Remove superfluous --multiquery/-n

.github/actions/debug/action.yml

@@ -4,31 +4,15 @@ description: Prints workflow debug info
 runs:
   using: "composite"
   steps:
-    - name: Envs, event.json and contexts
+    - name: Print envs
       shell: bash
       run: |
-          echo '::group::Environment variables'
-          env | sort
-          echo '::endgroup::'
-
-          echo '::group::event.json'
+          echo "::group::Envs"
+          env
+          echo "::endgroup::"
+    - name: Print Event.json
+      shell: bash
+      run: |
+          echo "::group::Event.json"
           python3 -m json.tool "$GITHUB_EVENT_PATH"
-          echo '::endgroup::'
-
-          cat << 'EOF'
-          ::group::github context
-          ${{ toJSON(github) }}
-          ::endgroup::
-
-          ::group::env context
-          ${{ toJSON(env) }}
-          ::endgroup::
-
-          ::group::runner context
-          ${{ toJSON(runner) }}
-          ::endgroup::
-
-          ::group::job context
-          ${{ toJSON(job) }}
-          ::endgroup::
-          EOF
+          echo "::endgroup::"

.github/workflows/backport_branches.yml

@@ -27,8 +27,6 @@ jobs:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Labels check
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"

.github/workflows/cherry_pick.yml

@@ -33,8 +33,6 @@ jobs:
           clear-repository: true
           token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
           fetch-depth: 0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Cherry pick
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"

.github/workflows/create_release.yml

@@ -56,13 +56,13 @@ jobs:
       GH_TOKEN: ${{ secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN }}
     runs-on: [self-hosted, release-maker]
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           token: ${{secrets.ROBOT_CLICKHOUSE_COMMIT_TOKEN}}
           fetch-depth: 0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Prepare Release Info
         shell: bash
         run: |

.github/workflows/docker_test_images.yml

@@ -11,7 +11,6 @@ name: Build docker images
         required: false
         type: boolean
         default: false
-
 jobs:
   DockerBuildAarch64:
     runs-on: [self-hosted, style-checker-aarch64]

.github/workflows/jepsen.yml

@@ -8,28 +8,27 @@ on: # yamllint disable-line rule:truthy
   schedule:
     - cron: '0 */6 * * *'
   workflow_dispatch:
-
 jobs:
   RunConfig:
     runs-on: [self-hosted, style-checker-aarch64]
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: PrepareRunConfig
         id: runconfig
         run: |
           echo "::group::configure CI run"
           python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --workflow "$GITHUB_WORKFLOW" --outfile ${{ runner.temp }}/ci_run_data.json
           echo "::endgroup::"
-
+          
           echo "::group::CI run configure results"
           python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
           echo "::endgroup::"

.github/workflows/master.yml

@@ -15,14 +15,14 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Merge sync PR
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"

.github/workflows/merge_queue.yml

@@ -14,14 +14,14 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get a version
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Cancel PR workflow
         run: |
           python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run

.github/workflows/nightly.yml

@@ -15,14 +15,14 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: PrepareRunConfig
         id: runconfig
         run: |

.github/workflows/pull_request.yml

@@ -25,14 +25,14 @@ jobs:
     outputs:
       data: ${{ steps.runconfig.outputs.CI_DATA }}
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get a version
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Cancel previous Sync PR workflow
         run: |
           python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run

.github/workflows/release_branches.yml

@@ -24,8 +24,6 @@ jobs:
           clear-repository: true # to ensure correct digests
           fetch-depth: 0 # to get version
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Labels check
         run: |
           cd "$GITHUB_WORKSPACE/tests/ci"

.github/workflows/reusable_simple_job.yml

@@ -62,6 +62,8 @@ jobs:
     env:
       GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}
     steps:
+      - name: DebugInfo
+        uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
       - name: Check out repository code
         uses: ClickHouse/checkout@v1
         with:
@@ -70,8 +72,6 @@ jobs:
           submodules: ${{inputs.submodules}}
           fetch-depth: ${{inputs.checkout_depth}}
           filter: tree:0
-      - name: Debug Info
-        uses: ./.github/actions/debug
       - name: Set build envs
         run: |
           cat >> "$GITHUB_ENV" << 'EOF'

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

@@ -107,10 +107,6 @@ The vector similarity index currently does not work with per-table, non-default
 [here](https://github.com/ClickHouse/ClickHouse/pull/51325#issuecomment-1605920475)). If necessary, the value must be changed in config.xml.
 :::
 
-Vector index creation is known to be slow. To speed the process up, index creation can be parallelized. The maximum number of threads can be
-configured using server configuration
-setting [max_build_vector_similarity_index_thread_pool_size](../../../operations/server-configuration-parameters/settings.md#server_configuration_parameters_max_build_vector_similarity_index_thread_pool_size).
-
 ANN indexes are built during column insertion and merge. As a result, `INSERT` and `OPTIMIZE` statements will be slower than for ordinary
 tables. ANNIndexes are ideally used only with immutable or rarely changed data, respectively when are far more read requests than write
 requests.

docs/en/interfaces/formats.md

@@ -1396,7 +1396,6 @@ SELECT * FROM json_each_row_nested
 - [input_format_json_ignore_unknown_keys_in_named_tuple](/docs/en/operations/settings/settings-formats.md/#input_format_json_ignore_unknown_keys_in_named_tuple) - ignore unknown keys in json object for named tuples. Default value - `false`.
 - [input_format_json_compact_allow_variable_number_of_columns](/docs/en/operations/settings/settings-formats.md/#input_format_json_compact_allow_variable_number_of_columns) - allow variable number of columns in JSONCompact/JSONCompactEachRow format, ignore extra columns and use default values on missing columns. Default value - `false`.
 - [input_format_json_throw_on_bad_escape_sequence](/docs/en/operations/settings/settings-formats.md/#input_format_json_throw_on_bad_escape_sequence) - throw an exception if JSON string contains bad escape sequence. If disabled, bad escape sequences will remain as is in the data. Default value - `true`.
-- [input_format_json_empty_as_default](/docs/en/operations/settings/settings-formats.md/#input_format_json_empty_as_default) - treat empty fields in JSON input as default values. Default value - `false`. For complex default expressions [input_format_defaults_for_omitted_fields](/docs/en/operations/settings/settings-formats.md/#input_format_defaults_for_omitted_fields) must be enabled too.
 - [output_format_json_quote_64bit_integers](/docs/en/operations/settings/settings-formats.md/#output_format_json_quote_64bit_integers) - controls quoting of 64-bit integers in JSON output format. Default value - `true`.
 - [output_format_json_quote_64bit_floats](/docs/en/operations/settings/settings-formats.md/#output_format_json_quote_64bit_floats) - controls quoting of 64-bit floats in JSON output format. Default value - `false`.
 - [output_format_json_quote_denormals](/docs/en/operations/settings/settings-formats.md/#output_format_json_quote_denormals) - enables '+nan', '-nan', '+inf', '-inf' outputs in JSON output format. Default value - `false`.

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

@@ -491,14 +491,6 @@ Type: Double
 
 Default: 0.9
 
-## max_build_vector_similarity_index_thread_pool_size {#server_configuration_parameters_max_build_vector_similarity_index_thread_pool_size}
-
-The maximum number of threads to use for building vector indexes. 0 means all cores.
-
-Type: UInt64
-
-Default: 16
-
 ## cgroups_memory_usage_observer_wait_time
 
 Interval in seconds during which the server's maximum allowed memory consumption is adjusted by the corresponding threshold in cgroups. (see

docs/en/operations/settings/settings-formats.md

@@ -752,17 +752,6 @@ Possible values:
 
 Default value: 0.
 
-### input_format_json_empty_as_default {#input_format_json_empty_as_default}
-
-When enabled, replace empty input fields in JSON with default values. For complex default expressions `input_format_defaults_for_omitted_fields` must be enabled too.
-
-Possible values:
-
-+ 0 — Disable.
-+ 1 — Enable.
-
-Default value: 0.
-
 ## TSV format settings {#tsv-format-settings}
 
 ### input_format_tsv_empty_as_default {#input_format_tsv_empty_as_default}

src/Common/CurrentMetrics.cpp

@@ -178,9 +178,6 @@
     M(ObjectStorageAzureThreads, "Number of threads in the AzureObjectStorage thread pool.") \
     M(ObjectStorageAzureThreadsActive, "Number of threads in the AzureObjectStorage thread pool running a task.") \
     M(ObjectStorageAzureThreadsScheduled, "Number of queued or active jobs in the AzureObjectStorage thread pool.") \
-    M(BuildVectorSimilarityIndexThreads, "Number of threads in the build vector similarity index thread pool.") \
-    M(BuildVectorSimilarityIndexThreadsActive, "Number of threads in the build vector similarity index thread pool running a task.") \
-    M(BuildVectorSimilarityIndexThreadsScheduled, "Number of queued or active jobs in the build vector similarity index thread pool.") \
     \
     M(DiskPlainRewritableAzureDirectoryMapSize, "Number of local-to-remote path entries in the 'plain_rewritable' in-memory map for AzureObjectStorage.") \
     M(DiskPlainRewritableLocalDirectoryMapSize, "Number of local-to-remote path entries in the 'plain_rewritable' in-memory map for LocalObjectStorage.") \

src/Common/ErrorCodes.cpp

@@ -609,7 +609,6 @@
     M(728, UNEXPECTED_DATA_TYPE) \
     M(729, ILLEGAL_TIME_SERIES_TAGS) \
     M(730, REFRESH_FAILED) \
-    M(731, QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE) \
     \
     M(900, DISTRIBUTED_CACHE_ERROR) \
     M(901, CANNOT_USE_DISTRIBUTED_CACHE) \

src/Common/FailPoint.cpp

@@ -63,7 +63,6 @@ static struct InitFiu
     REGULAR(keepermap_fail_drop_data) \
     REGULAR(lazy_pipe_fds_fail_close) \
     PAUSEABLE(infinite_sleep) \
-    PAUSEABLE(stop_moving_part_before_swap_with_active) \
 
