first attribute
         uint8_t attr_offset;
         // Offset within debug info.
-        uint32_t offset;
+        uint64_t offset;
         uint64_t code;
         DIEAbbreviation abbr;
     };
@@ -252,10 +252,10 @@ private:
         uint8_t unit_type = DW_UT_compile; // DW_UT_compile or DW_UT_skeleton
         uint8_t addr_size = 0;
         // Offset in .debug_info of this compilation unit.
-        uint32_t offset = 0;
-        uint32_t size = 0;
+        uint64_t offset = 0;
+        uint64_t size = 0;
         // Offset in .debug_info for the first DIE in this compilation unit.
-        uint32_t first_die = 0;
+        uint64_t first_die = 0;
         uint64_t abbrev_offset = 0;
 
         // The beginning of the CU's contribution to .debug_addr

src/Common/HashTable/Hash.h

@@ -48,6 +48,9 @@ inline DB::UInt64 intHash64(DB::UInt64 x)
 #include <arm_acle.h>
 #endif
 
+/// NOTE: Intel intrinsic can be confusing.
+/// - https://code.google.com/archive/p/sse-intrinsics/wikis/PmovIntrinsicBug.wiki
+/// - https://stackoverflow.com/questions/15752770/mm-crc32-u64-poorly-defined
 inline DB::UInt64 intHashCRC32(DB::UInt64 x)
 {
 #ifdef __SSE4_2__
@@ -56,16 +59,16 @@ inline DB::UInt64 intHashCRC32(DB::UInt64 x)
     return __crc32cd(-1U, x);
 #else
     /// On other platforms we do not have CRC32. NOTE This can be confusing.
+    /// NOTE: consider using intHash32()
     return intHash64(x);
 #endif
 }
-
 inline DB::UInt64 intHashCRC32(DB::UInt64 x, DB::UInt64 updated_value)
 {
 #ifdef __SSE4_2__
     return _mm_crc32_u64(updated_value, x);
 #elif defined(__aarch64__) && defined(__ARM_FEATURE_CRC32)
-    return  __crc32cd(updated_value, x);
+    return __crc32cd(static_cast<UInt32>(updated_value), x);
 #else
     /// On other platforms we do not have CRC32. NOTE This can be confusing.
     return intHash64(x) ^ updated_value;
@@ -123,14 +126,14 @@ inline UInt32 updateWeakHash32(const DB::UInt8 * pos, size_t size, DB::UInt32 up
         }
 
         reinterpret_cast<unsigned char *>(&value)[7] = size;
-        return intHashCRC32(value, updated_value);
+        return static_cast<UInt32>(intHashCRC32(value, updated_value));
     }
 
     const auto * end = pos + size;
     while (pos + 8 <= end)
     {
         auto word = unalignedLoad<UInt64>(pos);
-        updated_value = intHashCRC32(word, updated_value);
+        updated_value = static_cast<UInt32>(intHashCRC32(word, updated_value));
 
         pos += 8;
     }
@@ -148,7 +151,7 @@ inline UInt32 updateWeakHash32(const DB::UInt8 * pos, size_t size, DB::UInt32 up
         /// Use least byte to store tail length.
         word |= tail_size;
         /// Now word is '\3\0\0\0\0XYZ'
-        updated_value = intHashCRC32(word, updated_value);
+        updated_value = static_cast<UInt32>(intHashCRC32(word, updated_value));
     }
 
