[SPARK-20483] Mesos Coarse mode may starve other Mesos frameworks #17786
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Set max cores to a multiple of the smallestExecutorSize
|
Jenkins, add to whitelist. |
|
Jenkins, ok to test. |
|
Test build #76234 has finished for PR 17786 at commit
|
|
LGTM. Merged into master and branch 2.2. Thanks. |
asfgit
pushed a commit
that referenced
this pull request
Apr 27, 2017
## What changes were proposed in this pull request? Set maxCores to be a multiple of the smallest executor that can be launched. This ensures that we correctly detect the condition where no more executors will be launched when spark.cores.max is not a multiple of spark.executor.cores ## How was this patch tested? This was manually tested with other sample frameworks measuring their incoming offers to determine if starvation would occur. dbtsai mgummelt Author: Davis Shepherd <[email protected]> Closes #17786 from dgshep/fix_mesos_max_cores. (cherry picked from commit 7633933) Signed-off-by: DB Tsai <[email protected]>
asfgit
pushed a commit
that referenced
this pull request
Apr 27, 2017
…s frameworks ## What changes were proposed in this pull request? Add test case for scenarios where executor.cores is set as a (non)divisor of spark.cores.max This tests the change in #17786 ## How was this patch tested? Ran the existing test suite with the new tests dbtsai Author: Davis Shepherd <[email protected]> Closes #17788 from dgshep/add_mesos_test. (cherry picked from commit 039e32c) Signed-off-by: DB Tsai <[email protected]>
ghost
pushed a commit
to dbtsai/spark
that referenced
this pull request
Apr 27, 2017
…s frameworks ## What changes were proposed in this pull request? Add test case for scenarios where executor.cores is set as a (non)divisor of spark.cores.max This tests the change in apache#17786 ## How was this patch tested? Ran the existing test suite with the new tests dbtsai Author: Davis Shepherd <[email protected]> Closes apache#17788 from dgshep/add_mesos_test.
|
Tests are added in a followup PR. #17788 |
dbtsai
reviewed
Apr 27, 2017
| private val maxCores = maxCoresOption.getOrElse(Int.MaxValue) | ||
| private val maxCores = { | ||
| val cores = maxCoresOption.getOrElse(Int.MaxValue) | ||
| // Set maxCores to a multiple of smallest executor we can launch |
There was a problem hiding this comment.
Should we have a log here to let users know?
|
I agree with @mgummelt, maxCores should have reflected user config option. |
|
Fair point. This felt like a succinct way to handle this corner case, but if it makes sense to harden the offer refusal code instead, I can update. |
|
@mgummelt We tested this in our production env, and it solves our issue. Since it seems to be a trivial change, I made my judgement. Gonna wait for more feedback. Thanks. |
jzhuge
pushed a commit
to jzhuge/spark
that referenced
this pull request
Aug 20, 2018
Set maxCores to be a multiple of the smallest executor that can be launched. This ensures that we correctly detect the condition where no more executors will be launched when spark.cores.max is not a multiple of spark.executor.cores This was manually tested with other sample frameworks measuring their incoming offers to determine if starvation would occur. dbtsai mgummelt Author: Davis Shepherd <[email protected]> Closes apache#17786 from dgshep/fix_mesos_max_cores.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What changes were proposed in this pull request?
Set maxCores to be a multiple of the smallest executor that can be launched. This ensures that we correctly detect the condition where no more executors will be launched when spark.cores.max is not a multiple of spark.executor.cores
How was this patch tested?
This was manually tested with other sample frameworks measuring their incoming offers to determine if starvation would occur.
@dbtsai @mgummelt