 
 namespace FailPoints

src/Core/ServerSettings.h

@@ -50,7 +50,7 @@ namespace DB
     M(UInt32, asynchronous_heavy_metrics_update_period_s, 120, "Period in seconds for updating heavy asynchronous metrics.", 0) \
     M(String, default_database, "default", "Default database name.", 0) \
     M(String, tmp_policy, "", "Policy for storage with temporary data.", 0) \
-    M(UInt64, max_temporary_data_on_disk_size, 0, "The maximum amount of storage that could be used for external aggregation, joins or sorting.", 0) \
+    M(UInt64, max_temporary_data_on_disk_size, 0, "The maximum amount of storage that could be used for external aggregation, joins or sorting., ", 0) \
     M(String, temporary_data_in_cache, "", "Cache disk name for temporary data.", 0) \
     M(UInt64, aggregate_function_group_array_max_element_size, 0xFFFFFF, "Max array element size in bytes for groupArray function. This limit is checked at serialization and help to avoid large state size.", 0) \
     M(GroupArrayActionWhenLimitReached, aggregate_function_group_array_action_when_limit_is_reached, GroupArrayActionWhenLimitReached::THROW, "Action to execute when max array element size is exceeded in groupArray: `throw` exception, or `discard` extra values", 0) \
@@ -65,7 +65,6 @@ namespace DB
     M(UInt64, async_insert_threads, 16, "Maximum number of threads to actually parse and insert data in background. Zero means asynchronous mode is disabled", 0) \
     M(Bool, async_insert_queue_flush_on_shutdown, true, "If true queue of asynchronous inserts is flushed on graceful shutdown", 0) \
     M(Bool, ignore_empty_sql_security_in_create_view_query, true, "If true, ClickHouse doesn't write defaults for empty SQL security statement in CREATE VIEW queries. This setting is only necessary for the migration period and will become obsolete in 24.4", 0)  \
-    M(UInt64, max_build_vector_similarity_index_thread_pool_size, 16, "The maximum number of threads to use to build vector similarity indexes. 0 means all cores.", 0) \
     \
     /* Database Catalog */ \
     M(UInt64, database_atomic_delay_before_drop_table_sec, 8 * 60, "The delay during which a dropped table can be restored using the UNDROP statement. If DROP TABLE ran with a SYNC modifier, the setting is ignored.", 0) \

src/Core/Settings.h

@@ -1144,7 +1144,6 @@ class IColumn;
     M(Bool, input_format_try_infer_variants, false, "Try to infer the Variant type in text formats when there is more than one possible type for column/array elements", 0) \
     M(Bool, type_json_skip_duplicated_paths, false, "When enabled, during parsing JSON object into JSON type duplicated paths will be ignored and only the first one will be inserted instead of an exception", 0) \
     M(UInt64, input_format_json_max_depth, 1000, "Maximum depth of a field in JSON. This is not a strict limit, it does not have to be applied precisely.", 0) \
-    M(Bool, input_format_json_empty_as_default, false, "Treat empty fields in JSON input as default values.", 0) \
     M(Bool, input_format_try_infer_integers, true, "Try to infer integers instead of floats while schema inference in text formats", 0) \
     M(Bool, input_format_try_infer_dates, true, "Try to infer dates from string fields while schema inference in text formats", 0) \
     M(Bool, input_format_try_infer_datetimes, true, "Try to infer datetimes from string fields while schema inference in text formats", 0) \

src/Core/SettingsChangesHistory.cpp

@@ -71,7 +71,6 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
     },
     {"24.9",
         {
-            {"input_format_json_empty_as_default", false, false, "Added new setting to allow to treat empty fields in JSON input as default values."},
             {"input_format_try_infer_variants", false, false, "Try to infer Variant type in text formats when there is more than one possible type for column/array elements"},
             {"join_output_by_rowlist_perkey_rows_threshold", 0, 5, "The lower limit of per-key average rows in the right table to determine whether to output by row list in hash join."},
             {"create_if_not_exists", false, false, "New setting."},

src/DataTypes/Serializations/SerializationArray.cpp

@@ -11,7 +11,6 @@
 #include <IO/WriteBufferFromString.h>
 
 #include <Formats/FormatSettings.h>
-#include <Formats/JSONUtils.h>
 
 namespace DB
 {
@@ -616,49 +615,28 @@ void SerializationArray::serializeTextJSONPretty(const IColumn & column, size_t
 }
 
 
-template <typename ReturnType>
-ReturnType SerializationArray::deserializeTextJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
-{
-    auto deserialize_nested = [&settings, this](IColumn & nested_column, ReadBuffer & buf) -> ReturnType
-    {
-        if constexpr (std::is_same_v<ReturnType, void>)
-        {
-            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(nested_column))
-                SerializationNullable::deserializeNullAsDefaultOrNestedTextJSON(nested_column, buf, settings, nested);
-            else
-                nested->deserializeTextJSON(nested_column, buf, settings);
-        }
-        else
-        {
-            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(nested_column))
-                return SerializationNullable::tryDeserializeNullAsDefaultOrNestedTextJSON(nested_column, buf, settings, nested);
-            return nested->tryDeserializeTextJSON(nested_column, buf, settings);
-        }
-    };
-
-    if (settings.json.empty_as_default)
-        return deserializeTextImpl<ReturnType>(column, istr,
-            [&deserialize_nested, &istr](IColumn & nested_column) -> ReturnType
-            {
-                return JSONUtils::deserializeEmpyStringAsDefaultOrNested<ReturnType>(nested_column, istr, deserialize_nested);
-            }, false);
-    else
-        return deserializeTextImpl<ReturnType>(column, istr,
-            [&deserialize_nested, &istr](IColumn & nested_column) -> ReturnType
-            {
-                return deserialize_nested(nested_column, istr);
-            }, false);
-}
-
-
 void SerializationArray::deserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
 {
-    deserializeTextJSONImpl<void>(column, istr, settings);
+    deserializeTextImpl(column, istr,
+        [&](IColumn & nested_column)
+        {
+            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(nested_column))
+                SerializationNullable::deserializeNullAsDefaultOrNestedTextJSON(nested_column, istr, settings, nested);
+            else
+                nested->deserializeTextJSON(nested_column, istr, settings);
+        }, false);
 }
 
 bool SerializationArray::tryDeserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
 {
-    return deserializeTextJSONImpl<bool>(column, istr, settings);
+    auto read_nested = [&](IColumn & nested_column)
+    {
+        if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(nested_column))
+            return SerializationNullable::tryDeserializeNullAsDefaultOrNestedTextJSON(nested_column, istr, settings, nested);
+        return nested->tryDeserializeTextJSON(nested_column, istr, settings);
+    };
+
+    return deserializeTextImpl<bool>(column, istr, std::move(read_nested), false);
 }
 
 

src/DataTypes/Serializations/SerializationArray.h

@@ -82,10 +82,6 @@ public:
         SerializationPtr create(const SerializationPtr & prev) const override;
         ColumnPtr create(const ColumnPtr & prev) const override;
     };
-
-private:
-    template <typename ReturnType>
-    ReturnType deserializeTextJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const;
 };
 
 }

src/DataTypes/Serializations/SerializationMap.cpp

@@ -6,7 +6,6 @@
 #include <Columns/ColumnMap.h>
 #include <Core/Field.h>
 #include <Formats/FormatSettings.h>
-#include <Formats/JSONUtils.h>
 #include <Common/assert_cast.h>
 #include <Common/quoteString.h>
 #include <IO/WriteHelpers.h>
@@ -317,52 +316,28 @@ void SerializationMap::serializeTextJSONPretty(const IColumn & column, size_t ro
 }
 
 
-template <typename ReturnType>
-ReturnType SerializationMap::deserializeTextJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
+void SerializationMap::deserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
 {
-    auto deserialize_nested = [&settings](IColumn & subcolumn, ReadBuffer & buf, const SerializationPtr & subcolumn_serialization) -> ReturnType
-    {
-        if constexpr (std::is_same_v<ReturnType, void>)
+    deserializeTextImpl(column, istr,
+        [&settings](ReadBuffer & buf, const SerializationPtr & subcolumn_serialization, IColumn & subcolumn)
         {
             if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(subcolumn))
                 SerializationNullable::deserializeNullAsDefaultOrNestedTextJSON(subcolumn, buf, settings, subcolumn_serialization);
             else
                 subcolumn_serialization->deserializeTextJSON(subcolumn, buf, settings);
-        }
-        else
-        {
-            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(subcolumn))
-                return SerializationNullable::tryDeserializeNullAsDefaultOrNestedTextJSON(subcolumn, buf, settings, subcolumn_serialization);
-            return subcolumn_serialization->tryDeserializeTextJSON(subcolumn, buf, settings);
-        }
-    };
-
-    if (settings.json.empty_as_default)
-        return deserializeTextImpl<ReturnType>(column, istr,
-            [&deserialize_nested](ReadBuffer & buf, const SerializationPtr & subcolumn_serialization, IColumn & subcolumn) -> ReturnType
-            {
-                return JSONUtils::deserializeEmpyStringAsDefaultOrNested<ReturnType>(subcolumn, buf,
-                    [&deserialize_nested, &subcolumn_serialization](IColumn & subcolumn_, ReadBuffer & buf_) -> ReturnType
-                    {
-                        return deserialize_nested(subcolumn_, buf_, subcolumn_serialization);
-                    });
-            });
-    else
-        return deserializeTextImpl<ReturnType>(column, istr,
-            [&deserialize_nested](ReadBuffer & buf, const SerializationPtr & subcolumn_serialization, IColumn & subcolumn) -> ReturnType
-            {
-                return deserialize_nested(subcolumn, buf, subcolumn_serialization);
-            });
-}
-
-void SerializationMap::deserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
-{
-    deserializeTextJSONImpl<void>(column, istr, settings);
+        });
 }
 
 bool SerializationMap::tryDeserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
 {
-    return deserializeTextJSONImpl<bool>(column, istr, settings);
+    auto reader = [&settings](ReadBuffer & buf, const SerializationPtr & subcolumn_serialization, IColumn & subcolumn)
+    {
+        if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(subcolumn))
+            return SerializationNullable::tryDeserializeNullAsDefaultOrNestedTextJSON(subcolumn, buf, settings, subcolumn_serialization);
+        return subcolumn_serialization->tryDeserializeTextJSON(subcolumn, buf, settings);
+    };
+
+    return deserializeTextImpl<bool>(column, istr, reader);
 }
 
 void SerializationMap::serializeTextXML(const IColumn & column, size_t row_num, WriteBuffer & ostr, const FormatSettings & settings) const

src/DataTypes/Serializations/SerializationMap.h

@@ -74,9 +74,6 @@ private:
 
     template <typename ReturnType = void, typename Reader>
     ReturnType deserializeTextImpl(IColumn & column, ReadBuffer & istr, Reader && reader) const;
-
-    template <typename ReturnType>
-    ReturnType deserializeTextJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const;
 };
 
