Merge remote-tracking branch 'rschu1ze/master' into clang-tidy-reenable-checks

base/base/hex.h

@@ -289,3 +289,13 @@ inline void writeBinByte(UInt8 byte, void * out)
 {
     memcpy(out, &impl::bin_byte_to_char_table[static_cast<size_t>(byte) * 8], 8);
 }
+
+/// Converts byte array to a hex string. Useful for debug logging.
+inline std::string hexString(const void * data, size_t size)
+{
+    const char * p = reinterpret_cast<const char *>(data);
+    std::string s(size * 2, '\0');
+    for (size_t i = 0; i < size; ++i)
+        writeHexByteLowercase(p[i], s.data() + i * 2);
+    return s;
+}

cmake/tools.cmake

@@ -75,9 +75,11 @@ endif ()
 
 if (LINKER_NAME)
     message(STATUS "Using linker: ${LINKER_NAME}")
-else()
+elseif (NOT ARCH_S390X AND NOT OS_FREEBSD)
+    message (FATAL_ERROR "The only supported linker is LLVM's LLD, but we cannot find it.")
+else ()
     message(STATUS "Using linker: <default>")
-endif()
+endif ()
 
 # Archiver
 

docker/packager/binary/build.sh

@@ -56,7 +56,7 @@ ccache_status
 ccache --zero-stats ||:
 
 # Check whether the directory with pre-build scripts exists and not empty.
-if [ -d "/build/packages/pre-build" ] && [ -z "$(ls -A /build/packages/pre-build)" ]; then
+if [ ! -d "/build/packages/pre-build" ] || [ -n "$(ls -A /build/packages/pre-build)" ]; then
    echo "There are no subcommands to execute :)"
 else
   # Execute all commands

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

@@ -7,28 +7,34 @@ Contains information about normal and aggregate functions.
 
 Columns:
 
-- `name`(`String`) – The name of the function.
+- `name` ([String](../../sql-reference/data-types/string.md)) – The name of the function.
-- `is_aggregate`(`UInt8`) — Whether the function is aggregate.
+- `is_aggregate` ([UInt8](../../sql-reference/data-types/int-uint.md)) — Whether the function is an aggregate function.
+- `is_deterministic` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt8](../../sql-reference/data-types/int-uint.md))) - Whether the function is deterministic.
+- `case_insensitive`, ([UInt8](../../sql-reference/data-types/int-uint.md)) - Whether the function name can be used case-insensitively.
+- `alias_to`, ([String](../../sql-reference/data-types/string.md)) - The original function name, if the function name is an alias.
+- `create_query`, ([String](../../sql-reference/data-types/enum.md)) - Unused.
+- `origin`, ([Enum8](../../sql-reference/data-types/string.md)) - Unused.
+- `description`, ([String](../../sql-reference/data-types/string.md)) - A high-level description what the function does.
+- `syntax`, ([String](../../sql-reference/data-types/string.md)) - Signature of the function.
+- `arguments`, ([String](../../sql-reference/data-types/string.md)) - What arguments does the function take.
+- `returned_value`, ([String](../../sql-reference/data-types/string.md)) - What does the function return.
+- `examples`, ([String](../../sql-reference/data-types/string.md)) - Example usage of the function.
+- `categories`, ([String](../../sql-reference/data-types/string.md)) - The category of the function.
 
 **Example**
 
 ```sql
- SELECT * FROM system.functions LIMIT 10;
+ SELECT name, is_aggregate, is_deterministic, case_insensitive, alias_to FROM system.functions LIMIT 5;
 ```
 
 ```text
-┌─name──────────────────┬─is_aggregate─┬─case_insensitive─┬─alias_to─┬─create_query─┬─origin─┐
+┌─name─────────────────────┬─is_aggregate─┬─is_deterministic─┬─case_insensitive─┬─alias_to─┐
-│ logTrace              │            0 │                0 │          │              │ System │
+│ BLAKE3                   │            0 │                1 │                0 │          │
-│ aes_decrypt_mysql     │            0 │                0 │          │              │ System │
+│ sipHash128Reference      │            0 │                1 │                0 │          │
-│ aes_encrypt_mysql     │            0 │                0 │          │              │ System │
+│ mapExtractKeyLike        │            0 │                1 │                0 │          │
-│ decrypt               │            0 │                0 │          │              │ System │
+│ sipHash128ReferenceKeyed │            0 │                1 │                0 │          │
-│ encrypt               │            0 │                0 │          │              │ System │
+│ mapPartialSort           │            0 │                1 │                0 │          │
-│ toBool                │            0 │                0 │          │              │ System │
+└──────────────────────────┴──────────────┴──────────────────┴──────────────────┴──────────┘
-│ windowID              │            0 │                0 │          │              │ System │
-│ hopStart              │            0 │                0 │          │              │ System │
-│ hop                   │            0 │                0 │          │              │ System │
-│ snowflakeToDateTime64 │            0 │                0 │          │              │ System │
-└───────────────────────┴──────────────┴──────────────────┴──────────┴──────────────┴────────┘
 
-10 rows in set. Elapsed: 0.002 sec.
+5 rows in set. Elapsed: 0.002 sec.
 ```

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

@@ -198,8 +198,10 @@ Columns:
     - `FOREIGN TABLE`
     - `LOCAL TEMPORARY`
     - `SYSTEM VIEW`
+- `data_length` ([Nullable](../../sql-reference/data-types/nullable.md)([UInt64](../../sql-reference/data-types/int-uint.md))) — The size of
+  the data on-disk. NULL if it could not be determined.
+- `table_collation` ([Nullable](../../sql-reference/data-types/nullable.md)([String](../../sql-reference/data-types/string.md))) — The table default collation. Always `utf8mb4_0900_ai_ci`.
 - `table_comment` ([Nullable](../../sql-reference/data-types/nullable.md)([String](../../sql-reference/data-types/string.md))) — The comment used when creating the table.
-- `table_collation` ([Nullable](../../sql-reference/data-types/nullable.md)([String](../../sql-reference/data-types/string.md))) — The table default collation. Always `utf8mb4`.
 
 **Example**
 
@@ -291,7 +293,7 @@ is_trigger_deletable:       NO
 is_trigger_insertable_into: NO
 ```
 
-## KEY_COLUMN_USAGE (#key_column_usage)
+## KEY_COLUMN_USAGE {#key_column_usage}
 
 Contains columns from the [system.tables](../../operations/system-tables/tables.md) system table which are restricted by constraints.
 
@@ -350,7 +352,7 @@ referenced_table_name:         ᴺᵁᴸᴸ
 referenced_column_name:        ᴺᵁᴸᴸ
 ```
 
-## REFERENTIAL_CONSTRAINTS (#referential_constraints)
+## REFERENTIAL_CONSTRAINTS {#referential_constraints}
 
 Contains information about foreign keys. Currently returns an empty result (no rows) which is just enough to provide compatibility with 3rd party tools like Tableau Online.
 

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

@@ -684,12 +684,12 @@ Like [hasSubsequenceUTF8](#hasSubsequenceUTF8) but searches case-insensitively.
 
 ## byteHammingDistance
 
-Calculates the hamming distance between two byte strings.
+Calculates the [hamming distance](https://en.wikipedia.org/wiki/Hamming_distance) between two byte strings.
 
 **Syntax**
 
 ```sql
-byteHammingDistance(haystack, needle)
+byteHammingDistance(string2, string2)
 ```
 
 **Examples**
@@ -710,12 +710,12 @@ Result:
 
 ## byteJaccardIndex
 
-Calculates the jaccard similarity index between two byte strings.
+Calculates the [Jaccard similarity index](https://en.wikipedia.org/wiki/Jaccard_index) between two byte strings.
 
 **Syntax**
 
 ```sql
-byteJaccardIndex(haystack, needle)
+byteJaccardIndex(string1, string2)
 ```
 
 **Examples**
@@ -734,12 +734,12 @@ Result:
 
 ## byteEditDistance
 
-Calculates the edit distance between two byte strings.
+Calculates the [edit distance](https://en.wikipedia.org/wiki/Edit_distance) between two byte strings.
 
 **Syntax**
 
 ```sql
-byteEidtDistance(haystack, needle)
+byteEditDistance(string1, string2)
 ```
 
 **Examples**

programs/diagnostics/testdata/configs/xml/config.xml

@@ -760,27 +760,6 @@
     </graphite>
     -->
 
-    <!-- Serve endpoint for Prometheus monitoring. -->
-    <!--
-        endpoint - mertics path (relative to root, statring with "/")
-        port - port to setup server. If not defined or 0 than http_port used
-        metrics - send data from table system.metrics
-        events - send data from table system.events
-        asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
-    -->
-    <!--
-    <prometheus>
-        <endpoint>/metrics</endpoint>
-        <port>9363</port>
-
-        <metrics>true</metrics>
-        <events>true</events>
-        <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
-    </prometheus>
-    -->
-
     <!-- Query log. Used only for queries with setting log_queries = 1. -->
     <query_log>
         <!-- What table to insert data. If table is not exist, it will be created.

programs/diagnostics/testdata/configs/yaml/config.yaml

@@ -638,7 +638,6 @@ default_session_timeout: 60
 # metrics - send data from table system.metrics
 # events - send data from table system.events
 # asynchronous_metrics - send data from table system.asynchronous_metrics
-# status_info - send data from different component from CH, ex: Dictionaries status
 
 # prometheus:
 #     endpoint: /metrics
@@ -647,7 +646,6 @@ default_session_timeout: 60
 #     metrics: true
 #     events: true
 #     asynchronous_metrics: true
-#     status_info: true
 
 # Query log. Used only for queries with setting log_queries = 1.
 query_log:

programs/diagnostics/testdata/configs/yandex_xml/config.xml

@@ -760,27 +760,6 @@
     </graphite>
     -->
 
-    <!-- Serve endpoint for Prometheus monitoring. -->
-    <!--
-        endpoint - mertics path (relative to root, statring with "/")
-        port - port to setup server. If not defined or 0 than http_port used
-        metrics - send data from table system.metrics
-        events - send data from table system.events
-        asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
-    -->
-    <!--
-    <prometheus>
-        <endpoint>/metrics</endpoint>
-        <port>9363</port>
-
-        <metrics>true</metrics>
-        <events>true</events>
-        <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
-    </prometheus>
-    -->
-
     <!-- Query log. Used only for queries with setting log_queries = 1. -->
     <query_log>
         <!-- What table to insert data. If table is not exist, it will be created.

programs/server/config.xml

@@ -969,7 +969,6 @@
         metrics - send data from table system.metrics
         events - send data from table system.events
         asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
     -->
     <!--
     <prometheus>
@@ -979,7 +978,6 @@
         <metrics>true</metrics>
         <events>true</events>
         <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
     </prometheus>
     -->
 

programs/server/config.yaml.example

@@ -639,7 +639,6 @@ default_session_timeout: 60
 # metrics - send data from table system.metrics
 # events - send data from table system.events
 # asynchronous_metrics - send data from table system.asynchronous_metrics
-# status_info - send data from different component from CH, ex: Dictionaries status
 
 # prometheus:
 #     endpoint: /metrics
@@ -648,7 +647,6 @@ default_session_timeout: 60
 #     metrics: true
 #     events: true
 #     asynchronous_metrics: true
-#     status_info: true
 
