This is an automated email from the ASF dual-hosted git repository.
changchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-gluten.git
The following commit(s) were added to refs/heads/main by this push:
new c93649d22 [GLUTEN-1632][CH]Daily Update Clickhouse Version (20240906)
(#7137)
c93649d22 is described below
commit c93649d22feec46c5049b6f07bf9405813352d5f
Author: Kyligence Git <[email protected]>
AuthorDate: Fri Sep 6 11:53:44 2024 -0500
[GLUTEN-1632][CH]Daily Update Clickhouse Version (20240906) (#7137)
* [GLUTEN-1632][CH]Daily Update Clickhouse Version (20240906)
* Fix build due to https://github.com/ClickHouse/ClickHouse/pull/65832
* Fix UT due to https://github.com/ClickHouse/ClickHouse/pull/65832
* Fix conflict with https://github.com/apache/incubator-gluten/pull/7122
* Fix conflict with https://github.com/apache/incubator-gluten/pull/7029
* Run GlutenClickHouseMergeTreeCacheDataSSuite locally
---------
Co-authored-by: kyligence-git <[email protected]>
Co-authored-by: Chang Chen <[email protected]>
---
.../GlutenClickHouseMergeTreeCacheDataSSuite.scala | 1 +
cpp-ch/clickhouse.version | 4 ++--
cpp-ch/local-engine/Parser/MergeTreeRelParser.cpp | 3 +--
cpp-ch/local-engine/Storages/Cache/CacheManager.cpp | 3 +--
.../Storages/MergeTree/SparkMergeTreeMeta.cpp | 1 -
.../Storages/MergeTree/SparkStorageMergeTree.h | 20 +++++++++++++++++++-
6 files changed, 24 insertions(+), 8 deletions(-)
diff --git
a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeCacheDataSSuite.scala
b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeCacheDataSSuite.scala
index 960c92178..a55067185 100644
---
a/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeCacheDataSSuite.scala
+++
b/backends-clickhouse/src/test/scala/org/apache/gluten/execution/GlutenClickHouseMergeTreeCacheDataSSuite.scala
@@ -58,6 +58,7 @@ class GlutenClickHouseMergeTreeCacheDataSSuite
.set(
"spark.gluten.sql.columnar.backend.ch.runtime_settings.mergetree.merge_after_insert",
"false")
+ // .set("spark.gluten.sql.columnar.backend.ch.runtime_config.path",
"/data") // for local test
}
override protected def beforeEach(): Unit = {
diff --git a/cpp-ch/clickhouse.version b/cpp-ch/clickhouse.version
index 93bf97d78..0b81f8afe 100644
--- a/cpp-ch/clickhouse.version
+++ b/cpp-ch/clickhouse.version
@@ -1,3 +1,3 @@
CH_ORG=Kyligence
-CH_BRANCH=rebase_ch/20240830
-CH_COMMIT=5e2eaab52ac
+CH_BRANCH=rebase_ch/20240906
+CH_COMMIT=4513a954b95
\ No newline at end of file
diff --git a/cpp-ch/local-engine/Parser/MergeTreeRelParser.cpp
b/cpp-ch/local-engine/Parser/MergeTreeRelParser.cpp
index b85ed25e1..20340a099 100644
--- a/cpp-ch/local-engine/Parser/MergeTreeRelParser.cpp
+++ b/cpp-ch/local-engine/Parser/MergeTreeRelParser.cpp
@@ -96,8 +96,7 @@ DB::QueryPlanPtr MergeTreeRelParser::parseReadRel(
auto read_step = storage->reader.readFromParts(
selected_parts,
- /* alter_conversions = */
- {},
+ storage->getMutationsSnapshot({}),
names_and_types_list.getNames(),
storage_snapshot,
*query_info,
diff --git a/cpp-ch/local-engine/Storages/Cache/CacheManager.cpp
b/cpp-ch/local-engine/Storages/Cache/CacheManager.cpp
index e74a74ae0..a2943f0b7 100644
--- a/cpp-ch/local-engine/Storages/Cache/CacheManager.cpp