 }

src/DataTypes/Serializations/SerializationTuple.cpp

@@ -5,7 +5,6 @@
 #include <Core/Field.h>
 #include <Columns/ColumnTuple.h>
 #include <Common/assert_cast.h>
-#include <Formats/JSONUtils.h>
 #include <IO/WriteHelpers.h>
 #include <IO/ReadHelpers.h>
 #include <IO/ReadBufferFromString.h>
@@ -314,9 +313,27 @@ void SerializationTuple::serializeTextJSONPretty(const IColumn & column, size_t
 }
 
 template <typename ReturnType>
-ReturnType SerializationTuple::deserializeTupleJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings, auto && deserialize_element) const
+ReturnType SerializationTuple::deserializeTextJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
 {
-    static constexpr auto throw_exception = std::is_same_v<ReturnType, void>;
+    static constexpr bool throw_exception = std::is_same_v<ReturnType, void>;
+
+    auto deserialize_element = [&](IColumn & element_column, size_t element_pos)
+    {
+        if constexpr (throw_exception)
+        {
+            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(element_column))
+                SerializationNullable::deserializeNullAsDefaultOrNestedTextJSON(element_column, istr, settings, elems[element_pos]);
+            else
+                elems[element_pos]->deserializeTextJSON(element_column, istr, settings);
+            return true;
+        }
+        else
+        {
+            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(element_column))
+                return SerializationNullable::tryDeserializeNullAsDefaultOrNestedTextJSON(element_column, istr, settings, elems[element_pos]);
+            return elems[element_pos]->tryDeserializeTextJSON(element_column, istr, settings);
+        }
+    };
 
     if (settings.json.read_named_tuples_as_objects
         && have_explicit_names)
@@ -489,51 +506,12 @@ ReturnType SerializationTuple::deserializeTupleJSONImpl(IColumn & column, ReadBu
     }
 }
 
-template <typename ReturnType>
-ReturnType SerializationTuple::deserializeTextJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
+void SerializationTuple::deserializeTextJSON(DB::IColumn & column, DB::ReadBuffer & istr, const DB::FormatSettings & settings) const
 {
-    auto deserialize_nested = [&settings](IColumn & nested_column, ReadBuffer & buf, const SerializationPtr & nested_column_serialization) -> ReturnType
-    {
-        if constexpr (std::is_same_v<ReturnType, void>)
-        {
-            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(nested_column))
-                SerializationNullable::deserializeNullAsDefaultOrNestedTextJSON(nested_column, buf, settings, nested_column_serialization);
-            else
-                nested_column_serialization->deserializeTextJSON(nested_column, buf, settings);
-        }
-        else
-        {
-            if (settings.null_as_default && !isColumnNullableOrLowCardinalityNullable(nested_column))
-                return SerializationNullable::tryDeserializeNullAsDefaultOrNestedTextJSON(nested_column, buf, settings, nested_column_serialization);
-            else
-                return nested_column_serialization->tryDeserializeTextJSON(nested_column, buf, settings);
-        }
-    };
-
-    if (settings.json.empty_as_default)
-        return deserializeTupleJSONImpl<ReturnType>(column, istr, settings,
-            [&deserialize_nested, &istr, this](IColumn & nested_column, size_t element_pos) -> ReturnType
-            {
-                return JSONUtils::deserializeEmpyStringAsDefaultOrNested<ReturnType>(nested_column, istr,
-                    [&deserialize_nested, element_pos, this](IColumn & nested_column_, ReadBuffer & buf) -> ReturnType
-                    {
-                        return deserialize_nested(nested_column_, buf, elems[element_pos]);
-                    });
-            });
-    else
-        return deserializeTupleJSONImpl<ReturnType>(column, istr, settings,
-            [&deserialize_nested, &istr, this](IColumn & nested_column, size_t element_pos) -> ReturnType
-            {
-                return deserialize_nested(nested_column, istr, elems[element_pos]);
-            });
+    deserializeTextJSONImpl(column, istr, settings);
 }
 
-void SerializationTuple::deserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
-{
-    deserializeTextJSONImpl<void>(column, istr, settings);
-}
-
-bool SerializationTuple::tryDeserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
+bool SerializationTuple::tryDeserializeTextJSON(DB::IColumn & column, DB::ReadBuffer & istr, const DB::FormatSettings & settings) const
 {
     return deserializeTextJSONImpl<bool>(column, istr, settings);
 }

src/DataTypes/Serializations/SerializationTuple.h

@@ -81,10 +81,7 @@ private:
     template <typename ReturnType = void>
     ReturnType deserializeTextImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings, bool whole) const;
 
-    template <typename ReturnType>
-    ReturnType deserializeTupleJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings, auto && deserialize_element) const;
-
-    template <typename ReturnType>
+    template <typename ReturnType = void>
     ReturnType deserializeTextJSONImpl(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const;
 
     template <typename ReturnType = void>

src/Formats/FormatFactory.cpp

@@ -152,7 +152,6 @@ FormatSettings getFormatSettings(const ContextPtr & context, const Settings & se
     format_settings.json.try_infer_objects_as_tuples = settings.input_format_json_try_infer_named_tuples_from_objects;
     format_settings.json.throw_on_bad_escape_sequence = settings.input_format_json_throw_on_bad_escape_sequence;
     format_settings.json.ignore_unnecessary_fields = settings.input_format_json_ignore_unnecessary_fields;
-    format_settings.json.empty_as_default = settings.input_format_json_empty_as_default;
     format_settings.json.type_json_skip_duplicated_paths = settings.type_json_skip_duplicated_paths;
     format_settings.null_as_default = settings.input_format_null_as_default;
     format_settings.force_null_for_omitted_fields = settings.input_format_force_null_for_omitted_fields;

src/Formats/FormatSettings.h

@@ -237,7 +237,6 @@ struct FormatSettings
         bool infer_incomplete_types_as_strings = true;
         bool throw_on_bad_escape_sequence = true;
         bool ignore_unnecessary_fields = true;
-        bool empty_as_default = false;
         bool type_json_skip_duplicated_paths = false;
     } json{};
 

src/Formats/JSONUtils.cpp

@@ -2,14 +2,12 @@
 #include <Formats/JSONUtils.h>
 #include <Formats/ReadSchemaUtils.h>
 #include <Formats/EscapingRuleUtils.h>
-#include <IO/PeekableReadBuffer.h>
 #include <IO/ReadBufferFromString.h>
 #include <IO/WriteBufferValidUTF8.h>
 #include <DataTypes/Serializations/SerializationNullable.h>
 #include <DataTypes/DataTypeNullable.h>
 #include <DataTypes/DataTypeObjectDeprecated.h>
 #include <DataTypes/DataTypeFactory.h>
-#include <Common/assert_cast.h>
 
 #include <base/find_symbols.h>
 
@@ -288,19 +286,11 @@ namespace JSONUtils
                 return true;
             }
 
-            auto deserialize = [as_nullable, &format_settings, &serialization](IColumn & column_, ReadBuffer & buf) -> bool
-            {
-                if (as_nullable)
-                    return SerializationNullable::deserializeNullAsDefaultOrNestedTextJSON(column_, buf, format_settings, serialization);
+            if (as_nullable)
+                return SerializationNullable::deserializeNullAsDefaultOrNestedTextJSON(column, in, format_settings, serialization);
 
-                serialization->deserializeTextJSON(column_, buf, format_settings);
-                return true;
-            };
-
-            if (format_settings.json.empty_as_default)
-                return JSONUtils::deserializeEmpyStringAsDefaultOrNested<bool, false>(column, in, deserialize);
-            else
-                return deserialize(column, in);
+            serialization->deserializeTextJSON(column, in, format_settings);
+            return true;
         }
         catch (Exception & e)
         {
@@ -930,78 +920,6 @@ namespace JSONUtils
         }
     }
 
-    template <typename ReturnType, bool default_column_return_value>
-    ReturnType deserializeEmpyStringAsDefaultOrNested(IColumn & column, ReadBuffer & istr, const NestedDeserialize<ReturnType> & deserialize_nested)
-    {
-        static constexpr auto throw_exception = std::is_same_v<ReturnType, void>;
-
-        static constexpr auto EMPTY_STRING = "\"\"";
-        static constexpr auto EMPTY_STRING_LENGTH = std::string_view(EMPTY_STRING).length();
-
-        if (istr.eof() || *istr.position() != EMPTY_STRING[0])
-            return deserialize_nested(column, istr);
-
-        auto do_deserialize = [](IColumn & column_, ReadBuffer & buf, auto && check_for_empty_string, auto && deserialize) -> ReturnType
-        {
-            if (check_for_empty_string(buf))
-            {
-                column_.insertDefault();
-                return ReturnType(default_column_return_value);
-            }
-            return deserialize(column_, buf);
-        };
-
-        if (istr.available() >= EMPTY_STRING_LENGTH)
-        {
-            /// We have enough data in buffer to check if we have an empty string.
-            auto check_for_empty_string = [](ReadBuffer & buf) -> bool
-            {
-                auto * pos = buf.position();
-                if (checkString(EMPTY_STRING, buf))
-                    return true;
-                buf.position() = pos;
-                return false;
-            };
-
-            return do_deserialize(column, istr, check_for_empty_string, deserialize_nested);
-        }
-
-        /// We don't have enough data in buffer to check if we have an empty string.
-        /// Use PeekableReadBuffer to make a checkpoint before checking for an
-        /// empty string and rollback if check was failed.
-
-        auto check_for_empty_string = [](ReadBuffer & buf) -> bool
-        {
-            auto & peekable_buf = assert_cast<PeekableReadBuffer &>(buf);
-            peekable_buf.setCheckpoint();
-            SCOPE_EXIT(peekable_buf.dropCheckpoint());
-            if (checkString(EMPTY_STRING, peekable_buf))
-                return true;
-            peekable_buf.rollbackToCheckpoint();
-            return false;
-        };
-
-        auto deserialize_nested_with_check = [&deserialize_nested](IColumn & column_, ReadBuffer & buf) -> ReturnType
-        {
-            auto & peekable_buf = assert_cast<PeekableReadBuffer &>(buf);
-            if constexpr (throw_exception)
-                deserialize_nested(column_, peekable_buf);
-            else if (!deserialize_nested(column_, peekable_buf))
-                return ReturnType(false);
-
-            if (unlikely(peekable_buf.hasUnreadData()))
-                throw Exception(ErrorCodes::LOGICAL_ERROR, "Incorrect state while parsing JSON: PeekableReadBuffer has unread data in own memory: {}", String(peekable_buf.position(), peekable_buf.available()));
-
-            return ReturnType(true);
-        };
-
-        PeekableReadBuffer peekable_buf(istr, true);
-        return do_deserialize(column, peekable_buf, check_for_empty_string, deserialize_nested_with_check);
-    }
-
-    template void deserializeEmpyStringAsDefaultOrNested<void, true>(IColumn & column, ReadBuffer & istr, const NestedDeserialize<void> & deserialize_nested);
-    template bool deserializeEmpyStringAsDefaultOrNested<bool, true>(IColumn & column, ReadBuffer & istr, const NestedDeserialize<bool> & deserialize_nested);
-    template bool deserializeEmpyStringAsDefaultOrNested<bool, false>(IColumn & column, ReadBuffer & istr, const NestedDeserialize<bool> & deserialize_nested);
 }
 
