mridulm commented on a change in pull request #33034:
URL: https://github.com/apache/spark/pull/33034#discussion_r680622302
##########
File path:
common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/RemoteBlockPushResolver.java
##########
@@ -188,49 +228,70 @@ private AppShufflePartitionInfo
getOrCreateAppShufflePartitionInfo(
AppShufflePartitionInfo newAppShufflePartitionInfo(
String appId,
int shuffleId,
+ int shuffleMergeId,
int reduceId,
File dataFile,
File indexFile,
File metaFile) throws IOException {
- return new AppShufflePartitionInfo(appId, shuffleId, reduceId, dataFile,
+ return new AppShufflePartitionInfo(appId, shuffleId, shuffleMergeId,
reduceId, dataFile,
new MergeShuffleFile(indexFile), new MergeShuffleFile(metaFile));
}
@Override
- public MergedBlockMeta getMergedBlockMeta(String appId, int shuffleId, int
reduceId) {
+ public MergedBlockMeta getMergedBlockMeta(
+ String appId,
+ int shuffleId,
+ int shuffleMergeId,
+ int reduceId) {
AppShuffleInfo appShuffleInfo = validateAndGetAppShuffleInfo(appId);
+ AppShuffleMergePartitionsInfo partitionsInfo =
appShuffleInfo.shuffles.get(shuffleId);
+ if (null != partitionsInfo && partitionsInfo.shuffleMergeId >
shuffleMergeId) {
+ throw new RuntimeException(String.format(
+ "MergedBlockMeta fetch for shuffle %s with shuffleMergeId %s reduceId
%s is %s",
+ shuffleId, shuffleMergeId, reduceId,
+ ErrorHandler.BlockFetchErrorHandler.STALE_SHUFFLE_BLOCK_FETCH));
+ }
File indexFile =
- appShuffleInfo.getMergedShuffleIndexFile(shuffleId, reduceId);
+ appShuffleInfo.getMergedShuffleIndexFile(shuffleId, shuffleMergeId,
reduceId);
if (!indexFile.exists()) {
throw new RuntimeException(String.format(
"Merged shuffle index file %s not found", indexFile.getPath()));
}
int size = (int) indexFile.length();
// First entry is the zero offset
int numChunks = (size / Long.BYTES) - 1;
- File metaFile = appShuffleInfo.getMergedShuffleMetaFile(shuffleId,
reduceId);
+ File metaFile = appShuffleInfo.getMergedShuffleMetaFile(shuffleId,
shuffleMergeId, reduceId);
if (!metaFile.exists()) {
throw new RuntimeException(String.format("Merged shuffle meta file %s
not found",
metaFile.getPath()));
}
FileSegmentManagedBuffer chunkBitMaps =
new FileSegmentManagedBuffer(conf, metaFile, 0L, metaFile.length());
logger.trace(
- "{} shuffleId {} reduceId {} num chunks {}", appId, shuffleId, reduceId,
numChunks);
+ "{} shuffleId {} shuffleMergeId {} reduceId {} num chunks {}",
+ appId, shuffleId, shuffleMergeId, reduceId, numChunks);
return new MergedBlockMeta(numChunks, chunkBitMaps);
}
@SuppressWarnings("UnstableApiUsage")
@Override
- public ManagedBuffer getMergedBlockData(String appId, int shuffleId, int
reduceId, int chunkId) {
+ public ManagedBuffer getMergedBlockData(
+ String appId, int shuffleId, int shuffleMergeId, int reduceId, int
chunkId) {
AppShuffleInfo appShuffleInfo = validateAndGetAppShuffleInfo(appId);
- File dataFile = appShuffleInfo.getMergedShuffleDataFile(shuffleId,
reduceId);
+ AppShuffleMergePartitionsInfo partitionsInfo =
appShuffleInfo.shuffles.get(shuffleId);
+ if (null != partitionsInfo && partitionsInfo.shuffleMergeId >
shuffleMergeId) {
Review comment:
Same as `getMergedBlockMeta` above.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
