You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by felixcheung <gi...@git.apache.org> on 2018/06/01 04:22:04 UTC
[GitHub] spark pull request #21474: [SPARK-24297][CORE] Fetch-to-disk by default for ...
Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/21474#discussion_r192295318
--- Diff: core/src/main/scala/org/apache/spark/internal/config/package.scala ---
@@ -429,7 +429,11 @@ package object config {
"external shuffle service, this feature can only be worked when external shuffle" +
"service is newer than Spark 2.2.")
.bytesConf(ByteUnit.BYTE)
- .createWithDefault(Long.MaxValue)
+ // fetch-to-mem is guaranteed to fail if the message is bigger than 2 GB, so we might
+ // as well use fetch-to-disk in that case. The message includes some metadata in addition
+ // to the block data itself (in particular UploadBlock has a lot of metadata), so we leave
+ // extra room.
+ .createWithDefault(Int.MaxValue - 500)
--- End diff --
is the fixed buffer of 500 bytes enough for metadata?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org