 }

src/Formats/JSONUtils.h

@@ -8,7 +8,6 @@
 #include <IO/Progress.h>
 #include <Core/NamesAndTypes.h>
 #include <Common/Stopwatch.h>
-#include <functional>
 #include <utility>
 
 namespace DB
@@ -147,16 +146,6 @@ namespace JSONUtils
 
     bool skipUntilFieldInObject(ReadBuffer & in, const String & desired_field_name, const FormatSettings::JSON & settings);
     void skipTheRestOfObject(ReadBuffer & in, const FormatSettings::JSON & settings);
-
-    template <typename ReturnType>
-    using NestedDeserialize = std::function<ReturnType(IColumn &, ReadBuffer &)>;
-
-    template <typename ReturnType, bool default_column_return_value = true>
-    ReturnType deserializeEmpyStringAsDefaultOrNested(IColumn & column, ReadBuffer & istr, const NestedDeserialize<ReturnType> & deserialize_nested);
-
-    extern template void deserializeEmpyStringAsDefaultOrNested<void, true>(IColumn & column, ReadBuffer & istr, const NestedDeserialize<void> & deserialize_nested);
-    extern template bool deserializeEmpyStringAsDefaultOrNested<bool, true>(IColumn & column, ReadBuffer & istr, const NestedDeserialize<bool> & deserialize_nested);
-    extern template bool deserializeEmpyStringAsDefaultOrNested<bool, false>(IColumn & column, ReadBuffer & istr, const NestedDeserialize<bool> & deserialize_nested);
 }
 
 }

src/Interpreters/Context.cpp

@@ -10,7 +10,6 @@
 #include <Common/SensitiveDataMasker.h>
 #include <Common/Macros.h>
 #include <Common/EventNotifier.h>
-#include <Common/getNumberOfPhysicalCPUCores.h>
 #include <Common/Stopwatch.h>
 #include <Common/formatReadable.h>
 #include <Common/Throttler.h>
@@ -122,6 +121,7 @@
 #include <Interpreters/InterpreterSelectWithUnionQuery.h>
 #include <base/defines.h>
 
+
 namespace fs = std::filesystem;
 
 namespace ProfileEvents
@@ -164,9 +164,6 @@ namespace CurrentMetrics
     extern const Metric TablesLoaderForegroundThreadsActive;
     extern const Metric TablesLoaderForegroundThreadsScheduled;
     extern const Metric IOWriterThreadsScheduled;
-    extern const Metric BuildVectorSimilarityIndexThreads;
-    extern const Metric BuildVectorSimilarityIndexThreadsActive;
-    extern const Metric BuildVectorSimilarityIndexThreadsScheduled;
     extern const Metric AttachedTable;
     extern const Metric AttachedView;
     extern const Metric AttachedDictionary;
@@ -300,8 +297,6 @@ struct ContextSharedPart : boost::noncopyable
     mutable std::unique_ptr<ThreadPool> load_marks_threadpool;  /// Threadpool for loading marks cache.
     mutable OnceFlag prefetch_threadpool_initialized;
     mutable std::unique_ptr<ThreadPool> prefetch_threadpool;    /// Threadpool for loading marks cache.
-    mutable OnceFlag build_vector_similarity_index_threadpool_initialized;
-    mutable std::unique_ptr<ThreadPool> build_vector_similarity_index_threadpool; /// Threadpool for vector-similarity index creation.
     mutable UncompressedCachePtr index_uncompressed_cache TSA_GUARDED_BY(mutex);      /// The cache of decompressed blocks for MergeTree indices.
     mutable QueryCachePtr query_cache TSA_GUARDED_BY(mutex);                          /// Cache of query results.
     mutable MarkCachePtr index_mark_cache TSA_GUARDED_BY(mutex);                      /// Cache of marks in compressed files of MergeTree indices.
@@ -3302,21 +3297,6 @@ size_t Context::getPrefetchThreadpoolSize() const
     return config.getUInt(".prefetch_threadpool_pool_size", 100);
 }
 
-ThreadPool & Context::getBuildVectorSimilarityIndexThreadPool() const
-{
-    callOnce(shared->build_vector_similarity_index_threadpool_initialized, [&] {
-            size_t pool_size = shared->server_settings.max_build_vector_similarity_index_thread_pool_size > 0
-                ? shared->server_settings.max_build_vector_similarity_index_thread_pool_size
-                : getNumberOfPhysicalCPUCores();
-            shared->build_vector_similarity_index_threadpool = std::make_unique<ThreadPool>(
-                CurrentMetrics::BuildVectorSimilarityIndexThreads,
-                CurrentMetrics::BuildVectorSimilarityIndexThreadsActive,
-                CurrentMetrics::BuildVectorSimilarityIndexThreadsScheduled,
-                pool_size);
-        });
-    return *shared->build_vector_similarity_index_threadpool;
-}
-
 BackgroundSchedulePool & Context::getBufferFlushSchedulePool() const
 {
     callOnce(shared->buffer_flush_schedule_pool_initialized, [&] {

src/Interpreters/Context.h

@@ -1097,8 +1097,6 @@ public:
     /// and make a prefetch by putting a read task to threadpoolReader.
     size_t getPrefetchThreadpoolSize() const;
 
-    ThreadPool & getBuildVectorSimilarityIndexThreadPool() const;
-
     /// Settings for MergeTree background tasks stored in config.xml
     BackgroundTaskSchedulingSettings getBackgroundProcessingTaskSchedulingSettings() const;
     BackgroundTaskSchedulingSettings getBackgroundMoveTaskSchedulingSettings() const;

src/Interpreters/HashJoin/HashJoin.cpp

@@ -1236,7 +1236,6 @@ IBlocksStreamPtr HashJoin::getNonJoinedBlocks(const Block & left_sample_block,
 
 void HashJoin::reuseJoinedData(const HashJoin & join)
 {
-    have_compressed = join.have_compressed;
     data = join.data;
     from_storage_join = true;
 

src/Interpreters/executeQuery.cpp

@@ -99,7 +99,6 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int QUERY_CACHE_USED_WITH_NONDETERMINISTIC_FUNCTIONS;
-    extern const int QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE;
     extern const int QUERY_CACHE_USED_WITH_SYSTEM_TABLE;
     extern const int INTO_OUTFILE_NOT_ALLOWED;
     extern const int INVALID_TRANSACTION;
@@ -1119,24 +1118,22 @@ static std::tuple<ASTPtr, BlockIO> executeQueryImpl(
             && settings.use_query_cache
             && !internal
             && client_info.query_kind == ClientInfo::QueryKind::INITIAL_QUERY
+            /// Bug 67476: Avoid that the query cache stores truncated results if the query ran with a non-THROW overflow mode and hit a limit.
+            /// This is more workaround than a fix ... unfortunately it is hard to detect from the perspective of the query cache that the
+            /// query result is truncated.
+            && (settings.read_overflow_mode == OverflowMode::THROW
+                && settings.read_overflow_mode_leaf == OverflowMode::THROW
+                && settings.group_by_overflow_mode == OverflowMode::THROW
+                && settings.sort_overflow_mode == OverflowMode::THROW
+                && settings.result_overflow_mode == OverflowMode::THROW
+                && settings.timeout_overflow_mode == OverflowMode::THROW
+                && settings.set_overflow_mode == OverflowMode::THROW
+                && settings.join_overflow_mode == OverflowMode::THROW
+                && settings.transfer_overflow_mode == OverflowMode::THROW
+                && settings.distinct_overflow_mode == OverflowMode::THROW)
             && (ast->as<ASTSelectQuery>() || ast->as<ASTSelectWithUnionQuery>());
         QueryCache::Usage query_cache_usage = QueryCache::Usage::None;
 
-        /// Bug 67476: If the query runs with a non-THROW overflow mode and hits a limit, the query cache will store a truncated result (if
-        /// enabled). This is incorrect. Unfortunately it is hard to detect from the perspective of the query cache that the query result
-        /// is truncated. Therefore throw an exception, to notify the user to disable either the query cache or use another overflow mode.
-        if (settings.use_query_cache && (settings.read_overflow_mode != OverflowMode::THROW
-            || settings.read_overflow_mode_leaf != OverflowMode::THROW
-            || settings.group_by_overflow_mode != OverflowMode::THROW
-            || settings.sort_overflow_mode != OverflowMode::THROW
-            || settings.result_overflow_mode != OverflowMode::THROW
-            || settings.timeout_overflow_mode != OverflowMode::THROW
-            || settings.set_overflow_mode != OverflowMode::THROW
-            || settings.join_overflow_mode != OverflowMode::THROW
-            || settings.transfer_overflow_mode != OverflowMode::THROW
-            || settings.distinct_overflow_mode != OverflowMode::THROW))
-            throw Exception(ErrorCodes::QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE, "use_query_cache and overflow_mode != 'throw' cannot be used together");
-
         /// If the query runs with "use_query_cache = 1", we first probe if the query cache already contains the query result (if yes:
         /// return result from cache). If doesn't, we execute the query normally and write the result into the query cache. Both steps use a
         /// hash of the AST, the current database and the settings as cache key. Unfortunately, the settings are in some places internally

src/Parsers/FunctionSecretArgumentsFinderAST.h

@@ -74,8 +74,7 @@ private:
             findMySQLFunctionSecretArguments();
         }
         else if ((function.name == "s3") || (function.name == "cosn") || (function.name == "oss") ||
-                 (function.name == "deltaLake") || (function.name == "hudi") || (function.name == "iceberg") ||
-                 (function.name == "gcs"))
+                    (function.name == "deltaLake") || (function.name == "hudi") || (function.name == "iceberg"))
         {
             /// s3('url', 'aws_access_key_id', 'aws_secret_access_key', ...)
             findS3FunctionSecretArguments(/* is_cluster_function= */ false);

src/Processors/QueryPlan/ReadFromMergeTree.cpp

@@ -2009,6 +2009,33 @@ void ReadFromMergeTree::initializePipeline(QueryPipelineBuilder & pipeline, cons
 {
     auto result = getAnalysisResult();
 
