[jira] [Commented] (YARN-2882) Add ExecutionType to denote if a container execution is GUARANTEED or QUEUEABLE

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15057717#comment-15057717 ] Karthik Kambatla commented on YARN-2882: In YARN-1011, we plan to allocate resource

[jira] [Commented] (YARN-110) AM releases too many containers due to the protocol

[ https://issues.apache.org/jira/browse/YARN-110?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15057747#comment-15057747 ] Karthik Kambatla commented on YARN-110: --- bq. but it looks like this increases latencie

[jira] [Commented] (YARN-4293) ResourceUtilization should be a part of yarn node CLI

[ https://issues.apache.org/jira/browse/YARN-4293?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15057758#comment-15057758 ] Karthik Kambatla commented on YARN-4293: Just saw the ping here (was out on vacatio

[jira] [Commented] (YARN-4438) Implement RM leader election with curator

[ https://issues.apache.org/jira/browse/YARN-4438?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15059248#comment-15059248 ] Karthik Kambatla commented on YARN-4438: bq. I'll make the change accordingly. Not

[jira] [Updated] (YARN-4462) Scheduler should prevent certain application from being preempted

[ https://issues.apache.org/jira/browse/YARN-4462?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4462: --- Component/s: (was: scheduler) fairscheduler > Scheduler should prevent cer

[jira] [Updated] (YARN-4462) FairScheduler: Disallow preemption from a queue

[ https://issues.apache.org/jira/browse/YARN-4462?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4462: --- Summary: FairScheduler: Disallow preemption from a queue (was: Scheduler should prevent certai

[jira] [Assigned] (YARN-4462) FairScheduler: Disallow preemption from a queue

[ https://issues.apache.org/jira/browse/YARN-4462?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla reassigned YARN-4462: -- Assignee: Karthik Kambatla > FairScheduler: Disallow preemption from a queue > -

[jira] [Commented] (YARN-4462) FairScheduler: Disallow preemption from a queue

[ https://issues.apache.org/jira/browse/YARN-4462?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15060909#comment-15060909 ] Karthik Kambatla commented on YARN-4462: Today, FairScheduler allows disabling pree

[jira] [Updated] (YARN-4464) default value of yarn.resourcemanager.state-store.max-completed-applications should lower.

[ https://issues.apache.org/jira/browse/YARN-4464?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4464: --- Target Version/s: 3.0.0 Priority: Blocker (was: Major) Hadoop Flags: Incomp

[jira] [Assigned] (YARN-4462) FairScheduler: Disallow preemption from a queue

[ https://issues.apache.org/jira/browse/YARN-4462?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla reassigned YARN-4462: -- Assignee: Tao Jie (was: Karthik Kambatla) All yours, [~Tao Jie]. > FairScheduler: Dis

[jira] [Commented] (YARN-914) (Umbrella) Support graceful decommission of nodemanager

[ https://issues.apache.org/jira/browse/YARN-914?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065119#comment-15065119 ] Karthik Kambatla commented on YARN-914: --- bq. On the other hand, there are additional d

[jira] [Commented] (YARN-110) AM releases too many containers due to the protocol

[ https://issues.apache.org/jira/browse/YARN-110?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065236#comment-15065236 ] Karthik Kambatla commented on YARN-110: --- Got it. See the value in fixing it. Proposals

[jira] [Commented] (YARN-4032) Corrupted state from a previous version can still cause RM to fail with NPE due to same reasons as YARN-2834

[ https://issues.apache.org/jira/browse/YARN-4032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065249#comment-15065249 ] Karthik Kambatla commented on YARN-4032: [~jianhe] - are you working on this? If no

[jira] [Created] (YARN-4485) Capture per-application and per-queue container allocation latency

Karthik Kambatla created YARN-4485: -- Summary: Capture per-application and per-queue container allocation latency Key: YARN-4485 URL: https://issues.apache.org/jira/browse/YARN-4485 Project: Hadoop YA

[jira] [Commented] (YARN-4485) Capture per-application and per-queue container allocation latency

[ https://issues.apache.org/jira/browse/YARN-4485?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065253#comment-15065253 ] Karthik Kambatla commented on YARN-4485: One potential approach is to add requestTi

[jira] [Created] (YARN-4486) Add requestTime to ResourceRequest

Karthik Kambatla created YARN-4486: -- Summary: Add requestTime to ResourceRequest Key: YARN-4486 URL: https://issues.apache.org/jira/browse/YARN-4486 Project: Hadoop YARN Issue Type: Sub-task