 # Query log. Used only for queries with setting log_queries = 1.
 query_log:

src/Client/MultiplexedConnections.cpp

@@ -1,10 +1,13 @@
 #include <Client/MultiplexedConnections.h>
 
 #include <Common/thread_local_rng.h>
+#include <Common/logger_useful.h>
 #include <Core/Protocol.h>
 #include <IO/ConnectionTimeouts.h>
 #include <IO/Operators.h>
 #include <Interpreters/ClientInfo.h>
+#include <base/getThreadId.h>
+#include <base/hex.h>
 
 namespace DB
 {
@@ -19,6 +22,13 @@ namespace ErrorCodes
 }
 
 
+#define MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION \
+    mutex_last_locked_by.store((getThreadId() << 32) | __LINE__); \
+    memcpy(mutex_memory_dump.data(), &cancel_mutex, mutex_memory_dump.size()); \
+    mutex_locked += 1; \
+    SCOPE_EXIT({ mutex_locked -= 1; });
+
+
 MultiplexedConnections::MultiplexedConnections(Connection & connection, const Settings & settings_, const ThrottlerPtr & throttler)
     : settings(settings_)
 {
@@ -73,6 +83,7 @@ MultiplexedConnections::MultiplexedConnections(
 void MultiplexedConnections::sendScalarsData(Scalars & data)
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
 
     if (!sent_query)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot send scalars data: query not yet sent.");
@@ -88,6 +99,7 @@ void MultiplexedConnections::sendScalarsData(Scalars & data)
 void MultiplexedConnections::sendExternalTablesData(std::vector<ExternalTablesData> & data)
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
 
     if (!sent_query)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot send external tables data: query not yet sent.");
@@ -116,6 +128,7 @@ void MultiplexedConnections::sendQuery(
     bool with_pending_data)
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
 
     if (sent_query)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Query already sent.");
@@ -173,6 +186,7 @@ void MultiplexedConnections::sendQuery(
 void MultiplexedConnections::sendIgnoredPartUUIDs(const std::vector<UUID> & uuids)
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
 
     if (sent_query)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot send uuids after query is sent.");
@@ -189,6 +203,7 @@ void MultiplexedConnections::sendIgnoredPartUUIDs(const std::vector<UUID> & uuid
 void MultiplexedConnections::sendReadTaskResponse(const String & response)
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
     if (cancelled)
         return;
     current_connection->sendReadTaskResponse(response);
@@ -198,6 +213,7 @@ void MultiplexedConnections::sendReadTaskResponse(const String & response)
 void MultiplexedConnections::sendMergeTreeReadTaskResponse(const ParallelReadResponse & response)
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
     if (cancelled)
         return;
     current_connection->sendMergeTreeReadTaskResponse(response);
@@ -207,13 +223,29 @@ void MultiplexedConnections::sendMergeTreeReadTaskResponse(const ParallelReadRes
 Packet MultiplexedConnections::receivePacket()
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
     Packet packet = receivePacketUnlocked({});
     return packet;
 }
 
 void MultiplexedConnections::disconnect()
 {
-    std::lock_guard lock(cancel_mutex);
+    /// We've seen this lock mysteriously get stuck forever, without any other thread seeming to
+    /// hold the mutex. This is temporary code to print some extra information next time it happens.
+    /// std::lock_guard lock(cancel_mutex);
+    if (!cancel_mutex.try_lock_for(std::chrono::hours(1)))
+    {
+        UInt64 last_locked = mutex_last_locked_by.load();
+        std::array<UInt8, sizeof(std::timed_mutex)> new_memory_dump;
+        memcpy(new_memory_dump.data(), &cancel_mutex, new_memory_dump.size());
+        LOG_ERROR(&Poco::Logger::get("MultiplexedConnections"), "Deadlock in MultiplexedConnections::disconnect()! Mutex was last (instrumentedly) locked by thread {} on line {}, lock balance: {}, mutex memory when last locked: {}, mutex memory now: {}", last_locked >> 32, last_locked & 0xffffffff, mutex_locked.load(), hexString(mutex_memory_dump.data(), mutex_memory_dump.size()), hexString(new_memory_dump.data(), new_memory_dump.size()));
+        throw Exception(ErrorCodes::LOGICAL_ERROR, "Deadlock in MultiplexedConnections::disconnect()");
+    }
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wthread-safety-analysis"
+    std::lock_guard lock(cancel_mutex, std::adopt_lock);
+#pragma clang diagnostic pop
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
 
     for (ReplicaState & state : replica_states)
     {
@@ -229,6 +261,7 @@ void MultiplexedConnections::disconnect()
 void MultiplexedConnections::sendCancel()
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
 
     if (!sent_query || cancelled)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot cancel. Either no query sent or already cancelled.");
@@ -246,6 +279,7 @@ void MultiplexedConnections::sendCancel()
 Packet MultiplexedConnections::drain()
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
 
     if (!cancelled)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot drain connections: cancel first.");
@@ -286,6 +320,7 @@ Packet MultiplexedConnections::drain()
 std::string MultiplexedConnections::dumpAddresses() const
 {
     std::lock_guard lock(cancel_mutex);
+    MUTEX_LOCK_TEMPORARY_DEBUG_INSTRUMENTATION
     return dumpAddressesUnlocked();
 }
 

src/Client/MultiplexedConnections.h

@@ -105,9 +105,15 @@ private:
     /// std::nullopt if parallel reading from replicas is not used
     std::optional<ReplicaInfo> replica_info;
 
-    /// A mutex for the sendCancel function to execute safely
+    /// A mutex for the sendCancel function to execute safely in separate thread.
-    /// in separate thread.
+    mutable std::timed_mutex cancel_mutex;
-    mutable std::mutex cancel_mutex;
+
+    /// Temporary instrumentation to debug a weird deadlock on cancel_mutex.
+    /// TODO: Once the investigation is done, get rid of these, and of INSTRUMENTED_LOCK_MUTEX, and
+    ///       change cancel_mutex to std::mutex.
+    mutable std::atomic<UInt64> mutex_last_locked_by{0};
+    mutable std::atomic<Int64> mutex_locked{0};
+    mutable std::array<UInt8, sizeof(std::timed_mutex)> mutex_memory_dump;
 
     friend struct RemoteQueryExecutorRoutine;
 };

src/Common/ProfileEvents.cpp

@@ -211,6 +211,7 @@
     \
     M(RegexpCreated, "Compiled regular expressions. Identical regular expressions compiled just once and cached forever.") \
     M(ContextLock, "Number of times the lock of Context was acquired or tried to acquire. This is global lock.") \
+    M(ContextLockWaitMicroseconds, "Context lock wait time in microseconds") \
     \
     M(StorageBufferFlush, "Number of times a buffer in a 'Buffer' table was flushed.") \
     M(StorageBufferErrorOnFlush, "Number of times a buffer in the 'Buffer' table has not been able to flush due to error writing in the destination table.") \

src/Common/StatusInfo.cpp

@@ -1,57 +0,0 @@
-#include <Common/StatusInfo.h>
-#include <Common/ExternalLoaderStatus.h>
-
-/// Available status. Add something here as you wish.
-#define APPLY_FOR_STATUS(M) \
-    M(DictionaryStatus, "Dictionary Status.", DB::getStatusEnumAllPossibleValues()) \
-
-
-namespace CurrentStatusInfo
-{
-    #define M(NAME, DOCUMENTATION, ENUM) extern const Status NAME = Status(__COUNTER__);
-        APPLY_FOR_STATUS(M)
-    #undef M
-    constexpr Status END = Status(__COUNTER__);
-
-    std::mutex locks[END] {};
-    std::unordered_map<String, Int8> values[END] {};
-
-    const char * getName(Status event)
-    {
-        static const char * strings[] =
-        {
-        #define M(NAME, DOCUMENTATION, ENUM) #NAME,
-            APPLY_FOR_STATUS(M)
-        #undef M
-        };
-
-        return strings[event];
-    }
-
-    const char * getDocumentation(Status event)
-    {
-        static const char * strings[] =
-        {
-        #define M(NAME, DOCUMENTATION, ENUM) #DOCUMENTATION,
-            APPLY_FOR_STATUS(M)
-        #undef M
-        };
-
-        return strings[event];
-    }
-
-    const std::vector<std::pair<String, Int8>> & getAllPossibleValues(Status event)
-    {
-        static const std::vector<std::pair<String, Int8>> enum_values [] =
-        {
-        #define M(NAME, DOCUMENTATION, ENUM) ENUM,
-            APPLY_FOR_STATUS(M)
-        #undef M
-        };
-        return enum_values[event];
-    }
-
-    Status end() { return END; }
-}
-
-#undef APPLY_FOR_STATUS

src/Common/StatusInfo.h

@@ -1,39 +0,0 @@
-#pragma once
-
-#include <stddef.h>
-#include <cstdint>
-#include <utility>
-#include <atomic>
-#include <vector>
-#include <base/types.h>
-#include <base/strong_typedef.h>
-#include <mutex>
-#include <unordered_map>
-
-
-namespace CurrentStatusInfo
-{
-    using Status = StrongTypedef<size_t, struct StatusTag>;
-    using Key = std::string;
-
-    const char * getName(Status event);
-    const char * getDocumentation(Status event);
-    const std::vector<std::pair<String, Int8>> & getAllPossibleValues(Status event);
-
-    extern std::unordered_map<String, Int8> values[];
-    extern std::mutex locks[];
-
-    Status end();
-
-    inline void set(Status status, Key key, Int8 value)
-    {
-        std::lock_guard lock(locks[status]);
-        values[status][key] = value;
-    }
-
-    inline void unset(Status status, Key key)
-    {
-        std::lock_guard lock(locks[status]);
-        values[status].erase(key);
-    }
-}

src/Core/Settings.h

@@ -149,7 +149,7 @@ class IColumn;
     M(Bool, allow_suspicious_indices, false, "Reject primary/secondary indexes and sorting keys with identical expressions", 0) \
     M(Bool, compile_expressions, false, "Compile some scalar functions and operators to native code.", 0) \
     M(UInt64, min_count_to_compile_expression, 3, "The number of identical expressions before they are JIT-compiled", 0) \
-    M(Bool, compile_aggregate_expressions, true, "Compile aggregate functions to native code. This feature has a bug and should not be used.", 0) \
+    M(Bool, compile_aggregate_expressions, true, "Compile aggregate functions to native code.", 0) \
     M(UInt64, min_count_to_compile_aggregate_expression, 3, "The number of identical aggregate expressions before they are JIT-compiled", 0) \
     M(Bool, compile_sort_description, true, "Compile sort description to native code.", 0) \
     M(UInt64, min_count_to_compile_sort_description, 3, "The number of identical sort descriptions before they are JIT-compiled", 0) \

src/Functions/FunctionsStringDistance.cpp

@@ -18,7 +18,7 @@ extern const int TOO_LARGE_STRING_SIZE;
 }
 
 template <typename Op>
-struct FunctionDistanceImpl
+struct FunctionStringDistanceImpl
 {
     using ResultType = typename Op::ResultType;
 
@@ -195,12 +195,11 @@ struct NameByteEditDistance
     static constexpr auto name = "byteEditDistance";
 };
 
-using FunctionByteHammingDistance
+using FunctionByteHammingDistance = FunctionsStringSimilarity<FunctionStringDistanceImpl<ByteHammingDistanceImpl>, NameByteHammingDistance>;
-    = FunctionsStringSimilarity<FunctionDistanceImpl<ByteHammingDistanceImpl>, NameByteHammingDistance>;
 
-using FunctionByteJaccardIndex = FunctionsStringSimilarity<FunctionDistanceImpl<ByteJaccardIndexImpl>, NameByteJaccardIndex>;
+using FunctionByteJaccardIndex = FunctionsStringSimilarity<FunctionStringDistanceImpl<ByteJaccardIndexImpl>, NameByteJaccardIndex>;
 
-using FunctionByteEditDistance = FunctionsStringSimilarity<FunctionDistanceImpl<ByteEditDistanceImpl>, NameByteEditDistance>;
+using FunctionByteEditDistance = FunctionsStringSimilarity<FunctionStringDistanceImpl<ByteEditDistanceImpl>, NameByteEditDistance>;
 
 REGISTER_FUNCTION(StringHammingDistance)
 {

src/Functions/if.cpp

@@ -1096,22 +1096,25 @@ public:
             return res != nullptr;
         };
 
-        TypeIndex left_id = arg_then.type->getTypeId();
+        DataTypePtr left_type = arg_then.type;
-        TypeIndex right_id = arg_else.type->getTypeId();
+        DataTypePtr right_type = arg_else.type;
 
         if (const auto * left_array = checkAndGetDataType<DataTypeArray>(arg_then.type.get()))
-            left_id = left_array->getNestedType()->getTypeId();
+            left_type = left_array->getNestedType();
 
         if (const auto * right_array = checkAndGetDataType<DataTypeArray>(arg_else.type.get()))
-            right_id = right_array->getNestedType()->getTypeId();
+            right_type = right_array->getNestedType();
 
