[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated MAPREDUCE-5044: --- Resolution: Fixed Hadoop Flags: Reviewed Fix Version/s: 2.8.0 Status: Resolved (was: Patch Available) > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Eric Payne > Fix For: 2.8.0 > > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.011.patch, MAPREDUCE-5044.012.patch, > MAPREDUCE-5044.013.patch, MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, > MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, > MAPREDUCE-5044.v06.patch, MAPREDUCE-5044.v07.local.patch, Screen Shot > 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Attachment: MAPREDUCE-5044.013.patch {{MAPREDUCE-5044.013.patch}} addresses most of the checkstyle warnings from the previous pre-commit build. The one exception is for those flagged in {{TestMRJobs.java}}. It is triggering the alert because of an inner assignments in the following for loop: {code} for (String line; (line = syslogReader.readLine()) != null; ) { ... } {code} The code could be changed to something like the following, but I think that would be more awkward: {code} String line = syslogReader.readLine(); for (String line; line != null; ) { ... line = syslogReader.readLine(); } {code} > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Eric Payne > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.011.patch, MAPREDUCE-5044.012.patch, > MAPREDUCE-5044.013.patch, MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, > MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, > MAPREDUCE-5044.v06.patch, MAPREDUCE-5044.v07.local.patch, Screen Shot > 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Attachment: MAPREDUCE-5044.012.patch The new test case ({{TestMRJobs#testThreadDumpOnTaskTimeout}}) when run with {{TestUberAM}}, detected that timeout did not cause a thread dump within an uber AM. So, I added code in {{LocalContainerLauncher}} in the latest patch ({{MAPREDUCE-5044.012.patch}}) to handle the timeout event. Instead of having the uber AM connect to the NM which would then send the QUIT signal back to the uber AM, I chose to dump the stack directly from the uber AM. I chose to use {{ThreadMXBean#dumpAllThreads}} even though there was already a Hadoop {{ReflwctionUtils#printThreadInfo}} method which would create a dump. The reason is because the output of {{ThreadMXBean#dumpAllThreads}} much more closely resembles the standard thread stack dump than does the output of {{ReflwctionUtils#printThreadInfo}}. > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Eric Payne > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.011.patch, MAPREDUCE-5044.012.patch, > MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, > MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, > MAPREDUCE-5044.v07.local.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, > Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Assignee: Eric Payne (was: Gera Shegalov) > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Eric Payne > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.011.patch, MAPREDUCE-5044.v01.patch, > MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, > MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, > MAPREDUCE-5044.v07.local.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, > Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Status: Patch Available (was: Open) > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.011.patch, MAPREDUCE-5044.v01.patch, > MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, > MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, > MAPREDUCE-5044.v07.local.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, > Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Status: Open (was: Patch Available) It looks like the pre-commit build faild: https://builds.apache.org/job/PreCommit-MAPREDUCE-Build/6528/console {quote} Slave went offline during the build ERROR: Connection was broken: java.io.IOException: Sorry, this connection is closed. {quote} Cancelling patch and re-Submitting patch > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.011.patch, MAPREDUCE-5044.v01.patch, > MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, > MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, > MAPREDUCE-5044.v07.local.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, > Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Attachment: MAPREDUCE-5044.011.patch Thanks for the continuing review, [~mingma]. I made the suggested changes. Please find them in attachment {{MAPREDUCE-5044.011.patch}}. > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.011.patch, MAPREDUCE-5044.v01.patch, > MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, > MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, > MAPREDUCE-5044.v07.local.