     return updated_value;
@@ -302,8 +305,8 @@ struct UInt128HashCRC32
     size_t operator()(UInt128 x) const
     {
         UInt64 crc = -1ULL;
-        crc = __crc32cd(crc, x.items[0]);
-        crc = __crc32cd(crc, x.items[1]);
+        crc = __crc32cd(static_cast<UInt32>(crc), x.items[0]);
+        crc = __crc32cd(static_cast<UInt32>(crc), x.items[1]);
         return crc;
     }
 };
@@ -358,10 +361,10 @@ struct UInt256HashCRC32
     size_t operator()(UInt256 x) const
     {
         UInt64 crc = -1ULL;
-        crc = __crc32cd(crc, x.items[0]);
-        crc = __crc32cd(crc, x.items[1]);
-        crc = __crc32cd(crc, x.items[2]);
-        crc = __crc32cd(crc, x.items[3]);
+        crc = __crc32cd(static_cast<UInt32>(crc), x.items[0]);
+        crc = __crc32cd(static_cast<UInt32>(crc), x.items[1]);
+        crc = __crc32cd(static_cast<UInt32>(crc), x.items[2]);
+        crc = __crc32cd(static_cast<UInt32>(crc), x.items[3]);
         return crc;
     }
 };
@@ -423,7 +426,7 @@ inline DB::UInt32 intHash32(DB::UInt64 key)
     key = key + (key << 6);
     key = key ^ ((key >> 22) | (key << 42));
 
-    return key;
+    return static_cast<UInt32>(key);
 }
 
 

src/Common/HashTable/TwoLevelHashTable.h

@@ -44,8 +44,8 @@ protected:
 public:
     using Impl = ImplTable;
 
-    static constexpr size_t NUM_BUCKETS = 1ULL << BITS_FOR_BUCKET;
-    static constexpr size_t MAX_BUCKET = NUM_BUCKETS - 1;
+    static constexpr UInt32 NUM_BUCKETS = 1ULL << BITS_FOR_BUCKET;
+    static constexpr UInt32 MAX_BUCKET = NUM_BUCKETS - 1;
 
     size_t hash(const Key & x) const { return Hash::operator()(x); }
 
@@ -286,13 +286,13 @@ public:
 
     void write(DB::WriteBuffer & wb) const
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             impls[i].write(wb);
     }
 
     void writeText(DB::WriteBuffer & wb) const
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
         {
             if (i != 0)
                 DB::writeChar(',', wb);
@@ -302,13 +302,13 @@ public:
 
     void read(DB::ReadBuffer & rb)
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             impls[i].read(rb);
     }
 
     void readText(DB::ReadBuffer & rb)
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
         {
             if (i != 0)
                 DB::assertChar(',', rb);
@@ -320,7 +320,7 @@ public:
     size_t size() const
     {
         size_t res = 0;
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             res += impls[i].size();
 
         return res;
@@ -328,7 +328,7 @@ public:
 
     bool empty() const
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             if (!impls[i].empty())
                 return false;
 
@@ -338,7 +338,7 @@ public:
     size_t getBufferSizeInBytes() const
     {
         size_t res = 0;
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             res += impls[i].getBufferSizeInBytes();
 
         return res;

src/Common/HashTable/TwoLevelStringHashTable.h

@@ -13,8 +13,8 @@ public:
     using Key = StringRef;
     using Impl = ImplTable;
 
-    static constexpr size_t NUM_BUCKETS = 1ULL << BITS_FOR_BUCKET;
-    static constexpr size_t MAX_BUCKET = NUM_BUCKETS - 1;
+    static constexpr UInt32 NUM_BUCKETS = 1ULL << BITS_FOR_BUCKET;
+    static constexpr UInt32 MAX_BUCKET = NUM_BUCKETS - 1;
 
     // TODO: currently hashing contains redundant computations when doing distributed or external aggregations
     size_t hash(const Key & x) const
@@ -175,13 +175,13 @@ public:
 
     void write(DB::WriteBuffer & wb) const
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             impls[i].write(wb);
     }
 
     void writeText(DB::WriteBuffer & wb) const
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
         {
             if (i != 0)
                 DB::writeChar(',', wb);
@@ -191,13 +191,13 @@ public:
 
     void read(DB::ReadBuffer & rb)
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             impls[i].read(rb);
     }
 
     void readText(DB::ReadBuffer & rb)
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
         {
             if (i != 0)
                 DB::assertChar(',', rb);
@@ -208,7 +208,7 @@ public:
     size_t size() const
     {
         size_t res = 0;
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             res += impls[i].size();
 
         return res;
@@ -216,7 +216,7 @@ public:
 
     bool empty() const
     {
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             if (!impls[i].empty())
                 return false;
 
