Skip to content

fixed bug in S3 Physical Optimizer 2 #13391

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

Merged
merged 4 commits into from
Jan 17, 2025
Merged

fixed bug in S3 Physical Optimizer 2 #13391

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
60a4bfe
fixed bug in S3 Physical Optimizer 2
evanevanevanevannnn Jan 15, 2025
93822ed
test fix
evanevanevanevannnn Jan 17, 2025
44ee62f
test fix 2
evanevanevanevannnn Jan 17, 2025
9b9dc00
new test
evanevanevanevannnn Jan 17, 2025
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
30 changes: 30 additions & 0 deletions ydb/core/kqp/ut/federated_query/s3/kqp_federated_query_ut.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2366,6 +2366,21 @@ Y_UNIT_TEST_SUITE(KqpFederatedQuery) {

auto db = kikimr->GetQueryClient();

{
const TString sql = fmt::format(R"(
INSERT INTO {destination}
SELECT key, value FROM {source};)",
"destination"_a = table1,
"source"_a = olapTable);

auto scriptExecutionOperation = db.ExecuteScript(sql).ExtractValueSync();
UNIT_ASSERT_VALUES_EQUAL_C(scriptExecutionOperation.Status().GetStatus(), EStatus::SUCCESS, scriptExecutionOperation.Status().GetIssues().ToString());
UNIT_ASSERT(scriptExecutionOperation.Metadata().ExecutionId);

NYdb::NQuery::TScriptExecutionOperation readyOp = WaitScriptExecutionOperation(scriptExecutionOperation.Id(), kikimr->GetDriver());
UNIT_ASSERT_EQUAL_C(readyOp.Metadata().ExecStatus, EExecStatus::Completed, readyOp.Status().GetIssues().ToString());
}

{
const TString sql = fmt::format(R"(
INSERT INTO {destination}
Expand All @@ -2381,6 +2396,21 @@ Y_UNIT_TEST_SUITE(KqpFederatedQuery) {
UNIT_ASSERT_EQUAL_C(readyOp.Metadata().ExecStatus, EExecStatus::Completed, readyOp.Status().GetIssues().ToString());
}

{
const TString sql = fmt::format(R"(
INSERT INTO {destination}
SELECT key, value, "2024" AS year FROM {source};)",
"destination"_a = table2,
"source"_a = olapTable);

auto scriptExecutionOperation = db.ExecuteScript(sql).ExtractValueSync();
UNIT_ASSERT_VALUES_EQUAL_C(scriptExecutionOperation.Status().GetStatus(), EStatus::SUCCESS, scriptExecutionOperation.Status().GetIssues().ToString());
UNIT_ASSERT(scriptExecutionOperation.Metadata().ExecutionId);

NYdb::NQuery::TScriptExecutionOperation readyOp = WaitScriptExecutionOperation(scriptExecutionOperation.Id(), kikimr->GetDriver());
UNIT_ASSERT_EQUAL_C(readyOp.Metadata().ExecStatus, EExecStatus::Completed, readyOp.Status().GetIssues().ToString());
}

{
const TString sql = fmt::format(R"(
INSERT INTO {destination}
Expand Down
34 changes: 23 additions & 11 deletions ydb/library/yql/providers/s3/provider/yql_s3_phy_opt.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,17 +199,31 @@ class TS3PhysicalOptProposalTransformer : public TOptimizeTransformerBase {
}
}

if (!FindNode(input.Ptr(), [] (const TExprNode::TPtr& node) { return node->IsCallable(TDqCnUnionAll::CallableName()); })) {
if (!FindNode(input.Ptr(), [] (const TExprNode::TPtr& node) { return node->IsCallable(TCoDataSource::CallableName()); })) {
YQL_CLOG(INFO, ProviderS3) << "Rewrite pure S3WriteObject `" << cluster << "`.`" << target.Path().StringValue() << "` as stage with sink.";
auto shouldBePassedAsInput = FindNode(input.Ptr(), [] (const TExprNode::TPtr& node) { return node->IsCallable(TDqStage::CallableName()); });

auto stageInputs = Build<TExprList>(ctx, writePos);
auto toFlow = Build<TCoToFlow>(ctx, writePos);
TVector<TCoArgument> args;

if (shouldBePassedAsInput) {
auto arg = Build<TCoArgument>(ctx, writePos).Name("in").Done();
stageInputs.Add(input);
args.push_back(arg);
toFlow.Input(arg);
}
else {
toFlow.Input(input);
}

return keys.empty() ?
Build<TDqStage>(ctx, writePos)
.Inputs().Build()
.Inputs(stageInputs.Done())
.Program<TCoLambda>()
.Args({})
.Args(args)
.Body<TS3SinkOutput>()
.Input<TCoToFlow>()
.Input(input)
.Build()
.Input(toFlow.Done())
.Format(target.Format())
.KeyColumns().Build()
.Settings(sinkOutputSettingsBuilder.Done())
Expand Down Expand Up @@ -237,12 +251,10 @@ class TS3PhysicalOptProposalTransformer : public TOptimizeTransformerBase {
.Add<TDqCnHashShuffle>()
.Output<TDqOutput>()
.Stage<TDqStage>()
.Inputs().Build()
.Inputs(stageInputs.Done())
.Program<TCoLambda>()
.Args({})
.Body<TCoToFlow>()
.Input(input)
.Build()
.Args(args)
.Body(toFlow.Done())
.Build()
.Settings().Build()
.Build()
Expand Down
Loading