         /// Special case when one column is Integer and another is UInt64 that can be actually Int64.
         /// The result type for this case is Int64 and we need to change UInt64 type to Int64
         /// so the NumberTraits::ResultOfIf will return Int64 instead if Int128.
-        if (isNativeInteger(arg_then.type) && isUInt64ThatCanBeInt64(arg_else.type))
+        if (isNativeInteger(left_type) && isUInt64ThatCanBeInt64(right_type))
-            right_id = TypeIndex::Int64;
+            right_type = std::make_shared<DataTypeInt64>();
-        else if (isNativeInteger(arg_else.type) && isUInt64ThatCanBeInt64(arg_then.type))
+        else if (isNativeInteger(right_type) && isUInt64ThatCanBeInt64(left_type))
-            left_id = TypeIndex::Int64;
+            left_type = std::make_shared<DataTypeInt64>();
+
+        TypeIndex left_id = left_type->getTypeId();
+        TypeIndex right_id = right_type->getTypeId();
 
         if (!(callOnBasicTypes<true, true, true, false>(left_id, right_id, call)
             || (res = executeTyped<UUID, UUID>(cond_col, arguments, result_type, input_rows_count))

src/Interpreters/Context.cpp

@@ -108,6 +108,7 @@ namespace fs = std::filesystem;
 namespace ProfileEvents
 {
     extern const Event ContextLock;
+    extern const Event ContextLockWaitMicroseconds;
 }
 
 namespace CurrentMetrics
@@ -704,7 +705,10 @@ std::unique_lock<std::recursive_mutex> Context::getLock() const
 {
     ProfileEvents::increment(ProfileEvents::ContextLock);
     CurrentMetrics::Increment increment{CurrentMetrics::ContextLockWait};
-    return std::unique_lock(shared->mutex);
+    Stopwatch watch;
+    auto lock = std::unique_lock(shared->mutex);
+    ProfileEvents::increment(ProfileEvents::ContextLockWaitMicroseconds, watch.elapsedMicroseconds());
+    return lock;
 }
 
 ProcessList & Context::getProcessList() { return shared->process_list; }

src/Interpreters/ExternalLoader.cpp

@@ -1,7 +1,6 @@
 #include "ExternalLoader.h"
 
 #include <mutex>
-#include <pcg_random.hpp>
 #include <Common/MemoryTrackerBlockerInThread.h>
 #include <Common/Config/AbstractConfigurationComparison.h>
 #include <Common/Exception.h>
@@ -9,7 +8,6 @@
 #include <Common/ThreadPool.h>
 #include <Common/randomSeed.h>
 #include <Common/setThreadName.h>
-#include <Common/StatusInfo.h>
 #include <Common/scope_guard_safe.h>
 #include <Common/logger_useful.h>
 #include <base/chrono_io.h>
@@ -18,12 +16,6 @@
 #include <unordered_set>
 
 
-namespace CurrentStatusInfo
-{
-    extern const Status DictionaryStatus;
-}
-
-
 namespace DB
 {
 namespace ErrorCodes
@@ -1145,7 +1137,6 @@ private:
         if (info && (info->loading_id == loading_id))
         {
             info->loading_id = info->state_id;
-            CurrentStatusInfo::set(CurrentStatusInfo::DictionaryStatus, name, static_cast<Int8>(info->status()));
         }
         min_id_to_finish_loading_dependencies.erase(std::this_thread::get_id());
 
@@ -1307,7 +1298,6 @@ scope_guard ExternalLoader::addConfigRepository(std::unique_ptr<IExternalLoaderC
     return [this, ptr, name]()
     {
         config_files_reader->removeConfigRepository(ptr);
-        CurrentStatusInfo::unset(CurrentStatusInfo::DictionaryStatus, name);
         reloadConfig(name);
     };
 }

src/Processors/Merges/Algorithms/AggregatingSortedAlgorithm.h

@@ -24,6 +24,7 @@ public:
         size_t max_block_size_rows_,
         size_t max_block_size_bytes_);
 
+    const char * getName() const override { return "AggregatingSortedAlgorithm"; }
     void initialize(Inputs inputs) override;
     void consume(Input & input, size_t source_num) override;
     Status merge() override;

src/Processors/Merges/Algorithms/CollapsingSortedAlgorithm.h

@@ -38,6 +38,7 @@ public:
         WriteBuffer * out_row_sources_buf_ = nullptr,
         bool use_average_block_sizes = false);
 
+    const char * getName() const override { return "CollapsingSortedAlgorithm"; }
     Status merge() override;
 
 private:

src/Processors/Merges/Algorithms/FinishAggregatingInOrderAlgorithm.h

@@ -45,6 +45,7 @@ public:
         size_t max_block_size_rows_,
         size_t max_block_size_bytes_);
 
+    const char * getName() const override { return "FinishAggregatingInOrderAlgorithm"; }
     void initialize(Inputs inputs) override;
     void consume(Input & input, size_t source_num) override;
     Status merge() override;

src/Processors/Merges/Algorithms/GraphiteRollupSortedAlgorithm.h

@@ -30,6 +30,7 @@ public:
         Graphite::Params params_,
         time_t time_of_merge_);
 
+    const char * getName() const override { return "GraphiteRollupSortedAlgorithm"; }
     Status merge() override;
 
     struct ColumnsDefinition

src/Processors/Merges/Algorithms/IMergingAlgorithm.h

@@ -47,6 +47,7 @@ public:
 
     using Inputs = std::vector<Input>;
 
+    virtual const char * getName() const = 0;
     virtual void initialize(Inputs inputs) = 0;
     virtual void consume(Input & input, size_t source_num) = 0;
     virtual Status merge() = 0;

src/Processors/Merges/Algorithms/MergingSortedAlgorithm.h

@@ -26,6 +26,7 @@ public:
 
     void addInput();
 
+    const char * getName() const override { return "MergingSortedAlgorithm"; }
     void initialize(Inputs inputs) override;
     void consume(Input & input, size_t source_num) override;
     Status merge() override;

src/Processors/Merges/Algorithms/ReplacingSortedAlgorithm.h

@@ -30,6 +30,7 @@ public:
         bool cleanup = false,
         size_t * cleanedup_rows_count = nullptr);
 
+    const char * getName() const override { return "ReplacingSortedAlgorithm"; }
     Status merge() override;
 
 private:

src/Processors/Merges/Algorithms/SummingSortedAlgorithm.h

@@ -25,6 +25,7 @@ public:
         size_t max_block_size_rows,
         size_t max_block_size_bytes);
 
+    const char * getName() const override { return "SummingSortedAlgorithm"; }
     void initialize(Inputs inputs) override;
     void consume(Input & input, size_t source_num) override;
     Status merge() override;

src/Processors/Merges/Algorithms/VersionedCollapsingAlgorithm.h

@@ -25,6 +25,7 @@ public:
         WriteBuffer * out_row_sources_buf_ = nullptr,
         bool use_average_block_sizes = false);
 
+    const char * getName() const override { return "VersionedCollapsingAlgorithm"; }
     Status merge() override;
 
 private:

src/Processors/Transforms/ColumnGathererTransform.h

@@ -59,6 +59,7 @@ class ColumnGathererStream final : public IMergingAlgorithm
 public:
     ColumnGathererStream(size_t num_inputs, ReadBuffer & row_sources_buf_, size_t block_preferred_size_ = DEFAULT_BLOCK_SIZE);
 
+    const char * getName() const override { return "ColumnGathererStream"; }
     void initialize(Inputs inputs) override;
     void consume(Input & input, size_t source_num) override;
     Status merge() override;

src/Processors/Transforms/CreatingSetsTransform.cpp

@@ -17,9 +17,25 @@ namespace ErrorCodes
 {
     extern const int LOGICAL_ERROR;
     extern const int SET_SIZE_LIMIT_EXCEEDED;
+    extern const int UNKNOWN_EXCEPTION;
 }
 
-CreatingSetsTransform::~CreatingSetsTransform() = default;
+CreatingSetsTransform::~CreatingSetsTransform()
+{
+    if (promise_to_build)
+    {
+        /// set_exception can also throw
+        try
+        {
+            promise_to_build->set_exception(std::make_exception_ptr(
+                Exception(ErrorCodes::UNKNOWN_EXCEPTION, "Failed to build set, most likely pipeline executor was stopped")));
+        }
+        catch (...)
+        {
+            tryLogCurrentException(log, "Failed to set_exception for promise");
+        }
+    }
+}
 
 CreatingSetsTransform::CreatingSetsTransform(
     Block in_header_,
@@ -86,7 +102,7 @@ void CreatingSetsTransform::startSubquery()
             }
             else
             {
-                LOG_TRACE(log, "Waiting for set to be build by another thread, key: {}", set_and_key->key);
+                LOG_TRACE(log, "Waiting for set to be built by another thread, key: {}", set_and_key->key);
                 SharedSet set_built_by_another_thread = std::move(std::get<1>(from_cache));
                 const SetPtr & ready_set = set_built_by_another_thread.get();
                 if (!ready_set)
@@ -188,7 +204,10 @@ Chunk CreatingSetsTransform::generate()
     {
         set_and_key->set->finishInsert();
         if (promise_to_build)
+        {
             promise_to_build->set_value(set_and_key->set);
+            promise_to_build.reset();
+        }
     }
 
     if (table_out.initialized())

src/Processors/Transforms/MergeJoinTransform.h

@@ -229,6 +229,7 @@ class MergeJoinAlgorithm final : public IMergingAlgorithm
 public:
     explicit MergeJoinAlgorithm(JoinPtr table_join, const Blocks & input_headers, size_t max_block_size_);
 
+    const char * getName() const override { return "MergeJoinAlgorithm"; }
     virtual void initialize(Inputs inputs) override;
     virtual void consume(Input & input, size_t source_num) override;
     virtual Status merge() override;

src/Server/PrometheusMetricsWriter.cpp

@@ -1,7 +1,6 @@
 #include "PrometheusMetricsWriter.h"
 
 #include <IO/WriteHelpers.h>
-#include <Common/StatusInfo.h>
 #include <regex>    /// TODO: this library is harmful.
 #include <algorithm>
 
@@ -51,7 +50,6 @@ PrometheusMetricsWriter::PrometheusMetricsWriter(
     , send_events(config.getBool(config_name + ".events", true))
     , send_metrics(config.getBool(config_name + ".metrics", true))
     , send_asynchronous_metrics(config.getBool(config_name + ".asynchronous_metrics", true))
-    , send_status_info(config.getBool(config_name + ".status_info", true))
 {
 }
 
@@ -120,42 +118,6 @@ void PrometheusMetricsWriter::write(WriteBuffer & wb) const
             writeOutLine(wb, key, value.value);
         }
     }
-
-    if (send_status_info)
-    {
-        for (size_t i = 0, end = CurrentStatusInfo::end(); i < end; ++i)
-        {
-            std::lock_guard lock(CurrentStatusInfo::locks[static_cast<CurrentStatusInfo::Status>(i)]);
-            std::string metric_name{CurrentStatusInfo::getName(static_cast<CurrentStatusInfo::Status>(i))};
-            std::string metric_doc{CurrentStatusInfo::getDocumentation(static_cast<CurrentStatusInfo::Status>(i))};
-
-            convertHelpToSingleLine(metric_doc);
-
-            if (!replaceInvalidChars(metric_name))
-                continue;
-            std::string key{current_status_prefix + metric_name};
-
-            writeOutLine(wb, "# HELP", key, metric_doc);
-            writeOutLine(wb, "# TYPE", key, "gauge");
-
-            for (const auto & value: CurrentStatusInfo::values[i])
-            {
-                for (const auto & enum_value: CurrentStatusInfo::getAllPossibleValues(static_cast<CurrentStatusInfo::Status>(i)))
-                {
-                    DB::writeText(key, wb);
-                    DB::writeChar('{', wb);
-                    DB::writeText(key, wb);
-                    DB::writeChar('=', wb);
-                    writeDoubleQuotedString(enum_value.first, wb);
-                    DB::writeText(",name=", wb);
-                    writeDoubleQuotedString(value.first, wb);
-                    DB::writeText("} ", wb);
-                    DB::writeText(value.second == enum_value.second, wb);
-                    DB::writeChar('\n', wb);
-                }
-            }
-        }
-    }
 }
 
 }

src/Server/PrometheusMetricsWriter.h

@@ -27,12 +27,10 @@ private:
     const bool send_events;
     const bool send_metrics;
     const bool send_asynchronous_metrics;
-    const bool send_status_info;
 
     static inline constexpr auto profile_events_prefix = "ClickHouseProfileEvents_";
     static inline constexpr auto current_metrics_prefix = "ClickHouseMetrics_";
     static inline constexpr auto asynchronous_metrics_prefix = "ClickHouseAsyncMetrics_";
-    static inline constexpr auto current_status_prefix = "ClickHouseStatusInfo_";
 };
 
