[jira] [Commented] (YARN-3926) Extend the YARN resource model for easier resource-type management and profiles

[ https://issues.apache.org/jira/browse/YARN-3926?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15952056#comment-15952056 ] Zhankun Tang commented on YARN-3926: {quote} As mentioned above, the overrides will only be allowed for

[jira] [Commented] (YARN-6425) Move out FS state dump code out of method update()

[ https://issues.apache.org/jira/browse/YARN-6425?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15952050#comment-15952050 ] Vrushali C commented on YARN-6425: -- Where do you think is a good place to put the dump call? In the

[jira] [Commented] (YARN-6421) Build failure in Yarn-UI on ppc64le

[ https://issues.apache.org/jira/browse/YARN-6421?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15952040#comment-15952040 ] Sunil G commented on YARN-6421: --- Thanks [~Sonia] There is a potential issue here. frontend-maven-plugin 1.1

[jira] [Commented] (YARN-6414) ATSv2 tests fail due to guava version upgrade

[ https://issues.apache.org/jira/browse/YARN-6414?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15952036#comment-15952036 ] Vrushali C commented on YARN-6414: -- Hmm trunk is allowed to take in incompatible changes, so we need a

[jira] [Comment Edited] (YARN-6414) ATSv2 tests fail due to guava version upgrade

[ https://issues.apache.org/jira/browse/YARN-6414?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15952036#comment-15952036 ] Vrushali C edited comment on YARN-6414 at 4/1/17 5:22 AM: -- Hmm trunk is allowed to

[jira] [Commented] (YARN-6424) TimelineCollector is not stopped when an app finishes in RM

[ https://issues.apache.org/jira/browse/YARN-6424?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15952034#comment-15952034 ] Vrushali C commented on YARN-6424: -- Thanks for the jira and patch Varun! I am wondering if it should be

[jira] [Commented] (YARN-6363) Extending SLS: Synthetic Load Generator

[ https://issues.apache.org/jira/browse/YARN-6363?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15952005#comment-15952005 ] Carlo Curino commented on YARN-6363: It might be possible, but the case I was making is that the

[jira] [Commented] (YARN-6363) Extending SLS: Synthetic Load Generator

[ https://issues.apache.org/jira/browse/YARN-6363?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951992#comment-15951992 ] Wangda Tan commented on YARN-6363: -- [~curino], Agree with all except: bq. I think that might be an issue

[jira] [Commented] (YARN-6223) [Umbrella] Natively support GPU configuration/discovery/scheduling/isolation on YARN

[ https://issues.apache.org/jira/browse/YARN-6223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951989#comment-15951989 ] Wangda Tan commented on YARN-6223: -- [~tangzhankun], all great suggestions. >From what you mentioned,

[jira] [Commented] (YARN-6223) [Umbrella] Natively support GPU configuration/discovery/scheduling/isolation on YARN

[ https://issues.apache.org/jira/browse/YARN-6223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951985#comment-15951985 ] Wangda Tan commented on YARN-6223: -- [~grey], [~hex108] mentioned sharing one GPU to multiple applications

[jira] [Commented] (YARN-6223) [Umbrella] Natively support GPU configuration/discovery/scheduling/isolation on YARN

[ https://issues.apache.org/jira/browse/YARN-6223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951986#comment-15951986 ] Wangda Tan commented on YARN-6223: -- [~Ying Zhang] sure thing :), could you take the uploaded doc/poc patch

[jira] [Updated] (YARN-6223) [Umbrella] Natively support GPU configuration/discovery/scheduling/isolation on YARN

[ https://issues.apache.org/jira/browse/YARN-6223?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-6223: - Attachment: YARN-6223.Natively-support-GPU-on-YARN-v1.pdf YARN-6223.wip.1.patch Attached

[jira] [Comment Edited] (YARN-6223) [Umbrella] Natively support GPU configuration/discovery/scheduling/isolation on YARN

[ https://issues.apache.org/jira/browse/YARN-6223?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15950199#comment-15950199 ] Zhankun Tang edited comment on YARN-6223 at 4/1/17 3:23 AM: [~wangda], thanks

[jira] [Commented] (YARN-6302) Fail the node, if Linux Container Executor is not configured properly

[ https://issues.apache.org/jira/browse/YARN-6302?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951954#comment-15951954 ] Hadoop QA commented on YARN-6302: - | (/) *{color:green}+1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-5829) FS preemption should reserve a node before considering containers on it for preemption

