[jira] [Updated] (GIRAPH-259) TestBspBasic.testBspPageRank is broken

[ https://issues.apache.org/jira/browse/GIRAPH-259?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maja Kabiljo updated GIRAPH-259: Attachment: GIRAPH-259-5.patch TestBspBasic.testBspPageRank is broken

[jira] [Commented] (GIRAPH-259) TestBspBasic.testBspPageRank is broken

[ https://issues.apache.org/jira/browse/GIRAPH-259?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430368#comment-13430368 ] Maja Kabiljo commented on GIRAPH-259: - Removed json. Passes mvn verify and test in

Re: [jira] [Commented] (GIRAPH-259) TestBspBasic.testBspPageRank is broken

Eli, the sum error I get in the pseudo distributed mode. I tried your patch again, it passes mvn verify, and if I comment out the sum check (and leave the 31 check) it also passes tests in pseudo distributed mode. You can try running the tests again, I don't know why would it be any different. On

[jira] [Created] (GIRAPH-287) Add option to limit the number of open requests

Maja Kabiljo created GIRAPH-287: --- Summary: Add option to limit the number of open requests Key: GIRAPH-287 URL: https://issues.apache.org/jira/browse/GIRAPH-287 Project: Giraph Issue Type:

[jira] [Commented] (GIRAPH-287) Add option to limit the number of open requests

[ https://issues.apache.org/jira/browse/GIRAPH-287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430422#comment-13430422 ] Alessandro Presta commented on GIRAPH-287: -- Just to be clear, this allows to

[jira] [Commented] (GIRAPH-275) Restore data locality to workers reading InputSplits where possible without querying NameNode, ZooKeeper

[ https://issues.apache.org/jira/browse/GIRAPH-275?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430434#comment-13430434 ] Eli Reisman commented on GIRAPH-275: Will do. This is the only spot (including inside

[jira] [Commented] (GIRAPH-275) Restore data locality to workers reading InputSplits where possible without querying NameNode, ZooKeeper

[ https://issues.apache.org/jira/browse/GIRAPH-275?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430440#comment-13430440 ] Eli Reisman commented on GIRAPH-275: This is a typical blow-up when I configure wrong.

[jira] [Commented] (GIRAPH-26) Improve PseudoRandomVertexInputFormat to create a more realistic synthetic graph (e.g. power-law distributed vertex-cardinality).

[ https://issues.apache.org/jira/browse/GIRAPH-26?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430457#comment-13430457 ] Sean Choi commented on GIRAPH-26: - Hello Eli Yes, that's exactly what I am doing to pass

Re: Review Request: GIRAPH-262 Netty optimizations and bandwidth tracking

On Aug. 6, 2012, 6:15 p.m., Eugene Koontz wrote: http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/giraph/comm/NettyClient.java, line 112 https://reviews.apache.org/r/6008/diff/1/?file=123493#file123493line112 For consistency with other pipeline components,

[jira] [Created] (GIRAPH-288) Bandwidth tracking - subset of GIRAPH-262

Avery Ching created GIRAPH-288: -- Summary: Bandwidth tracking - subset of GIRAPH-262 Key: GIRAPH-288 URL: https://issues.apache.org/jira/browse/GIRAPH-288 Project: Giraph Issue Type: New Feature

[jira] [Updated] (GIRAPH-288) Bandwidth tracking - subset of GIRAPH-262

[ https://issues.apache.org/jira/browse/GIRAPH-288?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Avery Ching updated GIRAPH-288: --- Attachment: GIRAPH-288.patch Split out the bandwidth tracking. Bandwidth tracking

[jira] [Created] (GIRAPH-289) Add channel pool to NettyClient and thread pool to NettyServer

Eugene Koontz created GIRAPH-289: Summary: Add channel pool to NettyClient and thread pool to NettyServer Key: GIRAPH-289 URL: https://issues.apache.org/jira/browse/GIRAPH-289 Project: Giraph

[jira] [Updated] (GIRAPH-289) Add thread and channel pooling to NettyClient and NettyServer

[ https://issues.apache.org/jira/browse/GIRAPH-289?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eugene Koontz updated GIRAPH-289: - Summary: Add thread and channel pooling to NettyClient and NettyServer (was: Add channel pool

[jira] [Updated] (GIRAPH-289) Add thread and channel pooling to NettyClient and NettyServer

[ https://issues.apache.org/jira/browse/GIRAPH-289?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eugene Koontz updated GIRAPH-289: - Attachment: GIRAPH-289.patch passes mvn clean verify. Add thread and channel

[jira] [Updated] (GIRAPH-288) Bandwidth tracking - subset of GIRAPH-262

[ https://issues.apache.org/jira/browse/GIRAPH-288?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Avery Ching updated GIRAPH-288: --- Attachment: (was: GIRAPH-288.patch) Bandwidth tracking - subset of GIRAPH-262

[jira] [Commented] (GIRAPH-288) Bandwidth tracking - subset of GIRAPH-262

[ https://issues.apache.org/jira/browse/GIRAPH-288?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430538#comment-13430538 ] Eugene Koontz commented on GIRAPH-288: -- +1 Bandwidth tracking -

[jira] [Resolved] (GIRAPH-288) Bandwidth tracking - subset of GIRAPH-262

[ https://issues.apache.org/jira/browse/GIRAPH-288?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Avery Ching resolved GIRAPH-288. Resolution: Fixed Thanks Eugene. Committed. Bandwidth tracking - subset of

[jira] [Commented] (GIRAPH-287) Add option to limit the number of open requests

[ https://issues.apache.org/jira/browse/GIRAPH-287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430558#comment-13430558 ] Jakob Homan commented on GIRAPH-287: How has this patch been tested?

