[GitHub] spark pull request #17300: [SPARK-19956][Core]Optimize a location order of b...

[viirya <gi...@git.apache.org>]

Github user viirya commented on a diff in the pull request:

    https://github.com/apache/spark/pull/17300#discussion_r114929963
  
    --- Diff: core/src/main/scala/org/apache/spark/storage/BlockManager.scala ---
    @@ -555,12 +555,15 @@ private[spark] class BlockManager(
     
       /**
        * Return a list of locations for the given block, prioritizing the local machine since
    -   * multiple block managers can share the same host.
    +   * multiple block managers can share the same host, followed by hosts on the same rack.
        */
       private def getLocations(blockId: BlockId): Seq[BlockManagerId] = {
         val locs = Random.shuffle(master.getLocations(blockId))
         val (preferredLocs, otherLocs) = locs.partition { loc => blockManagerId.host == loc.host }
    -    preferredLocs ++ otherLocs
    +    val (sameRackLocs, differentRackLocs) = otherLocs.partition {
    +      loc => blockManagerId.topologyInfo == loc.topologyInfo
    --- End diff --
    
    If `blockManagerId.topologyInfo` is `None`, we will prefer the locations with empty `topologyInfo`. It is slightly different with what the shuffling wants to do here.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org