 }

src/Storages/MergeTree/MergeTreeDataWriter.cpp

@@ -365,7 +365,7 @@ Block MergeTreeDataWriter::mergeBlock(
 
     /// Check that after first merge merging_algorithm is waiting for data from input 0.
     if (status.required_source != 0)
-        throw Exception(ErrorCodes::LOGICAL_ERROR, "Logical error: required source after the first merge is not 0.");
+        throw Exception(ErrorCodes::LOGICAL_ERROR, "Logical error: required source after the first merge is not 0. Chunk rows: {}, is_finished: {}, required_source: {}, algorithm: {}", status.chunk.getNumRows(), status.is_finished, status.required_source, merging_algorithm->getName());
 
     status = merging_algorithm->merge();
 

src/Storages/System/StorageSystemFunctions.cpp

@@ -1,5 +1,6 @@
 #include <AggregateFunctions/AggregateFunctionFactory.h>
 #include <DataTypes/DataTypeMap.h>
+#include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypeString.h>
 #include <DataTypes/DataTypesNumber.h>
 #include <DataTypes/DataTypeEnum.h>
@@ -15,6 +16,15 @@
 namespace DB
 {
 
+namespace ErrorCodes
+{
+    extern const int DICTIONARIES_WAS_NOT_LOADED;
+    extern const int FUNCTION_NOT_ALLOWED;
+    extern const int LOGICAL_ERROR;
+    extern const int NOT_IMPLEMENTED;
+    extern const int SUPPORT_IS_DISABLED;
+};
+
 enum class FunctionOrigin : Int8
 {
     SYSTEM = 0,
@@ -29,6 +39,7 @@ namespace
         MutableColumns & res_columns,
         const String & name,
         UInt64 is_aggregate,
+        std::optional<UInt64> is_deterministic,
         const String & create_query,
         FunctionOrigin function_origin,
         const Factory & factory)
@@ -36,53 +47,58 @@ namespace
         res_columns[0]->insert(name);
         res_columns[1]->insert(is_aggregate);
 
+        if (!is_deterministic.has_value())
+            res_columns[2]->insertDefault();
+        else
+            res_columns[2]->insert(*is_deterministic);
+
         if constexpr (std::is_same_v<Factory, UserDefinedSQLFunctionFactory> || std::is_same_v<Factory, UserDefinedExecutableFunctionFactory>)
         {
-            res_columns[2]->insert(false);
+            res_columns[3]->insert(false);
-            res_columns[3]->insertDefault();
+            res_columns[4]->insertDefault();
         }
         else
         {
-            res_columns[2]->insert(factory.isCaseInsensitive(name));
+            res_columns[3]->insert(factory.isCaseInsensitive(name));
             if (factory.isAlias(name))
-                res_columns[3]->insert(factory.aliasTo(name));
+                res_columns[4]->insert(factory.aliasTo(name));
             else
-                res_columns[3]->insertDefault();
+                res_columns[4]->insertDefault();
         }
 
-        res_columns[4]->insert(create_query);
+        res_columns[5]->insert(create_query);
-        res_columns[5]->insert(static_cast<Int8>(function_origin));
+        res_columns[6]->insert(static_cast<Int8>(function_origin));
 
         if constexpr (std::is_same_v<Factory, FunctionFactory>)
         {
             if (factory.isAlias(name))
             {
-                res_columns[6]->insertDefault();
                 res_columns[7]->insertDefault();
                 res_columns[8]->insertDefault();
                 res_columns[9]->insertDefault();
                 res_columns[10]->insertDefault();
                 res_columns[11]->insertDefault();
+                res_columns[12]->insertDefault();
             }
             else
             {
                 auto documentation = factory.getDocumentation(name);
-                res_columns[6]->insert(documentation.description);
+                res_columns[7]->insert(documentation.description);
-                res_columns[7]->insert(documentation.syntax);
+                res_columns[8]->insert(documentation.syntax);
-                res_columns[8]->insert(documentation.argumentsAsString());
+                res_columns[9]->insert(documentation.argumentsAsString());
-                res_columns[9]->insert(documentation.returned_value);
+                res_columns[10]->insert(documentation.returned_value);
-                res_columns[10]->insert(documentation.examplesAsString());
+                res_columns[11]->insert(documentation.examplesAsString());
-                res_columns[11]->insert(documentation.categoriesAsString());
+                res_columns[12]->insert(documentation.categoriesAsString());
             }
         }
         else
         {
-            res_columns[6]->insertDefault();
             res_columns[7]->insertDefault();
             res_columns[8]->insertDefault();
             res_columns[9]->insertDefault();
             res_columns[10]->insertDefault();
             res_columns[11]->insertDefault();
+            res_columns[12]->insertDefault();
         }
     }
 }
@@ -102,6 +118,7 @@ NamesAndTypesList StorageSystemFunctions::getNamesAndTypes()
     return {
         {"name", std::make_shared<DataTypeString>()},
         {"is_aggregate", std::make_shared<DataTypeUInt8>()},
+        {"is_deterministic", std::make_shared<DataTypeNullable>(std::make_shared<DataTypeUInt8>())},
         {"case_insensitive", std::make_shared<DataTypeUInt8>()},
         {"alias_to", std::make_shared<DataTypeString>()},
         {"create_query", std::make_shared<DataTypeString>()},
@@ -121,14 +138,34 @@ void StorageSystemFunctions::fillData(MutableColumns & res_columns, ContextPtr c
     const auto & function_names = functions_factory.getAllRegisteredNames();
     for (const auto & function_name : function_names)
     {
-        fillRow(res_columns, function_name, UInt64(0), "", FunctionOrigin::SYSTEM, functions_factory);
+        std::optional<UInt64> is_deterministic;
+        try
+        {
+            is_deterministic = functions_factory.tryGet(function_name, context)->isDeterministic();
+        }
+        catch (const Exception & e)
+        {
+            /// Some functions throw because they need special configuration or setup before use.
+            if (e.code() == ErrorCodes::DICTIONARIES_WAS_NOT_LOADED
+                || e.code() == ErrorCodes::FUNCTION_NOT_ALLOWED
+                || e.code() == ErrorCodes::LOGICAL_ERROR
+                || e.code() == ErrorCodes::NOT_IMPLEMENTED
+                || e.code() == ErrorCodes::SUPPORT_IS_DISABLED)
+            {
+                /// Ignore exception, show is_deterministic = NULL.
+            }
+            else
+                throw;
+        }
+
+        fillRow(res_columns, function_name, 0, is_deterministic, "", FunctionOrigin::SYSTEM, functions_factory);
     }
 
     const auto & aggregate_functions_factory = AggregateFunctionFactory::instance();
     const auto & aggregate_function_names = aggregate_functions_factory.getAllRegisteredNames();
     for (const auto & function_name : aggregate_function_names)
     {
-        fillRow(res_columns, function_name, UInt64(1), "", FunctionOrigin::SYSTEM, aggregate_functions_factory);
+        fillRow(res_columns, function_name, 1, {1}, "", FunctionOrigin::SYSTEM, aggregate_functions_factory);
     }
 
     const auto & user_defined_sql_functions_factory = UserDefinedSQLFunctionFactory::instance();
@@ -136,14 +173,14 @@ void StorageSystemFunctions::fillData(MutableColumns & res_columns, ContextPtr c
     for (const auto & function_name : user_defined_sql_functions_names)
     {
         auto create_query = queryToString(user_defined_sql_functions_factory.get(function_name));
-        fillRow(res_columns, function_name, UInt64(0), create_query, FunctionOrigin::SQL_USER_DEFINED, user_defined_sql_functions_factory);
+        fillRow(res_columns, function_name, 0, {0}, create_query, FunctionOrigin::SQL_USER_DEFINED, user_defined_sql_functions_factory);
     }
 
     const auto & user_defined_executable_functions_factory = UserDefinedExecutableFunctionFactory::instance();
     const auto & user_defined_executable_functions_names = user_defined_executable_functions_factory.getRegisteredNames(context);
     for (const auto & function_name : user_defined_executable_functions_names)
     {
-        fillRow(res_columns, function_name, UInt64(0), "", FunctionOrigin::EXECUTABLE_USER_DEFINED, user_defined_executable_functions_factory);
+        fillRow(res_columns, function_name, 0, {0}, "", FunctionOrigin::EXECUTABLE_USER_DEFINED, user_defined_executable_functions_factory);
     }
 }
 

src/Storages/System/attachInformationSchemaTables.cpp

@@ -61,12 +61,14 @@ static constexpr std::string_view tables = R"(
         `table_schema` String,
         `table_name` String,
         `table_type` String,
+        `data_length` Nullable(UInt64),
         `table_collation` Nullable(String),
         `table_comment` Nullable(String),
         `TABLE_CATALOG` String,
         `TABLE_SCHEMA` String,
         `TABLE_NAME` String,
         `TABLE_TYPE` String,
+        `DATA_LENGTH` Nullable(UInt64),
         `TABLE_COLLATION` Nullable(String),
         `TABLE_COMMENT` Nullable(String)
     ) AS
@@ -80,12 +82,14 @@ static constexpr std::string_view tables = R"(
                 has_own_data = 0,      'FOREIGN TABLE',
                 'BASE TABLE'
                 )            AS table_type,
+        total_bytes AS data_length,
         'utf8mb4_0900_ai_ci' AS table_collation,
         comment              AS table_comment,
         table_catalog        AS TABLE_CATALOG,
         table_schema         AS TABLE_SCHEMA,
         table_name           AS TABLE_NAME,
         table_type           AS TABLE_TYPE,
+        data_length          AS DATA_LENGTH,
         table_collation      AS TABLE_COLLATION,
         table_comment        AS TABLE_COMMENT
     FROM system.tables

tests/integration/runner

@@ -27,7 +27,7 @@ CONTAINER_NAME = f"{VOLUME_NAME}_{random_str()}"
 
 CONFIG_DIR_IN_REPO = "programs/server"
 INTEGRATION_DIR_IN_REPO = "tests/integration"
-SRC_DIR_IN_REPO = "src"
+UTILS_DIR_IN_REPO = "utils"
 
 DIND_INTEGRATION_TESTS_IMAGE_NAME = "clickhouse/integration-tests-runner"
 
@@ -89,12 +89,16 @@ def check_args_and_update_paths(args):
         )
         logging.info("Cases dir is not set. Will use %s" % (args.cases_dir))
 
-    if args.src_dir:
+    if args.utils_dir:
-        if not os.path.isabs(args.src_dir):
+        if not os.path.isabs(args.utils_dir):
-            args.src_dir = os.path.abspath(os.path.join(CURRENT_WORK_DIR, args.src_dir))
+            args.utils_dir = os.path.abspath(
+                os.path.join(CURRENT_WORK_DIR, args.utils_dir)
+            )
     else:
-        args.src_dir = os.path.abspath(os.path.join(CLICKHOUSE_ROOT, SRC_DIR_IN_REPO))
+        args.utils_dir = os.path.abspath(
-        logging.info("src dir is not set. Will use %s" % (args.src_dir))
+            os.path.join(CLICKHOUSE_ROOT, UTILS_DIR_IN_REPO)
+        )
+        logging.info("utils dir is not set. Will use %s" % (args.utils_dir))
 
     logging.info(
         "base_configs_dir: {}, binary: {}, cases_dir: {} ".format(
@@ -115,7 +119,7 @@ def check_args_and_update_paths(args):
 
     if args.dockerd_volume:
         if not os.path.isabs(args.dockerd_volume):
-            args.src_dir = os.path.abspath(
+            args.dockerd_volume = os.path.abspath(
                 os.path.join(CURRENT_WORK_DIR, args.dockerd_volume)
             )
 
