Skip to content

[SPARK-34534][CORE] Fix blockIds order when use FetchShuffleBlocks to fetch blocks #31643

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

Closed
seayoun wants to merge 13 commits into from
Closed

[SPARK-34534][CORE] Fix blockIds order when use FetchShuffleBlocks to fetch blocks #31643

Changes from 2 commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
0af3b01
fix blockIds order when use FetchShuffleBlocks to fetch blocks
Feb 25, 2021
384f43c
fix unOrder mapIds, and check mapIds order and reduce order when pars…
Feb 26, 2021
0006553
change code
Feb 26, 2021
006a5ec
add comment
Feb 26, 2021
a08ca1d
add test case
Feb 26, 2021
1234253
fix some wrong words and update test case
Feb 26, 2021
7987a25
change for line length
Feb 27, 2021
e823930
change indentations
Mar 1, 2021
0748d20
revert inital fix and regenerate blockIds
Mar 2, 2021
42b9621
add `mapIdToBlockIds` to fill blockIds
Mar 2, 2021
575ca5e
replace a single map instead of two in createFetchShuffleBlocksMsgAnd…
Mar 2, 2021
6377217
change mapIdToBlocksInfo to a LinkedHashMap
Mar 2, 2021
9cf23df
remove public
Mar 3, 2021
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
11 changes: 9 additions & 2 deletions ...network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,17 +117,23 @@ private FetchShuffleBlocks createFetchShuffleBlocksMsg(
boolean batchFetchEnabled = firstBlock.length == 5;

HashMap<Long, ArrayList<Integer>> mapIdToReduceIds = new HashMap<>();
ArrayList<Long> orderedMapId = new ArrayList<>();
for (String blockId : blockIds) {
String[] blockIdParts = splitBlockId(blockId);
if (Integer.parseInt(blockIdParts[1]) != shuffleId) {
throw new IllegalArgumentException("Expected shuffleId=" + shuffleId +
", got:" + blockId);
}
long mapId = Long.parseLong(blockIdParts[2]);
assert(orderedMapId.isEmpty() || mapId >= orderedMapId.get(orderedMapId.size() - 1));
if (!mapIdToReduceIds.containsKey(mapId)) {
mapIdToReduceIds.put(mapId, new ArrayList<>());
orderedMapId.add(mapId);
}
mapIdToReduceIds.get(mapId).add(Integer.parseInt(blockIdParts[3]));
ArrayList<Integer> reduceIdsByMapId = mapIdToReduceIds.get(mapId);
int reduceId = Integer.parseInt(blockIdParts[3]);
assert(reduceIdsByMapId.isEmpty() || reduceId > reduceIdsByMapId.get(reduceIdsByMapId.size() - 1));
reduceIdsByMapId.add(reduceId);
if (batchFetchEnabled) {
// When we read continuous shuffle blocks in batch, we will reuse reduceIds in
// FetchShuffleBlocks to store the start and end reduce id for range
Expand All @@ -136,11 +142,12 @@ private FetchShuffleBlocks createFetchShuffleBlocksMsg(
mapIdToReduceIds.get(mapId).add(Integer.parseInt(blockIdParts[4]));
}
}
long[] mapIds = Longs.toArray(mapIdToReduceIds.keySet());
long[] mapIds = Longs.toArray(orderedMapId);
int[][] reduceIdArr = new int[mapIds.length][];
for (int i = 0; i < mapIds.length; i++) {
reduceIdArr[i] = Ints.toArray(mapIdToReduceIds.get(mapIds[i]));
}

return new FetchShuffleBlocks(
appId, execId, shuffleId, mapIds, reduceIdArr, batchFetchEnabled);
}
Expand Down