[jira] [Commented] (GIRAPH-287) Add option to limit the number of open requests

[ https://issues.apache.org/jira/browse/GIRAPH-287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430569#comment-13430569 ] Maja Kabiljo commented on GIRAPH-287: - I tested it on a cluster, as I described on the

[jira] [Commented] (GIRAPH-288) Bandwidth tracking - subset of GIRAPH-262

[ https://issues.apache.org/jira/browse/GIRAPH-288?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430572#comment-13430572 ] Hudson commented on GIRAPH-288: --- Integrated in Giraph-trunk-Commit #161 (See

[jira] [Commented] (GIRAPH-262) Netty optimization to handle requests locally whenever possible

[ https://issues.apache.org/jira/browse/GIRAPH-262?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430570#comment-13430570 ] Hudson commented on GIRAPH-262: --- Integrated in Giraph-trunk-Commit #161 (See

[jira] [Commented] (GIRAPH-289) Add thread and channel pooling to NettyClient and NettyServer

[ https://issues.apache.org/jira/browse/GIRAPH-289?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430571#comment-13430571 ] Hudson commented on GIRAPH-289: --- Integrated in Giraph-trunk-Commit #161 (See

Please welcome our newest committer, Alessandro!

I'm excited to announce that the Giraph PMC has voted Alessandro Presta in as a committer and that he has accepted our offer. Alessandro has been very active in the Giraph community, here is a list of some of his great contributions. GIRAPH-276: Fix broken tests in pseudo-distributed mode.

[jira] [Commented] (GIRAPH-262) Netty optimization to handle requests locally whenever possible

[ https://issues.apache.org/jira/browse/GIRAPH-262?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430577#comment-13430577 ] Eugene Koontz commented on GIRAPH-262: -- +1. Passes mvn clean verify with no -P

[jira] [Commented] (GIRAPH-287) Add option to limit the number of open requests

[ https://issues.apache.org/jira/browse/GIRAPH-287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430588#comment-13430588 ] Jakob Homan commented on GIRAPH-287: OK. My only comment would be to move the

[jira] [Commented] (GIRAPH-287) Add option to limit the number of open requests

[ https://issues.apache.org/jira/browse/GIRAPH-287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430632#comment-13430632 ] Hudson commented on GIRAPH-287: --- Integrated in Giraph-trunk-Commit #162 (See

[jira] [Commented] (GIRAPH-246) Periodic worker calls to context.progress() will prevent timeout on some Hadoop clusters during barrier waits

[ https://issues.apache.org/jira/browse/GIRAPH-246?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430675#comment-13430675 ] Avery Ching commented on GIRAPH-246: I don't understand why you are removing Context

[jira] [Comment Edited] (GIRAPH-246) Periodic worker calls to context.progress() will prevent timeout on some Hadoop clusters during barrier waits

[ https://issues.apache.org/jira/browse/GIRAPH-246?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430688#comment-13430688 ] Avery Ching edited comment on GIRAPH-246 at 8/7/12 10:29 PM: -

[jira] [Commented] (GIRAPH-246) Periodic worker calls to context.progress() will prevent timeout on some Hadoop clusters during barrier waits

[ https://issues.apache.org/jira/browse/GIRAPH-246?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430690#comment-13430690 ] Jakob Homan commented on GIRAPH-246: The PredicateLock stuff is fine, but according to

[jira] [Commented] (GIRAPH-246) Periodic worker calls to context.progress() will prevent timeout on some Hadoop clusters during barrier waits

[ https://issues.apache.org/jira/browse/GIRAPH-246?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430702#comment-13430702 ] Eli Reisman commented on GIRAPH-246: lets call it every time, I was not aware it was

[jira] [Updated] (GIRAPH-256) Partitioning outgoing graph data during INPUT_SUPERSTEP by # of vertices results in wide variance in RPC message sizes

[ https://issues.apache.org/jira/browse/GIRAPH-256?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eli Reisman updated GIRAPH-256: --- Attachment: GIRAPH-256-6.patch This refactors msg size regulator into a separate class, adds unit

[jira] [Commented] (GIRAPH-256) Partitioning outgoing graph data during INPUT_SUPERSTEP by # of vertices results in wide variance in RPC message sizes

[ https://issues.apache.org/jira/browse/GIRAPH-256?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430725#comment-13430725 ] Jakob Homan commented on GIRAPH-256: Looking good. Can you move the new constants to

[jira] [Commented] (GIRAPH-246) Periodic worker calls to context.progress() will prevent timeout on some Hadoop clusters during barrier waits

[ https://issues.apache.org/jira/browse/GIRAPH-246?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430755#comment-13430755 ] Avery Ching commented on GIRAPH-246: The configurableness of the progress is nice to

[jira] [Commented] (GIRAPH-246) Periodic worker calls to context.progress() will prevent timeout on some Hadoop clusters during barrier waits

[ https://issues.apache.org/jira/browse/GIRAPH-246?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430802#comment-13430802 ] Avery Ching commented on GIRAPH-246: I appreciate your testing Eli, glad to hear that

[jira] [Updated] (GIRAPH-246) Periodic worker calls to context.progress() will prevent timeout on some Hadoop clusters during barrier waits

[ https://issues.apache.org/jira/browse/GIRAPH-246?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eli Reisman updated GIRAPH-246: --- Attachment: GIRAPH-246-8.patch Jakob had a very useful insight about Progressable earlier, while

[jira] [Commented] (GIRAPH-274) Jobs still failing due to tasks timeout during INPUT_SUPERSTEP

[ https://issues.apache.org/jira/browse/GIRAPH-274?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13430879#comment-13430879 ] Jaeho Shin commented on GIRAPH-274: --- As I just commented on GIRAPH-246, I would be happy