[ https://issues.apache.org/jira/browse/YARN-5829?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951936#comment-15951936 ] Hadoop QA commented on YARN-5829: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Updated] (YARN-6368) Decommissioning an NM results in a -1 exit code

[ https://issues.apache.org/jira/browse/YARN-6368?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Miklos Szegedi updated YARN-6368: - Attachment: YARN-6368.003.patch > Decommissioning an NM results in a -1 exit code >

[jira] [Updated] (YARN-6302) Fail the node, if Linux Container Executor is not configured properly

[ https://issues.apache.org/jira/browse/YARN-6302?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Miklos Szegedi updated YARN-6302: - Attachment: YARN-6302.002.patch > Fail the node, if Linux Container Executor is not configured

[jira] [Commented] (YARN-6426) Compress ZK YARN keys to scale up (especially AppStateData

[ https://issues.apache.org/jira/browse/YARN-6426?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951889#comment-15951889 ] Hadoop QA commented on YARN-6426: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-6202) Configuration item Dispatcher.DISPATCHER_EXIT_ON_ERROR_KEY is disregarded

[ https://issues.apache.org/jira/browse/YARN-6202?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951887#comment-15951887 ] Yufei Gu commented on YARN-6202: You are right. No matter what default value is, this shouldn't be a

[jira] [Commented] (YARN-6344) Rethinking OFF_SWITCH locality in CapacityScheduler

[ https://issues.apache.org/jira/browse/YARN-6344?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951861#comment-15951861 ] Hadoop QA commented on YARN-6344: - | (/) *{color:green}+1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-6423) Queue metrics doesn't work for Fair Scheduler in SLS

[ https://issues.apache.org/jira/browse/YARN-6423?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951860#comment-15951860 ] Hadoop QA commented on YARN-6423: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Updated] (YARN-6426) Compress ZK YARN keys to scale up (especially AppStateData

[ https://issues.apache.org/jira/browse/YARN-6426?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Roni Burd updated YARN-6426: Attachment: zkcompression.patch > Compress ZK YARN keys to scale up (especially AppStateData >

[jira] [Commented] (YARN-6426) Compress ZK YARN keys to scale up (especially AppStateData

[ https://issues.apache.org/jira/browse/YARN-6426?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951854#comment-15951854 ] Roni Burd commented on YARN-6426: - I've added a patch. The compression goes from 1MB to 28K for example

[jira] [Updated] (YARN-5829) FS preemption should reserve a node before considering containers on it for preemption

[ https://issues.apache.org/jira/browse/YARN-5829?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Miklos Szegedi updated YARN-5829: - Attachment: YARN-5829.001.patch > FS preemption should reserve a node before considering

[jira] [Commented] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951845#comment-15951845 ] Arun Suresh commented on YARN-6406: --- Thanks for the review [~leftnoteasy], bq. Why changes of AppInfo

[jira] [Created] (YARN-6426) Compress ZK YARN keys to scale up (especially AppStateData

Roni Burd created YARN-6426: --- Summary: Compress ZK YARN keys to scale up (especially AppStateData Key: YARN-6426 URL: https://issues.apache.org/jira/browse/YARN-6426 Project: Hadoop YARN Issue

[jira] [Commented] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951837#comment-15951837 ] Hadoop QA commented on YARN-5995: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-6316) Provide help information and documentation for TimelineSchemaCreator

[ https://issues.apache.org/jira/browse/YARN-6316?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951836#comment-15951836 ] Haibo Chen commented on YARN-6316: -- bq. I am also wondering about providing a set of table creation

[jira] [Commented] (YARN-5067) Support specifying resources for AM containers in SLS

[ https://issues.apache.org/jira/browse/YARN-5067?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951834#comment-15951834 ] Yufei Gu commented on YARN-5067: Hi [~wangda], are you still working on this? Do you mind if I take this?

