vanzin commented on a change in pull request #23602:
[SPARK-26674][CORE]Consolidate CompositeByteBuf when reading large frame
URL: https://github.com/apache/spark/pull/23602#discussion_r253684583
##########
File path:
common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java
##########
@@ -94,6 +96,23 @@ public boolean preferDirectBufs() {
return conf.getBoolean(SPARK_NETWORK_IO_PREFERDIRECTBUFS_KEY, true);
}
+ /** The threshold for consolidation, it is derived upon the memoryOverhead
in yarn mode. */
+ public long consolidateBufsThreshold() {
+ boolean isDriver = conf.get("spark.executor.id").equals("driver");
Review comment:
Not only what Sean said, but really, this is sort of broken. This isn't even
set in the external shuffle service. There's no memory overhead configuration
there, either.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on 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
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