[jira] [Created] (YARN-4487) FairScheduler: Compute per-container allocation latency and roll up to get per-application and per-queue

Karthik Kambatla created YARN-4487: -- Summary: FairScheduler: Compute per-container allocation latency and roll up to get per-application and per-queue Key: YARN-4487 URL: https://issues.apache.org/jira/browse/YAR

[jira] [Created] (YARN-4488) CapacityScheduler: Compute per-container allocation latency and roll up to get per-application and per-queue

Karthik Kambatla created YARN-4488: -- Summary: CapacityScheduler: Compute per-container allocation latency and roll up to get per-application and per-queue Key: YARN-4488 URL: https://issues.apache.org/jira/browse

[jira] [Updated] (YARN-4485) [Umbrella] Capture per-application and per-queue container allocation latency

[ https://issues.apache.org/jira/browse/YARN-4485?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4485: --- Summary: [Umbrella] Capture per-application and per-queue container allocation latency (was: C

[jira] [Assigned] (YARN-4485) Capture per-application and per-queue container allocation latency

[ https://issues.apache.org/jira/browse/YARN-4485?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla reassigned YARN-4485: -- Assignee: (was: Karthik Kambatla) Leaving the umbrella JIRA unassigned. > Capture

[jira] [Updated] (YARN-2962) ZKRMStateStore: Limit the number of znodes under a znode

[ https://issues.apache.org/jira/browse/YARN-2962?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-2962: --- Hadoop Flags: Incompatible change > ZKRMStateStore: Limit the number of znodes under a znode >

[jira] [Commented] (YARN-2882) Add ExecutionType to denote if a container execution is GUARANTEED or QUEUEABLE

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065547#comment-15065547 ] Karthik Kambatla commented on YARN-2882: Synced up with [~asuresh], [~kkaranasos] a

[jira] [Commented] (YARN-4478) [Umbrella] : Track all the Test failures in YARN

[ https://issues.apache.org/jira/browse/YARN-4478?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065559#comment-15065559 ] Karthik Kambatla commented on YARN-4478: I am fine with using components too. > [

[jira] [Commented] (YARN-4478) [Umbrella] : Track all the Test failures in YARN

[ https://issues.apache.org/jira/browse/YARN-4478?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065558#comment-15065558 ] Karthik Kambatla commented on YARN-4478: We ll likely always have failing unit test

[jira] [Commented] (YARN-1856) cgroups based memory monitoring for containers

[ https://issues.apache.org/jira/browse/YARN-1856?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15065570#comment-15065570 ] Karthik Kambatla commented on YARN-1856: Thanks [~vvasudev] for working on this, [~

[jira] [Commented] (YARN-4438) Implement RM leader election with curator

[ https://issues.apache.org/jira/browse/YARN-4438?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15069202#comment-15069202 ] Karthik Kambatla commented on YARN-4438: bq. And because ZKRMStateStore is currentl

[jira] [Commented] (YARN-4353) Provide short circuit user group mapping for NM/AM

[ https://issues.apache.org/jira/browse/YARN-4353?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15070358#comment-15070358 ] Karthik Kambatla commented on YARN-4353: bq. If secure LDAP is configured for group

[jira] [Commented] (YARN-4156) TestAMRestart#testAMBlacklistPreventsRestartOnSameNode assumes CapacityScheduler

[ https://issues.apache.org/jira/browse/YARN-4156?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15070387#comment-15070387 ] Karthik Kambatla commented on YARN-4156: +1 > TestAMRestart#testAMBlacklistPrevent

[jira] [Commented] (YARN-1856) cgroups based memory monitoring for containers

[ https://issues.apache.org/jira/browse/YARN-1856?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15071322#comment-15071322 ] Karthik Kambatla commented on YARN-1856: bq. Ideally oom_control, swappiness would

[jira] [Updated] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-1011: --- Attachment: yarn-1011-design-v0.pdf > [Umbrella] Schedule containers based on utilization of cu

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15071335#comment-15071335 ] Karthik Kambatla commented on YARN-1011: Just put my thoughts in a design doc here.