[jira] [Commented] (YARN-6316) Provide help information and documentation for TimelineSchemaCreator

[ https://issues.apache.org/jira/browse/YARN-6316?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951833#comment-15951833 ] Haibo Chen commented on YARN-6316: -- Looked into this a little bit. I was thinking of have two subcommands,

[jira] [Commented] (YARN-6289) Fail to achieve data locality when runing MapReduce and Spark on HDFS

[ https://issues.apache.org/jira/browse/YARN-6289?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951829#comment-15951829 ] Wangda Tan commented on YARN-6289: -- [~Huangkx6810], I think this issue is caused by YARN-6344. Could you

[jira] [Commented] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951819#comment-15951819 ] Hadoop QA commented on YARN-6406: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-6423) Queue metrics doesn't work for Fair Scheduler in SLS

[ https://issues.apache.org/jira/browse/YARN-6423?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951815#comment-15951815 ] Yufei Gu commented on YARN-6423: Uploaded patch v1. # The queue metrics issue is due to queue name

[jira] [Updated] (YARN-6423) Queue metrics doesn't work for Fair Scheduler in SLS

[ https://issues.apache.org/jira/browse/YARN-6423?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yufei Gu updated YARN-6423: --- Attachment: YARN-6423.001.patch > Queue metrics doesn't work for Fair Scheduler in SLS >

[jira] [Updated] (YARN-6423) Queue metrics doesn't work for Fair Scheduler in SLS

[ https://issues.apache.org/jira/browse/YARN-6423?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yufei Gu updated YARN-6423: --- Description: Queue allocated memory and vcores always be 0. (was: Queue allocated memory # always be 0.) >

[jira] [Commented] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951798#comment-15951798 ] Wangda Tan commented on YARN-6406: -- Thanks [~asuresh] for working on the fix, my comments: 1) Why

[jira] [Updated] (YARN-6344) Rethinking OFF_SWITCH locality in CapacityScheduler

[ https://issues.apache.org/jira/browse/YARN-6344?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Konstantinos Karanasos updated YARN-6344: - Attachment: YARN-6344.003.patch Fixing a couple more checkstyles and test cases.

[jira] [Updated] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangyubiao updated YARN-5995: -- Attachment: YARN-5995.0004.patch fix findbugs and some checkstyle. YARN-5995.0004.patch is commit >

[jira] [Updated] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Arun Suresh updated YARN-6406: -- Affects Version/s: 2.8.0 2.7.3 3.0.0-alpha2 > Garbage

[jira] [Updated] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Arun Suresh updated YARN-6406: -- Attachment: YARN-6406.001.patch Attaching initial patch. * Moved the schedulerKeys dataStructure to a

[jira] [Commented] (YARN-5301) NM mount cpu cgroups failed on some systems

[ https://issues.apache.org/jira/browse/YARN-5301?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951734#comment-15951734 ] Hadoop QA commented on YARN-5301: - | (/) *{color:green}+1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Updated] (YARN-5301) NM mount cpu cgroups failed on some systems

[ https://issues.apache.org/jira/browse/YARN-5301?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Miklos Szegedi updated YARN-5301: - Attachment: YARN-5301.002.patch > NM mount cpu cgroups failed on some systems >

[jira] [Commented] (YARN-5301) NM mount cpu cgroups failed on some systems

[ https://issues.apache.org/jira/browse/YARN-5301?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951701#comment-15951701 ] Miklos Szegedi commented on YARN-5301: -- Thank you, [~templedf] for the review. Most of the comments

[jira] [Created] (YARN-6425) Move out FS state dump code out of method update()

Yufei Gu created YARN-6425: -- Summary: Move out FS state dump code out of method update() Key: YARN-6425 URL: https://issues.apache.org/jira/browse/YARN-6425 Project: Hadoop YARN Issue Type: Bug

[jira] [Commented] (YARN-6344) Rethinking OFF_SWITCH locality in CapacityScheduler

[ https://issues.apache.org/jira/browse/YARN-6344?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951663#comment-15951663 ] Hadoop QA commented on YARN-6344: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951658#comment-15951658 ] Hadoop QA commented on YARN-5995: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Comment Edited] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951609#comment-15951609 ] zhangyubiao edited comment on YARN-5995 at 3/31/17 8:49 PM: Sorry for late

[jira] [Commented] (YARN-6424) TimelineCollector is not stopped when an app finishes in RM

[ https://issues.apache.org/jira/browse/YARN-6424?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951621#comment-15951621 ] Hadoop QA commented on YARN-6424: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951609#comment-15951609 ] zhangyubiao commented on YARN-5995: --- Sorry for late response. > Add RMStateStore metrics to monitor all

[jira] [Updated] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangyubiao updated YARN-5995: -- Attachment: YARN-5995.0003.patch > Add RMStateStore metrics to monitor all

[jira] [Updated] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangyubiao updated YARN-5995: -- Attachment: (was: YARN-5995.003.patch) > Add RMStateStore metrics to monitor all

[jira] [Updated] (YARN-5995) Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition performance

