[jira] [Commented] (TEZ-3666) Integer overflow in ShuffleVertexManagerBase

2017-10-26 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3666?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16221394#comment-16221394 ] Ming Ma commented on TEZ-3666: -- Thanks [~aplusplus]! > Integer overflow in ShuffleVertexManage

[jira] [Assigned] (TEZ-3818) Support a new data routing policy for small partitions

2017-08-14 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3818?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma reassigned TEZ-3818: Assignee: Ming Ma > Support a new data routing policy for small partitions > ---

[jira] [Updated] (TEZ-3818) Support a new data routing policy for small partitions

2017-08-14 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3818?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3818: - Attachment: TEZ-3818.patch Here is the draft patch. Besides the added unit test, I tested on a hadoop cluster with

[jira] [Created] (TEZ-3818) Support a new data routing policy for small partitions

2017-08-14 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3818: Summary: Support a new data routing policy for small partitions Key: TEZ-3818 URL: https://issues.apache.org/jira/browse/TEZ-3818 Project: Apache Tez Issue Type: Sub-task

[jira] [Updated] (TEZ-3722) Have MultiMROutput support different configurations for different writers

2017-05-11 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3722?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3722: - Attachment: TEZ-3722.patch Here is the draft patch. Applications will first get the configuration object created by

[jira] [Created] (TEZ-3722) Have MultiMROutput support different configurations for different writers

2017-05-11 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3722: Summary: Have MultiMROutput support different configurations for different writers Key: TEZ-3722 URL: https://issues.apache.org/jira/browse/TEZ-3722 Project: Apache Tez Iss

[jira] [Updated] (TEZ-3666) Integer overflow in ShuffleVertexManagerBase

2017-05-11 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3666?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3666: - Attachment: TEZ-3666-2.patch Thanks [~aplusplus]! Here is the updated patch to address your comments. Regarding the

[jira] [Created] (TEZ-3676) Desired number of tasks in TezGroupedSplitsInputFormat could be negative

2017-03-29 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3676: Summary: Desired number of tasks in TezGroupedSplitsInputFormat could be negative Key: TEZ-3676 URL: https://issues.apache.org/jira/browse/TEZ-3676 Project: Apache Tez Issu

[jira] [Updated] (TEZ-3666) Integer overflow in ShuffleVertexManagerBase

2017-03-26 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3666?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3666: - Attachment: TEZ-3666.patch Here is the draft patch. The code path with the issue is only used by FairShuffleVertexM

[jira] [Assigned] (TEZ-3666) Integer overflow in ShuffleVertexManagerBase

2017-03-26 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3666?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma reassigned TEZ-3666: Assignee: Ming Ma > Integer overflow in ShuffleVertexManagerBase > --

[jira] [Created] (TEZ-3666) Integer overflow in ShuffleVertexManagerBase

2017-03-22 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3666: Summary: Integer overflow in ShuffleVertexManagerBase Key: TEZ-3666 URL: https://issues.apache.org/jira/browse/TEZ-3666 Project: Apache Tez Issue Type: Bug Repor

[jira] [Commented] (TEZ-3588) Tez containers exiting with Yarn status = -105 (killed by app master) instead of 0

2017-01-25 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3588?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15838238#comment-15838238 ] Ming Ma commented on TEZ-3588: -- Configuration of NM metrics is a global change that applies to

[jira] [Commented] (TEZ-3458) Auto grouping for cartesian product edge(unpartitioned case)

2017-01-20 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15832276#comment-15832276 ] Ming Ma commented on TEZ-3458: -- Thanks [~kshukla]. It seems TestFaultTolerance have issue witho

[jira] [Commented] (TEZ-3458) Auto grouping for cartesian product edge(unpartitioned case)

2017-01-17 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15827090#comment-15827090 ] Ming Ma commented on TEZ-3458: -- [~aplusplus] apologies for the delay. +1 for the patch. Can you

[jira] [Created] (TEZ-3578) Enable RLE during merge in TezMerger

2017-01-13 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3578: Summary: Enable RLE during merge in TezMerger Key: TEZ-3578 URL: https://issues.apache.org/jira/browse/TEZ-3578 Project: Apache Tez Issue Type: Improvement Repor

[jira] [Created] (TEZ-3577) DefaultSorter doesn't compute RLE properly

2017-01-13 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3577: Summary: DefaultSorter doesn't compute RLE properly Key: TEZ-3577 URL: https://issues.apache.org/jira/browse/TEZ-3577 Project: Apache Tez Issue Type: Bug Reporte

