Github user jinxing64 commented on a diff in the pull request:
https://github.com/apache/spark/pull/18231#discussion_r120809215
--- Diff:
common/network-shuffle/src/main/java/org/apache/spark/network/shuffle/ExternalShuffleBlockHandler.java
---
@@ -209,4 +190,47 @@ private ShuffleMetrics() {
}
}
+ private class ManagedBufferIterator implements Iterator<ManagedBuffer> {
+
+ private int index = 0;
+ private String appId;
+ private String execId;
+ private String shuffleId;
+ // mapId and reduceId are stored as bytes to save memory.
+ private byte[][] mapIdAndReduceIds;
+
+ ManagedBufferIterator(String appId, String execId, String[] blockIds) {
+ this.appId = appId;
+ this.execId = execId;
+ String blockId = blockIds[0];
+ String[] blockIdParts = blockId.split("_");
+ if (blockIdParts.length < 4) {
+ throw new IllegalArgumentException("Unexpected block id format: "
+ blockId);
+ } else if (!blockIdParts[0].equals("shuffle")) {
+ throw new IllegalArgumentException("Expected shuffle block id,
got: " + blockId);
+ }
+ this.shuffleId = blockIdParts[1];
+ mapIdAndReduceIds = new byte[blockIds.length][];
+ if (blockIds.length > 0) {
+ for (int i = 0; i< blockIds.length; i++) {
+ mapIdAndReduceIds[i] = (blockIdParts[2] + "_" +
blockIdParts[3]).getBytes();
--- End diff --
Yes, I think this is a good idea. In current change, I make it to be
`int[blockIds.length][2]`. I'm not sure if I understand your comment correctly.
Please take another look :)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
