diff options
author | Cheng Lian <lian.cs.zju@gmail.com> | 2014-03-07 23:26:46 -0800 |
---|---|---|
committer | Patrick Wendell <pwendell@gmail.com> | 2014-03-07 23:26:46 -0800 |
commit | 0b7b7fd45cd9037d23cb090e62be3ff075214fe7 (patch) | |
tree | 46782bbf6260cbfa33c85cb492ca70e543823f35 /core | |
parent | 8ad486add941c9686dfb39309adaf5b7ca66345d (diff) | |
download | spark-0b7b7fd45cd9037d23cb090e62be3ff075214fe7.tar.gz spark-0b7b7fd45cd9037d23cb090e62be3ff075214fe7.tar.bz2 spark-0b7b7fd45cd9037d23cb090e62be3ff075214fe7.zip |
[SPARK-1194] Fix the same-RDD rule for cache replacement
SPARK-1194: https://spark-project.atlassian.net/browse/SPARK-1194
In the current implementation, when selecting candidate blocks to be swapped out, once we find a block from the same RDD that the block to be stored belongs to, cache eviction fails and aborts.
In this PR, we keep selecting blocks *not* from the RDD that the block to be stored belongs to until either enough free space can be ensured (cache eviction succeeds) or all such blocks are checked (cache eviction fails).
Author: Cheng Lian <lian.cs.zju@gmail.com>
Closes #96 from liancheng/fix-spark-1194 and squashes the following commits:
2524ab9 [Cheng Lian] Added regression test case for SPARK-1194
6e40c22 [Cheng Lian] Remove redundant comments
40cdcb2 [Cheng Lian] Bug fix, and addressed PR comments from @mridulm
62c92ac [Cheng Lian] Fixed SPARK-1194 https://spark-project.atlassian.net/browse/SPARK-1194
Diffstat (limited to 'core')
-rw-r--r-- | core/src/main/scala/org/apache/spark/storage/MemoryStore.scala | 11 | ||||
-rw-r--r-- | core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala | 14 |
2 files changed, 19 insertions, 6 deletions
diff --git a/core/src/main/scala/org/apache/spark/storage/MemoryStore.scala b/core/src/main/scala/org/apache/spark/storage/MemoryStore.scala index b89212eaab..38836d44b0 100644 --- a/core/src/main/scala/org/apache/spark/storage/MemoryStore.scala +++ b/core/src/main/scala/org/apache/spark/storage/MemoryStore.scala @@ -236,13 +236,10 @@ private class MemoryStore(blockManager: BlockManager, maxMemory: Long) while (maxMemory - (currentMemory - selectedMemory) < space && iterator.hasNext) { val pair = iterator.next() val blockId = pair.getKey - if (rddToAdd.isDefined && rddToAdd == getRddId(blockId)) { - logInfo("Will not store " + blockIdToAdd + " as it would require dropping another " + - "block from the same RDD") - return false + if (rddToAdd.isEmpty || rddToAdd != getRddId(blockId)) { + selectedBlocks += blockId + selectedMemory += pair.getValue.size } - selectedBlocks += blockId - selectedMemory += pair.getValue.size } } @@ -264,6 +261,8 @@ private class MemoryStore(blockManager: BlockManager, maxMemory: Long) } return true } else { + logInfo(s"Will not store $blockIdToAdd as it would require dropping another block " + + "from the same RDD") return false } } diff --git a/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala b/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala index 121e47c7b1..1036b9f34e 100644 --- a/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala +++ b/core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala @@ -662,4 +662,18 @@ class BlockManagerSuite extends FunSuite with BeforeAndAfter with PrivateMethodT assert(store.getSingle("a1") == None, "a1 should not be in store") } } + + test("SPARK-1194 regression: fix the same-RDD rule for cache replacement") { + store = new BlockManager("<driver>", actorSystem, master, serializer, 1200, conf, securityMgr) + store.putSingle(rdd(0, 0), new Array[Byte](400), StorageLevel.MEMORY_ONLY) + store.putSingle(rdd(1, 0), new Array[Byte](400), StorageLevel.MEMORY_ONLY) + // Access rdd_1_0 to ensure it's not least recently used. + assert(store.getSingle(rdd(1, 0)).isDefined, "rdd_1_0 was not in store") + // According to the same-RDD rule, rdd_1_0 should be replaced here. + store.putSingle(rdd(0, 1), new Array[Byte](400), StorageLevel.MEMORY_ONLY) + // rdd_1_0 should have been replaced, even it's not least recently used. + assert(store.memoryStore.contains(rdd(0, 0)), "rdd_0_0 was not in store") + assert(store.memoryStore.contains(rdd(0, 1)), "rdd_0_1 was not in store") + assert(!store.memoryStore.contains(rdd(1, 0)), "rdd_1_0 was in store") + } } |