[ https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] zhangyubiao updated YARN-5995: -- Attachment: YARN-5995.003.patch > Add RMStateStore metrics to monitor all

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951572#comment-15951572 ] Wangda Tan commented on YARN-2113: -- [~jlowe], thanks for the explanations, to me it makes sense to have

[jira] [Commented] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951542#comment-15951542 ] Jason Lowe commented on YARN-6406: -- Yep, the refcount was only added because of the possibility of the two

[jira] [Commented] (YARN-5892) Capacity Scheduler: Support user-specific minimum user limit percent

[ https://issues.apache.org/jira/browse/YARN-5892?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951539#comment-15951539 ] Wangda Tan commented on YARN-5892: -- Thanks [~eepayne] to update the patch. Several comments: 1) For User

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951538#comment-15951538 ] Jason Lowe commented on YARN-2113: -- The answer is no to both questions. Both users are below the 100%

[jira] [Commented] (YARN-6363) Extending SLS: Synthetic Load Generator

[ https://issues.apache.org/jira/browse/YARN-6363?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951534#comment-15951534 ] Carlo Curino commented on YARN-6363: Thanks [~wangda] for reviewing. Answering your questions: 1) ACK

[jira] [Updated] (YARN-6424) TimelineCollector is not stopped when an app finishes in RM

[ https://issues.apache.org/jira/browse/YARN-6424?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Varun Saxena updated YARN-6424: --- Attachment: YARN-6424.01.patch > TimelineCollector is not stopped when an app finishes in RM >

[jira] [Commented] (YARN-6344) Rethinking OFF_SWITCH locality in CapacityScheduler

[ https://issues.apache.org/jira/browse/YARN-6344?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951528#comment-15951528 ] Konstantinos Karanasos commented on YARN-6344: -- I just uploaded a new version in which I

[jira] [Commented] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951526#comment-15951526 ] Arun Suresh commented on YARN-6406: --- bq. Regarding to this, I don't think we need the #ref any more,

[jira] [Created] (YARN-6424) TimelineCollector is not stopped when an app finishes in RM

Varun Saxena created YARN-6424: -- Summary: TimelineCollector is not stopped when an app finishes in RM Key: YARN-6424 URL: https://issues.apache.org/jira/browse/YARN-6424 Project: Hadoop YARN

[jira] [Updated] (YARN-6344) Rethinking OFF_SWITCH locality in CapacityScheduler

[ https://issues.apache.org/jira/browse/YARN-6344?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Konstantinos Karanasos updated YARN-6344: - Attachment: YARN-6344.002.patch Uploading new version of the patch. I applied

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951489#comment-15951489 ] Wangda Tan commented on YARN-2113: -- [~jlowe], I agree with some of your point, for example, app priority

[jira] [Commented] (YARN-6265) yarn.resourcemanager.fail-fast is used inconsistently

[ https://issues.apache.org/jira/browse/YARN-6265?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951458#comment-15951458 ] Junping Du commented on YARN-6265: -- The patch looks mostly fine. About the message, actually, this new

[jira] [Commented] (YARN-6418) Reduce Resource object creation and overhead in Capacity scheduler inner loop

[ https://issues.apache.org/jira/browse/YARN-6418?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951451#comment-15951451 ] Wangda Tan commented on YARN-6418: -- [~roniburd]/[~asuresh]. I have done some similar works in YARN-6245

[jira] [Commented] (YARN-6245) Add FinalResource object to reduce overhead of Resource class instancing

[ https://issues.apache.org/jira/browse/YARN-6245?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951449#comment-15951449 ] Wangda Tan commented on YARN-6245: -- [~kasha], Sorry for the long delay of response, I missed your

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951445#comment-15951445 ] Jason Lowe commented on YARN-2113: -- bq. once user submit app3 with highest priority, it should get

[jira] [Commented] (YARN-6377) NMTimelinePublisher#serviceStop does not stop timeline clients

[ https://issues.apache.org/jira/browse/YARN-6377?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951434#comment-15951434 ] Varun Saxena commented on YARN-6377: By the way, if I am reading the code correctly, we do not stop

[jira] [Created] (YARN-6423) Queue metrics doesn't work for Fair Scheduler in SLS

Yufei Gu created YARN-6423: -- Summary: Queue metrics doesn't work for Fair Scheduler in SLS Key: YARN-6423 URL: https://issues.apache.org/jira/browse/YARN-6423 Project: Hadoop YARN Issue Type:

[jira] [Commented] (YARN-6377) NMTimelinePublisher#serviceStop does not stop timeline clients