[jira] [Updated] (TEZ-3552) Shuffle split array when size-based sorting is turned off

2016-12-07 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3552?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3552: - Assignee: Zhiyuan Yang (was: Ming Ma) Thanks [~aplusplus]! Given you provided the fix, assign the jira to you. > S

[jira] [Commented] (TEZ-2132) Support fault tolerance & speculation in pipelined data transfer for ordered output

2016-12-06 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-2132?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15727703#comment-15727703 ] Ming Ma commented on TEZ-2132: -- [~rajesh.balamohan], any plan to work on it? It appears the iss

[jira] [Commented] (TEZ-3552) Shuffle split array when size-based sorting is turned off

2016-12-06 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3552?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15727694#comment-15727694 ] Ming Ma commented on TEZ-3552: -- [~aplusplus] any comment on the unit tests? Please modify if ne

[jira] [Updated] (TEZ-3552) Shuffle split array when size-based sorting is turned off

2016-12-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3552?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3552: - Attachment: (was: TEZ-3552-2.patch) > Shuffle split array when size-based sorting is turned off > --

[jira] [Updated] (TEZ-3552) Shuffle split array when size-based sorting is turned off

2016-12-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3552?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3552: - Attachment: TEZ-3552-2.patch > Shuffle split array when size-based sorting is turned off > -

[jira] [Updated] (TEZ-3552) Shuffle split array when size-based sorting is turned off

2016-12-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3552?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3552: - Attachment: TEZ-3552-2.patch oh, I didn't upload the patch. Thanks [~aplusplus]. To get the unit test pass and veri

[jira] [Commented] (TEZ-3222) Reduce messaging overhead for auto-reduce parallelism case

2016-12-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3222?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15717500#comment-15717500 ] Ming Ma commented on TEZ-3222: -- +1. Thanks [~jeagles]. > Reduce messaging overhead for auto-re

[jira] [Commented] (TEZ-3222) Reduce messaging overhead for auto-reduce parallelism case

2016-11-30 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3222?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15710215#comment-15710215 ] Ming Ma commented on TEZ-3222: -- Thanks for the clarification! For the wording for "CompositeRo

[jira] [Created] (TEZ-3552) Shuffle split array when size-based sorting is turned off

2016-11-30 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3552: Summary: Shuffle split array when size-based sorting is turned off Key: TEZ-3552 URL: https://issues.apache.org/jira/browse/TEZ-3552 Project: Apache Tez Issue Type: Improvem

[jira] [Updated] (TEZ-3430) Make split sorting optional

2016-11-30 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3430?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3430: - Issue Type: Improvement (was: Bug) > Make split sorting optional > --- > >

[jira] [Commented] (TEZ-3463) Remove hadoop-mapreduce-client-common and hadoop-mapreduce-client-core from minimal distribution

2016-11-21 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3463?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15685626#comment-15685626 ] Ming Ma commented on TEZ-3463: -- We also want MR jars to be excluded for the same reason [~jeagl

[jira] [Comment Edited] (TEZ-3222) Reduce messaging overhead for auto-reduce parallelism case

2016-11-18 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3222?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15677445#comment-15677445 ] Ming Ma edited comment on TEZ-3222 at 11/18/16 6:56 PM: [~jeagles],

[jira] [Commented] (TEZ-3222) Reduce messaging overhead for auto-reduce parallelism case

2016-11-18 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3222?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15677445#comment-15677445 ] Ming Ma commented on TEZ-3222: -- [~jeagles], the fair routing part looks good. Couple questions:

[jira] [Commented] (TEZ-3458) Auto grouping for cartesian product edge(unpartitioned case)

2016-11-14 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15665901#comment-15665901 ] Ming Ma commented on TEZ-3458: -- Thanks [~aplusplus]. * Grouper abstraction is nice. Maybe Fai

[jira] [Commented] (TEZ-2104) A CrossProductEdge which produces synthetic cross-product parallelism

2016-11-08 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-2104?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15649457#comment-15649457 ] Ming Ma commented on TEZ-2104: -- ok. Thanks for the jira. It is useful. > A CrossProductEdge wh

[jira] [Commented] (TEZ-3477) MRInputHelpers generateInputSplitsToMem public API modified