+    if (is_parallel_reading_from_replicas && context->canUseParallelReplicasOnInitiator()
+        && context->getSettingsRef().parallel_replicas_local_plan)
+    {
+        CoordinationMode mode = CoordinationMode::Default;
+        switch (result.read_type)
+        {
+            case ReadFromMergeTree::ReadType::Default:
+                mode = CoordinationMode::Default;
+                break;
+            case ReadFromMergeTree::ReadType::InOrder:
+                mode = CoordinationMode::WithOrder;
+                break;
+            case ReadFromMergeTree::ReadType::InReverseOrder:
+                mode = CoordinationMode::ReverseOrder;
+                break;
+            case ReadFromMergeTree::ReadType::ParallelReplicas:
+                throw Exception(ErrorCodes::LOGICAL_ERROR, "Read type can't be ParallelReplicas on initiator");
+        }
+
+        chassert(number_of_current_replica.has_value());
+        chassert(all_ranges_callback.has_value());
+
+        /// initialize working set from local replica
+        all_ranges_callback.value()(
+            InitialAllRangesAnnouncement(mode, result.parts_with_ranges.getDescriptions(), number_of_current_replica.value()));
+    }
+
     if (enable_remove_parts_from_snapshot_optimization)
     {
         /// Do not keep data parts in snapshot.

src/Storages/MergeTree/MergeTreeIndexVectorSimilarity.cpp

@@ -5,11 +5,9 @@
 #include <Columns/ColumnArray.h>
 #include <Common/BitHelpers.h>
 #include <Common/formatReadable.h>
-#include <Common/getNumberOfPhysicalCPUCores.h>
 #include <Common/logger_useful.h>
 #include <Common/typeid_cast.h>
 #include <Core/Field.h>
-#include <Core/ServerSettings.h>
 #include <DataTypes/DataTypeArray.h>
 #include <IO/ReadHelpers.h>
 #include <IO/WriteHelpers.h>
@@ -31,6 +29,7 @@ namespace DB
 
 namespace ErrorCodes
 {
+    extern const int CANNOT_ALLOCATE_MEMORY;
     extern const int FORMAT_VERSION_TOO_OLD;
     extern const int ILLEGAL_COLUMN;
     extern const int INCORRECT_DATA;
@@ -132,7 +131,8 @@ void USearchIndexWithSerialization::deserialize(ReadBuffer & istr)
         /// See the comment in MergeTreeIndexGranuleVectorSimilarity::deserializeBinary why we throw here
         throw Exception(ErrorCodes::INCORRECT_DATA, "Could not load vector similarity index. Please drop the index and create it again. Error: {}", String(result.error.release()));
 
-    try_reserve(limits());
+    if (!try_reserve(limits()))
+        throw Exception(ErrorCodes::CANNOT_ALLOCATE_MEMORY, "Could not reserve memory for usearch index");
 }
 
 USearchIndexWithSerialization::Statistics USearchIndexWithSerialization::getStatistics() const
@@ -270,49 +270,20 @@ void updateImpl(const ColumnArray * column_array, const ColumnArray::Offsets & c
             throw Exception(ErrorCodes::INCORRECT_DATA, "All arrays in column with vector similarity index must have equal length");
 
     /// Reserving space is mandatory
-    size_t max_thread_pool_size = Context::getGlobalContextInstance()->getServerSettings().max_build_vector_similarity_index_thread_pool_size;
-    if (max_thread_pool_size == 0)
-        max_thread_pool_size = getNumberOfPhysicalCPUCores();
-    unum::usearch::index_limits_t limits(roundUpToPowerOfTwoOrZero(index->size() + rows), max_thread_pool_size);
-    index->reserve(limits);
+    if (!index->try_reserve(roundUpToPowerOfTwoOrZero(index->size() + rows)))
+        throw Exception(ErrorCodes::CANNOT_ALLOCATE_MEMORY, "Could not reserve memory for vector similarity index");
 
-    /// Vector index creation is slooooow. Add the new rows in parallel. The threadpool is global to avoid oversubscription when multiple
-    /// indexes are build simultaneously (e.g. multiple merges run at the same time).
-    auto & thread_pool = Context::getGlobalContextInstance()->getBuildVectorSimilarityIndexThreadPool();
-
-    auto add_vector_to_index = [&](USearchIndex::vector_key_t key, size_t row, ThreadGroupPtr thread_group)
+    for (size_t row = 0; row < rows; ++row)
     {
-        SCOPE_EXIT_SAFE(
-            if (thread_group)
-                CurrentThread::detachFromGroupIfNotDetached();
-        );
-
-        if (thread_group)
-            CurrentThread::attachToGroupIfDetached(thread_group);
-
-        /// add is thread-safe
-        if (auto result = index->add(key, &column_array_data_float_data[column_array_offsets[row - 1]]); !result)
-        {
+        if (auto result = index->add(static_cast<USearchIndex::vector_key_t>(index->size()), &column_array_data_float_data[column_array_offsets[row - 1]]); !result)
             throw Exception(ErrorCodes::INCORRECT_DATA, "Could not add data to vector similarity index. Error: {}", String(result.error.release()));
-        }
         else
         {
             ProfileEvents::increment(ProfileEvents::USearchAddCount);
             ProfileEvents::increment(ProfileEvents::USearchAddVisitedMembers, result.visited_members);
             ProfileEvents::increment(ProfileEvents::USearchAddComputedDistances, result.computed_distances);
         }
-    };
-
-    size_t index_size = index->size();
-
-    for (size_t row = 0; row < rows; ++row)
-    {
-        auto key = static_cast<USearchIndex::vector_key_t>(index_size + row);
-        auto task = [group = CurrentThread::getGroup(), &add_vector_to_index, key, row] { add_vector_to_index(key, row, group); };
-        thread_pool.scheduleOrThrowOnError(task);
     }
-
-    thread_pool.wait();
 }
 
 }

src/Storages/MergeTree/MergeTreePartsMover.cpp

@@ -1,7 +1,6 @@
 #include <Storages/MergeTree/MergeTreeData.h>
 #include <Storages/MergeTree/MergeTreePartsMover.h>
 #include <Storages/MergeTree/MergeTreeSettings.h>
-#include <Common/FailPoint.h>
 #include <Common/logger_useful.h>
 
 #include <set>
@@ -16,11 +15,6 @@ namespace ErrorCodes
     extern const int DIRECTORY_ALREADY_EXISTS;
 }
 
-namespace FailPoints
-{
-    extern const char stop_moving_part_before_swap_with_active[];
-}
-
 namespace
 {
 
@@ -232,7 +226,6 @@ MergeTreePartsMover::TemporaryClonedPart MergeTreePartsMover::clonePart(const Me
     cloned_part.temporary_directory_lock = data->getTemporaryPartDirectoryHolder(part->name);
 
     MutableDataPartStoragePtr cloned_part_storage;
-    bool preserve_blobs = false;
     if (disk->supportZeroCopyReplication() && settings->allow_remote_fs_zero_copy_replication)
     {
         /// Try zero-copy replication and fallback to default copy if it's not possible
@@ -260,7 +253,6 @@ MergeTreePartsMover::TemporaryClonedPart MergeTreePartsMover::clonePart(const Me
         if (zero_copy_part)
         {
             /// FIXME for some reason we cannot just use this part, we have to re-create it through MergeTreeDataPartBuilder
-            preserve_blobs = true;
             zero_copy_part->is_temp = false;    /// Do not remove it in dtor
             cloned_part_storage = zero_copy_part->getDataPartStoragePtr();
         }
@@ -280,17 +272,7 @@ MergeTreePartsMover::TemporaryClonedPart MergeTreePartsMover::clonePart(const Me
     cloned_part.part = std::move(builder).withPartFormatFromDisk().build();
     LOG_TRACE(log, "Part {} was cloned to {}", part->name, cloned_part.part->getDataPartStorage().getFullPath());
 
-    cloned_part.part->is_temp = false;
-    if (data->allowRemoveStaleMovingParts())
-    {
-        cloned_part.part->is_temp = true;
-        /// Setting it in case connection to zookeeper is lost while moving
-        /// Otherwise part might be stuck in the moving directory due to the KEEPER_EXCEPTION in part's destructor
-        if (preserve_blobs)
-            cloned_part.part->remove_tmp_policy = IMergeTreeDataPart::BlobsRemovalPolicyForTemporaryParts::PRESERVE_BLOBS;
-        else
-            cloned_part.part->remove_tmp_policy = IMergeTreeDataPart::BlobsRemovalPolicyForTemporaryParts::REMOVE_BLOBS;
-    }
+    cloned_part.part->is_temp = data->allowRemoveStaleMovingParts();
     cloned_part.part->loadColumnsChecksumsIndexes(true, true);
     cloned_part.part->loadVersionMetadata();
     cloned_part.part->modification_time = cloned_part.part->getDataPartStorage().getLastModified().epochTime();
@@ -300,8 +282,6 @@ MergeTreePartsMover::TemporaryClonedPart MergeTreePartsMover::clonePart(const Me
 
 void MergeTreePartsMover::swapClonedPart(TemporaryClonedPart & cloned_part) const
 {
-    /// Used to get some stuck parts in the moving directory by stopping moves while pause is active
-    FailPointInjection::pauseFailPoint(FailPoints::stop_moving_part_before_swap_with_active);
     if (moves_blocker.isCancelled())
         throw Exception(ErrorCodes::ABORTED, "Cancelled moving parts.");
 

src/Storages/MergeTree/ReplicatedMergeTreeAttachThread.cpp

@@ -15,7 +15,6 @@ namespace ErrorCodes
 {
     extern const int SUPPORT_IS_DISABLED;
     extern const int REPLICA_STATUS_CHANGED;
-    extern const int LOGICAL_ERROR;
 }
 
 ReplicatedMergeTreeAttachThread::ReplicatedMergeTreeAttachThread(StorageReplicatedMergeTree & storage_)
@@ -118,67 +117,6 @@ void ReplicatedMergeTreeAttachThread::checkHasReplicaMetadataInZooKeeper(const z
     }
 }
 