@@ -226,7 +226,7 @@ public:
     size_t getBufferSizeInBytes() const
     {
         size_t res = 0;
-        for (size_t i = 0; i < NUM_BUCKETS; ++i)
+        for (UInt32 i = 0; i < NUM_BUCKETS; ++i)
             res += impls[i].getBufferSizeInBytes();
 
         return res;

src/Common/HyperLogLogCounter.h

@@ -264,7 +264,8 @@ enum class HyperLogLogMode
 /// of Algorithms).
 template <
     UInt8 precision,
-    typename Hash = IntHash32<UInt64>,
+    typename Key = UInt64,
+    typename Hash = IntHash32<Key>,
     typename HashValueType = UInt32,
     typename DenominatorType = double,
     typename BiasEstimator = TrivialBiasEstimator,
@@ -409,7 +410,9 @@ private:
 
     inline HashValueType getHash(Value key) const
     {
-        return Hash::operator()(key);
+        /// NOTE: this should be OK, since value is the same as key for HLL.
+        return static_cast<HashValueType>(
+            Hash::operator()(static_cast<Key>(key)));
     }
 
     /// Update maximum rank for current bucket.
@@ -532,6 +535,7 @@ private:
 template
 <
     UInt8 precision,
+    typename Key,
     typename Hash,
     typename HashValueType,
     typename DenominatorType,
@@ -542,6 +546,7 @@ template
 details::LogLUT<precision> HyperLogLogCounter
 <
     precision,
+    Key,
     Hash,
     HashValueType,
     DenominatorType,
@@ -555,6 +560,7 @@ details::LogLUT<precision> HyperLogLogCounter
 /// Serialization format must not be changed.
 using HLL12 = HyperLogLogCounter<
     12,
+    UInt64,
     IntHash32<UInt64>,
     UInt32,
     double,

src/Common/HyperLogLogWithSmallSetOptimization.h

@@ -26,7 +26,7 @@ class HyperLogLogWithSmallSetOptimization : private boost::noncopyable
 {
 private:
     using Small = SmallSet<Key, small_set_size>;
-    using Large = HyperLogLogCounter<K, Hash, UInt32, DenominatorType>;
+    using Large = HyperLogLogCounter<K, Key, Hash, UInt32, DenominatorType>;
     using LargeValueType = typename Large::value_type;
 
     Small small;

src/Common/OptimizedRegularExpression.cpp

@@ -506,8 +506,16 @@ unsigned OptimizedRegularExpressionImpl<thread_safe>::match(const char * subject
 
         DB::PODArrayWithStackMemory<StringPieceType, 128> pieces(limit);
 
-        if (!re2->Match(StringPieceType(subject, subject_size), 0, subject_size, RegexType::UNANCHORED, pieces.data(), pieces.size()))
+        if (!re2->Match(
+            StringPieceType(subject, subject_size),
+            0,
+            subject_size,
+            RegexType::UNANCHORED,
+            pieces.data(),
+            static_cast<int>(pieces.size())))
+        {
             return 0;
+        }
         else
         {
             matches.resize(limit);

src/Common/OvercommitTracker.cpp

@@ -5,6 +5,7 @@
 #include <Common/ProfileEvents.h>
 #include <Interpreters/ProcessList.h>
 
+
 namespace ProfileEvents
 {
     extern const Event MemoryOvercommitWaitTimeMicroseconds;
@@ -170,7 +171,8 @@ void UserOvercommitTracker::pickQueryToExcludeImpl()
 
 GlobalOvercommitTracker::GlobalOvercommitTracker(DB::ProcessList * process_list_)
     : OvercommitTracker(process_list_)
-{}
+{
+}
 
 void GlobalOvercommitTracker::pickQueryToExcludeImpl()
 {
@@ -180,16 +182,16 @@ void GlobalOvercommitTracker::pickQueryToExcludeImpl()
     // This is guaranteed by locking global_mutex in OvercommitTracker::needToStopQuery.
     for (auto const & query : process_list->processes)
     {
-        if (query.isKilled())
+        if (query->isKilled())
             continue;
 