2016-11-08 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3477?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15648157#comment-15648157 ] Ming Ma commented on TEZ-3477: -- +1. Thanks! > MRInputHelpers generateInputSplitsToMem public A

[jira] [Commented] (TEZ-3477) MRInputHelpers generateInputSplitsToMem public API modified

2016-11-07 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3477?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15646080#comment-15646080 ] Ming Ma commented on TEZ-3477: -- Thanks [~jeagles] for the clarification. Is the missing annotat

[jira] [Commented] (TEZ-2104) A CrossProductEdge which produces synthetic cross-product parallelism

2016-11-07 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-2104?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15646078#comment-15646078 ] Ming Ma commented on TEZ-2104: -- [~aplusplus] is there a scenario where applications want to do

[jira] [Commented] (TEZ-3465) Support broadcast edge into cartesian product vertex and forbid other edges

2016-11-06 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3465?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15643079#comment-15643079 ] Ming Ma commented on TEZ-3465: -- +1. BTW, do you expect that is how applications will do cartes

[jira] [Commented] (TEZ-2442) Support DFS based shuffle in addition to HTTP shuffle

2016-11-04 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-2442?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15637351#comment-15637351 ] Ming Ma commented on TEZ-2442: -- Nice work. bq. The doc mentioned "For skewed intermediate outp

[jira] [Commented] (TEZ-3458) Auto grouping for cartesian product edge(unpartitioned case)

2016-11-04 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15637341#comment-15637341 ] Ming Ma commented on TEZ-3458: -- Cool. For the partitioned case, do we also need to do something

[jira] [Commented] (TEZ-3465) Support broadcast edge into cartesian product vertex and forbid other edges

2016-10-31 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3465?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15623698#comment-15623698 ] Ming Ma commented on TEZ-3465: -- [~aplusplus] sorry for the delay. The patch looks good overall.

[jira] [Updated] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-10-31 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3269: - Attachment: TEZ-3269-5.patch Update findbugs-exclude.xml as it isn't a real issue. > Provide basic fair routing and

[jira] [Comment Edited] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-10-30 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15621405#comment-15621405 ] Ming Ma edited comment on TEZ-3269 at 10/31/16 6:29 AM: Thanks [~sse

[jira] [Comment Edited] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-10-30 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15621405#comment-15621405 ] Ming Ma edited comment on TEZ-3269 at 10/31/16 6:28 AM: Thanks [~sse

[jira] [Updated] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-10-30 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3269: - Attachment: TEZ-3269-4.patch Thanks @sseth. bq. final where possible Fixed. bq. Would be good to have some more doc

[jira] [Updated] (TEZ-3500) Fair routing support for multiple source vertices

2016-10-30 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3500?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3500: - Summary: Fair routing support for multiple source vertices (was: Support for multiple source vertices) > Fair rout

[jira] [Created] (TEZ-3500) Support for multiple source vertices

2016-10-30 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3500: Summary: Support for multiple source vertices Key: TEZ-3500 URL: https://issues.apache.org/jira/browse/TEZ-3500 Project: Apache Tez Issue Type: Sub-task Reporter

[jira] [Commented] (TEZ-3477) MRInputHelpers generateInputSplitsToMem public API modified

2016-10-27 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3477?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15613988#comment-15613988 ] Ming Ma commented on TEZ-3477: -- [~jeagles] sorry about that. * The patch added protected crea

[jira] [Updated] (TEZ-3215) Support for MultipleOutputs

2016-10-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3215?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3215: - Attachment: TEZ-3215-6.patch Thanks [~sseth]. Regarding OutputCommitter, it should be ok as long as basePath specif

[jira] [Commented] (TEZ-3452) Auto-reduce parallelism calculation can overflow with large inputs

2016-10-18 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3452?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15585906#comment-15585906 ] Ming Ma commented on TEZ-3452: -- +1. Thanks [~jeagles]. > Auto-reduce parallelism calculation c

[jira] [Commented] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-10-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15569234#comment-15569234 ] Ming Ma commented on TEZ-3269: -- [~aplusplus] [~sseth] or anyone else, any additional comments?