-Int32 ReplicatedMergeTreeAttachThread::fixReplicaMetadataVersionIfNeeded(zkutil::ZooKeeperPtr zookeeper)
-{
-    const String & zookeeper_path = storage.zookeeper_path;
-    const String & replica_path = storage.replica_path;
-    const bool replica_readonly = storage.is_readonly;
-
-    for (size_t i = 0; i != 2; ++i)
-    {
-        String replica_metadata_version_str;
-        const bool replica_metadata_version_exists = zookeeper->tryGet(replica_path + "/metadata_version", replica_metadata_version_str);
-        if (!replica_metadata_version_exists)
-            return -1;
-
-        const Int32 metadata_version = parse<Int32>(replica_metadata_version_str);
-
-        if (metadata_version != 0 || replica_readonly)
-        {
-            /// No need to fix anything
-            return metadata_version;
-        }
-
-        Coordination::Stat stat;
-        zookeeper->get(fs::path(zookeeper_path) / "metadata", &stat);
-        if (stat.version == 0)
-        {
-            /// No need to fix anything
-            return metadata_version;
-        }
-
-        ReplicatedMergeTreeQueue & queue = storage.queue;
-        queue.pullLogsToQueue(zookeeper);
-        if (queue.getStatus().metadata_alters_in_queue != 0)
-        {
-            LOG_DEBUG(log, "No need to update metadata_version as there are ALTER_METADATA entries in the queue");
-            return metadata_version;
-        }
-
-        const Coordination::Requests ops = {
-            zkutil::makeSetRequest(fs::path(replica_path) / "metadata_version", std::to_string(stat.version), 0),
-            zkutil::makeCheckRequest(fs::path(zookeeper_path) / "metadata", stat.version),
-        };
-        Coordination::Responses ops_responses;
-        const auto code = zookeeper->tryMulti(ops, ops_responses);
-        if (code == Coordination::Error::ZOK)
-        {
-            LOG_DEBUG(log, "Successfully set metadata_version to {}", stat.version);
-            return stat.version;
-        }
-        if (code != Coordination::Error::ZBADVERSION)
-        {
-            throw zkutil::KeeperException(code);
-        }
-    }
-
-    /// Second attempt is only possible if metadata_version != 0 or metadata.version changed during the first attempt.
-    /// If metadata_version != 0, on second attempt we will return the new metadata_version.
-    /// If metadata.version changed, on second attempt we will either get metadata_version != 0 and return the new metadata_version or we will get metadata_alters_in_queue != 0 and return 0.
-    /// Either way, on second attempt this method should return.
-    throw Exception(ErrorCodes::LOGICAL_ERROR, "Failed to fix replica metadata_version in ZooKeeper after two attempts");
-}
-
 void ReplicatedMergeTreeAttachThread::runImpl()
 {
     storage.setZooKeeper();
@@ -222,11 +160,11 @@ void ReplicatedMergeTreeAttachThread::runImpl()
     /// Just in case it was not removed earlier due to connection loss
     zookeeper->tryRemove(replica_path + "/flags/force_restore_data");
 
-    const Int32 replica_metadata_version = fixReplicaMetadataVersionIfNeeded(zookeeper);
-    const bool replica_metadata_version_exists = replica_metadata_version != -1;
+    String replica_metadata_version;
+    const bool replica_metadata_version_exists = zookeeper->tryGet(replica_path + "/metadata_version", replica_metadata_version);
     if (replica_metadata_version_exists)
     {
-        storage.setInMemoryMetadata(metadata_snapshot->withMetadataVersion(replica_metadata_version));
+        storage.setInMemoryMetadata(metadata_snapshot->withMetadataVersion(parse<int>(replica_metadata_version)));
     }
     else
     {

src/Storages/MergeTree/ReplicatedMergeTreeAttachThread.h

@@ -48,8 +48,6 @@ private:
     void runImpl();
 
     void finalizeInitialization();
-
-    Int32 fixReplicaMetadataVersionIfNeeded(zkutil::ZooKeeperPtr zookeeper);
 };
 
 }

src/Storages/MergeTree/ReplicatedMergeTreeQueue.cpp

@@ -2222,7 +2222,6 @@ ReplicatedMergeTreeQueue::Status ReplicatedMergeTreeQueue::getStatus() const
     res.inserts_in_queue = 0;
     res.merges_in_queue = 0;
     res.part_mutations_in_queue = 0;
-    res.metadata_alters_in_queue = 0;
     res.queue_oldest_time = 0;
     res.inserts_oldest_time = 0;
     res.merges_oldest_time = 0;
@@ -2265,11 +2264,6 @@ ReplicatedMergeTreeQueue::Status ReplicatedMergeTreeQueue::getStatus() const
                 res.oldest_part_to_mutate_to = entry->new_part_name;
             }
         }
-
-        if (entry->type == LogEntry::ALTER_METADATA)
-        {
-            ++res.metadata_alters_in_queue;
-        }
     }
 
     return res;

src/Storages/MergeTree/ReplicatedMergeTreeQueue.h

@@ -473,7 +473,6 @@ public:
         UInt32 inserts_in_queue;
         UInt32 merges_in_queue;
         UInt32 part_mutations_in_queue;
-        UInt32 metadata_alters_in_queue;
         UInt32 queue_oldest_time;
         UInt32 inserts_oldest_time;
         UInt32 merges_oldest_time;

src/Storages/MergeTree/registerStorageMergeTree.cpp

@@ -277,7 +277,7 @@ static void extractZooKeeperPathAndReplicaNameFromEngineArgs(
 
     if (has_valid_arguments)
     {
-        if (!query.attach && is_replicated_database && local_context->getSettingsRef().database_replicated_allow_replicated_engine_arguments == 0)
+        if (is_replicated_database && local_context->getSettingsRef().database_replicated_allow_replicated_engine_arguments == 0)
         {
             throw Exception(ErrorCodes::BAD_ARGUMENTS,
                             "It's not allowed to specify explicit zookeeper_path and replica_name "
@@ -285,7 +285,7 @@ static void extractZooKeeperPathAndReplicaNameFromEngineArgs(
                             "specify them explicitly, enable setting "
                             "database_replicated_allow_replicated_engine_arguments.");
         }
-        else if (!query.attach && is_replicated_database && local_context->getSettingsRef().database_replicated_allow_replicated_engine_arguments == 1)
+        else if (is_replicated_database && local_context->getSettingsRef().database_replicated_allow_replicated_engine_arguments == 1)
         {
             LOG_WARNING(&Poco::Logger::get("registerStorageMergeTree"), "It's not recommended to explicitly specify "
                                                             "zookeeper_path and replica_name in ReplicatedMergeTree arguments");
@@ -305,7 +305,7 @@ static void extractZooKeeperPathAndReplicaNameFromEngineArgs(
             throw Exception(ErrorCodes::BAD_ARGUMENTS, "Replica name must be a string literal{}", verbose_help_message);
 
 
-        if (!query.attach && is_replicated_database && local_context->getSettingsRef().database_replicated_allow_replicated_engine_arguments == 2)
+        if (is_replicated_database && local_context->getSettingsRef().database_replicated_allow_replicated_engine_arguments == 2)
         {
             LOG_WARNING(&Poco::Logger::get("registerStorageMergeTree"), "Replacing user-provided ZooKeeper path and replica name ({}, {}) "
                                                                      "with default arguments", zookeeper_path, replica_name);

tests/config/config.d/keeper_port.xml

@@ -42,7 +42,6 @@
             <multi_read>1</multi_read>
             <check_not_exists>1</check_not_exists>
             <create_if_not_exists>1</create_if_not_exists>
-            <remove_recursive>1</remove_recursive>
         </feature_flags>
     </keeper_server>
 </clickhouse>

tests/docker_scripts/stress_tests.lib

@@ -64,7 +64,6 @@ function configure()
         randomize_config_boolean_value multi_read keeper_port
         randomize_config_boolean_value check_not_exists keeper_port
         randomize_config_boolean_value create_if_not_exists keeper_port
-        randomize_config_boolean_value remove_recursive keeper_port
     fi
 
     sudo chown clickhouse /etc/clickhouse-server/config.d/keeper_port.xml

tests/integration/test_mask_sensitive_info/test.py

@@ -393,7 +393,6 @@ def test_table_functions():
         f"azureBlobStorageCluster('test_shard_localhost', named_collection_2, connection_string = '{azure_conn_string}', container = 'cont', blob_path = 'test_simple_16.csv', format = 'CSV')",
         f"azureBlobStorageCluster('test_shard_localhost', named_collection_2, storage_account_url = '{azure_storage_account_url}', container = 'cont', blob_path = 'test_simple_17.csv', account_name = '{azure_account_name}', account_key = '{azure_account_key}')",
         f"iceberg('http://minio1:9001/root/data/test11.csv.gz', 'minio', '{password}')",
-        f"gcs('http://minio1:9001/root/data/test11.csv.gz', 'minio', '{password}')",
     ]
 
     def make_test_case(i):

tests/integration/test_parallel_replicas_snapshot_from_initiator/configs/remote_servers.xml

@@ -1,33 +0,0 @@
-<clickhouse>
-    <remote_servers>
-        <parallel_replicas>
-            <shard>
-                <internal_replication>false</internal_replication>
-                <replica>
-                    <host>node0</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>node1</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>node2</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>node3</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>node4</host>
-                    <port>9000</port>
-                </replica>
-                <replica>
-                    <host>node5</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </parallel_replicas>
-    </remote_servers>
-</clickhouse>

tests/integration/test_parallel_replicas_snapshot_from_initiator/test.py

@@ -1,73 +0,0 @@
-import pytest
-
-from helpers.cluster import ClickHouseCluster
-
-cluster = ClickHouseCluster(__file__)
-
-nodes = [
-    cluster.add_instance(
-        f"node{num}", main_configs=["configs/remote_servers.xml"], with_zookeeper=True
-    )
-    for num in range(6)
-]
-
-
-@pytest.fixture(scope="module", autouse=True)
-def start_cluster():
-    try:
-        cluster.start()
-        yield cluster
-    finally:
-        cluster.shutdown()
-
-
-def _create_tables(table_name):
-    for idx, node in enumerate(nodes):
-        node.query(
-            f"DROP TABLE IF EXISTS {table_name}",
-            settings={"database_atomic_wait_for_drop_and_detach_synchronously": True},
-        )
-
-        node.query(
-            f"""
-            CREATE TABLE {table_name} (value Int64)
-            Engine=ReplicatedMergeTree('/test_parallel_replicas/shard/{table_name}', '{idx}')
-            ORDER BY ()
-            """
-        )
-
-    nodes[0].query(
-        f"INSERT INTO {table_name} SELECT * FROM numbers(1000)",
-        settings={"insert_deduplicate": 0},
-    )
-    nodes[0].query(f"SYSTEM SYNC REPLICA ON CLUSTER 'parallel_replicas' {table_name}")
-
-    for idx, node in enumerate(nodes):
-        node.query("SYSTEM STOP REPLICATED SENDS")
-        # the same data on all nodes except for a single value
-        node.query(
-            f"INSERT INTO {table_name} VALUES ({idx})",
-            settings={"insert_deduplicate": 0},
-        )
-
-
-# check that we use the state of data parts from the initiator node (for some sort of determinism of what is been read).
-# currently it is implemented only when we build local plan for the initiator node (we aim to make this behavior default)
-def test_initiator_snapshot_is_used_for_reading(start_cluster):
-    table_name = "t"
-    _create_tables(table_name)
-
-    for idx, node in enumerate(nodes):
-        expected = 499500 + idx  # sum of all integers 0..999 + idx
-        assert (
-            node.query(
-                f"SELECT sum(value) FROM {table_name}",
-                settings={
-                    "allow_experimental_parallel_reading_from_replicas": 2,
-                    "max_parallel_replicas": 100,
-                    "cluster_for_parallel_replicas": "parallel_replicas",
-                    "parallel_replicas_local_plan": True,
-                },
-            )
-            == f"{expected}\n"
-        )