[jira] [Comment Edited] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15071335#comment-15071335 ] Karthik Kambatla edited comment on YARN-1011 at 12/25/15 2:45 AM: ---

[jira] [Updated] (YARN-2882) Add ExecutionType to denote if a container execution is GUARANTEED or OPPORTUNISTIC

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-2882: --- Component/s: (was: resourcemanager) > Add ExecutionType to denote if a container execution

[jira] [Updated] (YARN-2882) Add ExecutionType to denote if a container execution is GUARANTEED or OPPORTUNISTIC

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-2882: --- Issue Type: New Feature (was: Sub-task) Parent: (was: YARN-2877) > Add ExecutionTy

[jira] [Commented] (YARN-4335) Allow ResourceRequests to specify ExecutionType of a request ask

[ https://issues.apache.org/jira/browse/YARN-4335?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15071740#comment-15071740 ] Karthik Kambatla commented on YARN-4335: My impression from the offline conversatio

[jira] [Commented] (YARN-2882) Add ExecutionType to denote if a container execution is GUARANTEED or OPPORTUNISTIC

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15071750#comment-15071750 ] Karthik Kambatla commented on YARN-2882: [~asuresh], [~leftnoteasy] - We should pro

[jira] [Created] (YARN-4509) Promote containers from OPPORTUNISTIC to GUARANTEED

Karthik Kambatla created YARN-4509: -- Summary: Promote containers from OPPORTUNISTIC to GUARANTEED Key: YARN-4509 URL: https://issues.apache.org/jira/browse/YARN-4509 Project: Hadoop YARN Iss

[jira] [Commented] (YARN-2882) Add ExecutionType to denote if a container execution is GUARANTEED or OPPORTUNISTIC

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15071759#comment-15071759 ] Karthik Kambatla commented on YARN-2882: bq. Only the RM can approve the promotion

[jira] [Commented] (YARN-4509) Promote containers from OPPORTUNISTIC to GUARANTEED

[ https://issues.apache.org/jira/browse/YARN-4509?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15071765#comment-15071765 ] Karthik Kambatla commented on YARN-4509: In an offline discussion with [~asuresh],

[jira] [Commented] (YARN-2882) Add ExecutionType to denote if a container execution is GUARANTEED or OPPORTUNISTIC

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072036#comment-15072036 ] Karthik Kambatla commented on YARN-2882: Thanks for picking this up, [~elgoiri]. Ho

[jira] [Updated] (YARN-2882) Add an OPPORTUNISTIC ExecutionType

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-2882: --- Summary: Add an OPPORTUNISTIC ExecutionType (was: Add ExecutionType to denote if a container e

[jira] [Commented] (YARN-2882) Add an OPPORTUNISTIC ExecutionType

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072037#comment-15072037 ] Karthik Kambatla commented on YARN-2882: Just committed this to trunk. The only unc

[jira] [Updated] (YARN-1014) Ensure OOM Killer kills OPPORTUNISTIC containers before GUARANTEED containers

[ https://issues.apache.org/jira/browse/YARN-1014?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-1014: --- Summary: Ensure OOM Killer kills OPPORTUNISTIC containers before GUARANTEED containers (was: E

[jira] [Assigned] (YARN-1014) Ensure OOM Killer kills OPPORTUNISTIC containers before GUARANTEED containers

[ https://issues.apache.org/jira/browse/YARN-1014?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla reassigned YARN-1014: -- Assignee: Karthik Kambatla (was: Zhijie Shen) [~zjshen] - hope you don't mind me taking

[jira] [Updated] (YARN-1014) Ensure OOM Killer kills OPPORTUNISTIC containers before GUARANTEED containers

[ https://issues.apache.org/jira/browse/YARN-1014?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-1014: --- Description: YARN-2882 introduces the notion of OPPORTUNISTIC containers. These containers sho

[jira] [Updated] (YARN-1014) Configure OOM Killer to kill OPPORTUNISTIC containers first

[ https://issues.apache.org/jira/browse/YARN-1014?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-1014: --- Summary: Configure OOM Killer to kill OPPORTUNISTIC containers first (was: Ensure OOM Killer k

[jira] [Commented] (YARN-2882) Add an OPPORTUNISTIC ExecutionType

[ https://issues.apache.org/jira/browse/YARN-2882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072081#comment-15072081 ] Karthik Kambatla commented on YARN-2882: [~leftnoteasy] - my bad. Didn't realize an

[jira] [Updated] (YARN-1014) Configure OOM Killer to kill OPPORTUNISTIC containers first