+++ b/cpp-ch/local-engine/Storages/Cache/CacheManager.cpp
@@ -101,8 +101,7 @@ Task CacheManager::cachePart(const MergeTreeTableInstance &
table, const MergeTr
=
StorageMergeTreeFactory::getDataPartsByNames(storage->getStorageID(), "",
{job_detail.table.parts.front().name});
auto read_step = storage->reader.readFromParts(
selected_parts,
- /* alter_conversions = */
- {},
+ storage->getMutationsSnapshot({}),
names_and_types_list.getNames(),
storage_snapshot,
*query_info,
diff --git a/cpp-ch/local-engine/Storages/MergeTree/SparkMergeTreeMeta.cpp
b/cpp-ch/local-engine/Storages/MergeTree/SparkMergeTreeMeta.cpp
index 788b1b39f..2921fc887 100644
--- a/cpp-ch/local-engine/Storages/MergeTree/SparkMergeTreeMeta.cpp
+++ b/cpp-ch/local-engine/Storages/MergeTree/SparkMergeTreeMeta.cpp
@@ -286,7 +286,6 @@ RangesInDataParts
MergeTreeTableInstance::extractRange(DataPartsVector parts_vec
ranges_in_data_part.data_part = name_index.at(part.name);
ranges_in_data_part.part_index_in_query = 0;
ranges_in_data_part.ranges.emplace_back(MarkRange(part.begin,
part.end));
- ranges_in_data_part.alter_conversions =
std::make_shared<AlterConversions>();
return ranges_in_data_part;
});
return ranges_in_data_parts;
diff --git a/cpp-ch/local-engine/Storages/MergeTree/SparkStorageMergeTree.h
b/cpp-ch/local-engine/Storages/MergeTree/SparkStorageMergeTree.h
index fbd19de64..7d51a731b 100644
--- a/cpp-ch/local-engine/Storages/MergeTree/SparkStorageMergeTree.h
+++ b/cpp-ch/local-engine/Storages/MergeTree/SparkStorageMergeTree.h
@@ -50,6 +50,19 @@ class SparkStorageMergeTree : public MergeTreeData
{
friend class MergeSparkMergeTreeTask;
+ struct SparkMutationsSnapshot : public IMutationsSnapshot
+ {
+ SparkMutationsSnapshot() = default;
+
+ MutationCommands getAlterMutationCommandsForPart(const
MergeTreeData::DataPartPtr & part) const override { return {}; }
+ std::shared_ptr<MergeTreeData::IMutationsSnapshot> cloneEmpty() const
override
+ {
+ return std::make_shared<SparkMutationsSnapshot>();
+ }
+
+ NameSet getAllUpdatedColumns() const override { return {}; }
+ };
+
public:
static void wrapRangesInDataParts(DB::ReadFromMergeTree & source, const
DB::RangesInDataParts & ranges);
static void analysisPartsByRanges(DB::ReadFromMergeTree & source, const
DB::RangesInDataParts & ranges_in_data_parts);
@@ -94,8 +107,13 @@ protected:
void replacePartitionFrom(const StoragePtr & source_table, const ASTPtr &
partition, bool replace, ContextPtr context) override;
void movePartitionToTable(const StoragePtr & dest_table, const ASTPtr &
partition, ContextPtr context) override;
bool partIsAssignedToBackgroundOperation(const DataPartPtr & part) const
override;
- MutationCommands getAlterMutationCommandsForPart(const DataPartPtr &
/*part*/) const override { return {}; }
void attachRestoredParts(MutableDataPartsVector && /*parts*/) override {
throw std::runtime_error("not implement"); }
+
+public:
+ MutationsSnapshotPtr getMutationsSnapshot(const IMutationsSnapshot::Params
& /*params*/) const override
+ {
+ return std::make_shared<SparkMutationsSnapshot>();
+ };
};
class SparkWriteStorageMergeTree final : public SparkStorageMergeTree
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]