[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935930#comment-14935930 ] Hudson commented on YARN-4066: -- FAILURE: Integrated in Hadoop-Hdfs-trunk-Java8 #435 (See [https://builds.apache.org/job/Hadoop-Hdfs-trunk-Java8/435/]) YARN-4066. Large number of queues choke fair scheduler. (Johan Gustavsson via kasha) (kasha: rev a0b5a0a419dfc07b7ac45c06b11b4c8dc7e79958) * hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/QueueManager.java * hadoop-yarn-project/CHANGES.txt > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Fix For: 2.8.0 > > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935834#comment-14935834 ] Hudson commented on YARN-4066: -- FAILURE: Integrated in Hadoop-Hdfs-trunk #2375 (See [https://builds.apache.org/job/Hadoop-Hdfs-trunk/2375/]) YARN-4066. Large number of queues choke fair scheduler. (Johan Gustavsson via kasha) (kasha: rev a0b5a0a419dfc07b7ac45c06b11b4c8dc7e79958) * hadoop-yarn-project/CHANGES.txt * hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/QueueManager.java > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Fix For: 2.8.0 > > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935728#comment-14935728 ] Hudson commented on YARN-4066: -- FAILURE: Integrated in Hadoop-Mapreduce-trunk #2403 (See [https://builds.apache.org/job/Hadoop-Mapreduce-trunk/2403/]) YARN-4066. Large number of queues choke fair scheduler. (Johan Gustavsson via kasha) (kasha: rev a0b5a0a419dfc07b7ac45c06b11b4c8dc7e79958) * hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/QueueManager.java * hadoop-yarn-project/CHANGES.txt > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Fix For: 2.8.0 > > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935496#comment-14935496 ] Hudson commented on YARN-4066: -- FAILURE: Integrated in Hadoop-Yarn-trunk #1198 (See [https://builds.apache.org/job/Hadoop-Yarn-trunk/1198/]) YARN-4066. Large number of queues choke fair scheduler. (Johan Gustavsson via kasha) (kasha: rev a0b5a0a419dfc07b7ac45c06b11b4c8dc7e79958) * hadoop-yarn-project/CHANGES.txt * hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/QueueManager.java > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Fix For: 2.8.0 > > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935489#comment-14935489 ] Hudson commented on YARN-4066: -- SUCCESS: Integrated in Hadoop-Yarn-trunk-Java8 #467 (See [https://builds.apache.org/job/Hadoop-Yarn-trunk-Java8/467/]) YARN-4066. Large number of queues choke fair scheduler. (Johan Gustavsson via kasha) (kasha: rev a0b5a0a419dfc07b7ac45c06b11b4c8dc7e79958) * hadoop-yarn-project/CHANGES.txt * hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/QueueManager.java > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Fix For: 2.8.0 > > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935341#comment-14935341 ] Hudson commented on YARN-4066: -- FAILURE: Integrated in Hadoop-trunk-Commit #8540 (See [https://builds.apache.org/job/Hadoop-trunk-Commit/8540/]) YARN-4066. Large number of queues choke fair scheduler. (Johan Gustavsson via kasha) (kasha: rev a0b5a0a419dfc07b7ac45c06b11b4c8dc7e79958) * hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/QueueManager.java * hadoop-yarn-project/CHANGES.txt > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Fix For: 2.8.0 > > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935347#comment-14935347 ] Hudson commented on YARN-4066: -- FAILURE: Integrated in Hadoop-Mapreduce-trunk-Java8 #459 (See [https://builds.apache.org/job/Hadoop-Mapreduce-trunk-Java8/459/]) YARN-4066. Large number of queues choke fair scheduler. (Johan Gustavsson via kasha) (kasha: rev a0b5a0a419dfc07b7ac45c06b11b4c8dc7e79958) * hadoop-yarn-project/CHANGES.txt * hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/QueueManager.java > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Fix For: 2.8.0 > > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14935279#comment-14935279 ] Karthik Kambatla commented on YARN-4066: +1, checking this in. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14910113#comment-14910113 ] Johan Gustavsson commented on YARN-4066: Thanks for re-running this. Looking at the tests in place I see no need to introduce new tests for this patch, also this patch doesn't break the tests in place. