-
Notifications
You must be signed in to change notification settings - Fork 29k
[SPARK-35794][SQL] Allow custom plugin for AQE cost evaluator #32944
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.
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
Changes from all commits
494b8bc
f1ee7ec
9fd1bbe
c5ed8e7
ac5c121
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -1898,4 +1898,54 @@ class AdaptiveQueryExecSuite | |
| assert(coalesceReader.head.partitionSpecs.length == 1) | ||
| } | ||
| } | ||
|
|
||
| test("SPARK-35794: Allow custom plugin for cost evaluator") { | ||
| CostEvaluator.instantiate( | ||
| classOf[SimpleShuffleSortCostEvaluator].getCanonicalName, spark.sparkContext.getConf) | ||
| intercept[IllegalArgumentException] { | ||
| CostEvaluator.instantiate( | ||
| classOf[InvalidCostEvaluator].getCanonicalName, spark.sparkContext.getConf) | ||
| } | ||
|
|
||
| withSQLConf( | ||
| SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true", | ||
| SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "80") { | ||
| val query = "SELECT * FROM testData join testData2 ON key = a where value = '1'" | ||
|
|
||
| withSQLConf(SQLConf.ADAPTIVE_CUSTOM_COST_EVALUATOR_CLASS.key -> | ||
| "org.apache.spark.sql.execution.adaptive.SimpleShuffleSortCostEvaluator") { | ||
|
||
| val (plan, adaptivePlan) = runAdaptiveAndVerifyResult(query) | ||
| val smj = findTopLevelSortMergeJoin(plan) | ||
| assert(smj.size == 1) | ||
| val bhj = findTopLevelBroadcastHashJoin(adaptivePlan) | ||
| assert(bhj.size == 1) | ||
| checkNumLocalShuffleReaders(adaptivePlan) | ||
| } | ||
|
|
||
| withSQLConf(SQLConf.ADAPTIVE_CUSTOM_COST_EVALUATOR_CLASS.key -> | ||
| "org.apache.spark.sql.execution.adaptive.InvalidCostEvaluator") { | ||
| intercept[IllegalArgumentException] { | ||
| runAdaptiveAndVerifyResult(query) | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * Invalid implementation class for [[CostEvaluator]]. | ||
| */ | ||
| private class InvalidCostEvaluator() {} | ||
|
|
||
| /** | ||
| * A simple [[CostEvaluator]] to count number of [[ShuffleExchangeLike]] and [[SortExec]]. | ||
| */ | ||
| private case class SimpleShuffleSortCostEvaluator() extends CostEvaluator { | ||
| override def evaluateCost(plan: SparkPlan): Cost = { | ||
| val cost = plan.collect { | ||
| case s: ShuffleExchangeLike => s | ||
| case s: SortExec => s | ||
| }.size | ||
| SimpleCost(cost) | ||
| } | ||
| } | ||
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the only think is that the version has to be 3.3.0 since we cut the branch now. Since this PR won't likely affect anything in the main code, I am okay with merging to 3.2.0 either tho. I will leave it to @cloud-fan and you.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
3.2 is the first version that enables AQE by default, and this seems to be a useful extension. Let's include it in 3.2.