[jira] [Commented] (TEZ-3452) Auto-reduce parallelism calculation can overflow with large inputs

2016-10-05 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3452?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15550811#comment-15550811 ] Ming Ma commented on TEZ-3452: -- [~jeagles], perhaps BigInteger could also address the issue. Wh

[jira] [Commented] (TEZ-3454) Support UniformityPartitioner

2016-10-05 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3454?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15550618#comment-15550618 ] Ming Ma commented on TEZ-3454: -- [~darion], is it for the unordered shuffle scenario? It will be

[jira] [Updated] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-10-03 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3269: - Attachment: TEZ-3269-3.patch Thank you [~aplusplus]! The new patch has addressed the issues you raised. Regarding "

[jira] [Updated] (TEZ-3000) Fix TestContainerReuse

2016-09-21 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3000?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3000: - Hadoop Flags: Reviewed > Fix TestContainerReuse > -- > > Key: TEZ-3000 >

[jira] [Updated] (TEZ-3000) Fix TestContainerReuse

2016-09-21 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3000?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3000: - Summary: Fix TestContainerReuse (was: TestContainerReuse.testReuseWithTaskSpecificLaunchCmdOption fails) > Fix Tes

[jira] [Commented] (TEZ-3429) Set reconfigureDoneTime on VertexConfigurationDoneEvent properly

2016-09-20 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3429?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15508274#comment-15508274 ] Ming Ma commented on TEZ-3429: -- Thanks [~sseth]! Per https://builds.apache.org/job/PreCommit-T

[jira] [Commented] (TEZ-3215) Support for MultipleOutputs

2016-09-20 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3215?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15507477#comment-15507477 ] Ming Ma commented on TEZ-3215: -- [~aplusplus] [~hitesh] any additional comments? > Support for

[jira] [Updated] (TEZ-3000) TestContainerReuse.testReuseWithTaskSpecificLaunchCmdOption fails

2016-09-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3000?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3000: - Attachment: TEZ-3000-2.patch Updated patch to exclude the find bug warning. > TestContainerReuse.testReuseWithTaskS

[jira] [Resolved] (TEZ-2905) TestContainerReuse fails in jenkins

2016-09-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-2905?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma resolved TEZ-2905. -- Resolution: Duplicate > TestContainerReuse fails in jenkins > --- > >

[jira] [Updated] (TEZ-3000) TestContainerReuse.testReuseWithTaskSpecificLaunchCmdOption fails

2016-09-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3000?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3000: - Attachment: TEZ-3000.patch Linked another similar jira. Here is the draft path. There are couple issues. * {{TestTa

[jira] [Updated] (TEZ-3430) Make split sorting optional

2016-09-16 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3430?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3430: - Attachment: TEZ-3430.patch Here is the draft patch. It adds a new option sortSplitsEnabled to configuration. > Mak

[jira] [Updated] (TEZ-3429) Set reconfigureDoneTime on VertexConfigurationDoneEvent properly

2016-09-16 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3429?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3429: - Attachment: TEZ-3429.patch Here is the draft patch. It also enables info level logging during recovery which should

[jira] [Updated] (TEZ-3215) Support for MultipleOutputs

2016-09-15 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3215?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3215: - Attachment: TEZ-3215-5.patch bq. Why do we want to remove this line in MROutput.KeyValueWriter.write? Yeah, I also

[jira] [Updated] (TEZ-3215) Support for MultipleOutputs

2016-09-15 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3215?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3215: - Attachment: TEZ-3215-4.patch Thanks [~aplusplus]! bq. LAZY_OUTPUTFORMAT_OUTPUTFORMAT looks like a config for mapred

[jira] [Updated] (TEZ-3215) Support for MultipleOutputs

2016-09-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3215?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3215: - Attachment: TEZ-3215-3.patch The failed test is unrelated. Here is the rebased patch. > Support for MultipleOutputs

[jira] [Created] (TEZ-3430) Make split sorting optional

2016-09-07 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3430: Summary: Make split sorting optional Key: TEZ-3430 URL: https://issues.apache.org/jira/browse/TEZ-3430 Project: Apache Tez Issue Type: Bug Reporter: Ming Ma Th

[jira] [Created] (TEZ-3429) Set reconfigureDoneTime on VertexConfigurationDoneEvent properly

2016-09-07 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3429: Summary: Set reconfigureDoneTime on VertexConfigurationDoneEvent properly Key: TEZ-3429 URL: https://issues.apache.org/jira/browse/TEZ-3429 Project: Apache Tez Issue Type:

[jira] [Resolved] (TEZ-3239) ShuffleVertexManager recovery issue when auto parallelism is enabled

2016-09-06 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3239?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma resolved TEZ-3239. -- Resolution: Invalid Verified that the issue no longer exists in the master branch. > ShuffleVertexManager recover