tests/integration/test_remove_stale_moving_parts/config.xml

@@ -1,46 +0,0 @@
-<clickhouse>
-    <remote_servers>
-        <cluster>
-            <shard>
-                <replica>
-                    <host>ch1</host>
-                    <port>9000</port>
-                </replica>
-            </shard>
-        </cluster>
-    </remote_servers>
-    <macros>
-        <shard>01</shard>
-    </macros>
-    <storage_configuration>
-        <disks>
-            <s3>
-                <type>s3</type>
-                <endpoint>http://minio1:9001/root/data/</endpoint>
-                <access_key_id>minio</access_key_id>
-                <secret_access_key>minio123</secret_access_key>
-            </s3>
-        </disks>
-        <policies>
-            <s3>
-                <volumes>
-                    <default>
-                        <disk>default</disk>
-                        <perform_ttl_move_on_insert>False</perform_ttl_move_on_insert>
-                    </default>
-                    <s3>
-                        <disk>s3</disk>
-                        <perform_ttl_move_on_insert>False</perform_ttl_move_on_insert>
-                    </s3>
-                </volumes>
-                <move_factor>0.0</move_factor>
-            </s3>
-        </policies>
-    </storage_configuration>
-
-    <merge_tree>
-        <allow_remote_fs_zero_copy_replication>true</allow_remote_fs_zero_copy_replication>
-        <storage_policy>s3</storage_policy>
-    </merge_tree>
-    <allow_remove_stale_moving_parts>true</allow_remove_stale_moving_parts>
-</clickhouse>

tests/integration/test_remove_stale_moving_parts/test.py

@@ -1,117 +0,0 @@
-from pathlib import Path
-import time
-import pytest
-from helpers.cluster import ClickHouseCluster
-
-cluster = ClickHouseCluster(__file__)
-ch1 = cluster.add_instance(
-    "ch1",
-    main_configs=[
-        "config.xml",
-    ],
-    macros={"replica": "node1"},
-    with_zookeeper=True,
-    with_minio=True,
-)
-
-DATABASE_NAME = "stale_moving_parts"
-
-
-@pytest.fixture(scope="module")
-def started_cluster():
-    try:
-        cluster.start()
-        yield cluster
-
-    finally:
-        cluster.shutdown()
-
-
-def q(node, query):
-    return node.query(database=DATABASE_NAME, sql=query)
-
-
-# .../disks/s3/store/
-def get_table_path(node, table):
-    return (
-        node.query(
-            sql=f"SELECT data_paths FROM system.tables WHERE table = '{table}' and database = '{DATABASE_NAME}' LIMIT 1"
-        )
-        .strip('"\n[]')
-        .split(",")[1]
-        .strip("'")
-    )
-
-
-def exec(node, cmd, path):
-    return node.exec_in_container(
-        [
-            "bash",
-            "-c",
-            f"{cmd} {path}",
-        ]
-    )
-
-
-def wait_part_is_stuck(node, table_moving_path, moving_part):
-    num_tries = 5
-    while q(node, "SELECT part_name FROM system.moves").strip() != moving_part:
-        if num_tries == 0:
-            raise Exception("Part has not started to move")
-        num_tries -= 1
-        time.sleep(1)
-    num_tries = 5
-    while exec(node, "ls", table_moving_path).strip() != moving_part:
-        if num_tries == 0:
-            raise Exception("Part is not stuck in the moving directory")
-        num_tries -= 1
-        time.sleep(1)
-
-
-def wait_zookeeper_node_to_start(zk_nodes, timeout=60):
-    start = time.time()
-    while time.time() - start < timeout:
-        try:
-            for instance in zk_nodes:
-                conn = cluster.get_kazoo_client(instance)
-                conn.get_children("/")
-            print("All instances of ZooKeeper started")
-            return
-        except Exception as ex:
-            print(("Can't connect to ZooKeeper " + str(ex)))
-            time.sleep(0.5)
-
-
-def test_remove_stale_moving_parts_without_zookeeper(started_cluster):
-    ch1.query(f"CREATE DATABASE IF NOT EXISTS {DATABASE_NAME}")
-
-    q(
-        ch1,
-        "CREATE TABLE test_remove ON CLUSTER cluster ( id UInt32 ) ENGINE ReplicatedMergeTree() ORDER BY id;",
-    )
-
-    table_moving_path = Path(get_table_path(ch1, "test_remove")) / "moving"
-
-    q(ch1, "SYSTEM ENABLE FAILPOINT stop_moving_part_before_swap_with_active")
-    q(ch1, "INSERT INTO test_remove SELECT number FROM numbers(100);")
-    moving_part = "all_0_0_0"
-    move_response = ch1.get_query_request(
-        sql=f"ALTER TABLE test_remove MOVE PART '{moving_part}' TO DISK 's3'",
-        database=DATABASE_NAME,
-    )
-
-    wait_part_is_stuck(ch1, table_moving_path, moving_part)
-
-    cluster.stop_zookeeper_nodes(["zoo1", "zoo2", "zoo3"])
-    # Stop moves in case table is not read-only yet
-    q(ch1, "SYSTEM STOP MOVES")
-    q(ch1, "SYSTEM DISABLE FAILPOINT stop_moving_part_before_swap_with_active")
-
-    assert "Cancelled moving parts" in move_response.get_error()
-    assert exec(ch1, "ls", table_moving_path).strip() == ""
-
-    cluster.start_zookeeper_nodes(["zoo1", "zoo2", "zoo3"])
-    wait_zookeeper_node_to_start(["zoo1", "zoo2", "zoo3"])
-    q(ch1, "SYSTEM START MOVES")
-
-    q(ch1, f"DROP TABLE test_remove")

tests/integration/test_replicated_database/test.py

@@ -1549,19 +1549,3 @@ def test_all_groups_cluster(started_cluster):
     assert "bad_settings_node\ndummy_node\n" == bad_settings_node.query(
         "select host_name from system.clusters where name='all_groups.db_cluster' order by host_name"
     )
-
-
-def test_detach_attach_table(started_cluster):
-    main_node.query("DROP DATABASE IF EXISTS detach_attach_db SYNC")
-    main_node.query(
-        "CREATE DATABASE detach_attach_db ENGINE = Replicated('/clickhouse/databases/detach_attach_db');"
-    )
-    main_node.query(
-        "CREATE TABLE detach_attach_db.detach_attach_table (k UInt64) ENGINE=ReplicatedMergeTree ORDER BY k;"
-    )
-    main_node.query("INSERT INTO detach_attach_db.detach_attach_table VALUES (1);")
-    main_node.query("DETACH TABLE detach_attach_db.detach_attach_table PERMANENTLY;")
-    main_node.query("ATTACH TABLE detach_attach_db.detach_attach_table;")
-    assert (
-        main_node.query("SELECT * FROM detach_attach_db.detach_attach_table;") == "1\n"
-    )

tests/queries/0_stateless/02494_query_cache_bugs.reference

@@ -23,3 +23,23 @@ Row 1:
 x: 1
 2
 -- Bug 67476: Queries with overflow mode != throw must not be cached by the query cache
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0
+0

tests/queries/0_stateless/02494_query_cache_bugs.sql

@@ -43,15 +43,25 @@ DROP TABLE IF EXISTS tab;
 CREATE TABLE tab(c UInt64) ENGINE = Memory;
 
 SYSTEM DROP QUERY CACHE;
-SELECT sum(c) FROM tab SETTINGS read_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS read_overflow_mode_leaf = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS group_by_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS sort_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS result_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS timeout_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS set_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS join_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS transfer_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
-SELECT sum(c) FROM tab SETTINGS distinct_overflow_mode = 'break', use_query_cache = 1; -- { serverError QUERY_CACHE_USED_WITH_NON_THROW_OVERFLOW_MODE }
+SELECT sum(c) FROM tab SETTINGS read_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS read_overflow_mode_leaf = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS group_by_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS sort_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS result_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS timeout_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS set_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS join_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS transfer_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
+SELECT sum(c) FROM tab SETTINGS distinct_overflow_mode = 'break', use_query_cache = 1;
+SELECT count(*) from system.query_cache;
 
 SYSTEM DROP QUERY CACHE;

tests/queries/0_stateless/02735_system_zookeeper_connection.reference

@@ -1,2 +1,2 @@
-default	127.0.0.1	9181	0	0	0	1	1	['FILTERED_LIST','MULTI_READ','CHECK_NOT_EXISTS','CREATE_IF_NOT_EXISTS','REMOVE_RECURSIVE']
+default	127.0.0.1	9181	0	0	0	1	1	['FILTERED_LIST','MULTI_READ','CHECK_NOT_EXISTS','CREATE_IF_NOT_EXISTS']
 zookeeper2	localhost	9181	0	0	0	1

