[jira] [Commented] (HDFS-1861) Rename dfs.datanode.max.xcievers and bump its default value

[ https://issues.apache.org/jira/browse/HDFS-1861?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025871#comment-13025871 ] Aaron T. Myers commented on HDFS-1861: -- Apologies for showing up to this JIRA late, bu

[jira] [Commented] (HDFS-1052) HDFS scalability with multiple namenodes

[ https://issues.apache.org/jira/browse/HDFS-1052?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025897#comment-13025897 ] Suresh Srinivas commented on HDFS-1052: --- Some benchmark results: h3. TestDFSIO read t

[jira] [Commented] (HDFS-1052) HDFS scalability with multiple namenodes

[ https://issues.apache.org/jira/browse/HDFS-1052?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025908#comment-13025908 ] Suresh Srinivas commented on HDFS-1052: --- BTW just to clarify - the above benchmarks a

[jira] [Commented] (HDFS-671) Documentation change for updated configuration keys.

[ https://issues.apache.org/jira/browse/HDFS-671?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025913#comment-13025913 ] Tom White commented on HDFS-671: > This needs to go in trunk as well right? Correct. > Com

[jira] [Commented] (HDFS-1840) Terminate LeaseChecker when all writing files are closed.

[ https://issues.apache.org/jira/browse/HDFS-1840?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025923#comment-13025923 ] Cheng Leong commented on HDFS-1840: --- So the number of threads keeps increasing (in my cas

[jira] [Commented] (HDFS-1840) Terminate LeaseChecker when all writing files are closed.

[ https://issues.apache.org/jira/browse/HDFS-1840?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025932#comment-13025932 ] Tsz Wo (Nicholas), SZE commented on HDFS-1840: -- Before the patch in this issue

[jira] [Created] (HDFS-1866) Document dfs.datanode.max.transfer.threads in hdfs-default.xml

Document dfs.datanode.max.transfer.threads in hdfs-default.xml -- Key: HDFS-1866 URL: https://issues.apache.org/jira/browse/HDFS-1866 Project: Hadoop HDFS Issue Type: Improvement

[jira] [Commented] (HDFS-1861) Rename dfs.datanode.max.xcievers and bump its default value

[ https://issues.apache.org/jira/browse/HDFS-1861?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025931#comment-13025931 ] Eli Collins commented on HDFS-1861: --- Filed HDFS-1866. > Rename dfs.datanode.max.xcievers

[jira] [Commented] (HDFS-1840) Terminate LeaseChecker when all writing files are closed.

[ https://issues.apache.org/jira/browse/HDFS-1840?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025943#comment-13025943 ] Cheng Leong commented on HDFS-1840: --- yeah exactly. I was just surprised that no one else

[jira] [Commented] (HDFS-1826) NameNode should save image to name directories in parallel during upgrade

[ https://issues.apache.org/jira/browse/HDFS-1826?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025950#comment-13025950 ] Hairong Kuang commented on HDFS-1826: - Matt, you are right. SaveCurrent already takes c

[jira] [Updated] (HDFS-671) Documentation change for updated configuration keys.

[ https://issues.apache.org/jira/browse/HDFS-671?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eli Collins updated HDFS-671: - Fix Version/s: 0.23.0 bq. This looks like an inconsistency. FsConfig is used by FileContext, and looks lik

[jira] [Commented] (HDFS-1826) NameNode should save image to name directories in parallel during upgrade

[ https://issues.apache.org/jira/browse/HDFS-1826?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025953#comment-13025953 ] Hairong Kuang commented on HDFS-1826: - +1. The patch looks good. I would prefer to have

[jira] [Updated] (HDFS-1862) Improve test reliability of HDFS-1594

[ https://issues.apache.org/jira/browse/HDFS-1862?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eli Collins updated HDFS-1862: -- Resolution: Fixed Hadoop Flags: [Reviewed] Status: Resolved (was: Patch Available) Yes

[jira] [Commented] (HDFS-1862) Improve test reliability of HDFS-1594

[ https://issues.apache.org/jira/browse/HDFS-1862?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025963#comment-13025963 ] Hudson commented on HDFS-1862: -- Integrated in Hadoop-Hdfs-trunk-Commit #610 (See [https://bui

[jira] [Commented] (HDFS-1594) When the disk becomes full Namenode is getting shutdown and not able to recover

[ https://issues.apache.org/jira/browse/HDFS-1594?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025962#comment-13025962 ] Hudson commented on HDFS-1594: -- Integrated in Hadoop-Hdfs-trunk-Commit #610 (See [https://bui

[jira] [Commented] (HDFS-1840) Terminate LeaseChecker when all writing files are closed.