[jira] [Updated] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-09-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3269: - Attachment: TEZ-3269-2.patch Here is the updated patch to include the followings: * exclude file update to fix find

[jira] [Commented] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-09-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15459809#comment-15459809 ] Ming Ma commented on TEZ-3230: -- +1. I will commit it earlier next week in case others have comm

[jira] [Resolved] (TEZ-3427) Add committer mingma to the Tez Team List

2016-09-01 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3427?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma resolved TEZ-3427. -- Resolution: Fixed Hadoop Flags: Reviewed Thanks [~hitesh]. I have committed it to the master branch. > Add

[jira] [Updated] (TEZ-3427) Add committer mingma to the Tez Team List

2016-09-01 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3427?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3427: - Attachment: TEZ-3427.patch Verified per https://cwiki.apache.org/confluence/display/TEZ/Updating+the+Tez+Website. C

[jira] [Created] (TEZ-3427) Add committer mingma to the Tez Team List

2016-09-01 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3427: Summary: Add committer mingma to the Tez Team List Key: TEZ-3427 URL: https://issues.apache.org/jira/browse/TEZ-3427 Project: Apache Tez Issue Type: Task Reporte

[jira] [Commented] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-08-31 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15453559#comment-15453559 ] Ming Ma commented on TEZ-3230: -- [~aplusplus] the latest patch looks good. One minor thing, in

[jira] [Updated] (TEZ-3269) Provide basic fair routing and scheduling functionality via custom VertexManager and EdgeManager

2016-08-26 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3269?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3269: - Attachment: TEZ-3269.patch Here is the draft patch. It supports two polices w.r.t. fair routing. * One policy is au

[jira] [Commented] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-08-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15429095#comment-15429095 ] Ming Ma commented on TEZ-3230: -- Thanks [~aplusplus]. Couple more comments: bq. But since there

[jira] [Commented] (TEZ-3395) Refactor ShuffleVertexManager to make parts of it re-usable in other plugins

2016-08-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3395?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15428666#comment-15428666 ] Ming Ma commented on TEZ-3395: -- Thanks [~sseth]! > Refactor ShuffleVertexManager to make parts

[jira] [Commented] (TEZ-3395) Refactor ShuffleVertexManager

2016-08-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3395?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15428543#comment-15428543 ] Ming Ma commented on TEZ-3395: -- Oops, yes please remove it. Thank you! > Refactor ShuffleVerte

[jira] [Updated] (TEZ-3395) Refactor ShuffleVertexManager

2016-08-18 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3395?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3395: - Attachment: TEZ-3395-4.patch Thanks [~sseth]. Here is the patch with findbugs-exclude.xml's update. > Refactor Shuf

[jira] [Updated] (TEZ-3395) Refactor ShuffleVertexManager

2016-08-17 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3395?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3395: - Attachment: TEZ-3395-3.patch Test failure and javac warnings aren't related. The synchronization issue in findbugs

[jira] [Updated] (TEZ-3395) Refactor ShuffleVertexManager

2016-08-17 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3395?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3395: - Attachment: TEZ-3395-2.patch Thanks [~sseth]. bq. ReconfigVertexParams - static class, and final params fixed bq.

[jira] [Commented] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-08-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15419756#comment-15419756 ] Ming Ma commented on TEZ-3230: -- About "Only on demand routing" question, I am trying to underst

[jira] [Comment Edited] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-08-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15419672#comment-15419672 ] Ming Ma edited comment on TEZ-3230 at 8/12/16 11:17 PM: Thanks [~apl

[jira] [Commented] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-08-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15419672#comment-15419672 ] Ming Ma commented on TEZ-3230: -- bq. For now, cDME is more prevalent given it won't consume too

[jira] [Commented] (TEZ-3209) Support for fair custom data routing

2016-08-11 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3209?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15417693#comment-15417693 ] Ming Ma commented on TEZ-3209: -- Thanks [~aplusplus]! Yes you are right about FairShuffleEdgeMan

[jira] [Commented] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-08-09 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15413956#comment-15413956 ] Ming Ma commented on TEZ-3230: -- Couple suggestions w.r.t. EdgeManager: * {{CartesianProductEdg

[jira] [Commented] (TEZ-3397) Better fault tolerance heuristics for custom edge

2016-08-09 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3397?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15413834#comment-15413834 ] Ming Ma commented on TEZ-3397: -- Is that only for specific custom edge scenario or it applies to