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14910065#comment-14910065 ] Hadoop QA commented on YARN-4066: - \\ \\ | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem || Runtime || Comment || | {color:blue}0{color} | pre-patch | 16m 34s | Pre-patch trunk compilation is healthy. | | {color:green}+1{color} | @author | 0m 0s | The patch does not contain any @author tags. | | {color:red}-1{color} | tests included | 0m 0s | The patch doesn't appear to include any new or modified tests. Please justify why no new tests are needed for this patch. Also please list what manual steps were performed to verify this patch. | | {color:green}+1{color} | javac | 7m 47s | There were no new javac warning messages. | | {color:green}+1{color} | javadoc | 9m 59s | There were no new javadoc warning messages. | | {color:green}+1{color} | release audit | 0m 24s | The applied patch does not increase the total number of release audit warnings. | | {color:green}+1{color} | checkstyle | 0m 49s | There were no new checkstyle issues. | | {color:green}+1{color} | whitespace | 0m 0s | The patch has no lines that end in whitespace. | | {color:green}+1{color} | install | 1m 29s | mvn install still works. | | {color:green}+1{color} | eclipse:eclipse | 0m 34s | The patch built with eclipse:eclipse. | | {color:green}+1{color} | findbugs | 1m 29s | The patch does not introduce any new Findbugs (version 3.0.0) warnings. | | {color:green}+1{color} | yarn tests | 60m 4s | Tests passed in hadoop-yarn-server-resourcemanager. | | | | 99m 11s | | \\ \\ || Subsystem || Report/Notes || | Patch URL | http://issues.apache.org/jira/secure/attachment/12762639/YARN-4066-3.patch | | Optional Tests | javadoc javac unit findbugs checkstyle | | git revision | trunk / 1c030c6 | | hadoop-yarn-server-resourcemanager test log | https://builds.apache.org/job/PreCommit-YARN-Build/9280/artifact/patchprocess/testrun_hadoop-yarn-server-resourcemanager.txt | | Test Results | https://builds.apache.org/job/PreCommit-YARN-Build/9280/testReport/ | | Java | 1.7.0_55 | | uname | Linux asf905.gq1.ygridcore.net 3.13.0-36-lowlatency #63-Ubuntu SMP PREEMPT Wed Sep 3 21:56:12 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux | | Console output | https://builds.apache.org/job/PreCommit-YARN-Build/9280/console | This message was automatically generated. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Attachments: YARN-4066-2.patch, YARN-4066-3.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14910003#comment-14910003 ] Hadoop QA commented on YARN-4066: - \\ \\ | (x) *{color:red}-1 overall{color}* | \\ \\ || Vote || Subsystem || Runtime || Comment || | {color:blue}0{color} | pre-patch | 16m 42s | Pre-patch trunk compilation is healthy. | | {color:green}+1{color} | @author | 0m 0s | The patch does not contain any @author tags. | | {color:red}-1{color} | tests included | 0m 0s | The patch doesn't appear to include any new or modified tests. Please justify why no new tests are needed for this patch. Also please list what manual steps were performed to verify this patch. | | {color:green}+1{color} | javac | 7m 50s | There were no new javac warning messages. | | {color:green}+1{color} | javadoc | 10m 2s | There were no new javadoc warning messages. | | {color:green}+1{color} | release audit | 0m 23s | The applied patch does not increase the total number of release audit warnings. | | {color:red}-1{color} | checkstyle | 0m 50s | The applied patch generated 4 new checkstyle issues (total was 15, now 18). | | {color:green}+1{color} | whitespace | 0m 0s | The patch has no lines that end in whitespace. | | {color:green}+1{color} | install | 1m 30s | mvn install still works. | | {color:green}+1{color} | eclipse:eclipse | 0m 33s | The patch built with eclipse:eclipse. | | {color:green}+1{color} | findbugs | 1m 29s | The patch does not introduce any new Findbugs (version 3.0.0) warnings. | | {color:green}+1{color} | yarn tests | 60m 3s | Tests passed in hadoop-yarn-server-resourcemanager. | | | | 99m 25s | | \\ \\ || Subsystem || Report/Notes || | Patch URL | http://issues.apache.org/jira/secure/attachment/12762628/YARN-4066-2.patch | | Optional Tests | javadoc javac unit findbugs checkstyle | | git revision | trunk / 1c030c6 | | checkstyle | https://builds.apache.org/job/PreCommit-YARN-Build/9279/artifact/patchprocess/diffcheckstylehadoop-yarn-server-resourcemanager.txt | | hadoop-yarn-server-resourcemanager test log | https://builds.apache.org/job/PreCommit-YARN-Build/9279/artifact/patchprocess/testrun_hadoop-yarn-server-resourcemanager.txt | | Test Results | https://builds.apache.org/job/PreCommit-YARN-Build/9279/testReport/ | | Java | 1.7.0_55 | | uname | Linux asf905.gq1.ygridcore.net 3.13.0-36-lowlatency #63-Ubuntu SMP PREEMPT Wed Sep 3 21:56:12 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux | | Console output | https://builds.apache.org/job/PreCommit-YARN-Build/9279/console | This message was automatically generated. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Attachments: YARN-4066-2.patch, yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14905783#comment-14905783 ] Johan Gustavsson commented on YARN-4066: Thanks for the feedback Karthik, I'll try to have a fixed patch ready by next week. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson >Assignee: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14803151#comment-14803151 ] Karthik Kambatla commented on YARN-4066: Thanks again for working on this, Johan. Took a closer look at the patch and have the following comments: # A few lines are longer than 80 characters. # For the method parameters, {{recomputeSteadyShares}} might be more descriptive thaan {{recalculate}} # While at it, I would suggest the following improvements in synchronization as well: ## In getQueue, some of the code could be outside the synchronized block {code} name = ensureRootPrefix(name); FSQueue queue; synchronized (queues) { queue = queues.get(name); if (queue == null && create) { // if the queue doesn't exist,create it and return queue = createQueue(name, queueType); } else { recalculate = false; } } if (recalculate) { rootQueue.recomputeSteadyShares(); } return queue; {code} ## In updateAllocationConfiguration, club the two synchronized blocks into one, and recomputeSteadyShares outside the synchronized block. Since we are changing some of the locking that would be hard to unit-tests, would appreciate if you could run the updated patch through the tests you previously reported. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14803119#comment-14803119 ] Karthik Kambatla commented on YARN-4066: Looking into it. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14746323#comment-14746323 ] Johan Gustavsson commented on YARN-4066: Please let me know if there is anything I can do to continue the process of merging this > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14706035#comment-14706035 ] Johan Gustavsson commented on YARN-4066: As I done seem to be able to edit the above comment and the tree ended up weird I'll repast it below root: 1 q1: veryhigh high default low verylow > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14706031#comment-14706031 ] Johan Gustavsson commented on YARN-4066: Basically its a tree as follows ranging from 1 to 16000. For each user group there is one general queue and one with weight divided sub queues. root - 1 - q1 - veryhigh - high - default - low - verylow > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14705094#comment-14705094 ] Arun Suresh commented on YARN-4066: --- +1 pending jenkins > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14705015#comment-14705015 ] Karthik Kambatla commented on YARN-4066: The patch looks reasonable. Could you comment on your queue setup (depth, average breadth etc.) for the 96,000 queues that you tested this on? Just curious. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14704334#comment-14704334 ] Johan Gustavsson commented on YARN-4066: Sorry, I re-uploaded it and I think it should be visible now > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > Attachments: yarn-4066-1.patch > > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-4066) Large number of queues choke fair scheduler
[ https://issues.apache.org/jira/browse/YARN-4066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14704320#comment-14704320 ] Arun Suresh commented on YARN-4066: --- [~johang], Thanks for reporting this... I don't think the patch has been successfully uploaded though. Kindly re-attach. > Large number of queues choke fair scheduler > --- > > Key: YARN-4066 > URL: https://issues.apache.org/jira/browse/YARN-4066 > Project: Hadoop YARN > Issue Type: Bug > Components: fairscheduler >Affects Versions: 2.7.1 >Reporter: Johan Gustavsson > > Due to synchronization and all the loops performed during queue creation, > setting a large amount of queues (12000+) will completely choke the > scheduler. To deal with this some optimization to > "QueueManager.updateAllocationConfiguration(AllocationConfiguration > queueConf)" should be done to reduce the amount of unnesecary loops. The > attached patch have been tested to work with atleast 96000 queues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)