@@ -197,9 +201,9 @@ if __name__ == "__main__":
     )
 
     parser.add_argument(
-        "--src-dir",
+        "--utils-dir",
-        default=os.environ.get("CLICKHOUSE_SRC_DIR"),
+        default=os.environ.get("CLICKHOUSE_UTILS_DIR"),
-        help="Path to the 'src' directory in repository. Used to provide schemas (e.g. *.proto) for some tests when those schemas are located in the 'src' directory",
+        help="Path to the 'utils' directory in repository. Used to provide Python modules for grpc protocol schemas which are located in the 'utils' directory",
     )
 
     parser.add_argument(
@@ -424,7 +428,7 @@ if __name__ == "__main__":
         f"--volume={args.library_bridge_binary}:/clickhouse-library-bridge "
         f"--volume={args.base_configs_dir}:/clickhouse-config "
         f"--volume={args.cases_dir}:/ClickHouse/tests/integration "
-        f"--volume={args.src_dir}/Server/grpc_protos:/ClickHouse/src/Server/grpc_protos "
+        f"--volume={args.utils_dir}/grpc-client/pb2:/ClickHouse/utils/grpc-client/pb2 "
         f"--volume=/run:/run/host:ro {dockerd_internal_volume} {env_tags} {env_cleanup} "
         f"-e DOCKER_CLIENT_TIMEOUT=300 -e COMPOSE_HTTP_TIMEOUT=600 {use_analyzer} -e PYTHONUNBUFFERED=1 "
         f'-e PYTEST_ADDOPTS="{parallel_args} {pytest_opts} {tests_list} {rand_args} -vvv"'

tests/integration/test_config_xml_full/configs/config.xml

@@ -674,27 +674,6 @@
     </graphite>
     -->
 
-    <!-- Serve endpoint for Prometheus monitoring. -->
-    <!--
-        endpoint - mertics path (relative to root, statring with "/")
-        port - port to setup server. If not defined or 0 than http_port used
-        metrics - send data from table system.metrics
-        events - send data from table system.events
-        asynchronous_metrics - send data from table system.asynchronous_metrics
-        status_info - send data from different component from CH, ex: Dictionaries status
-    -->
-    <!--
-    <prometheus>
-        <endpoint>/metrics</endpoint>
-        <port>9363</port>
-
-        <metrics>true</metrics>
-        <events>true</events>
-        <asynchronous_metrics>true</asynchronous_metrics>
-        <status_info>true</status_info>
-    </prometheus>
-    -->
-
     <!-- Query log. Used only for queries with setting log_queries = 1. -->
     <query_log>
         <!-- What table to insert data. If table is not exist, it will be created.

tests/integration/test_grpc_protocol/pb2

@@ -0,0 +1 @@
+../../../utils/grpc-client/pb2

tests/integration/test_grpc_protocol/protos/clickhouse_grpc.proto

@@ -1 +0,0 @@
-../../../../src/Server/grpc_protos/clickhouse_grpc.proto

tests/integration/test_grpc_protocol/test.py

@@ -10,32 +10,20 @@ from threading import Thread
 import gzip
 import lz4.frame
 
+script_dir = os.path.dirname(os.path.realpath(__file__))
+pb2_dir = os.path.join(script_dir, "pb2")
+if pb2_dir not in sys.path:
+    sys.path.append(pb2_dir)
+import clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc  # Execute pb2/generate.py to generate these modules.
+
+
 GRPC_PORT = 9100
-SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
 DEFAULT_ENCODING = "utf-8"
 
 
-# Use grpcio-tools to generate *pb2.py files from *.proto.
-
-proto_dir = os.path.join(SCRIPT_DIR, "./protos")
-gen_dir = os.path.join(SCRIPT_DIR, "./_gen")
-os.makedirs(gen_dir, exist_ok=True)
-run_and_check(
-    "python3 -m grpc_tools.protoc -I{proto_dir} --python_out={gen_dir} --grpc_python_out={gen_dir} \
-    {proto_dir}/clickhouse_grpc.proto".format(
-        proto_dir=proto_dir, gen_dir=gen_dir
-    ),
-    shell=True,
-)
-
-sys.path.append(gen_dir)
-import clickhouse_grpc_pb2
-import clickhouse_grpc_pb2_grpc
-
-
 # Utilities
 
-config_dir = os.path.join(SCRIPT_DIR, "./configs")
+config_dir = os.path.join(script_dir, "./configs")
 cluster = ClickHouseCluster(__file__)
 node = cluster.add_instance(
     "node",

tests/integration/test_grpc_protocol_ssl/pb2

@@ -0,0 +1 @@
+../../../utils/grpc-client/pb2

tests/integration/test_grpc_protocol_ssl/protos/clickhouse_grpc.proto

@@ -1 +0,0 @@
-../../../../src/Server/grpc_protos/clickhouse_grpc.proto

tests/integration/test_grpc_protocol_ssl/test.py

@@ -4,35 +4,23 @@ import sys
 import grpc
 from helpers.cluster import ClickHouseCluster, run_and_check
 
+script_dir = os.path.dirname(os.path.realpath(__file__))
+pb2_dir = os.path.join(script_dir, "pb2")
+if pb2_dir not in sys.path:
+    sys.path.append(pb2_dir)
+import clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc  # Execute pb2/generate.py to generate these modules.
+
+
 # The test cluster is configured with certificate for that host name, see 'server-ext.cnf'.
 # The client have to verify server certificate against that name. Client uses SNI
 SSL_HOST = "integration-tests.clickhouse.com"
 GRPC_PORT = 9100
-SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
 DEFAULT_ENCODING = "utf-8"
 
 
-# Use grpcio-tools to generate *pb2.py files from *.proto.
-
-proto_dir = os.path.join(SCRIPT_DIR, "./protos")
-gen_dir = os.path.join(SCRIPT_DIR, "./_gen")
-os.makedirs(gen_dir, exist_ok=True)
-run_and_check(
-    "python3 -m grpc_tools.protoc -I{proto_dir} --python_out={gen_dir} --grpc_python_out={gen_dir} \
-    {proto_dir}/clickhouse_grpc.proto".format(
-        proto_dir=proto_dir, gen_dir=gen_dir
-    ),
-    shell=True,
-)
-
-sys.path.append(gen_dir)
-import clickhouse_grpc_pb2
-import clickhouse_grpc_pb2_grpc
-
-
 # Utilities
 
-config_dir = os.path.join(SCRIPT_DIR, "./configs")
+config_dir = os.path.join(script_dir, "./configs")
 cluster = ClickHouseCluster(__file__)
 node = cluster.add_instance(
     "node",

tests/integration/test_profile_max_sessions_for_user/grpc_protocol_pb2

@@ -0,0 +1 @@
+../../../utils/grpc-client/pb2

tests/integration/test_profile_max_sessions_for_user/protos/clickhouse_grpc.proto

@@ -1 +0,0 @@
-../../../../src/Server/grpc_protos/clickhouse_grpc.proto

tests/integration/test_profile_max_sessions_for_user/test.py

@@ -9,9 +9,15 @@ import threading
 
 from helpers.cluster import ClickHouseCluster, run_and_check
 from helpers.test_tools import assert_logs_contain_with_retry
-
 from helpers.uclient import client, prompt
 
+script_dir = os.path.dirname(os.path.realpath(__file__))
+grpc_protocol_pb2_dir = os.path.join(script_dir, "grpc_protocol_pb2")
+if grpc_protocol_pb2_dir not in sys.path:
+    sys.path.append(grpc_protocol_pb2_dir)
+import clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc  # Execute grpc_protocol_pb2/generate.py to generate these modules.
+
+
 MAX_SESSIONS_FOR_USER = 2
 POSTGRES_SERVER_PORT = 5433
 MYSQL_SERVER_PORT = 9001
@@ -20,22 +26,8 @@ GRPC_PORT = 9100
 TEST_USER = "test_user"
 TEST_PASSWORD = "123"
 
-SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
 DEFAULT_ENCODING = "utf-8"
 
-# Use grpcio-tools to generate *pb2.py files from *.proto.
-proto_dir = os.path.join(SCRIPT_DIR, "./protos")
-gen_dir = os.path.join(SCRIPT_DIR, "./_gen")
-os.makedirs(gen_dir, exist_ok=True)
-run_and_check(
-    f"python3 -m grpc_tools.protoc -I{proto_dir} --python_out={gen_dir} --grpc_python_out={gen_dir} {proto_dir}/clickhouse_grpc.proto",
-    shell=True,
-)
-
-sys.path.append(gen_dir)
-
-import clickhouse_grpc_pb2
-import clickhouse_grpc_pb2_grpc
 
 cluster = ClickHouseCluster(__file__)
 instance = cluster.add_instance(

tests/integration/test_server_reload/grpc_protocol_pb2

@@ -0,0 +1 @@
+../../../utils/grpc-client/pb2

tests/integration/test_server_reload/protos/clickhouse_grpc.proto

@@ -1 +0,0 @@
-../../../../src/Server/grpc_protos/clickhouse_grpc.proto

tests/integration/test_server_reload/test.py

@@ -22,6 +22,13 @@ from pathlib import Path
 from requests.exceptions import ConnectionError
 from urllib3.util.retry import Retry
 
+script_dir = os.path.dirname(os.path.realpath(__file__))
+grpc_protocol_pb2_dir = os.path.join(script_dir, "grpc_protocol_pb2")
+if grpc_protocol_pb2_dir not in sys.path:
+    sys.path.append(grpc_protocol_pb2_dir)
+import clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc  # Execute grpc_protocol_pb2/generate.py to generate these modules.
+
+
 cluster = ClickHouseCluster(__file__)
 instance = cluster.add_instance(
     "instance",
@@ -44,22 +51,6 @@ instance = cluster.add_instance(
 LOADS_QUERY = "SELECT value FROM system.events WHERE event = 'MainConfigLoads'"
 
 
-# Use grpcio-tools to generate *pb2.py files from *.proto.
-
-proto_dir = Path(__file__).parent / "protos"
-gen_dir = Path(__file__).parent / "_gen"
-gen_dir.mkdir(exist_ok=True)
-run_and_check(
-    f"python3 -m grpc_tools.protoc -I{proto_dir!s} --python_out={gen_dir!s} --grpc_python_out={gen_dir!s} \
-    {proto_dir!s}/clickhouse_grpc.proto",
-    shell=True,
-)
-
-sys.path.append(str(gen_dir))
-import clickhouse_grpc_pb2
-import clickhouse_grpc_pb2_grpc
-
-
 @pytest.fixture(name="cluster", scope="module")
 def fixture_cluster():
     try:

tests/integration/test_session_log/grpc_protocol_pb2

@@ -0,0 +1 @@
+../../../utils/grpc-client/pb2

tests/integration/test_session_log/protos/clickhouse_grpc.proto

@@ -1 +0,0 @@
-../../../../src/Server/grpc_protos/clickhouse_grpc.proto

tests/integration/test_session_log/test.py

@@ -8,27 +8,19 @@ import threading
 
 from helpers.cluster import ClickHouseCluster, run_and_check
 
+script_dir = os.path.dirname(os.path.realpath(__file__))
+grpc_protocol_pb2_dir = os.path.join(script_dir, "grpc_protocol_pb2")
+if grpc_protocol_pb2_dir not in sys.path:
+    sys.path.append(grpc_protocol_pb2_dir)
+import clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc  # Execute grpc_protocol_pb2/generate.py to generate these modules.
+
+
 POSTGRES_SERVER_PORT = 5433
 MYSQL_SERVER_PORT = 9001
 GRPC_PORT = 9100
 SESSION_LOG_MATCHING_FIELDS = "auth_id, auth_type, client_version_major, client_version_minor, client_version_patch, interface"
-
-SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
 DEFAULT_ENCODING = "utf-8"
 
-# Use grpcio-tools to generate *pb2.py files from *.proto.
-proto_dir = os.path.join(SCRIPT_DIR, "./protos")
-gen_dir = os.path.join(SCRIPT_DIR, "./_gen")
-os.makedirs(gen_dir, exist_ok=True)
-run_and_check(
-    f"python3 -m grpc_tools.protoc -I{proto_dir} --python_out={gen_dir} --grpc_python_out={gen_dir} {proto_dir}/clickhouse_grpc.proto",
-    shell=True,
-)
-
-sys.path.append(gen_dir)
-
-import clickhouse_grpc_pb2
-import clickhouse_grpc_pb2_grpc
 
