Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[SPARK-19956][Core]Optimize a location order of blocks with topology information #17300

Closed
wants to merge 4 commits into from
Closed

[SPARK-19956][Core]Optimize a location order of blocks with topology information #17300

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
926ea25
optimize a location order of blocks with topology information
ConeyLiu Mar 15, 2017
56f5231
Address comments
ConeyLiu Mar 22, 2017
1d863b7
Merge branch 'master' into blockmanager
ConeyLiu May 5, 2017
a3e979f
address comments, and fix the test error
ConeyLiu May 5, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions core/src/main/scala/org/apache/spark/storage/BlockManager.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Modified, thanks a lot for the good advice.

}
preferredLocs ++ sameRackLocs ++ differentRackLocs
}

/**
Expand Down
27 changes: 25 additions & 2 deletions core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -485,7 +485,7 @@ class BlockManagerSuite extends SparkFunSuite with Matchers with BeforeAndAfterE
assert(list2DiskGet.get.readMethod === DataReadMethod.Disk)
}

test("optimize a location order of blocks") {
test("optimize a location order of blocks without topology information") {
val localHost = Utils.localHostName()
val otherHost = "otherHost"
val bmMaster = mock(classOf[BlockManagerMaster])
Expand All @@ -497,7 +497,30 @@ class BlockManagerSuite extends SparkFunSuite with Matchers with BeforeAndAfterE
val blockManager = makeBlockManager(128, "exec", bmMaster)
val getLocations = PrivateMethod[Seq[BlockManagerId]]('getLocations)
val locations = blockManager invokePrivate getLocations(BroadcastBlockId(0))
assert(locations.map(_.host).toSet === Set(localHost, localHost, otherHost))
assert(locations.map(_.host) === Seq(localHost, localHost, otherHost))
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There should also be Seq.

}

test("optimize a location order of blocks with topology information") {
val localHost = Utils.localHostName()
val otherHost = "otherHost"
val localRack = "localRack"
val otherRack = "otherRack"

val bmMaster = mock(classOf[BlockManagerMaster])
val bmId1 = BlockManagerId("id1", localHost, 1, Some(localRack))
val bmId2 = BlockManagerId("id2", localHost, 2, Some(localRack))
val bmId3 = BlockManagerId("id3", otherHost, 3, Some(otherRack))
val bmId4 = BlockManagerId("id4", otherHost, 4, Some(otherRack))
val bmId5 = BlockManagerId("id5", otherHost, 5, Some(localRack))
when(bmMaster.getLocations(mc.any[BlockId]))
.thenReturn(Seq(bmId1, bmId2, bmId5, bmId3, bmId4))

val blockManager = makeBlockManager(128, "exec", bmMaster)
val getLocations = PrivateMethod[Seq[BlockManagerId]]('getLocations)
val locations = blockManager invokePrivate getLocations(BroadcastBlockId(0))
assert(locations.map(_.host) === Seq(localHost, localHost, otherHost, otherHost, otherHost))
assert(locations.flatMap(_.topologyInfo)
=== Seq(localRack, localRack, localRack, otherRack, otherRack))
}

test("SPARK-9591: getRemoteBytes from another location when Exception throw") {
Expand Down