You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2020/03/21 14:15:00 UTC

[GitHub] [spark] running2 opened a new pull request #27963: [SPARK-31199]separate shuffle io connect timeout from idle timeout

running2 opened a new pull request #27963: [SPARK-31199]separate shuffle io connect timeout from idle timeout
URL: https://github.com/apache/spark/pull/27963
 
 
   <!--
   Thanks for sending a pull request!  Here are some tips for you:
     1. If this is your first time, please read our contributor guidelines: https://spark.apache.org/contributing.html
     2. Ensure you have added or run the appropriate tests for your PR: https://spark.apache.org/developer-tools.html
     3. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP][SPARK-XXXX] Your PR title ...'.
     4. Be sure to keep the PR description updated to reflect all changes.
     5. Please write your PR title to summarize what this PR proposes.
     6. If possible, provide a concise example to reproduce the issue for a faster review.
     7. If you want to add a new configuration, please read the guideline first for naming configurations in
        'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
   -->
   
   ### What changes were proposed in this pull request?
   <!--
   Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue. 
   If possible, please consider writing useful notes for better and faster reviews in your PR. See the examples below.
     1. If you refactor some codes with changing classes, showing the class hierarchy will help reviewers.
     2. If you fix some SQL features, you can provide some references of other DBMSes.
     3. If there is design documentation, please add the link.
     4. If there is a discussion in the mailing list, please add the link.
   -->
   When reading shuffle data, some fetch request may go to some shuffle server that go unstable/down and now the connection timeout to the shuffle server is controlled by spark.shuffle.io.connectionTimeout. Normally the connect time is just several ms in an internal cluster, in order to fail fast, we hope to shorten the time to around 10s.
   But this timeout also controls the connection idle timeout (https://github.com/apache/spark/pull/5584), that means if the connection seems idle for this time period, the connection will be killed even there is on-going request on it. For some big job with large chunks, the timeout could not be that small.
   I think these 2 timeout should be separated since they are for different purpose and their timeout maybe dramatically different.  
   
   
   ### Why are the changes needed?
   <!--
   Please clarify why the changes are needed. For instance,
     1. If you propose a new API, clarify the use case for a new API.
     2. If you fix a bug, you can clarify why it is a bug.
   -->
   To save time for some cases. 
   
   ### Does this PR introduce any user-facing change?
   <!--
   If yes, please clarify the previous behavior and the change this PR proposes - provide the console output, description and/or an example to show the behavior difference if possible.
   If no, write 'No'.
   -->
   Yes, we have one more parameter that user may need to be aware of.
   
   ### How was this patch tested?
   <!--
   If tests were added, say they were added here. Please make sure to add some test cases that check the changes thoroughly including negative and positive cases if possible.
   If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
   If tests were not added, please describe why they were not added and/or why it was difficult to add.
   -->
   Existing UTs.

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org