andygrove commented on code in PR #6876:
URL: https://github.com/apache/datafusion-comet/pull/6876#discussion_r4244034070
##########
spark/src/main/scala/org/apache/comet/udf/codegen/CometScalaUDFCodegen.scala:
##########
@@ -144,9 +169,14 @@ class CometScalaUDFCodegen extends CometUDF with Logging {
private def lookupOrCompile(
key: CometScalaUDFCodegen.CacheKey,
bytes: Array[Byte],
- specs: IndexedSeq[ArrowColumnSpec]): CometScalaUDFCodegen.CacheEntry = {
+ specs: IndexedSeq[ArrowColumnSpec],
+ partitionIndex: Int): CometScalaUDFCodegen.CacheEntry = {
assert(Thread.holdsLock(this), "lookupOrCompile must run under
this.synchronized")
- kernelCache.get(key) match {
+ // A deterministic kernel never reads the partition index, so one instance
under the planless
+ // key serves every plan in the task. Only a kernel with a
nondeterministic node is stored per
+ // plan.
+ val sharedKey = key.copy(planId = CometScalaUDFCodegen.NoPlan)
+ kernelCache.get(sharedKey).orElse(kernelCache.get(key)) match {
Review Comment:
Does this issue also exist in main branch? This PR is backporting an already
approved commit to main
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