[ https://issues.apache.org/jira/browse/YARN-1014?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-1014: --- Affects Version/s: 3.0.0 Target Version/s: 3.0.0 > Configure OOM Killer to kill OPPORTUNIS

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072223#comment-15072223 ] Karthik Kambatla commented on YARN-1011: bq. Would it make sense to make over-subsc

[jira] [Commented] (YARN-1014) Configure OOM Killer to kill OPPORTUNISTIC containers first

[ https://issues.apache.org/jira/browse/YARN-1014?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072224#comment-15072224 ] Karthik Kambatla commented on YARN-1014: [~asuresh], [~kkaranasos] - is this someth

[jira] [Created] (YARN-4512) Provide a knob to turn on over-subscription

Karthik Kambatla created YARN-4512: -- Summary: Provide a knob to turn on over-subscription Key: YARN-4512 URL: https://issues.apache.org/jira/browse/YARN-4512 Project: Hadoop YARN Issue Type:

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15072240#comment-15072240 ] Karthik Kambatla commented on YARN-1011: bq. For resource oversubscription enable/d

[jira] [Created] (YARN-4524) Cleanup AppSchedulingInfo

Karthik Kambatla created YARN-4524: -- Summary: Cleanup AppSchedulingInfo Key: YARN-4524 URL: https://issues.apache.org/jira/browse/YARN-4524 Project: Hadoop YARN Issue Type: Bug Com

[jira] [Commented] (YARN-4524) Cleanup AppSchedulingInfo

[ https://issues.apache.org/jira/browse/YARN-4524?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074236#comment-15074236 ] Karthik Kambatla commented on YARN-4524: I am taking a stab at it, and it appears s

[jira] [Updated] (YARN-4524) Cleanup AppSchedulingInfo

[ https://issues.apache.org/jira/browse/YARN-4524?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4524: --- Attachment: yarn-4524-1.patch A somewhat simpler version of AppSchedulingInfo - all methods fit

[jira] [Commented] (YARN-4524) Cleanup AppSchedulingInfo

[ https://issues.apache.org/jira/browse/YARN-4524?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074291#comment-15074291 ] Karthik Kambatla commented on YARN-4524: [~leftnoteasy] - with your recent node-lab

[jira] [Commented] (YARN-4257) Move scheduler validateConf method to AbstractYarnScheduler and make it protected

[ https://issues.apache.org/jira/browse/YARN-4257?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074393#comment-15074393 ] Karthik Kambatla commented on YARN-4257: [~leftnoteasy] - really appreciate the pin

[jira] [Commented] (YARN-4257) Move scheduler validateConf method to AbstractYarnScheduler and make it protected

[ https://issues.apache.org/jira/browse/YARN-4257?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074399#comment-15074399 ] Karthik Kambatla commented on YARN-4257: Just read the remainder of the description

[jira] [Updated] (YARN-4524) Cleanup AppSchedulingInfo

[ https://issues.apache.org/jira/browse/YARN-4524?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4524: --- Attachment: yarn-4524-2.patch Thanks Wangda. Good catch on the move() call, removing those line

[jira] [Created] (YARN-4526) Make SystemClock singleton so AppSchedulingInfo could use it

Karthik Kambatla created YARN-4526: -- Summary: Make SystemClock singleton so AppSchedulingInfo could use it Key: YARN-4526 URL: https://issues.apache.org/jira/browse/YARN-4526 Project: Hadoop YARN

[jira] [Updated] (YARN-4526) Make SystemClock singleton so AppSchedulingInfo could use it

[ https://issues.apache.org/jira/browse/YARN-4526?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4526: --- Attachment: yarn-4526-1.patch Uploading a patch that makes SystemClock a singleton. In addition

[jira] [Commented] (YARN-4524) Cleanup AppSchedulingInfo

[ https://issues.apache.org/jira/browse/YARN-4524?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074613#comment-15074613 ] Karthik Kambatla commented on YARN-4524: I think the test failures are unrelated, I

[jira] [Commented] (YARN-4524) Cleanup AppSchedulingInfo

[ https://issues.apache.org/jira/browse/YARN-4524?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074614#comment-15074614 ] Karthik Kambatla commented on YARN-4524: The checkstyle issues are marginal, and I

[jira] [Commented] (YARN-3870) Providing raw container request information for fine scheduling

[ https://issues.apache.org/jira/browse/YARN-3870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074658#comment-15074658 ] Karthik Kambatla commented on YARN-3870: +1 to improving the way we are storing Res

