attilapiros commented on a change in pull request #30062:
URL: https://github.com/apache/spark/pull/30062#discussion_r511923750
##########
File path:
common/network-common/src/main/java/org/apache/spark/network/util/TransportConf.java
##########
@@ -363,4 +363,26 @@ public boolean useOldFetchProtocol() {
return conf.getBoolean("spark.shuffle.useOldFetchProtocol", false);
}
+ /**
+ * The minimum size of a chunk when dividing a merged shuffle file into
multiple chunks during
+ * push-based shuffle.
+ * A merged shuffle file consists of multiple small shuffle blocks. Fetching
the
+ * complete merged shuffle file in a single response increases the memory
requirements for the
+ * clients. Instead of serving the entire merged file, the shuffle service
serves the
+ * merged file in `chunks`. A `chunk` constitutes few shuffle blocks in
entirety and this
+ * configuration controls how big a chunk can get. A corresponding index
file for each merged
+ * shuffle file will be generated indicating chunk boundaries.
+ */
+ public int minChunkSizeInMergedShuffleFile() {
+ return Ints.checkedCast(JavaUtils.byteStringAsBytes(
+ conf.get("spark.shuffle.server.minChunkSizeInMergedShuffleFile", "2m")));
Review comment:
I think it is fine to keep it on the server side first. Especially as
based on the aboves it does not seem to have huge impact right now (and of
course latter when we will have more experience with push-based shuffle this
decision can be revisited).
----------------------------------------------------------------
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