 cluster = ClickHouseCluster(__file__)
 instance = cluster.add_instance(

tests/queries/0_stateless/01161_information_schema.reference

@@ -22,34 +22,36 @@ referential_constraints
 schemata
 tables
 views
+-- information_schema.schemata
 INFORMATION_SCHEMA	INFORMATION_SCHEMA	default	\N	\N	\N	\N	INFORMATION_SCHEMA	INFORMATION_SCHEMA	default	\N	\N	\N	\N
 information_schema	information_schema	default	\N	\N	\N	\N	information_schema	information_schema	default	\N	\N	\N	\N
-default	default	kcu	BASE TABLE	utf8mb4_0900_ai_ci		default	default	kcu	BASE TABLE	utf8mb4_0900_ai_ci	
+-- information_schema.tables
-default	default	kcu2	BASE TABLE	utf8mb4_0900_ai_ci		default	default	kcu2	BASE TABLE	utf8mb4_0900_ai_ci	
+default	default	kcu1	BASE TABLE	0	utf8mb4_0900_ai_ci		default	default	kcu1	BASE TABLE	0	utf8mb4_0900_ai_ci	
-default	default	mv	VIEW	utf8mb4_0900_ai_ci		default	default	mv	VIEW	utf8mb4_0900_ai_ci	
+default	default	kcu2	BASE TABLE	0	utf8mb4_0900_ai_ci		default	default	kcu2	BASE TABLE	0	utf8mb4_0900_ai_ci	
-default	default	t	FOREIGN TABLE	utf8mb4_0900_ai_ci		default	default	t	FOREIGN TABLE	utf8mb4_0900_ai_ci	
+default	default	mv	VIEW	0	utf8mb4_0900_ai_ci		default	default	mv	VIEW	0	utf8mb4_0900_ai_ci	
-default	default	v	VIEW	utf8mb4_0900_ai_ci		default	default	v	VIEW	utf8mb4_0900_ai_ci	
+default	default	t	FOREIGN TABLE	0	utf8mb4_0900_ai_ci		default	default	t	FOREIGN TABLE	0	utf8mb4_0900_ai_ci	
-		tmp	LOCAL TEMPORARY	utf8mb4_0900_ai_ci				tmp	LOCAL TEMPORARY	utf8mb4_0900_ai_ci	
+default	default	v	VIEW	\N	utf8mb4_0900_ai_ci		default	default	v	VIEW	\N	utf8mb4_0900_ai_ci	
+-- information_schema.views
 default	default	mv	SELECT * FROM system.one	NONE	NO	YES	NO	NO	NO	default	default	mv	SELECT * FROM system.one	NONE	NO	YES	NO	NO	NO
 default	default	v	SELECT n, f FROM default.t	NONE	NO	NO	NO	NO	NO	default	default	v	SELECT n, f FROM default.t	NONE	NO	NO	NO	NO	NO
-default	default	kcu	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32	default	default	kcu	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32
+-- information_schema.columns
-default	default	kcu	s	2		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String	default	default	kcu	s	2		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String
+default	default	kcu1	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32	default	default	kcu1	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32
-default	default	kcu2	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32	default	default	kcu2	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32
+default	default	kcu1	s	2		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String	default	default	kcu1	s	2		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String
 default	default	kcu2	d	2		0	Date	\N	\N	\N	\N	\N	0	\N	\N	\N	\N	\N	\N	\N	\N	\N		Date	default	default	kcu2	d	2		0	Date	\N	\N	\N	\N	\N	0	\N	\N	\N	\N	\N	\N	\N	\N	\N		Date
+default	default	kcu2	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32	default	default	kcu2	i	1		0	UInt32	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt32
 default	default	kcu2	u	3		0	UUID	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UUID	default	default	kcu2	u	3		0	UUID	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UUID
 default	default	mv	dummy	1		0	UInt8	\N	\N	8	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt8	default	default	mv	dummy	1		0	UInt8	\N	\N	8	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt8
-default	default	t	n	1		0	UInt64	\N	\N	64	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt64	default	default	t	n	1		0	UInt64	\N	\N	64	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt64
-default	default	t	f	2		0	Float32	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Float32	default	default	t	f	2		0	Float32	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Float32
-default	default	t	s	3		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String	default	default	t	s	3		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String
-default	default	t	fs	4		0	FixedString(42)	42	42	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		FixedString(42)	default	default	t	fs	4		0	FixedString(42)	42	42	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		FixedString(42)
 default	default	t	d	5		0	Decimal(9, 6)	\N	\N	9	10	6	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Decimal(9, 6)	default	default	t	d	5		0	Decimal(9, 6)	\N	\N	9	10	6	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Decimal(9, 6)
-default	default	v	n	1		1	Nullable(Int32)	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Nullable(Int32)	default	default	v	n	1		1	Nullable(Int32)	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Nullable(Int32)
+default	default	t	f	2		0	Float32	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Float32	default	default	t	f	2		0	Float32	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Float32
+default	default	t	fs	4		0	FixedString(42)	42	42	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		FixedString(42)	default	default	t	fs	4		0	FixedString(42)	42	42	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		FixedString(42)
+default	default	t	n	1		0	UInt64	\N	\N	64	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt64	default	default	t	n	1		0	UInt64	\N	\N	64	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		UInt64
+default	default	t	s	3		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String	default	default	t	s	3		0	String	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		String
 default	default	v	f	2		0	Float64	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Float64	default	default	v	f	2		0	Float64	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Float64
-		tmp	d	1		0	Date	\N	\N	\N	\N	\N	0	\N	\N	\N	\N	\N	\N	\N	\N	\N		Date			tmp	d	1		0	Date	\N	\N	\N	\N	\N	0	\N	\N	\N	\N	\N	\N	\N	\N	\N		Date
+default	default	v	n	1		1	Nullable(Int32)	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Nullable(Int32)	default	default	v	n	1		1	Nullable(Int32)	\N	\N	32	2	0	\N	\N	\N	\N	\N	\N	\N	\N	\N	\N		Nullable(Int32)
-		tmp	dt	2		0	DateTime	\N	\N	\N	\N	\N	0	\N	\N	\N	\N	\N	\N	\N	\N	\N		DateTime			tmp	dt	2		0	DateTime	\N	\N	\N	\N	\N	0	\N	\N	\N	\N	\N	\N	\N	\N	\N		DateTime
+-- information_schema.key_column_usage
-		tmp	dtms	3		0	DateTime64(3)	\N	\N	\N	\N	\N	3	\N	\N	\N	\N	\N	\N	\N	\N	\N		DateTime64(3)			tmp	dtms	3		0	DateTime64(3)	\N	\N	\N	\N	\N	3	\N	\N	\N	\N	\N	\N	\N	\N	\N		DateTime64(3)
+def	default	PRIMARY	def	default	kcu1	i	1	\N	\N	\N	\N	def	default	PRIMARY	def	default	kcu1	i	1	\N	\N	\N	\N
-1
-1
-def	default	PRIMARY	def	default	kcu	i	1	\N	\N	\N	\N	def	default	PRIMARY	def	default	kcu	i	1	\N	\N	\N	\N
 def	default	PRIMARY	def	default	kcu2	d	1	\N	\N	\N	\N	def	default	PRIMARY	def	default	kcu2	d	1	\N	\N	\N	\N
 def	default	PRIMARY	def	default	kcu2	u	1	\N	\N	\N	\N	def	default	PRIMARY	def	default	kcu2	u	1	\N	\N	\N	\N
+-- information_schema.referential_constraints
+1
+1

tests/queries/0_stateless/01161_information_schema.sql

@@ -1,41 +1,52 @@
+-- Uppercase/lowercase are okay, mixed case isn't
 SHOW TABLES FROM information_schema;
 SHOW TABLES FROM INFORMATION_SCHEMA;
+SHOW TABLES FROM INFORMATION_schema; -- { serverError UNKNOWN_DATABASE }
 
-DROP TABLE IF EXISTS t;
 DROP VIEW IF EXISTS v;
+DROP TABLE IF EXISTS t;
 DROP VIEW IF EXISTS mv;
 DROP TABLE IF EXISTS tmp;
-DROP TABLE IF EXISTS kcu;
+DROP TABLE IF EXISTS kcu1;
 DROP TABLE IF EXISTS kcu2;
 
-CREATE TABLE t (n UInt64, f Float32, s String, fs FixedString(42), d Decimal(9, 6)) ENGINE=Memory;
+CREATE TABLE t (n UInt64, f Float32, s String, fs FixedString(42), d Decimal(9, 6)) ENGINE = Memory;
 CREATE VIEW v (n Nullable(Int32), f Float64) AS SELECT n, f FROM t;
-CREATE MATERIALIZED VIEW mv ENGINE=Null AS SELECT * FROM system.one;
+CREATE MATERIALIZED VIEW mv ENGINE = Null AS SELECT * FROM system.one;
 CREATE TEMPORARY TABLE tmp (d Date, dt DateTime, dtms DateTime64(3));
-CREATE TABLE kcu (i UInt32, s String) ENGINE MergeTree ORDER BY i;
+CREATE TABLE kcu1 (i UInt32, s String) ENGINE MergeTree ORDER BY i;
 CREATE TABLE kcu2 (i UInt32, d Date, u UUID) ENGINE MergeTree ORDER BY (u, d);
 
--- FIXME #28687
-SELECT * FROM information_schema.schemata WHERE schema_name ilike 'information_schema';
--- SELECT * FROM INFORMATION_SCHEMA.TABLES WHERE (TABLE_SCHEMA=currentDatabase() OR TABLE_SCHEMA='') AND TABLE_NAME NOT LIKE '%inner%';
-SELECT * FROM INFORMATION_SCHEMA.TABLES WHERE (table_schema = currentDatabase() OR table_schema = '') AND table_name NOT LIKE '%inner%';
-SELECT * FROM information_schema.views WHERE table_schema = currentDatabase();
--- SELECT * FROM INFORMATION_SCHEMA.COLUMNS WHERE (TABLE_SCHEMA=currentDatabase() OR TABLE_SCHEMA='') AND TABLE_NAME NOT LIKE '%inner%'
-SELECT * FROM INFORMATION_SCHEMA.COLUMNS WHERE (table_schema = currentDatabase() OR table_schema = '') AND table_name NOT LIKE '%inner%';
 
+SELECT '-- information_schema.schemata';
+SELECT * FROM information_schema.schemata WHERE schema_name ilike 'information_schema' ORDER BY schema_name;
+
+SELECT '-- information_schema.tables';
+SELECT * FROM information_schema.tables WHERE table_schema = currentDatabase() AND table_name NOT LIKE '%inner%' ORDER BY table_name;
+-- SELECT * FROM INFORMATION_SCHEMA.TABLES WHERE TABLE_SCHEMA=currentDatabase() ORDER BY schema_name;
+-- FIXME #28687
+
+SELECT '-- information_schema.views';
+SELECT * FROM information_schema.views WHERE table_schema = currentDatabase() ORDER BY table_name;
+-- SELECT * FROM INFORMATION_SCHEMA.COLUMNS WHERE (TABLE_SCHEMA=currentDatabase() OR TABLE_SCHEMA='') AND TABLE_NAME NOT LIKE '%inner%'
+
+SELECT '-- information_schema.columns';
+SELECT * FROM information_schema.columns WHERE table_schema = currentDatabase() AND table_name NOT LIKE '%inner%' ORDER BY table_name, column_name;
+
+SELECT '-- information_schema.key_column_usage';
+SELECT * FROM information_schema.key_column_usage WHERE table_schema = currentDatabase() AND table_name = 'kcu1' ORDER BY table_schema, column_name;
+SELECT * FROM information_schema.key_column_usage WHERE table_schema = currentDatabase() AND table_name = 'kcu2' ORDER BY table_schema, column_name;
+
+SELECT '-- information_schema.referential_constraints';
+SELECT * FROM information_schema.referential_constraints;
+--
 -- mixed upper/lowercase schema and table name:
 SELECT count() FROM information_schema.TABLES WHERE table_schema = currentDatabase() AND table_name = 't';
 SELECT count() FROM INFORMATION_SCHEMA.tables WHERE table_schema = currentDatabase() AND table_name = 't';
-SELECT count() FROM INFORMATION_schema.tables WHERE table_schema = currentDatabase() AND table_name = 't'; -- { serverError UNKNOWN_DATABASE }
 SELECT count() FROM information_schema.taBLES WHERE table_schema  =currentDatabase() AND table_name = 't'; -- { serverError UNKNOWN_TABLE }
 
