Github user ConeyLiu commented on the issue:
https://github.com/apache/spark/pull/22371
OK, thanks everyone for the help. Close it
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional
Github user cloud-fan commented on the issue:
https://github.com/apache/spark/pull/22371
My opinion is, it's not worth to spend time on it. The lock is not likely
to be a bottleneck and it's better to keep it simple even it's sub-optimal.
---
Github user cloud-fan commented on the issue:
https://github.com/apache/spark/pull/22371
@ConeyLiu we may have an executor lost and then come back, and may have 2
same tasks running on the same executor.
---
-
To
Github user ConeyLiu commented on the issue:
https://github.com/apache/spark/pull/22371
@squito , thanks for the review. I intend to using `ConcurrentHashMap[Int,
AtomicReferenceArray]` previously.
After re-think the code, I can know the lock here is used to prevent the
same
Github user ConeyLiu commented on the issue:
https://github.com/apache/spark/pull/22371
Thanks @felixcheung, @srowen, @cloud-fan for your time. There is only one
instance of `IndexShuffleBlockResolver` per executor, and the synchronize is
used to protect the modify safely when there
Github user cloud-fan commented on the issue:
https://github.com/apache/spark/pull/22371
How much perf can we save here? I don't think shuffle writing will be
bottlenecked by this lock.
---
-
To unsubscribe,
Github user felixcheung commented on the issue:
https://github.com/apache/spark/pull/22371
+ @srowen @squito @JoshRosen
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands,
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/22371
Can one of the admins verify this patch?
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/22371
Can one of the admins verify this patch?
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/22371
Can one of the admins verify this patch?
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional
Github user ConeyLiu commented on the issue:
https://github.com/apache/spark/pull/22371
@cloud-fan @jiangxb1987 Could you help to review this? Thanks a lot.
---
-
To unsubscribe, e-mail:
11 matches
Mail list logo