weijietong commented on a change in pull request #2000: DRILL-7607: support
dynamic credit based flow control
URL: https://github.com/apache/drill/pull/2000#discussion_r386008276
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/work/batch/UnlimitedRawBatchBuffer.java
##########
@@ -90,14 +100,39 @@ public boolean isEmpty() {
@Override
public void add(RawFragmentBatch batch) {
+ int recordCount = batch.getHeader().getDef().getRecordCount();
+ long bathByteSize = batch.getByteCount();
+ if (recordCount != 0) {
+ //skip first header batch
+ totalBatchSize += bathByteSize;
+ sampleTimes++;
+ }
+ if (sampleTimes == maxSampleTimes) {
+ long averageBathSize = totalBatchSize / sampleTimes;
+ //make a decision
+ long limit = context.getAllocator().getLimit();
Review comment:
One more answer to this question, to current SpoolingRawBatchBuffer, though
it could spill to disk, but when to spill is still not memory safe. The reason
is still we could not control the parallel receiver nodes one drillbit.
I also find a bug to its implementation. It calculates the memory usage of
one batch by calling the `RawFragmentBatchWrapper.getBodySize()` . That method
would always return 0. As the Drillbuf's writerIndex and readerIndex are all
zero at that time.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