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, > Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Attachment: MAPREDUCE-5044.010.patch Thank you very much, [~mingma], for your review and suggestions: {quote} - rename {{signalContainer}} to {{signalToContainer}} {quote} Done. {quote} -{{ContainerManagerImpl}}. It might be cleaner to abstract the common signal container code to a function used for both {{AM -> NM}} and {{RM -> NM}} cases. {quote} Done. {quote} -{{TaskAttemptImpl#PreemptedTransition}}. Given it is called only when the attempt is preempted, event.getType() == TaskAttemptEventType.TA_TIMED_OUT can be replaced by false. {quote} Very true. Good catch. {quote} -It will be useful to add an end-to-end new unit test, which can be found in Gera's original patch. {quote} Done. {quote} -Nit: {{ContainerLauncherImpl}}. Return value of {{getContainerManagementProtocol().signalContainer}} isn't used and can be removed. {quote} Done. {quote} -Nit: {{ContainerLauncherEvent}} has indent format issue. {quote} Done. > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.010.patch, MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, > MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, > MAPREDUCE-5044.v06.patch, MAPREDUCE-5044.v07.local.patch, Screen Shot > 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Attachment: MAPREDUCE-5044.009.patch [~jlowe], [~jira.shegalov], [~mingma], [~xgong], Patch 008 was no longer applying to trunk. I upmerged the patch and attaching MAPREDUCE-5044.009.patch. Can I please ask one of you to look at it? > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.009.patch, > MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, > MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, > MAPREDUCE-5044.v07.local.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, > Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: mapreduce-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: mapreduce-issues-h...@hadoop.apache.org
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Attachment: MAPREDUCE-5044.008.patch [~jira.shegalov], [~mingma], [~xgong], [~jlowe], Upmerged patch and attaching MAPREDUCE-5044.008.patch. > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.008.patch, MAPREDUCE-5044.v01.patch, > MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, > MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, > MAPREDUCE-5044.v07.local.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, > Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Target Version/s: 2.8.0, 2.7.3 (was: 2.8.0) Status: Patch Available (was: Open) > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, > MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, > MAPREDUCE-5044.v06.patch, MAPREDUCE-5044.v07.local.patch, Screen Shot > 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eric Payne updated MAPREDUCE-5044: -- Attachment: MAPREDUCE-5044.v07.local.patch Thanks, [~jira.shegalov] for all of the work already done on this JIRA. I have upmerged the latest patch and integrated it with the {{SignalContainerRequest}} that was added as part of YARN-445 and its children. [~mingma], [~xgong], [~jlowe], [~jira.shegalov], would you please take a look? I would like to see functionality in this JIRA implemented. We occasionally see containers time out, and it would be good if users could have direct feedback in the form of a jstack to help them debug their applications. IIUC, YARN-445 and its children put in place the infrastructure for a {{Client -> RM -> NM -> Container}} signal path. However, in order to automatically dump the jstack when a container times out, we still need an {{AM -> NM -> Container}} signal path. This JIRA (MAPREDUCE-5044 along with YARN-1515) adds this signal path along with the ability to send multiple signals per call. I think sending multiple signals per call could be split into a separate JIRA. > Have AM trigger jstack on task attempts that timeout before killing them > > > Key: MAPREDUCE-5044 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: mr-am >Affects Versions: 2.1.0-beta >Reporter: Jason Lowe >Assignee: Gera Shegalov > Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, > MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, > MAPREDUCE-5044.v06.patch, MAPREDUCE-5044.v07.local.patch, Screen Shot > 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png > > > When an AM expires a task attempt it would be nice if it triggered a jstack > output via SIGQUIT before killing the task attempt. This would be invaluable > for helping users debug their hung tasks, especially if they do not have > shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Allen Wittenauer updated MAPREDUCE-5044: Status: Open (was: Patch Available) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Allen Wittenauer updated MAPREDUCE-5044: Status: Patch Available (was: Open) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Allen Wittenauer updated MAPREDUCE-5044: Status: Open (was: Patch Available) Cancelling patch as it no longer applies. Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Karthik Kambatla updated MAPREDUCE-5044: Target Version/s: 2.6.0 (was: 2.5.0) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: MAPREDUCE-5044.v06.patch v06 that utilizes signalContainer API provided by YARN-1515.v08.patch Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, MAPREDUCE-5044.v06.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Vinod Kumar Vavilapalli updated MAPREDUCE-5044: --- Target Version/s: 2.5.0 (was: 2.4.0) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, MAPREDUCE-5044.v05.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Target Version/s: 2.4.0 Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: MAPREDUCE-5044.v04.patch v04 to apply on top of YARN-1515.v05. It now makes sure that a thread dump is created in the uber mode. Added unit tests for a normal MR job and uber MR job. While working on this I realized that we actually need to discuss how mapreduce.task.timeout is treated in the ubermode. Right now it's basically ignored because AM does not kill itself, LocalContainerLauncher processes CONTAINER_REMOTE_CLEANUP inline with the stuck in SubtaskRunner. The liveness monitor for AM in RM does not catch the problem either because RMCommunicator heartbeats in a separate allocator thread. I am considering two options: - move heartbeat() into SubtaskRunner for ubermode such that the liveness monitor catches the stuck ubertask. - do System.exit(errorcode) when TA_TIMEOUT occurs. Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, MAPREDUCE-5044.v04.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1.5#6160)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Status: Patch Available (was: Open) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: MAPREDUCE-5044.v03.patch Another attempt to remove yarn-related changes. Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, MAPREDUCE-5044.v03.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Vinod Kumar Vavilapalli updated MAPREDUCE-5044: --- Status: Open (was: Patch Available) I do think this is tied to YARN-445. But we can discuss that elsewhere. This patch has YARN changes. YARN and MapReduce are split into separate sub-modules of Hadoop. Please file a YARN ticket for the changes you need in YARN here: https://issues.apache.org/jira/browse/YARN Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: MAPREDUCE-5044.v02.patch Moved YARN-related changes into YARN-1515 Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Assignee: Gera Shegalov Attachments: MAPREDUCE-5044.v01.patch, MAPREDUCE-5044.v02.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: MAPREDUCE-5044.v01.patch Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Attachments: MAPREDUCE-5044.v01.patch When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Status: Patch Available (was: Open) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Attachments: MAPREDUCE-5044.v01.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: Screen Shot 2013-11-12 at 1.06.04 PM.png Screen Shot 2013-11-12 at 1.05.32 PM.png Test with $ bin/yarn jar share/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-*-tests.jar sleep -Dmapreduce.task.timeout=$((30*1000)) -m 1 -mt $((2*60*1000)) -r 0 -recordt $((2*60*1000)) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Attachments: MAPREDUCE-5044.v01.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: (was: MAPREDUCE-5044.v01.patch) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: (was: Screen Shot 2013-11-12 at 1.06.04 PM.png) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: (was: Screen Shot 2013-11-12 at 1.05.32 PM.png) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Status: Open (was: Patch Available) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: MAPREDUCE-5044.v01.patch Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Attachments: MAPREDUCE-5044.v01.patch When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Status: Patch Available (was: Open) Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Attachments: MAPREDUCE-5044.v01.patch When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)
[jira] [Updated] (MAPREDUCE-5044) Have AM trigger jstack on task attempts that timeout before killing them
[ https://issues.apache.org/jira/browse/MAPREDUCE-5044?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Gera Shegalov updated MAPREDUCE-5044: - Attachment: Screen Shot 2013-11-12 at 1.06.04 PM.png Screen Shot 2013-11-12 at 1.05.32 PM.png Have AM trigger jstack on task attempts that timeout before killing them Key: MAPREDUCE-5044 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5044 Project: Hadoop Map/Reduce Issue Type: Improvement Components: mr-am Affects Versions: 2.1.0-beta Reporter: Jason Lowe Attachments: MAPREDUCE-5044.v01.patch, Screen Shot 2013-11-12 at 1.05.32 PM.png, Screen Shot 2013-11-12 at 1.06.04 PM.png When an AM expires a task attempt it would be nice if it triggered a jstack output via SIGQUIT before killing the task attempt. This would be invaluable for helping users debug their hung tasks, especially if they do not have shell access to the nodes. -- This message was sent by Atlassian JIRA (v6.1#6144)