clay4megtr commented on code in PR #7553:
URL: https://github.com/apache/incubator-gluten/pull/7553#discussion_r1802291173
##########
cpp/core/shuffle/rss/RssPartitionWriter.cc:
##########
@@ -85,7 +85,7 @@ arrow::Status RssPartitionWriter::doEvict(
inMemoryPayload->toBlockPayload(
payloadType, payloadPool_.get(), codec_ ? codec_.get() : nullptr,
std::move(compressed)));
// Copy payload to arrow buffered os.
- ARROW_ASSIGN_OR_RAISE(auto rssBufferOs,
arrow::io::BufferOutputStream::Create(options_.pushBufferMaxSize, pool_));
+ ARROW_ASSIGN_OR_RAISE(auto rssBufferOs,
arrow::io::BufferOutputStream::Create(options_.pushBufferMaxSize));
Review Comment:
It is, actually I'm a little confused about delegate the timing of spill
trigger to spark framework, which means we can't make any memory allocation
when spilling.
--
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]
