attilapiros commented on a change in pull request #25299: [SPARK-27651][Core]
Avoid the network when shuffle blocks are fetched from the same host
URL: https://github.com/apache/spark/pull/25299#discussion_r347015373
##########
File path:
common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockResolver.java
##########
@@ -369,6 +371,12 @@ public int removeBlocks(String appId, String execId,
String[] blockIds) {
return numRemovedBlocks;
}
+ public Map<String, String[]> getLocalDirs(String appId, String[] execIds) {
+ return Arrays.stream(execIds)
+ .map(exec -> Pair.of(exec, executors.get(new AppExecId(appId,
exec)).localDirs))
Review comment:
Can it happen that `executors` is out-dated?
As the
`org.apache.spark.storage.BlockManager#registerWithExternalShuffleServer` is
synchronous and when it fails it throws a `SparkException` and
`org.apache.spark.network.shuffle.ExternalShuffleBlockResolver` is backed by a
level DB, do you think about the case when the level DB file is corrupt? Or is
there any other case?
----------------------------------------------------------------
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
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
