[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17407714#comment-17407714
]
Adam Kennedy commented on SPARK-36446:
--
[~tgraves] Yes, we are running with recovery enabled (in
[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17394905#comment-17394905
]
Adam Kennedy edited comment on SPARK-36446 at 8/6/21, 5:56 PM:
---
The
[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17394905#comment-17394905
]
Adam Kennedy edited comment on SPARK-36446 at 8/6/21, 5:06 PM:
---
The
[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17394905#comment-17394905
]
Adam Kennedy edited comment on SPARK-36446 at 8/6/21, 5:06 PM:
---
The
[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17394905#comment-17394905
]
Adam Kennedy commented on SPARK-36446:
--
The problem was particularly amplified by the Executor
[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17394873#comment-17394873
]
Adam Kennedy commented on SPARK-36446:
--
Note: While I haven't investigated any other shuffle
[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-36446:
-
Summary: YARN shuffle server restart crashes all dynamic allocation jobs
that have deallocated
[
https://issues.apache.org/jira/browse/SPARK-36446?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-36446:
-
Summary: YARN shuffle server restart crashes all dynamic allocation jobs
that have deallocated
Adam Kennedy created SPARK-36446:
Summary: After dynamic deallocation YARN shuffle server restart
crashes all jobs
Key: SPARK-36446
URL: https://issues.apache.org/jira/browse/SPARK-36446
Project:
[
https://issues.apache.org/jira/browse/SPARK-21097?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16909342#comment-16909342
]
Adam Kennedy commented on SPARK-21097:
--
Another supporting reason for supporting transfer of memory
[
https://issues.apache.org/jira/browse/SPARK-25889?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25889:
-
Description:
The time based exponential ramp up behavior for dynamic allocation is naive and
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Description:
Large and highly multi-tenant Spark on YARN clusters with diverse job execution
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Issue Type: New Feature (was: Improvement)
> Service requests for persist() blocks via
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Shepherd: DB Tsai
> Service requests for persist() blocks via external service after dynamic
>
Adam Kennedy created SPARK-25889:
Summary: Dynamic allocation load-aware ramp up
Key: SPARK-25889
URL: https://issues.apache.org/jira/browse/SPARK-25889
Project: Spark
Issue Type: New
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Description:
Large and highly multi-tenant Spark on YARN clusters with diverse job execution
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Description:
Large and highly multi-tenant Spark on YARN clusters with diverse job execution
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Environment: (was: Large YARN cluster with 1,000 nodes, 50,000 cores
and 250 users, with
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Environment:
Large YARN cluster with 1,000 nodes, 50,000 cores and 250 users, with
[
https://issues.apache.org/jira/browse/SPARK-25888?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Kennedy updated SPARK-25888:
-
Summary: Service requests for persist() blocks via external service after
dynamic deallocation
Adam Kennedy created SPARK-25888:
Summary: Service requests for persist() block via external service
after dynamic deallocation
Key: SPARK-25888
URL: https://issues.apache.org/jira/browse/SPARK-25888
[
https://issues.apache.org/jira/browse/SPARK-21155?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16222120#comment-16222120
]
Adam Kennedy commented on SPARK-21155:
--
It can already get fairly crowded in that run area on large
[
https://issues.apache.org/jira/browse/SPARK-19112?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16113653#comment-16113653
]
Adam Kennedy commented on SPARK-19112:
--
Will this be impacted by LEGAL-303? zstd-jni embeds zstd
23 matches
Mail list logo