         Int64 user_soft_limit = 0;
-        if (auto const * user_process_list = query.getUserProcessList())
+        if (auto const * user_process_list = query->getUserProcessList())
             user_soft_limit = user_process_list->user_memory_tracker.getSoftLimit();
         if (user_soft_limit == 0)
             continue;
 
-        auto * memory_tracker = query.getMemoryTracker();
+        auto * memory_tracker = query->getMemoryTracker();
         if (!memory_tracker)
             continue;
         auto ratio = memory_tracker->getOvercommitRatio(user_soft_limit);

src/Common/PoolWithFailoverBase.h

@@ -339,7 +339,7 @@ struct PoolWithFailoverBase<TNestedPool>::PoolState
     Int64 config_priority = 1;
     /// Priority from the GetPriorityFunc.
     Int64 priority = 0;
-    UInt32 random = 0;
+    UInt64 random = 0;
 
     void randomize()
     {
@@ -353,7 +353,7 @@ struct PoolWithFailoverBase<TNestedPool>::PoolState
     }
 
 private:
-    std::minstd_rand rng = std::minstd_rand(randomSeed());
+    std::minstd_rand rng = std::minstd_rand(static_cast<uint_fast32_t>(randomSeed()));
 };
 
 template <typename TNestedPool>

src/Common/QueryProfiler.cpp

@@ -132,11 +132,11 @@ QueryProfilerBase<ProfilerImpl>::QueryProfilerBase(UInt64 thread_id, int clock_t
         sev.sigev_signo = pause_signal;
 
 #if defined(OS_FREEBSD)
-        sev._sigev_un._threadid = thread_id;
+        sev._sigev_un._threadid = static_cast<pid_t>(thread_id);
 #elif defined(USE_MUSL)
-        sev.sigev_notify_thread_id = thread_id;
+        sev.sigev_notify_thread_id = static_cast<pid_t>(thread_id);
 #else
-        sev._sigev_un._tid = thread_id;
+        sev._sigev_un._tid = static_cast<pid_t>(thread_id);
 #endif
         timer_t local_timer_id;
         if (timer_create(clock_type, &sev, &local_timer_id))

src/Common/RadixSort.h

@@ -273,13 +273,13 @@ private:
 
         {
             /// Replace the histograms with the accumulated sums: the value in position i is the sum of the previous positions minus one.
-            size_t sums[NUM_PASSES] = {0};
+            CountType sums[NUM_PASSES] = {0};
 
             for (size_t i = 0; i < HISTOGRAM_SIZE; ++i)
             {
                 for (size_t pass = 0; pass < NUM_PASSES; ++pass)
                 {
-                    size_t tmp = histograms[pass * HISTOGRAM_SIZE + i] + sums[pass];
+                    CountType tmp = histograms[pass * HISTOGRAM_SIZE + i] + sums[pass];
                     histograms[pass * HISTOGRAM_SIZE + i] = sums[pass] - 1;
                     sums[pass] = tmp;
                 }

src/Common/StringSearcher.h

@@ -40,7 +40,7 @@ public:
 #ifdef __SSE2__
 protected:
     static constexpr auto n = sizeof(__m128i);
-    const int page_size = ::getPageSize();
+    const Int64 page_size = ::getPageSize();
 
     bool pageSafe(const void * const ptr) const
     {

src/Common/ThreadPool.cpp

@@ -87,7 +87,7 @@ void ThreadPoolImpl<Thread>::setQueueSize(size_t value)
 