[jira] [Updated] (YARN-3607) Allow users to choose between failing the daemons vs failing the apps/containers

[ https://issues.apache.org/jira/browse/YARN-3607?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-3607: --- Assignee: (was: Karthik Kambatla) > Allow users to choose between failing the daemons vs fa

[jira] [Updated] (YARN-3607) Allow users to choose between failing the daemons vs failing the apps/containers

[ https://issues.apache.org/jira/browse/YARN-3607?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-3607: --- Target Version/s: 3.0.0 (was: 2.8.0) > Allow users to choose between failing the daemons vs fa

[jira] [Commented] (YARN-1014) Configure OOM Killer to kill OPPORTUNISTIC containers first

[ https://issues.apache.org/jira/browse/YARN-1014?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15075733#comment-15075733 ] Karthik Kambatla commented on YARN-1014: bq. We were actually planning on getting t

[jira] [Commented] (YARN-3870) Providing raw container request information for fine scheduling

[ https://issues.apache.org/jira/browse/YARN-3870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15075740#comment-15075740 ] Karthik Kambatla commented on YARN-3870: bq. I think this JIRA and YARN-4485 are di

[jira] [Commented] (YARN-4524) Cleanup AppSchedulingInfo

[ https://issues.apache.org/jira/browse/YARN-4524?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15075819#comment-15075819 ] Karthik Kambatla commented on YARN-4524: Thanks for the prompt review, Wangda. Appr

[jira] [Commented] (YARN-4526) Make SystemClock singleton so AppSchedulingInfo could use it

[ https://issues.apache.org/jira/browse/YARN-4526?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15075829#comment-15075829 ] Karthik Kambatla commented on YARN-4526: bq. YARN-4403 introduced MonotonicClock an

[jira] [Commented] (YARN-4526) Make SystemClock singleton so AppSchedulingInfo could use it

[ https://issues.apache.org/jira/browse/YARN-4526?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15075840#comment-15075840 ] Karthik Kambatla commented on YARN-4526: Follow up on Jenkins report: # Fixed check

[jira] [Updated] (YARN-4526) Make SystemClock singleton so AppSchedulingInfo could use it

[ https://issues.apache.org/jira/browse/YARN-4526?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4526: --- Attachment: yarn-4526-2.patch > Make SystemClock singleton so AppSchedulingInfo could use it >

[jira] [Commented] (YARN-3870) Providing raw container request information for fine scheduling

[ https://issues.apache.org/jira/browse/YARN-3870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15076629#comment-15076629 ] Karthik Kambatla commented on YARN-3870: bq. Karthik Kambatla, I am thinking whethe

[jira] [Assigned] (YARN-3870) Providing raw container request information for fine scheduling

[ https://issues.apache.org/jira/browse/YARN-3870?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla reassigned YARN-3870: -- Assignee: Karthik Kambatla > Providing raw container request information for fine schedu

[jira] [Commented] (YARN-397) RM Scheduler api enhancements

[ https://issues.apache.org/jira/browse/YARN-397?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15076741#comment-15076741 ] Karthik Kambatla commented on YARN-397: --- I believe the intent of this umbrella JIRA wa

[jira] [Commented] (YARN-3870) Providing raw container request information for fine scheduling

[ https://issues.apache.org/jira/browse/YARN-3870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15076743#comment-15076743 ] Karthik Kambatla commented on YARN-3870: Was fleshing this out further. The number

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15076749#comment-15076749 ] Karthik Kambatla commented on YARN-1011: Thanks for chiming in, [~bikassaha]. bq.

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15076750#comment-15076750 ] Karthik Kambatla commented on YARN-1011: Forgot to respond to one comment: bq. whe

[jira] [Commented] (YARN-3870) Providing raw container request information for fine scheduling

[ https://issues.apache.org/jira/browse/YARN-3870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15079334#comment-15079334 ] Karthik Kambatla commented on YARN-3870: [~leftnoteasy] - agree that YARN-4485 does

[jira] [Commented] (YARN-3870) Providing raw container request information for fine scheduling

[ https://issues.apache.org/jira/browse/YARN-3870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15080363#comment-15080363 ] Karthik Kambatla commented on YARN-3870: I am not saying we shouldn't do this. I am

[jira] [Updated] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-1011: --- Attachment: yarn-1011-design-v1.pdf > [Umbrella] Schedule containers based on utilization of cu

[jira] [Commented] (YARN-1856) cgroups based memory monitoring for containers

[ https://issues.apache.org/jira/browse/YARN-1856?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15081359#comment-15081359 ] Karthik Kambatla commented on YARN-1856: Was catching up on YARN-3 (the JIRA that a

[jira] [Commented] (YARN-3446) FairScheduler HeadRoom calculation should exclude nodes in the blacklist.

