AngersZhuuuu commented on a change in pull request #33696:
URL: https://github.com/apache/spark/pull/33696#discussion_r686657719
##########
File path: core/src/main/scala/org/apache/spark/metrics/ExecutorMetricType.scala
##########
@@ -177,6 +177,16 @@ case object OnHeapUnifiedMemory extends
MemoryManagerExecutorMetricType(
case object OffHeapUnifiedMemory extends MemoryManagerExecutorMetricType(
(m => m.offHeapExecutionMemoryUsed + m.offHeapStorageMemoryUsed))
+case object OnHeapUnUnifiedMemory extends MemoryManagerExecutorMetricType(
Review comment:
> why do we need this? `JVMHeapMemory` reports it already and people can
easily calculate it by themselves.
Always we use event log/restful API to get the peakMemoryMetrics. what we
can get is the peakJVMOnHeap/peakOnHeapStorageMemory/peakOnHeapExecution memory
during a period of time.
But we can use the final status of
peakJVMOnHeap/peakOnHeapStorageMemory/peakOnHeapExecution to calculate and
get the peak unmanaged memory usage.
--
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]