tests/queries/0_stateless/03222_json_empty_as_default.reference

@@ -1,47 +0,0 @@
--- Simple types
--- { echoOn }
-SELECT x FROM format(JSONEachRow, 'x Date', '{"x":""}');
-1970-01-01
-SELECT x FROM format(JSONEachRow, 'x Date32', '{"x":""}');
-1970-01-01
-SELECT toTimeZone(x, 'UTC') FROM format(JSONEachRow, 'x DateTime', '{"x":""}');
-1970-01-01 00:00:00
-SELECT toTimeZone(x, 'UTC') FROM format(JSONEachRow, 'x DateTime64', '{"x":""}');
-1970-01-01 00:00:00.000
-SELECT x FROM format(JSONEachRow, 'x IPv4', '{"x":""}');
-0.0.0.0
-SELECT x FROM format(JSONEachRow, 'x IPv6', '{"x":""}');
-::
-SELECT x FROM format(JSONEachRow, 'x UUID', '{"x":""}');
-00000000-0000-0000-0000-000000000000
--- { echoOn }
-SELECT COUNT(DISTINCT col) FROM table1;
-1
--- { echoOn }
-SELECT * FROM table1 ORDER BY address ASC;
-::
-2001:db8:3333:4444:5555:6666:7777:8888
--- Nullable
--- { echoOn }
-SELECT x FROM format(JSONEachRow, 'x Nullable(IPv6)', '{"x":""}');
-\N
--- Compound types
-SELECT x FROM format(JSONEachRow, 'x Array(UUID)', '{"x":["00000000-0000-0000-0000-000000000000","b15f852c-c41a-4fd6-9247-1929c841715e",""]}');
-['00000000-0000-0000-0000-000000000000','b15f852c-c41a-4fd6-9247-1929c841715e','00000000-0000-0000-0000-000000000000']
-SELECT x FROM format(JSONEachRow, 'x Array(Nullable(IPv6))', '{"x":["",""]}');
-[NULL,NULL]
-SELECT x FROM format(JSONEachRow, 'x Tuple(Date, IPv4, String)', '{"x":["", "", "abc"]}');
-('1970-01-01','0.0.0.0','abc')
-SELECT x FROM format(JSONEachRow, 'x Map(String, IPv6)', '{"x":{"abc": ""}}');
-{'abc':'::'}
-SELECT x FROM format(JSONEachRow, 'x Variant(Date, UUID)', '{"x":""}');
-\N
--- Deep composition
-SELECT x FROM format(JSONEachRow, 'x Array(Array(IPv6))', '{"x":[["2001:db8:3333:4444:CCCC:DDDD:EEEE:FFFF", ""], ["", "2001:db8:3333:4444:5555:6666:7777:8888"]]}');
-[['2001:db8:3333:4444:cccc:dddd:eeee:ffff','::'],['::','2001:db8:3333:4444:5555:6666:7777:8888']]
-SELECT x FROM format(JSONEachRow, 'x Variant(Date, Array(UUID))', '{"x":["", "b15f852c-c41a-4fd6-9247-1929c841715e"]}');
-['00000000-0000-0000-0000-000000000000','b15f852c-c41a-4fd6-9247-1929c841715e']
-SELECT x FROM format(JSONEachRow, 'x Tuple(Array(UUID), Tuple(UUID, Map(String, IPv6)))', '{"x":[[""], ["",{"abc":""}]]}');
-(['00000000-0000-0000-0000-000000000000'],('00000000-0000-0000-0000-000000000000',{'abc':'::'}))
-SELECT x FROM format(JSONEachRow, 'x Map(Tuple(Date,IPv4), Variant(UUID,IPv6))', '{"x":{["",""]:""}}');
-{('1970-01-01','0.0.0.0'):NULL}

tests/queries/0_stateless/03222_json_empty_as_default.sql

@@ -1,60 +0,0 @@
-SET input_format_json_empty_as_default = 1, allow_experimental_variant_type = 1;
-
--- Simple types
--- { echoOn }
-SELECT x FROM format(JSONEachRow, 'x Date', '{"x":""}');
-SELECT x FROM format(JSONEachRow, 'x Date32', '{"x":""}');
-SELECT toTimeZone(x, 'UTC') FROM format(JSONEachRow, 'x DateTime', '{"x":""}');
-SELECT toTimeZone(x, 'UTC') FROM format(JSONEachRow, 'x DateTime64', '{"x":""}');
-SELECT x FROM format(JSONEachRow, 'x IPv4', '{"x":""}');
-SELECT x FROM format(JSONEachRow, 'x IPv6', '{"x":""}');
-SELECT x FROM format(JSONEachRow, 'x UUID', '{"x":""}');
--- { echoOff }
-
--- Simple type AggregateFunction
-DROP TABLE IF EXISTS table1;
-CREATE TABLE table1(col AggregateFunction(uniq, UInt64)) ENGINE=Memory();
-DROP TABLE IF EXISTS table2;
-CREATE TABLE table2(UserID UInt64) ENGINE=Memory();
-
-INSERT INTO table1 SELECT uniqState(UserID) FROM table2;
-INSERT INTO table1 SELECT x FROM format(JSONEachRow, 'x AggregateFunction(uniq, UInt64)' AS T, '{"x":""}');
-
--- { echoOn }
-SELECT COUNT(DISTINCT col) FROM table1;
--- { echoOff }
-
-DROP TABLE table1;
-DROP TABLE table2;
-
--- The setting input_format_defaults_for_omitted_fields determines the default value if enabled.
-CREATE TABLE table1(address IPv6 DEFAULT toIPv6('2001:db8:3333:4444:5555:6666:7777:8888')) ENGINE=Memory();
-
-SET input_format_defaults_for_omitted_fields = 0;
-INSERT INTO table1 FORMAT JSONEachRow {"address":""};
-
-SET input_format_defaults_for_omitted_fields = 1;
-INSERT INTO table1 FORMAT JSONEachRow {"address":""};
-
--- { echoOn }
-SELECT * FROM table1 ORDER BY address ASC;
--- { echoOff }
-
-DROP TABLE table1;
-
--- Nullable
--- { echoOn }
-SELECT x FROM format(JSONEachRow, 'x Nullable(IPv6)', '{"x":""}');
-
--- Compound types
-SELECT x FROM format(JSONEachRow, 'x Array(UUID)', '{"x":["00000000-0000-0000-0000-000000000000","b15f852c-c41a-4fd6-9247-1929c841715e",""]}');
-SELECT x FROM format(JSONEachRow, 'x Array(Nullable(IPv6))', '{"x":["",""]}');
-SELECT x FROM format(JSONEachRow, 'x Tuple(Date, IPv4, String)', '{"x":["", "", "abc"]}');
-SELECT x FROM format(JSONEachRow, 'x Map(String, IPv6)', '{"x":{"abc": ""}}');
-SELECT x FROM format(JSONEachRow, 'x Variant(Date, UUID)', '{"x":""}');
-
--- Deep composition
-SELECT x FROM format(JSONEachRow, 'x Array(Array(IPv6))', '{"x":[["2001:db8:3333:4444:CCCC:DDDD:EEEE:FFFF", ""], ["", "2001:db8:3333:4444:5555:6666:7777:8888"]]}');
-SELECT x FROM format(JSONEachRow, 'x Variant(Date, Array(UUID))', '{"x":["", "b15f852c-c41a-4fd6-9247-1929c841715e"]}');
-SELECT x FROM format(JSONEachRow, 'x Tuple(Array(UUID), Tuple(UUID, Map(String, IPv6)))', '{"x":[[""], ["",{"abc":""}]]}');
-SELECT x FROM format(JSONEachRow, 'x Map(Tuple(Date,IPv4), Variant(UUID,IPv6))', '{"x":{["",""]:""}}');

tests/queries/0_stateless/03222_json_empty_as_default_small_read_buffer.reference

@@ -1,8 +0,0 @@
-Array(UUID)
-{"x":["00000000-0000-0000-0000-000000000000","b15f852c-c41a-4fd6-9247-1929c841715e","00000000-0000-0000-0000-000000000000"]}
-{"x":["00000000-0000-0000-0000-000000000000","b15f852c-c41a-4fd6-9247-1929c841715e","00000000-0000-0000-0000-000000000000"]}
-{"x":["00000000-0000-0000-0000-000000000000","b15f852c-c41a-4fd6-9247-1929c841715e","00000000-0000-0000-0000-000000000000"]}
-Tuple(Array(UUID), Tuple(UUID, Map(String, IPv6)))
-{"x":[["00000000-0000-0000-0000-000000000000"],["00000000-0000-0000-0000-000000000000",{"abc":"::"}]]}
-{"x":[["00000000-0000-0000-0000-000000000000"],["00000000-0000-0000-0000-000000000000",{"abc":"::"}]]}
-{"x":[["00000000-0000-0000-0000-000000000000"],["00000000-0000-0000-0000-000000000000",{"abc":"::"}]]}

tests/queries/0_stateless/03222_json_empty_as_default_small_read_buffer.sh

@@ -1,31 +0,0 @@
-#!/usr/bin/env bash
-# Tags: no-parallel
-
-CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-# shellcheck source=../shell_config.sh
-. "$CURDIR"/../shell_config.sh
-
-DATA_FILE=$CLICKHOUSE_TEST_UNIQUE_NAME.json
-
-# Wrapper for clickhouse-client to always output in JSONEachRow format, that
-# way format settings will not affect output.
-function clickhouse_local()
-{
-    $CLICKHOUSE_LOCAL --output-format JSONEachRow "$@"
-}
-
-echo 'Array(UUID)'
-echo '{"x":["00000000-0000-0000-0000-000000000000","b15f852c-c41a-4fd6-9247-1929c841715e",""]}' > $DATA_FILE
-# Use increasingly smaller read buffers.
-clickhouse_local -q "SELECT x FROM file('$DATA_FILE', 'JSONEachRow', 'x Array(UUID)') SETTINGS input_format_json_empty_as_default=1, input_format_parallel_parsing=0, storage_file_read_method='read', max_read_buffer_size=4"
-clickhouse_local -q "SELECT x FROM file('$DATA_FILE', 'JSONEachRow', 'x Array(UUID)') SETTINGS input_format_json_empty_as_default=1, input_format_parallel_parsing=0, storage_file_read_method='read', max_read_buffer_size=2"
-clickhouse_local -q "SELECT x FROM file('$DATA_FILE', 'JSONEachRow', 'x Array(UUID)') SETTINGS input_format_json_empty_as_default=1, input_format_parallel_parsing=0, storage_file_read_method='read', max_read_buffer_size=1"
-
-echo 'Tuple(Array(UUID), Tuple(UUID, Map(String, IPv6)))'
-echo '{"x":[[""], ["",{"abc":""}]]}' > $DATA_FILE
-# Use increasingly smaller read buffers.
-clickhouse_local -q "SELECT x FROM file('$DATA_FILE', 'JSONEachRow', 'x Tuple(Array(UUID), Tuple(UUID, Map(String, IPv6)))') SETTINGS input_format_json_empty_as_default=1, input_format_parallel_parsing=0, storage_file_read_method='read', max_read_buffer_size=16"
-clickhouse_local -q "SELECT x FROM file('$DATA_FILE', 'JSONEachRow', 'x Tuple(Array(UUID), Tuple(UUID, Map(String, IPv6)))') SETTINGS input_format_json_empty_as_default=1, input_format_parallel_parsing=0, storage_file_read_method='read', max_read_buffer_size=8"
-clickhouse_local -q "SELECT x FROM file('$DATA_FILE', 'JSONEachRow', 'x Tuple(Array(UUID), Tuple(UUID, Map(String, IPv6)))') SETTINGS input_format_json_empty_as_default=1, input_format_parallel_parsing=0, storage_file_read_method='read', max_read_buffer_size=1"
-
-rm $DATA_FILE