[GitHub] [incubator-celeborn] AngersZhuuuu commented on a diff in pull request #1399: [CELEBORN-487][PERF] ShuffleClientSide support blacklist to avoid client side timeout in same worker multiple times

["AngersZhuuuu (via GitHub)" <gi...@apache.org>]

AngersZhuuuu commented on code in PR #1399:
URL: https://github.com/apache/incubator-celeborn/pull/1399#discussion_r1155223971


##########
client/src/main/java/org/apache/celeborn/client/ShuffleClientImpl.java:
##########
@@ -1196,6 +1242,12 @@ public void onFailure(Throwable e) {
                 remainReviveTimes,
                 e);
             if (!mapperEnded(shuffleId, mapId, attemptId)) {
+              int tmpRemainReviveTimes = remainReviveTimes;
+              // For blacklisted partition location, Celeborn should not use retry quota.
+              if (!isPushBlacklisted(cause)) {
+                tmpRemainReviveTimes = tmpRemainReviveTimes - 1;
+              }
+              int finalRemainReviveTimes = tmpRemainReviveTimes;

Review Comment:
   <img width="1156" alt="截屏2023-04-02 上午9 36 49" src="https://user-images.githubusercontent.com/46485123/229326321-dcb154de-75b6-49c2-8f2d-433eb0a1a408.png">
   



-- 
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: issues-unsubscribe@celeborn.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org