[ https://issues.apache.org/jira/browse/HDFS-1840?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025968#comment-13025968 ] Tsz Wo (Nicholas), SZE commented on HDFS-1840: -- Yes, we have seen this but we

[jira] [Commented] (HDFS-671) Documentation change for updated configuration keys.

[ https://issues.apache.org/jira/browse/HDFS-671?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025980#comment-13025980 ] Tom White commented on HDFS-671: "fs.default.name" has been deprecated in favour of "fs.defa

[jira] [Updated] (HDFS-1052) HDFS scalability with multiple namenodes

[ https://issues.apache.org/jira/browse/HDFS-1052?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eli Collins updated HDFS-1052: -- Comment: was deleted (was: From THU AUG19 till TUE AUG24 (SGT) I'm on vacations and I won't have access

[jira] [Updated] (HDFS-1822) Editlog opcodes overlap between 20 security and later releases

[ https://issues.apache.org/jira/browse/HDFS-1822?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Suresh Srinivas updated HDFS-1822: -- Resolution: Fixed Hadoop Flags: [Reviewed] Status: Resolved (was: Patch Availabl

[jira] [Commented] (HDFS-1822) Editlog opcodes overlap between 20 security and later releases

[ https://issues.apache.org/jira/browse/HDFS-1822?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026025#comment-13026025 ] Hudson commented on HDFS-1822: -- Integrated in Hadoop-Hdfs-trunk-Commit #611 (See [https://bui

[jira] [Commented] (HDFS-1842) Cannot upgrade 0.20.203 to 0.21 with an editslog present

[ https://issues.apache.org/jira/browse/HDFS-1842?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026026#comment-13026026 ] Hudson commented on HDFS-1842: -- Integrated in Hadoop-Hdfs-trunk-Commit #611 (See [https://bui

[jira] [Updated] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Aaron T. Myers updated HDFS-1846: - Attachment: hdfs-1846.1.patch Patch which implements the new preallocation scheme I've described,

[jira] [Updated] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Aaron T. Myers updated HDFS-1846: - Status: Patch Available (was: Open) > Don't fill preallocated portion of edits log with 0x00 > --

[jira] [Updated] (HDFS-1860) when renewing/canceling DelegationToken over http we need to pass exception information back to the caller.

[ https://issues.apache.org/jira/browse/HDFS-1860?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Boris Shkolnik updated HDFS-1860: - Attachment: HDFS-1860-2.patch implemented review comment and also added creation of exception pass

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026049#comment-13026049 ] Hadoop QA commented on HDFS-1846: - -1 overall. Here are the results of testing the latest

[jira] [Updated] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Aaron T. Myers updated HDFS-1846: - Attachment: hdfs-1846.2.patch For some reason I can't explain, on the Hudson box {{`du'}} determin

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026062#comment-13026062 ] Hadoop QA commented on HDFS-1846: - -1 overall. Here are the results of testing the latest

[jira] [Updated] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Aaron T. Myers updated HDFS-1846: - Attachment: editsStored hdfs-1846.3.patch Updated patch which fixes the TestOfflin

[jira] [Commented] (HDFS-1792) Add code to detect valid length of an edits file

[ https://issues.apache.org/jira/browse/HDFS-1792?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026073#comment-13026073 ] Aaron T. Myers commented on HDFS-1792: -- If the proposed change in HDFS-1846 gets check

[jira] [Commented] (HDFS-1850) DN should transmit absolute failed volume count rather than increments to the NN

[ https://issues.apache.org/jira/browse/HDFS-1850?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026074#comment-13026074 ] Todd Lipcon commented on HDFS-1850: --- Some small comments: - {{getNumFailedVols}} - probab

