xuanyuanking commented on a change in pull request #24892: [SPARK-25341][Core]
Support rolling back a shuffle map stage and re-generate the shuffle files
URL: https://github.com/apache/spark/pull/24892#discussion_r300171085
##########
File path:
common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/OneForOneBlockFetcher.java
##########
@@ -88,63 +76,27 @@ public OneForOneBlockFetcher(
if (blockIds.length == 0) {
throw new IllegalArgumentException("Zero-sized blockIds array");
}
- if (!transportConf.useOldFetchProtocol() && isShuffleBlocks(blockIds)) {
- this.message = createFetchShuffleBlocksMsg(appId, execId, blockIds);
- } else {
- this.message = new OpenBlocks(appId, execId, blockIds);
- }
- }
-
- private boolean isShuffleBlocks(String[] blockIds) {
- for (String blockId : blockIds) {
- if (!blockId.startsWith("shuffle_")) {
- return false;
- }
- }
- return true;
}
/**
- * Analyze the pass in blockIds and create FetchShuffleBlocks message.
- * The blockIds has been sorted by mapId and reduceId. It's produced in
- * org.apache.spark.MapOutputTracker.convertMapStatuses.
+ * Create the corresponding message for this fetcher.
*/
- private FetchShuffleBlocks createFetchShuffleBlocksMsg(
- String appId, String execId, String[] blockIds) {
- int shuffleId = splitBlockId(blockIds[0])[0];
- HashMap<Integer, ArrayList<Integer>> mapIdToReduceIds = new HashMap<>();
- for (String blockId : blockIds) {
- int[] blockIdParts = splitBlockId(blockId);
- if (blockIdParts[0] != shuffleId) {
- throw new IllegalArgumentException("Expected shuffleId=" + shuffleId +
- ", got:" + blockId);
- }
- int mapId = blockIdParts[1];
- if (!mapIdToReduceIds.containsKey(mapId)) {
- mapIdToReduceIds.put(mapId, new ArrayList<>());
- }
- mapIdToReduceIds.get(mapId).add(blockIdParts[2]);
- }
- int[] mapIds = Ints.toArray(mapIdToReduceIds.keySet());
- 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);
+ public abstract BlockTransferMessage createBlockTransferMessage();
+
+ public String getAppId() {
+ return appId;
}
- /** Split the shuffleBlockId and return shuffleId, mapId and reduceId. */
- private int[] splitBlockId(String blockId) {
- String[] blockIdParts = blockId.split("_");
- if (blockIdParts.length != 4 || !blockIdParts[0].equals("shuffle")) {
- throw new IllegalArgumentException(
- "Unexpected shuffle block id format: " + blockId);
- }
- return new int[] {
- Integer.parseInt(blockIdParts[1]),
- Integer.parseInt(blockIdParts[2]),
- Integer.parseInt(blockIdParts[3])
- };
+ public String getExecId() {
+ return execId;
+ }
+
+ public String[] getBlockIds() {
Review comment:
Done in 1cdefce.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