 template <typename Thread>
 template <typename ReturnType>
-ReturnType ThreadPoolImpl<Thread>::scheduleImpl(Job job, int priority, std::optional<uint64_t> wait_microseconds, bool propagate_opentelemetry_tracing_context)
+ReturnType ThreadPoolImpl<Thread>::scheduleImpl(Job job, ssize_t priority, std::optional<uint64_t> wait_microseconds, bool propagate_opentelemetry_tracing_context)
 {
     auto on_error = [&](const std::string & reason)
     {
@@ -163,19 +163,19 @@ ReturnType ThreadPoolImpl<Thread>::scheduleImpl(Job job, int priority, std::opti
 }
 
 template <typename Thread>
-void ThreadPoolImpl<Thread>::scheduleOrThrowOnError(Job job, int priority)
+void ThreadPoolImpl<Thread>::scheduleOrThrowOnError(Job job, ssize_t priority)
 {
     scheduleImpl<void>(std::move(job), priority, std::nullopt);
 }
 
 template <typename Thread>
-bool ThreadPoolImpl<Thread>::trySchedule(Job job, int priority, uint64_t wait_microseconds) noexcept
+bool ThreadPoolImpl<Thread>::trySchedule(Job job, ssize_t priority, uint64_t wait_microseconds) noexcept
 {
     return scheduleImpl<bool>(std::move(job), priority, wait_microseconds);
 }
 
 template <typename Thread>
-void ThreadPoolImpl<Thread>::scheduleOrThrow(Job job, int priority, uint64_t wait_microseconds, bool propagate_opentelemetry_tracing_context)
+void ThreadPoolImpl<Thread>::scheduleOrThrow(Job job, ssize_t priority, uint64_t wait_microseconds, bool propagate_opentelemetry_tracing_context)
 {
     scheduleImpl<void>(std::move(job), priority, wait_microseconds, propagate_opentelemetry_tracing_context);
 }

src/Common/ThreadPool.h

@@ -50,13 +50,13 @@ public:
     /// NOTE: Probably you should call wait() if exception was thrown. If some previously scheduled jobs are using some objects,
     /// located on stack of current thread, the stack must not be unwinded until all jobs finished. However,
     /// if ThreadPool is a local object, it will wait for all scheduled jobs in own destructor.
-    void scheduleOrThrowOnError(Job job, int priority = 0);
+    void scheduleOrThrowOnError(Job job, ssize_t priority = 0);
 
     /// Similar to scheduleOrThrowOnError(...). Wait for specified amount of time and schedule a job or return false.
-    bool trySchedule(Job job, int priority = 0, uint64_t wait_microseconds = 0) noexcept;
+    bool trySchedule(Job job, ssize_t priority = 0, uint64_t wait_microseconds = 0) noexcept;
 
     /// Similar to scheduleOrThrowOnError(...). Wait for specified amount of time and schedule a job or throw an exception.
-    void scheduleOrThrow(Job job, int priority = 0, uint64_t wait_microseconds = 0, bool propagate_opentelemetry_tracing_context = true);
+    void scheduleOrThrow(Job job, ssize_t priority = 0, uint64_t wait_microseconds = 0, bool propagate_opentelemetry_tracing_context = true);
 
     /// Wait for all currently active jobs to be done.
     /// You may call schedule and wait many times in arbitrary order.
@@ -96,10 +96,10 @@ private:
     struct JobWithPriority
     {
         Job job;
-        int priority;
+        ssize_t priority;
         DB::OpenTelemetry::TracingContextOnThread thread_trace_context;
 
-        JobWithPriority(Job job_, int priority_, const DB::OpenTelemetry::TracingContextOnThread& thread_trace_context_)
+        JobWithPriority(Job job_, ssize_t priority_, const DB::OpenTelemetry::TracingContextOnThread& thread_trace_context_)
             : job(job_), priority(priority_), thread_trace_context(thread_trace_context_) {}
 
         bool operator< (const JobWithPriority & rhs) const
@@ -113,7 +113,7 @@ private:
     std::exception_ptr first_exception;
 
     template <typename ReturnType>
-    ReturnType scheduleImpl(Job job, int priority, std::optional<uint64_t> wait_microseconds, bool propagate_opentelemetry_tracing_context = true);
+    ReturnType scheduleImpl(Job job, ssize_t priority, std::optional<uint64_t> wait_microseconds, bool propagate_opentelemetry_tracing_context = true);
 