[ https://issues.apache.org/jira/browse/YARN-6377?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951430#comment-15951430 ] Varun Saxena commented on YARN-6377: Sorry for repeating. Had missed Haibo's comment. >

[jira] [Commented] (YARN-6406) Garbage Collect unused SchedulerRequestKeys

[ https://issues.apache.org/jira/browse/YARN-6406?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951418#comment-15951418 ] Wangda Tan commented on YARN-6406: -- Nice catch [~arun.sur...@gmail.com]. [~asuresh]/[~jlowe], I totally

[jira] [Commented] (YARN-6265) yarn.resourcemanager.fail-fast is used inconsistently

[ https://issues.apache.org/jira/browse/YARN-6265?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951408#comment-15951408 ] Junping Du commented on YARN-6265: -- Sorry for coming late on this. I will review it today! >

[jira] [Commented] (YARN-6363) Extending SLS: Synthetic Load Generator

[ https://issues.apache.org/jira/browse/YARN-6363?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951406#comment-15951406 ] Wangda Tan commented on YARN-6363: -- [~curino], thanks for adding this feature, it will be very helpful and

[jira] [Commented] (YARN-6265) yarn.resourcemanager.fail-fast is used inconsistently

[ https://issues.apache.org/jira/browse/YARN-6265?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951399#comment-15951399 ] Daniel Templeton commented on YARN-6265: Overall seems fine to me. The message, "Should

[jira] [Commented] (YARN-6265) yarn.resourcemanager.fail-fast is used inconsistently

[ https://issues.apache.org/jira/browse/YARN-6265?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951397#comment-15951397 ] Daniel Templeton commented on YARN-6265: [~djp], could you take a look? I'm not comfortable making

[jira] [Commented] (YARN-6354) LeveldbRMStateStore can parse invalid keys when recovering reservations

[ https://issues.apache.org/jira/browse/YARN-6354?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951394#comment-15951394 ] Hudson commented on YARN-6354: -- SUCCESS: Integrated in Jenkins build Hadoop-trunk-Commit #11509 (See

[jira] [Commented] (YARN-6377) NMTimelinePublisher#serviceStop does not stop timeline clients

[ https://issues.apache.org/jira/browse/YARN-6377?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951377#comment-15951377 ] Varun Saxena commented on YARN-6377: [~vrushalic] bq. I am looking through the code and trying to

[jira] [Commented] (YARN-6354) LeveldbRMStateStore can parse invalid keys when recovering reservations

[ https://issues.apache.org/jira/browse/YARN-6354?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951352#comment-15951352 ] Eric Payne commented on YARN-6354: -- +1. Thanks [~jlowe]. I will merge to trunk, branch-2, and branch-2.8.

[jira] [Commented] (YARN-6377) NMTimelinePublisher#serviceStop does not stop timeline clients

[ https://issues.apache.org/jira/browse/YARN-6377?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951320#comment-15951320 ] Haibo Chen commented on YARN-6377: -- bq. do we have any timeline service related stop on the RM side? Not

[jira] [Commented] (YARN-6403) Invalid local resource request can raise NPE and make NM exit

[ https://issues.apache.org/jira/browse/YARN-6403?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951287#comment-15951287 ] Hadoop QA commented on YARN-6403: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951268#comment-15951268 ] Hadoop QA commented on YARN-2113: - | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951260#comment-15951260 ] Wangda Tan commented on YARN-2113: -- [~eepayne], bq. With the latest patch, there is still a use case in

[jira] [Commented] (YARN-6411) Clean up the overwrite of createDispatcher() in subclass of MockRM

[ https://issues.apache.org/jira/browse/YARN-6411?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951256#comment-15951256 ] Yufei Gu commented on YARN-6411: Thanks [~jlowe] for the review and commit! > Clean up the overwrite of

[jira] [Commented] (YARN-6377) NMTimelinePublisher#serviceStop does not stop timeline clients

[ https://issues.apache.org/jira/browse/YARN-6377?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951245#comment-15951245 ] Haibo Chen commented on YARN-6377: -- Thanks [~varun_saxena] and [~vrushalic] for the reviews >

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951244#comment-15951244 ] Wangda Tan commented on YARN-2113: -- Thanks [~sunilg], 1) validateOutSameAppPriorityFromDemand: Major:

[jira] [Updated] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated YARN-2113: - Attachment: TestNoIntraQueuePreemptionIfBelowUserLimitAndDifferentPrioritiesWithExtraUsers.txt > Add