[jira] [Commented] (TEZ-3369) Fixing Tez's DAGClients to work with Cascading

2016-08-08 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3369?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15412516#comment-15412516 ] Ming Ma commented on TEZ-3369: -- bq. For task level progress, we could do the same - just need t

[jira] [Commented] (TEZ-3230) Implement vertex manager and edge manager of cartesian product edge

2016-08-05 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3230?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15409872#comment-15409872 ] Ming Ma commented on TEZ-3230: -- Thanks [~aplusplus]. Nice patch! Some comments are about design

[jira] [Commented] (TEZ-3209) Support for fair custom data routing

2016-08-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3209?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15404939#comment-15404939 ] Ming Ma commented on TEZ-3209: -- Thanks [~sseth]. The refactoring work will be done in TEZ-3395.

[jira] [Updated] (TEZ-3395) Refactor ShuffleVertexManager

2016-08-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3395?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3395: - Attachment: TEZ-3395.patch Here is the draft patch. The major changes are: * Move event handling to {{ShuffleVertex

[jira] [Updated] (TEZ-3395) Refactor ShuffleVertexManager

2016-08-02 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3395?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3395: - Summary: Refactor ShuffleVertexManager (was: refactor ShuffleVertexManager) > Refactor ShuffleVertexManager > -

[jira] [Created] (TEZ-3395) refactor ShuffleVertexManager

2016-08-02 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3395: Summary: refactor ShuffleVertexManager Key: TEZ-3395 URL: https://issues.apache.org/jira/browse/TEZ-3395 Project: Apache Tez Issue Type: Sub-task Reporter: Ming

[jira] [Commented] (TEZ-3303) Have ShuffleVertexManager consume more precise partition stats

2016-08-01 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3303?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15402906#comment-15402906 ] Ming Ma commented on TEZ-3303: -- Nit: The TODO comment for TEZ_RUNTIME_REPORT_PARTITION_STATS in

[jira] [Commented] (TEZ-3113) massive increase of run time using PipelinedSorter rather than DefaultSorter

2016-07-26 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3113?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15394807#comment-15394807 ] Ming Ma commented on TEZ-3113: -- We also ran into similar issue. The pipeline sorter setting:

[jira] [Commented] (TEZ-3209) Support for fair custom data routing

2016-07-19 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3209?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15385449#comment-15385449 ] Ming Ma commented on TEZ-3209: -- Thanks [~sseth]! bq. primarily targeted towards Unordered Data

[jira] [Commented] (TEZ-3331) Add operation specific HDFS counters for Tez UI

2016-07-15 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3331?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15379771#comment-15379771 ] Ming Ma commented on TEZ-3331: -- [~hitesh], thanks for the explanation. So to make this patch co

[jira] [Commented] (TEZ-3331) Add operation specific HDFS counters for Tez UI

2016-07-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3331?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15373947#comment-15373947 ] Ming Ma commented on TEZ-3331: -- [~hitesh] thanks for the info about hadoop shim. bq. Mind addi

[jira] [Updated] (TEZ-3340) Add support for YARN Shared Cache

2016-07-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3340?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma updated TEZ-3340: - Description: YARN provides shared cache in functionality YARN-1492. According to [~ctrezzo] most of the YARN functi

[jira] [Created] (TEZ-3342) Have Tez AM generate thread dump on task attempts timeout before killing them

2016-07-12 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3342: Summary: Have Tez AM generate thread dump on task attempts timeout before killing them Key: TEZ-3342 URL: https://issues.apache.org/jira/browse/TEZ-3342 Project: Apache Tez

[jira] [Created] (TEZ-3341) Add thread dump support to Tez webUI

2016-07-12 Thread Ming Ma (JIRA)
Ming Ma created TEZ-3341: Summary: Add thread dump support to Tez webUI Key: TEZ-3341 URL: https://issues.apache.org/jira/browse/TEZ-3341 Project: Apache Tez Issue Type: Improvement Repor

[jira] [Moved] (TEZ-3340) Add support for YARN Shared Cache

2016-07-12 Thread Ming Ma (JIRA)
[ https://issues.apache.org/jira/browse/TEZ-3340?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Ming Ma moved YARN-5365 to TEZ-3340: Key: TEZ-3340 (was: YARN-5365) Project: Apache Tez (was: Hadoop YARN) > Add support

  1   2   >