-SELECT * FROM information_schema.key_column_usage WHERE table_schema = currentDatabase() AND table_name = 'kcu';
+DROP VIEW mv;
-SELECT * FROM information_schema.key_column_usage WHERE table_schema = currentDatabase() AND table_name = 'kcu2';
+DROP VIEW v;
-
+DROP TABLE t;
-SELECT * FROM information_schema.referential_constraints;
+DROP TABLE kcu1;
-
+DROP TABLE kcu2;
-drop view mv;
-drop view v;
-drop table t;
-drop table kcu;
-drop table kcu2;

tests/queries/0_stateless/02117_show_create_table_system.reference

@@ -283,6 +283,7 @@ CREATE TABLE system.functions
 (
     `name` String,
     `is_aggregate` UInt8,
+    `is_deterministic` Nullable(UInt8),
     `case_insensitive` UInt8,
     `alias_to` String,
     `create_query` String,

tests/queries/0_stateless/02206_information_schema_show_database.reference

@@ -1,6 +1,6 @@
 CREATE DATABASE INFORMATION_SCHEMA\nENGINE = Memory
 CREATE VIEW INFORMATION_SCHEMA.COLUMNS\n(\n    `table_catalog` String,\n    `table_schema` String,\n    `table_name` String,\n    `column_name` String,\n    `ordinal_position` UInt64,\n    `column_default` String,\n    `is_nullable` String,\n    `data_type` String,\n    `character_maximum_length` Nullable(UInt64),\n    `character_octet_length` Nullable(UInt64),\n    `numeric_precision` Nullable(UInt64),\n    `numeric_precision_radix` Nullable(UInt64),\n    `numeric_scale` Nullable(UInt64),\n    `datetime_precision` Nullable(UInt64),\n    `character_set_catalog` Nullable(String),\n    `character_set_schema` Nullable(String),\n    `character_set_name` Nullable(String),\n    `collation_catalog` Nullable(String),\n    `collation_schema` Nullable(String),\n    `collation_name` Nullable(String),\n    `domain_catalog` Nullable(String),\n    `domain_schema` Nullable(String),\n    `domain_name` Nullable(String),\n    `column_comment` String,\n    `column_type` String,\n    `TABLE_CATALOG` String,\n    `TABLE_SCHEMA` String,\n    `TABLE_NAME` String,\n    `COLUMN_NAME` String,\n    `ORDINAL_POSITION` UInt64,\n    `COLUMN_DEFAULT` String,\n    `IS_NULLABLE` String,\n    `DATA_TYPE` String,\n    `CHARACTER_MAXIMUM_LENGTH` Nullable(UInt64),\n    `CHARACTER_OCTET_LENGTH` Nullable(UInt64),\n    `NUMERIC_PRECISION` Nullable(UInt64),\n    `NUMERIC_PRECISION_RADIX` Nullable(UInt64),\n    `NUMERIC_SCALE` Nullable(UInt64),\n    `DATETIME_PRECISION` Nullable(UInt64),\n    `CHARACTER_SET_CATALOG` Nullable(String),\n    `CHARACTER_SET_SCHEMA` Nullable(String),\n    `CHARACTER_SET_NAME` Nullable(String),\n    `COLLATION_CATALOG` Nullable(String),\n    `COLLATION_SCHEMA` Nullable(String),\n    `COLLATION_NAME` Nullable(String),\n    `DOMAIN_CATALOG` Nullable(String),\n    `DOMAIN_SCHEMA` Nullable(String),\n    `DOMAIN_NAME` Nullable(String),\n    `COLUMN_COMMENT` String,\n    `COLUMN_TYPE` String\n) AS\nSELECT\n    database AS table_catalog,\n    database AS table_schema,\n    table AS table_name,\n    name AS column_name,\n    position AS ordinal_position,\n    default_expression AS column_default,\n    type LIKE \'Nullable(%)\' AS is_nullable,\n    type AS data_type,\n    character_octet_length AS character_maximum_length,\n    character_octet_length,\n    numeric_precision,\n    numeric_precision_radix,\n    numeric_scale,\n    datetime_precision,\n    NULL AS character_set_catalog,\n    NULL AS character_set_schema,\n    NULL AS character_set_name,\n    NULL AS collation_catalog,\n    NULL AS collation_schema,\n    NULL AS collation_name,\n    NULL AS domain_catalog,\n    NULL AS domain_schema,\n    NULL AS domain_name,\n    comment AS column_comment,\n    type AS column_type,\n    table_catalog AS TABLE_CATALOG,\n    table_schema AS TABLE_SCHEMA,\n    table_name AS TABLE_NAME,\n    column_name AS COLUMN_NAME,\n    ordinal_position AS ORDINAL_POSITION,\n    column_default AS COLUMN_DEFAULT,\n    is_nullable AS IS_NULLABLE,\n    data_type AS DATA_TYPE,\n    character_maximum_length AS CHARACTER_MAXIMUM_LENGTH,\n    character_octet_length AS CHARACTER_OCTET_LENGTH,\n    numeric_precision AS NUMERIC_PRECISION,\n    numeric_precision_radix AS NUMERIC_PRECISION_RADIX,\n    numeric_scale AS NUMERIC_SCALE,\n    datetime_precision AS DATETIME_PRECISION,\n    character_set_catalog AS CHARACTER_SET_CATALOG,\n    character_set_schema AS CHARACTER_SET_SCHEMA,\n    character_set_name AS CHARACTER_SET_NAME,\n    collation_catalog AS COLLATION_CATALOG,\n    collation_schema AS COLLATION_SCHEMA,\n    collation_name AS COLLATION_NAME,\n    domain_catalog AS DOMAIN_CATALOG,\n    domain_schema AS DOMAIN_SCHEMA,\n    domain_name AS DOMAIN_NAME,\n    column_comment AS COLUMN_COMMENT,\n    column_type AS COLUMN_TYPE\nFROM system.columns
-CREATE VIEW INFORMATION_SCHEMA.TABLES (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables
+CREATE VIEW INFORMATION_SCHEMA.TABLES (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `data_length` Nullable(UInt64), `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `DATA_LENGTH` Nullable(UInt64), `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, total_bytes AS data_length, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, data_length AS DATA_LENGTH, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables
-CREATE VIEW INFORMATION_SCHEMA.tables (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables
+CREATE VIEW INFORMATION_SCHEMA.tables (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `data_length` Nullable(UInt64), `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `DATA_LENGTH` Nullable(UInt64), `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, total_bytes AS data_length, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, data_length AS DATA_LENGTH, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables
-CREATE VIEW information_schema.TABLES (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables
+CREATE VIEW information_schema.TABLES (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `data_length` Nullable(UInt64), `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `DATA_LENGTH` Nullable(UInt64), `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, total_bytes AS data_length, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, data_length AS DATA_LENGTH, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables
-CREATE VIEW information_schema.tables (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables
+CREATE VIEW information_schema.tables (`table_catalog` String, `table_schema` String, `table_name` String, `table_type` String, `data_length` Nullable(UInt64), `table_collation` Nullable(String), `table_comment` Nullable(String), `TABLE_CATALOG` String, `TABLE_SCHEMA` String, `TABLE_NAME` String, `TABLE_TYPE` String, `DATA_LENGTH` Nullable(UInt64), `TABLE_COLLATION` Nullable(String), `TABLE_COMMENT` Nullable(String)) AS SELECT database AS table_catalog, database AS table_schema, name AS table_name, multiIf(is_temporary, \'LOCAL TEMPORARY\', engine LIKE \'%View\', \'VIEW\', engine LIKE \'System%\', \'SYSTEM VIEW\', has_own_data = 0, \'FOREIGN TABLE\', \'BASE TABLE\') AS table_type, total_bytes AS data_length, \'utf8mb4_0900_ai_ci\' AS table_collation, comment AS table_comment, table_catalog AS TABLE_CATALOG, table_schema AS TABLE_SCHEMA, table_name AS TABLE_NAME, table_type AS TABLE_TYPE, data_length AS DATA_LENGTH, table_collation AS TABLE_COLLATION, table_comment AS TABLE_COMMENT FROM system.tables

tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.reference

@@ -1,18 +0,0 @@
-status before reload
-status after reload
-NOT_LOADED 0
-LOADED 0
-FAILED 1
-LOADING 0
-FAILED_AND_RELOADING 0
-LOADED_AND_RELOADING 0
-NOT_EXIST 0
-status after reload, table exists
-NOT_LOADED 0
-LOADED 1
-FAILED 0
-LOADING 0
-FAILED_AND_RELOADING 0
-LOADED_AND_RELOADING 0
-NOT_EXIST 0
-status after drop

tests/queries/0_stateless/02390_prometheus_ClickHouseStatusInfo_DictionaryStatus.sh

@@ -1,38 +0,0 @@
-#!/usr/bin/env bash
-# Tags: no-ordinary-database
-
-CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-# shellcheck source=../shell_config.sh
-. "$CUR_DIR"/../shell_config.sh
-
-function get_dictionary_status()
-{
-    local name=$1 && shift
-    $CLICKHOUSE_CURL -sS "$CLICKHOUSE_URL_PROMETHEUS" | {
-        awk -F'[{}=," ]' -vname="$name" '/ClickHouseStatusInfo_DictionaryStatus{/ && $(NF-3) == name { print $4, $NF }'
-    }
-}
-
-$CLICKHOUSE_CLIENT -q "CREATE DICTIONARY dict (key Int, value String) PRIMARY KEY key SOURCE(CLICKHOUSE(TABLE data)) LAYOUT(HASHED()) LIFETIME(0)"
-uuid="$($CLICKHOUSE_CLIENT -q "SELECT uuid FROM system.dictionaries WHERE database = '$CLICKHOUSE_DATABASE' AND name = 'dict'")"
-
-echo 'status before reload'
-get_dictionary_status "$uuid"
-
-# source table does not exists
-# NOTE: when dictionary does not exist it produce BAD_ARGUMENTS error, so using UNKNOWN_TABLE is safe
-$CLICKHOUSE_CLIENT -n -q "SYSTEM RELOAD DICTIONARY dict -- { serverError UNKNOWN_TABLE }"
-echo 'status after reload'
-get_dictionary_status "$uuid"
-
-# create source
-$CLICKHOUSE_CLIENT -q "CREATE TABLE data (key Int, value String) Engine=Null"
-$CLICKHOUSE_CLIENT -q "SYSTEM RELOAD DICTIONARY dict"
-echo 'status after reload, table exists'
-get_dictionary_status "$uuid"
-
-# remove dictionary
-$CLICKHOUSE_CLIENT -q "DROP DICTIONARY dict"
-$CLICKHOUSE_CLIENT -q "DROP TABLE data"
-echo 'status after drop'
-get_dictionary_status "$uuid"

tests/queries/0_stateless/02815_no_throw_in_simple_queries.sh

@@ -53,4 +53,9 @@ expect eof
 EOF
 }
 
-run "$CLICKHOUSE_LOCAL"
+run "$CLICKHOUSE_LOCAL --disable_suggestion"
+# Suggestions are off because the suggestion feature initializes itself by reading all available function
+# names from "system.functions". Getting the value for field "is_obsolete" occasionally throws (e.g. for
+# certain dictionary functions when dictionaries are not set up yet). Exceptions are properly handled, but
+# they exist for a short time. This, in combination with CLICKHOUSE_TERMINATE_ON_ANY_EXCEPTION, terminates
+# clickhouse-local and clickhouse-client when run in interactive mode *with* suggestions.

tests/queries/0_stateless/02884_string_distance_function.reference

@@ -1,4 +1,25 @@
+const arguments byteHammingDistance
 0
+const arguments byteEditDistance
+6
+const arguments byteJaccardIndex
+0.4
+byteHammingDistance
+1
+7
+7
+10
+byteHammingDistance(const, non const)
+3
+6
+3
+10
+byteHammingDistance(non const, const)
+6
+6
+3
+10
+mismatches(alias)
 1
 7
 7
@@ -11,26 +32,17 @@
 6
 3
 10
-1
+byteJaccardIndex
-7
-7
-10
-3
-6
-3
-10
-6
-6
-3
-10
 0.8571428571428571
 0.8571428571428571
 0
 0.4
+byteEditDistance
 1
 1
 7
 6
+byteLevenshteinDistance
 1
 1
 7

tests/queries/0_stateless/02884_string_distance_function.sql

@@ -1,4 +1,10 @@
+select 'const arguments byteHammingDistance';
 select byteHammingDistance('abcd', 'abcd');
+select 'const arguments byteEditDistance';
+select byteEditDistance('clickhouse', 'mouse');
+select 'const arguments byteJaccardIndex';
+select byteJaccardIndex('clickhouse', 'mouse');
+
 drop table if exists t;
 create table t
 (
@@ -7,18 +13,25 @@ create table t
 ) engine = MergeTree order by s1;
 
 insert into t values ('abcdefg', 'abcdef') ('abcdefg', 'bcdefg') ('abcdefg', '') ('mouse', 'clickhouse');
+select 'byteHammingDistance';
 select byteHammingDistance(s1, s2) from t;
+select 'byteHammingDistance(const, non const)';
 select byteHammingDistance('abc', s2) from t;
+select 'byteHammingDistance(non const, const)';
 select byteHammingDistance(s2, 'def') from t;
 
+select 'mismatches(alias)';
 select mismatches(s1, s2) from t;
 select mismatches('abc', s2) from t;
 select mismatches(s2, 'def') from t;
 
+select 'byteJaccardIndex';
 select byteJaccardIndex(s1, s2) from t;
+select 'byteEditDistance';
 select byteEditDistance(s1, s2) from t;
+select 'byteLevenshteinDistance';
 select byteLevenshteinDistance(s1, s2) from t;
 