[jira] [Comment Edited] (YARN-6375) App level aggregation should not consider metric values reported in the previous aggregation cycle

[ https://issues.apache.org/jira/browse/YARN-6375?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951228#comment-15951228 ] Varun Saxena edited comment on YARN-6375 at 3/31/17 4:37 PM: - Thanks

[jira] [Commented] (YARN-6377) NMTimelinePublisher#serviceStop does not stop timeline clients

[ https://issues.apache.org/jira/browse/YARN-6377?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951229#comment-15951229 ] Varun Saxena commented on YARN-6377: +1 Will commit it later today > NMTimelinePublisher#serviceStop

[jira] [Commented] (YARN-6375) App level aggregation should not consider metric values reported in the previous aggregation cycle

[ https://issues.apache.org/jira/browse/YARN-6375?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951228#comment-15951228 ] Varun Saxena commented on YARN-6375: Thanks [~vrushalic] for the comments. I was primarily going by the

[jira] [Commented] (YARN-2113) Add cross-user preemption within CapacityScheduler's leaf-queue

[ https://issues.apache.org/jira/browse/YARN-2113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951222#comment-15951222 ] Eric Payne commented on YARN-2113: -- Thanks [~sunilg] for the updated patch. It looks good in gneral, but I

[jira] [Commented] (YARN-6414) ATSv2 tests fail due to guava version upgrade

[ https://issues.apache.org/jira/browse/YARN-6414?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951200#comment-15951200 ] Haibo Chen commented on YARN-6414: -- bq. I am wondering about the hbase client modules that might be using

[jira] [Commented] (YARN-6403) Invalid local resource request can raise NPE and make NM exit

[ https://issues.apache.org/jira/browse/YARN-6403?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951182#comment-15951182 ] Jason Lowe commented on YARN-6403: -- Thanks for updating the patch! bq.

[jira] [Commented] (YARN-6411) Clean up the overwrite of createDispatcher() in subclass of MockRM

[ https://issues.apache.org/jira/browse/YARN-6411?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951132#comment-15951132 ] Hudson commented on YARN-6411: -- SUCCESS: Integrated in Jenkins build Hadoop-trunk-Commit #11508 (See

[jira] [Commented] (YARN-6366) Refactor the NodeManager DeletionService to support additional DeletionTask types.

[ https://issues.apache.org/jira/browse/YARN-6366?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951115#comment-15951115 ] Hadoop QA commented on YARN-6366: - | (/) *{color:green}+1 overall{color}* | \\ \\ || Vote || Subsystem ||

[jira] [Commented] (YARN-5952) Create REST API for changing YARN scheduler configurations

[ https://issues.apache.org/jira/browse/YARN-5952?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951103#comment-15951103 ] Wangda Tan commented on YARN-5952: -- Looks good, thanks [~jhung], will commit shortly. > Create REST API

[jira] [Commented] (YARN-6411) Clean up the overwrite of createDispatcher() in subclass of MockRM

[ https://issues.apache.org/jira/browse/YARN-6411?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15951087#comment-15951087 ] Jason Lowe commented on YARN-6411: -- +1 lgtm. Committing this. > Clean up the overwrite of

[jira] [Updated] (YARN-6366) Refactor the NodeManager DeletionService to support additional DeletionTask types.

[ https://issues.apache.org/jira/browse/YARN-6366?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Shane Kumpf updated YARN-6366: -- Attachment: YARN-6366.001.patch > Refactor the NodeManager DeletionService to support additional

[jira] [Updated] (YARN-6422) Service REST API should have a way to specify YARN related params

[ https://issues.apache.org/jira/browse/YARN-6422?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jian He updated YARN-6422: -- Description: Currently, the service REST API doesn't have a way to specify the YARN related params (i.e. all

[jira] [Created] (YARN-6422) Service REST API should have a way to specify YARN related params

Jian He created YARN-6422: - Summary: Service REST API should have a way to specify YARN related params Key: YARN-6422 URL: https://issues.apache.org/jira/browse/YARN-6422 Project: Hadoop YARN Issue

[jira] [Commented] (YARN-5150) [YARN-3368] Add a sunburst chart view for queues/applications resource usage to new YARN UI

[ https://issues.apache.org/jira/browse/YARN-5150?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15950932#comment-15950932 ] Sunil G commented on YARN-5150: --- Thanks [~GergelyNovak]. It's really looking great. Very useful and good UX

  1   2   >