[ https://issues.apache.org/jira/browse/YARN-3446?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15081685#comment-15081685 ] Karthik Kambatla commented on YARN-3446: Sorry for not looking at this since the la

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15083223#comment-15083223 ] Karthik Kambatla commented on YARN-1011: We would run an opportunistic container on

[jira] [Comment Edited] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15083223#comment-15083223 ] Karthik Kambatla edited comment on YARN-1011 at 1/5/16 3:28 PM: -

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15083226#comment-15083226 ] Karthik Kambatla commented on YARN-1011: Since the plan is develop this on a branch

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15084543#comment-15084543 ] Karthik Kambatla commented on YARN-1011: Dropping a quick note here. (Traveling - w

[jira] [Created] (YARN-4551) Address the duplication between StatusUpdateWhenHealthy and StatusUpdateWhenUnhealthy transitions

Karthik Kambatla created YARN-4551: -- Summary: Address the duplication between StatusUpdateWhenHealthy and StatusUpdateWhenUnhealthy transitions Key: YARN-4551 URL: https://issues.apache.org/jira/browse/YARN-4551

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15085738#comment-15085738 ] Karthik Kambatla commented on YARN-1011: bq, Just to make sure I understand. When y

[jira] [Comment Edited] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15085738#comment-15085738 ] Karthik Kambatla edited comment on YARN-1011 at 1/6/16 4:12 PM: -

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15085840#comment-15085840 ] Karthik Kambatla commented on YARN-1011: bq. Lets say job capacity is 1 container a

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15085868#comment-15085868 ] Karthik Kambatla commented on YARN-1011: We might be better of calling this overall

[jira] [Commented] (YARN-1011) [Umbrella] Schedule containers based on utilization of currently allocated containers

[ https://issues.apache.org/jira/browse/YARN-1011?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15085872#comment-15085872 ] Karthik Kambatla commented on YARN-1011: BTW, if we agree on the simple policy, I b

[jira] [Updated] (YARN-4512) Provide a knob to turn on over-allocation

[ https://issues.apache.org/jira/browse/YARN-4512?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4512: --- Summary: Provide a knob to turn on over-allocation (was: Provide a knob to turn on over-subscr

[jira] [Resolved] (YARN-4032) Corrupted state from a previous version can still cause RM to fail with NPE due to same reasons as YARN-2834

[ https://issues.apache.org/jira/browse/YARN-4032?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla resolved YARN-4032. Resolution: Duplicate YARN-4347 should fix this issue. Closing this as a duplicate. > Corru

[jira] [Commented] (YARN-4180) AMLauncher does not retry on failures when talking to NM

[ https://issues.apache.org/jira/browse/YARN-4180?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15088346#comment-15088346 ] Karthik Kambatla commented on YARN-4180: Cherry-picked to 2.6.4 as well. Thanks for

[jira] [Updated] (YARN-4180) AMLauncher does not retry on failures when talking to NM

[ https://issues.apache.org/jira/browse/YARN-4180?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4180: --- Fix Version/s: 2.6.4 > AMLauncher does not retry on failures when talking to NM >

[jira] [Commented] (YARN-4559) Make leader elector and zk store share the same curator client

[ https://issues.apache.org/jira/browse/YARN-4559?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15088403#comment-15088403 ] Karthik Kambatla commented on YARN-4559: Quickly skimmed through the patch. High-le

[jira] [Updated] (YARN-4512) Provide a knob to turn on over-allocation

[ https://issues.apache.org/jira/browse/YARN-4512?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated YARN-4512: --- Attachment: YARN-4512-YARN-1011.001.patch > Provide a knob to turn on over-allocation > ---

[jira] [Commented] (YARN-4512) Provide a knob to turn on over-allocation

[ https://issues.apache.org/jira/browse/YARN-4512?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15090823#comment-15090823 ] Karthik Kambatla commented on YARN-4512: The patch attached here: # adds two thresh

  1   2   3   4   5   6   7   8   9   10   >