[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15947678#comment-15947678
]
Apache Spark commented on SPARK-3577:
-
User 'sitalkedia' has created a pull request for this issue:
https://github.com/apache/spark/pull/17471
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
> Attachments: spill_size.jpg
>
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15947669#comment-15947669
]
Sital Kedia commented on SPARK-3577:
I am making a change to report correct spill data size on disk.
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
> Attachments: spill_size.jpg
>
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15564472#comment-15564472
]
Reynold Xin commented on SPARK-3577:
[~dreamworks007] can you take a look at the problem here?
https://github.com/apache/spark/pull/15347
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
> Attachments: spill_size.jpg
>
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15563038#comment-15563038
]
Gaoxiang Liu commented on SPARK-3577:
-
I find that the spill size metrics is already added in
https://github.com/apache/spark/commit/bb8098f203e6faddf2e1a04b03d62037e6c7#diff-1bd3dc38f6306e0a822f93d62c32b1d0,
and I have confirm in the UI.
Also, we notices that it's wield that the spill size is somehow not reported in
the reducer , but reported in the mapper.
Back to the previous question, for the spill time, if it's still relevant to
add, then I plan to work on it if there is no objections.
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
> Attachments: spill_size.jpg
>
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15562945#comment-15562945
]
Reynold Xin commented on SPARK-3577:
Actually instead of tracking spill time, it's more important to first report
spill data size.
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15562938#comment-15562938
]
Reynold Xin commented on SPARK-3577:
This is still relevant.
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15562925#comment-15562925
]
Gaoxiang Liu commented on SPARK-3577:
-
Hi [~kayousterhout],
Just want to make sure that this JIRA is still relevant, right ? Is there any
changes to the requirement ?
I am currently working on this one, so just want to make sure.
Thanks !
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15417929#comment-15417929
]
Kay Ousterhout commented on SPARK-3577:
---
I believe spill time will currently be displayed as part of the task runtime,
but not as part of scheduler delay.
The scheduler delay is calculated by looking at the difference between two
values:
(1) The time that the task was running on the executor
(2) The time from when the scheduler sent information about the task to the
executor (so the executor could run the task) until the scheduler received a
message that the task completed.
Scheduler delay is (2) - (1). Usually when it's high, it's because of queueing
delays in the scheduler that are either delaying the task getting sent to the
executor (e.g., because the scheduler has a long queue of other tasks that need
to be launched, or because tasks are large so take a while to send over the
network) or that are delaying the task completion message getting back to the
scheduler (which can happen when the rate of task launch is high -- greater
than 1K or so task launches / second).
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15417916#comment-15417916
]
Tzach Zohar commented on SPARK-3577:
Does this mean that currently, spill time will be displayed as part of the
*Scheduler Delay*?
Scheduler Delay is calculated pretty much as "everything that isn't
specifically measured" (see
[StagePage.getSchedulerDelay|https://github.com/apache/spark/blob/v2.0.0/core/src/main/scala/org/apache/spark/ui/jobs/StagePage.scala#L770]),
so I'm wondering if indeed it might include spill time if it's not included
anywhere else.
If so - this might explain long Scheduler Delay values which would be hard to
make sense of otherwise (which I think is what I'm seeing...).
Thanks
> Add task metric to report spill time
>
>
> Key: SPARK-3577
> URL: https://issues.apache.org/jira/browse/SPARK-3577
> Project: Spark
> Issue Type: Bug
> Components: Shuffle, Spark Core
>Affects Versions: 1.1.0
>Reporter: Kay Ousterhout
>Priority: Minor
>
> The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
> {{ExternalSorter}}. The write time recorded in those metrics is never used.
> We should probably add task metrics to report this spill time, since for
> shuffles, this would have previously been reported as part of shuffle write
> time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14628646#comment-14628646
]
Tom Hubregtsen commented on SPARK-3577:
---
I could also use this metric
Add task metric to report spill time
Key: SPARK-3577
URL: https://issues.apache.org/jira/browse/SPARK-3577
Project: Spark
Issue Type: Bug
Components: Shuffle, Spark Core
Affects Versions: 1.1.0
Reporter: Kay Ousterhout
Assignee: Sandy Ryza
Priority: Minor
The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
{{ExternalSorter}}. The write time recorded in those metrics is never used.
We should probably add task metrics to report this spill time, since for
shuffles, this would have previously been reported as part of shuffle write
time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14578240#comment-14578240
]
Ming Chen commented on SPARK-3577:
--
Why have not the metric been added? I think this is rather important, it may
affect the results of the research work on this :
https://kayousterhout.github.io/trace-analysis/
Add task metric to report spill time
Key: SPARK-3577
URL: https://issues.apache.org/jira/browse/SPARK-3577
Project: Spark
Issue Type: Bug
Components: Shuffle, Spark Core
Affects Versions: 1.1.0
Reporter: Kay Ousterhout
Assignee: Sandy Ryza
Priority: Minor
The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
{{ExternalSorter}}. The write time recorded in those metrics is never used.
We should probably add task metrics to report this spill time, since for
shuffles, this would have previously been reported as part of shuffle write
time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[
https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14144412#comment-14144412
]
Apache Spark commented on SPARK-3577:
-
User 'sryza' has created a pull request for this issue:
https://github.com/apache/spark/pull/2504
Add task metric to report spill time
Key: SPARK-3577
URL: https://issues.apache.org/jira/browse/SPARK-3577
Project: Spark
Issue Type: Bug
Components: Spark Core
Affects Versions: 1.1.0
Reporter: Kay Ousterhout
Priority: Minor
The {{ExternalSorter}} passes its own {{ShuffleWriteMetrics}} into
{{ExternalSorter}}. The write time recorded in those metrics is never used.
We should probably add task metrics to report this spill time, since for
shuffles, this would have previously been reported as part of shuffle write
time (with the original hash-based sorter).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-3577) Add task metric to report spill time
[ https://issues.apache.org/jira/browse/SPARK-3577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14142524#comment-14142524 ] Sandy Ryza commented on SPARK-3577: --- No problem. Yeah, I agree that a spill time metric would be useful. Add task metric to report spill time Key: SPARK-3577 URL: https://issues.apache.org/jira/browse/SPARK-3577 Project: Spark Issue Type: Bug Components: Spark Core Affects Versions: 1.1.0 Reporter: Kay Ousterhout Priority: Minor The ExternalSorter passes its own ShuffleWriteMetrics into ExternalSorter. The write time recorded in those metrics is never used. We should probably add task metrics to report this spill time, since for shuffles, this would have previously been reported as part of shuffle write time (with the original hash-based sorter). -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
