Skip to content

feat: Support bucket write with non partitioned table #13283

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
JkSelf wants to merge 1 commit into from
Closed

feat: Support bucket write with non partitioned table #13283

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 0 additions & 3 deletions velox/connectors/hive/HiveDataSink.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1012,9 +1012,6 @@ HiveWriterParameters::UpdateMode HiveDataSink::getUpdateMode() const {
insertBehavior));
}
} else {
if (insertTableHandle_->isBucketed()) {
VELOX_USER_FAIL("Cannot insert into bucketed unpartitioned Hive table");
}
if (hiveConfig_->immutablePartitions()) {
VELOX_USER_FAIL("Unpartitioned Hive tables are immutable.");
}
Expand Down
78 changes: 78 additions & 0 deletions velox/exec/tests/TableWriterTest.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,6 +315,48 @@ class UnpartitionedTableWriterTest
}
};

class BucketedUnpartitionedTableWriterTest
: public TableWriterTestBase,
public testing::WithParamInterface<uint64_t> {
public:
BucketedUnpartitionedTableWriterTest() : TableWriterTestBase(GetParam()) {}

static std::vector<uint64_t> getTestParams() {
std::vector<uint64_t> testParams;
const std::vector<bool> multiDriverOptions = {false, true};
std::vector<FileFormat> fileFormats = {FileFormat::DWRF};
if (hasWriterFactory(FileFormat::PARQUET)) {
fileFormats.push_back(FileFormat::PARQUET);
}
const std::vector<TestMode> bucketModes = {TestMode::kOnlyBucketed};
for (bool multiDrivers : multiDriverOptions) {
for (FileFormat fileFormat : fileFormats) {
testParams.push_back(TestParam{
fileFormat,
TestMode::kOnlyBucketed,
CommitStrategy::kNoCommit,
HiveBucketProperty::Kind::kHiveCompatible,
true,
multiDrivers,
facebook::velox::common::CompressionKind_ZSTD,
/*scaleWriter=*/false}
.value);
testParams.push_back(TestParam{
fileFormat,
TestMode::kOnlyBucketed,
CommitStrategy::kTaskCommit,
HiveBucketProperty::Kind::kHiveCompatible,
true,
multiDrivers,
facebook::velox::common::CompressionKind_NONE,
/*scaleWriter=*/false}
.value);
}
}
return testParams;
}
};

class BucketedTableOnlyWriteTest
: public TableWriterTestBase,
public testing::WithParamInterface<uint64_t> {
Expand Down Expand Up @@ -1553,6 +1595,37 @@ TEST_P(UnpartitionedTableWriterTest, immutableSettings) {
}
}

TEST_P(BucketedUnpartitionedTableWriterTest, bucketNonPartitioned) {
SCOPED_TRACE(testParam_.toString());
auto input = makeVectors(1, 100);
createDuckDbTable(input);

auto outputDirectory = TempDirectoryPath::create();
setBucketProperty(
bucketProperty_->kind(),
bucketProperty_->bucketCount(),
bucketProperty_->bucketedBy(),
bucketProperty_->bucketedTypes(),
bucketProperty_->sortedBy());
auto plan = createInsertPlan(
PlanBuilder().values({input}),
rowType_,
outputDirectory->getPath(),
{},
bucketProperty_,
compressionKind_,
getNumWriters(),
connector::hive::LocationHandle::TableType::kExisting,
Copy link
Copy Markdown
Contributor Author

@JkSelf JkSelf May 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

#9740 only test the connector::hive::LocationHandle::TableType::kNew use case.

commitStrategy_);
assertQueryWithWriterConfigs(plan, "SELECT count(*) FROM tmp");

assertQuery(
PlanBuilder().tableScan(rowType_).planNode(),
makeHiveConnectorSplits(outputDirectory),
"SELECT * FROM tmp");
verifyTableWriterOutput(outputDirectory->getPath(), rowType_);
}

TEST_P(BucketedTableOnlyWriteTest, bucketCountLimit) {
SCOPED_TRACE(testParam_.toString());
auto input = makeVectors(1, 100);
Expand Down Expand Up @@ -2603,6 +2676,11 @@ VELOX_INSTANTIATE_TEST_SUITE_P(
UnpartitionedTableWriterTest,
testing::ValuesIn(UnpartitionedTableWriterTest::getTestParams()));

VELOX_INSTANTIATE_TEST_SUITE_P(
TableWriterTest,
BucketedUnpartitionedTableWriterTest,
testing::ValuesIn(BucketedUnpartitionedTableWriterTest::getTestParams()));

VELOX_INSTANTIATE_TEST_SUITE_P(
TableWriterTest,
PartitionedTableWriterTest,
Expand Down
Loading