-SELECT byteEditDistance(randomString(power(2, 17)), 'abc'); -- { serverError 131 }
+SELECT byteEditDistance(randomString(power(2, 17)), 'abc'); -- { serverError TOO_LARGE_STRING_SIZE}
 
 drop table t;

tests/queries/0_stateless/02888_integer_type_inference_in_if_function.reference

@@ -0,0 +1,24 @@
+-9223372036854775808
+9223372036854775806
+-9223372036854775808
+9223372036854775806
+-9223372036854775808
+9223372036854775806
+-9223372036854775808
+9223372036854775806
+[2,65537,-9223372036854775808]
+[9223372036854775806]
+[2,65537,-9223372036854775808]
+[9223372036854775806]
+[2,65537,-9223372036854775808]
+[9223372036854775806]
+[2,65537,-9223372036854775808]
+[9223372036854775806]
+[[2,65537,-9223372036854775808]]
+[[9223372036854775806]]
+[[2,65537,-9223372036854775808]]
+[[9223372036854775806]]
+[[2,65537,-9223372036854775808]]
+[[9223372036854775806]]
+[[2,65537,-9223372036854775808]]
+[[9223372036854775806]]

tests/queries/0_stateless/02888_integer_type_inference_in_if_function.sql

@@ -0,0 +1,13 @@
+SELECT if(number % 2, 9223372036854775806, -9223372036854775808) AS res FROM numbers(2);
+SELECT if(number % 2, materialize(9223372036854775806), -9223372036854775808) AS res FROM numbers(2);
+SELECT if(number % 2, 9223372036854775806, materialize(-9223372036854775808)) AS res FROM numbers(2);
+SELECT if(number % 2, materialize(9223372036854775806), materialize(-9223372036854775808)) AS res FROM numbers(2);
+SELECT if(number % 2, [9223372036854775806], [2, 65537, -9223372036854775808]) AS res FROM numbers(2);
+SELECT if(number % 2, materialize([9223372036854775806]), [2, 65537, -9223372036854775808]) AS res FROM numbers(2);
+SELECT if(number % 2, [9223372036854775806], materialize([2, 65537, -9223372036854775808])) AS res FROM numbers(2);
+SELECT if(number % 2, materialize([9223372036854775806]), materialize([2, 65537, -9223372036854775808])) AS res FROM numbers(2);
+SELECT if(number % 2, [[9223372036854775806]], [[2, 65537, -9223372036854775808]]) AS res FROM numbers(2);
+SELECT if(number % 2, materialize([[9223372036854775806]]), [[2, 65537, -9223372036854775808]]) AS res FROM numbers(2);
+SELECT if(number % 2, [[9223372036854775806]], materialize([[2, 65537, -9223372036854775808]])) AS res FROM numbers(2);
+SELECT if(number % 2, materialize([[9223372036854775806]]), materialize([[2, 65537, -9223372036854775808]])) AS res FROM numbers(2);
+

utils/check-style/check-black

@@ -12,12 +12,16 @@ tmp=$(mktemp)
 # in the repo except the contrib directory.
 find_cmd=(
   find "$GIT_ROOT" -type f -not -path "${GIT_ROOT}contrib/*"
+    \(
       \(
         -name '*.py' -or -name "*.python" -or
           \(
             -executable -not -name "*.*" -exec sh -c 'file {} | grep -q "Python script"' \;
           \)
       \)
+      # We skip modules generated by the protocol buffer compiler from *.proto files.
+      -and -not -name '*_pb2.py' -and -not -name '*_pb2_grpc.py'
+    \)
 )
 
 if ! "${find_cmd[@]}" -exec black --check --diff {} + 1>"$tmp" 2>&1; then

utils/grpc-client/clickhouse-grpc-client.py

@@ -10,10 +10,6 @@
 # Most of the command line options are the same, for more information type
 # ./clickhouse_grpc_client.py --help
 
-import grpc  # pip3 install grpcio
-import grpc_tools  # pip3 install grpcio-tools
-import argparse, cmd, os, signal, subprocess, sys, threading, time, uuid
-
 DEFAULT_HOST = "localhost"
 DEFAULT_PORT = 9100
 DEFAULT_USER_NAME = "default"
@@ -24,6 +20,16 @@ STDIN_BUFFER_SIZE = 1048576
 DEFAULT_ENCODING = "utf-8"
 
 
+import grpc  # pip3 install grpcio
+import argparse, cmd, os, signal, sys, threading, time, uuid
+
+script_dir = os.path.dirname(os.path.realpath(__file__))
+pb2_dir = os.path.join(script_dir, "pb2")
+if pb2_dir not in sys.path:
+    sys.path.append(pb2_dir)
+import clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc  # Execute pb2/generate.py to generate these modules.
+
+
 class ClickHouseGRPCError(Exception):
     pass
 
@@ -80,8 +86,6 @@ class ClickHouseGRPCClient(cmd.Cmd):
         self.session_id = None
 
     def __enter__(self):
-        ClickHouseGRPCClient.__generate_pb2()
-        ClickHouseGRPCClient.__import_pb2()
         self.__connect()
         return self
 
@@ -229,40 +233,6 @@ class ClickHouseGRPCClient(cmd.Cmd):
         if result.HasField("exception"):
             raise ClickHouseGRPCError(result.exception.display_text)
 
-    # Use grpcio-tools to generate *pb2.py files from *.proto.
-    @staticmethod
-    def __generate_pb2():
-        script_dir = os.path.dirname(os.path.realpath(__file__))
-        proto_dir = os.path.join(script_dir, "./protos")
-        gen_dir = os.path.join(script_dir, "./_gen")
-        if os.path.exists(os.path.join(gen_dir, "clickhouse_grpc_pb2_grpc.py")):
-            return
-        os.makedirs(gen_dir, exist_ok=True)
-        cmd = [
-            "python3",
-            "-m",
-            "grpc_tools.protoc",
-            "-I" + proto_dir,
-            "--python_out=" + gen_dir,
-            "--grpc_python_out=" + gen_dir,
-            proto_dir + "/clickhouse_grpc.proto",
-        ]
-        p = subprocess.Popen(cmd, stderr=subprocess.PIPE)
-        # We don't want to show grpc_tools warnings.
-        errors = p.stderr.read().decode().strip("\n").split("\n")
-        only_warnings = all(("Warning" in error) for error in errors)
-        if not only_warnings:
-            error_print("\n".join(errors))
-
-    # Import the generated *pb2.py files.
-    @staticmethod
-    def __import_pb2():
-        script_dir = os.path.dirname(os.path.realpath(__file__))
-        gen_dir = os.path.join(script_dir, "./_gen")
-        sys.path.append(gen_dir)
-        global clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc
-        import clickhouse_grpc_pb2, clickhouse_grpc_pb2_grpc
-
     # Prints only if interactive mode is activated.
     def verbatim_print(self, *args, **kwargs):
         if self.verbatim:

utils/grpc-client/pb2/clickhouse_grpc_pb2_grpc.py

@@ -0,0 +1,165 @@
+# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
+"""Client and server classes corresponding to protobuf-defined services."""
+import grpc
+
+import clickhouse_grpc_pb2 as clickhouse__grpc__pb2
+
+
+class ClickHouseStub(object):
+    """Missing associated documentation comment in .proto file."""
+
+    def __init__(self, channel):
+        """Constructor.
+
+        Args:
+            channel: A grpc.Channel.
+        """
+        self.ExecuteQuery = channel.unary_unary(
+                '/clickhouse.grpc.ClickHouse/ExecuteQuery',
+                request_serializer=clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+                response_deserializer=clickhouse__grpc__pb2.Result.FromString,
+                )
+        self.ExecuteQueryWithStreamInput = channel.stream_unary(
+                '/clickhouse.grpc.ClickHouse/ExecuteQueryWithStreamInput',
+                request_serializer=clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+                response_deserializer=clickhouse__grpc__pb2.Result.FromString,
+                )
+        self.ExecuteQueryWithStreamOutput = channel.unary_stream(
+                '/clickhouse.grpc.ClickHouse/ExecuteQueryWithStreamOutput',
+                request_serializer=clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+                response_deserializer=clickhouse__grpc__pb2.Result.FromString,
+                )
+        self.ExecuteQueryWithStreamIO = channel.stream_stream(
+                '/clickhouse.grpc.ClickHouse/ExecuteQueryWithStreamIO',
+                request_serializer=clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+                response_deserializer=clickhouse__grpc__pb2.Result.FromString,
+                )
+
+
+class ClickHouseServicer(object):
+    """Missing associated documentation comment in .proto file."""
+
+    def ExecuteQuery(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def ExecuteQueryWithStreamInput(self, request_iterator, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def ExecuteQueryWithStreamOutput(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def ExecuteQueryWithStreamIO(self, request_iterator, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+
+def add_ClickHouseServicer_to_server(servicer, server):
+    rpc_method_handlers = {
+            'ExecuteQuery': grpc.unary_unary_rpc_method_handler(
+                    servicer.ExecuteQuery,
+                    request_deserializer=clickhouse__grpc__pb2.QueryInfo.FromString,
+                    response_serializer=clickhouse__grpc__pb2.Result.SerializeToString,
+            ),
+            'ExecuteQueryWithStreamInput': grpc.stream_unary_rpc_method_handler(
+                    servicer.ExecuteQueryWithStreamInput,
+                    request_deserializer=clickhouse__grpc__pb2.QueryInfo.FromString,
+                    response_serializer=clickhouse__grpc__pb2.Result.SerializeToString,
+            ),
+            'ExecuteQueryWithStreamOutput': grpc.unary_stream_rpc_method_handler(
+                    servicer.ExecuteQueryWithStreamOutput,
+                    request_deserializer=clickhouse__grpc__pb2.QueryInfo.FromString,
+                    response_serializer=clickhouse__grpc__pb2.Result.SerializeToString,
+            ),
+            'ExecuteQueryWithStreamIO': grpc.stream_stream_rpc_method_handler(
+                    servicer.ExecuteQueryWithStreamIO,
+                    request_deserializer=clickhouse__grpc__pb2.QueryInfo.FromString,
+                    response_serializer=clickhouse__grpc__pb2.Result.SerializeToString,
+            ),
+    }
+    generic_handler = grpc.method_handlers_generic_handler(
+            'clickhouse.grpc.ClickHouse', rpc_method_handlers)
+    server.add_generic_rpc_handlers((generic_handler,))
+
+
+ # This class is part of an EXPERIMENTAL API.
+class ClickHouse(object):
+    """Missing associated documentation comment in .proto file."""
+
+    @staticmethod
+    def ExecuteQuery(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(request, target, '/clickhouse.grpc.ClickHouse/ExecuteQuery',
+            clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+            clickhouse__grpc__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def ExecuteQueryWithStreamInput(request_iterator,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.stream_unary(request_iterator, target, '/clickhouse.grpc.ClickHouse/ExecuteQueryWithStreamInput',
+            clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+            clickhouse__grpc__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def ExecuteQueryWithStreamOutput(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_stream(request, target, '/clickhouse.grpc.ClickHouse/ExecuteQueryWithStreamOutput',
+            clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+            clickhouse__grpc__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)
+
+    @staticmethod
+    def ExecuteQueryWithStreamIO(request_iterator,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.stream_stream(request_iterator, target, '/clickhouse.grpc.ClickHouse/ExecuteQueryWithStreamIO',
+            clickhouse__grpc__pb2.QueryInfo.SerializeToString,
+            clickhouse__grpc__pb2.Result.FromString,
+            options, channel_credentials,
+            insecure, call_credentials, compression, wait_for_ready, timeout, metadata)

utils/grpc-client/pb2/generate.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+
+import grpc_tools  # pip3 install grpcio-tools
+
+import os
+import subprocess
+
+
+script_dir = os.path.dirname(os.path.realpath(__file__))
+dest_dir = script_dir
+src_dir = os.path.abspath(os.path.join(script_dir, "../../../src/Server/grpc_protos"))
+src_filename = "clickhouse_grpc.proto"
+
+
+def generate():
+    cmd = [
+        "python3",
+        "-m",
+        "grpc_tools.protoc",
+        "-I" + src_dir,
+        "--python_out=" + dest_dir,
+        "--grpc_python_out=" + dest_dir,
+        os.path.join(src_dir, src_filename),
+    ]
+    subprocess.run(cmd)
+
+
+if __name__ == "__main__":
+    generate()

utils/grpc-client/protos/clickhouse_grpc.proto

@@ -1 +0,0 @@
-../../../src/Server/grpc_protos/clickhouse_grpc.proto