     void worker(typename std::list<Thread>::iterator thread_it);
 

src/Common/ThreadProfileEvents.cpp

@@ -121,7 +121,7 @@ TasksStatsCounters::TasksStatsCounters(const UInt64 tid, const MetricsProvider p
         stats_getter = [metrics_provider = std::make_shared<TaskStatsInfoGetter>(), tid]()
                 {
                     ::taskstats result{};
-                    metrics_provider->getStat(result, tid);
+                    metrics_provider->getStat(result, static_cast<pid_t>(tid));
                     return result;
                 };
         break;
@@ -526,7 +526,7 @@ void PerfEventsCounters::finalizeProfileEvents(ProfileEvents::Counters & profile
             continue;
 
         constexpr ssize_t bytes_to_read = sizeof(current_values[0]);
-        const int bytes_read = read(fd, &current_values[i], bytes_to_read);
+        const ssize_t bytes_read = read(fd, &current_values[i], bytes_to_read);
 
         if (bytes_read != bytes_to_read)
         {

src/Common/UTF8Helpers.h

@@ -99,7 +99,10 @@ requires (sizeof(CharT) == 1)
 size_t convertCodePointToUTF8(int code_point, CharT * out_bytes, size_t out_length)
 {
     static const Poco::UTF8Encoding utf8;
-    int res = utf8.convert(code_point, reinterpret_cast<uint8_t *>(out_bytes), out_length);
+    int res = utf8.convert(
+        code_point,
+        reinterpret_cast<uint8_t *>(out_bytes),
+        static_cast<int>(out_length));
     assert(res >= 0);
     return res;
 }
@@ -109,7 +112,9 @@ requires (sizeof(CharT) == 1)
 std::optional<uint32_t> convertUTF8ToCodePoint(const CharT * in_bytes, size_t in_length)
 {
     static const Poco::UTF8Encoding utf8;
-    int res = utf8.queryConvert(reinterpret_cast<const uint8_t *>(in_bytes), in_length);
+    int res = utf8.queryConvert(
+        reinterpret_cast<const uint8_t *>(in_bytes),
+        static_cast<int>(in_length));
 
     if (res >= 0)
         return res;

src/Common/Volnitsky.h

@@ -404,7 +404,8 @@ public:
         /// And also adding from the end guarantees that we will find first occurrence because we will lookup bigger offsets first.
         for (auto i = static_cast<ssize_t>(needle_size - sizeof(VolnitskyTraits::Ngram)); i >= 0; --i)
         {
-            bool ok = VolnitskyTraits::putNGram<CaseSensitive, ASCII>(needle + i, i + 1, needle, needle_size, callback);
+            bool ok = VolnitskyTraits::putNGram<CaseSensitive, ASCII>(
+                needle + i, static_cast<int>(i + 1), needle, needle_size, callback);
 
             /** `putNGramUTF8CaseInsensitive` does not work if characters with lower and upper cases
               * are represented by different number of bytes or code points.

src/Common/ZooKeeper/TestKeeper.cpp

@@ -218,7 +218,7 @@ std::pair<ResponsePtr, Undo> TestKeeperCreateRequest::process(TestKeeper::Contai
             created_node.stat.ctime = std::chrono::system_clock::now().time_since_epoch() / std::chrono::milliseconds(1);
             created_node.stat.mtime = created_node.stat.ctime;
             created_node.stat.numChildren = 0;
-            created_node.stat.dataLength = data.length();
+            created_node.stat.dataLength = static_cast<int>(data.length());
             created_node.data = data;
             created_node.is_ephemeral = is_ephemeral;
             created_node.is_sequental = is_sequential;

src/Common/ZooKeeper/ZooKeeper.h

@@ -45,7 +45,7 @@ struct ShuffleHost
 {
     String host;
     Int64 priority = 0;
-    UInt32 random = 0;
+    UInt64 random = 0;
 
     void randomize()
     {