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026076#comment-13026076 ] Hadoop QA commented on HDFS-1846: - -1 overall. Here are the results of testing the latest

[jira] [Updated] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Aaron T. Myers updated HDFS-1846: - Attachment: hdfs-1846.3.patch Re-uploading the patch, since the QA bot tried to apply the binary f

[jira] [Updated] (HDFS-1850) DN should transmit absolute failed volume count rather than increments to the NN

[ https://issues.apache.org/jira/browse/HDFS-1850?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Eli Collins updated HDFS-1850: -- Status: Patch Available (was: Open) > DN should transmit absolute failed volume count rather than incre

[jira] [Commented] (HDFS-1827) TestBlockReplacement waits forever, errs without giving information

[ https://issues.apache.org/jira/browse/HDFS-1827?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026081#comment-13026081 ] Todd Lipcon commented on HDFS-1827: --- +1, nice test improvements. > TestBlockReplacement

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026096#comment-13026096 ] Hadoop QA commented on HDFS-1846: - -1 overall. Here are the results of testing the latest

[jira] [Commented] (HDFS-1850) DN should transmit absolute failed volume count rather than increments to the NN

[ https://issues.apache.org/jira/browse/HDFS-1850?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026101#comment-13026101 ] Hadoop QA commented on HDFS-1850: - -1 overall. Here are the results of testing the latest

[jira] [Commented] (HDFS-1848) Datanodes should shutdown when a critical volume fails

[ https://issues.apache.org/jira/browse/HDFS-1848?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026121#comment-13026121 ] dhruba borthakur commented on HDFS-1848: > Point #1 is limited to allowing an admin

[jira] [Commented] (HDFS-1848) Datanodes should shutdown when a critical volume fails

[ https://issues.apache.org/jira/browse/HDFS-1848?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026125#comment-13026125 ] Koji Noguchi commented on HDFS-1848: bq. It seems like a good idea for a cluster admini

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026126#comment-13026126 ] Todd Lipcon commented on HDFS-1846: --- I ran tests on a non-SSD as well, and also added cod

[jira] [Commented] (HDFS-1848) Datanodes should shutdown when a critical volume fails

[ https://issues.apache.org/jira/browse/HDFS-1848?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026127#comment-13026127 ] dhruba borthakur commented on HDFS-1848: > Would something like mapreduce's healthC

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026130#comment-13026130 ] dhruba borthakur commented on HDFS-1846: +1 > Don't fill preallocated portion of e

[jira] [Commented] (HDFS-1865) Share LeaseChecker thread among DFSClients

[ https://issues.apache.org/jira/browse/HDFS-1865?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026131#comment-13026131 ] dhruba borthakur commented on HDFS-1865: why not share the DFSClient itself? > Sha

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026134#comment-13026134 ] Todd Lipcon commented on HDFS-1846: --- Just ran a sanity check where I disabled preallocati

[jira] [Updated] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Todd Lipcon updated HDFS-1846: -- Resolution: Fixed Fix Version/s: 0.23.0 Hadoop Flags: [Reviewed] Status: Resolved

[jira] [Updated] (HDFS-1827) TestBlockReplacement waits forever, errs without giving information

[ https://issues.apache.org/jira/browse/HDFS-1827?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Matt Foley updated HDFS-1827: - Description: In method checkBlocks(), TestBlockReplacement waits forever on a condition. Failures result

[jira] [Commented] (HDFS-1846) Don't fill preallocated portion of edits log with 0x00

[ https://issues.apache.org/jira/browse/HDFS-1846?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13026141#comment-13026141 ] Hudson commented on HDFS-1846: -- Integrated in Hadoop-Hdfs-trunk-Commit #612 (See [https://bui

[jira] [Updated] (HDFS-1827) TestBlockReplacement waits forever, errs without giving information

[ https://issues.apache.org/jira/browse/HDFS-1827?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Matt Foley updated HDFS-1827: - Attachment: 1827_TestBlockReplacement_v2.patch Thanks, Todd. Uploading again to try to trigger Hudson QA.