[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14565161#comment-14565161
]
Jing Zhao commented on HDFS-7609:
-
The 03 patch looks good to me. +1. I will commit it shor
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14564340#comment-14564340
]
Hadoop QA commented on HDFS-7609:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vo
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14562543#comment-14562543
]
Jing Zhao commented on HDFS-7609:
-
Thanks for sharing the thoughts, Ming! Totally agree wit
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14562214#comment-14562214
]
Ming Ma commented on HDFS-7609:
---
Thanks [~jingzhao]. Good point about saveNamespace.
Regardi
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14561372#comment-14561372
]
Jing Zhao commented on HDFS-7609:
-
bq. any ideas why the current implementation sets NN to
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14561354#comment-14561354
]
Jing Zhao commented on HDFS-7609:
-
Thanks Ming! The new patch looks good to me. One minor i
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14560362#comment-14560362
]
Hadoop QA commented on HDFS-7609:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vo
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14555402#comment-14555402
]
Jing Zhao commented on HDFS-7609:
-
Spent some further time digging into the issue. Besides
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14555024#comment-14555024
]
Jing Zhao commented on HDFS-7609:
-
Thanks for the response, Ming! Yes I agree that in most
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14555003#comment-14555003
]
Ming Ma commented on HDFS-7609:
---
Thanks, [~jingzhao]. In the scenario you described, IIUC, in
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14553292#comment-14553292
]
Jing Zhao commented on HDFS-7609:
-
Thanks for working on this, [~mingma]! Your analysis mak
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14549939#comment-14549939
]
Tsz Wo Nicholas Sze commented on HDFS-7609:
---
{quote}
PriorityQueue#remove is O\(n
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14527438#comment-14527438
]
Hadoop QA commented on HDFS-7609:
-
\\
\\
| (x) *{color:red}-1 overall{color}* |
\\
\\
|| Vo
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14527030#comment-14527030
]
Ming Ma commented on HDFS-7609:
---
#3 in the scenario description above should be "Before nn2 s
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14523562#comment-14523562
]
Ming Ma commented on HDFS-7609:
---
Small retryCache size can also impact the correctness, given
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14394599#comment-14394599
]
Kihwal Lee commented on HDFS-7609:
--
We have seen a related case. In a relatively small clu
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14318940#comment-14318940
]
Chris Nauroth commented on HDFS-7609:
-
I tried testing an old client without call ID su
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14292690#comment-14292690
]
Ming Ma commented on HDFS-7609:
---
[~cnauroth], we upgraded from hadoop 2.0.5 to hadoop 2.4, so
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14291438#comment-14291438
]
Carrey Zhan commented on HDFS-7609:
---
same call stack is found in origin problem. sorry fo
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14290735#comment-14290735
]
Chris Nauroth commented on HDFS-7609:
-
Specifically, the retry cache was added in 2.1.0
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14290731#comment-14290731
]
Chris Nauroth commented on HDFS-7609:
-
[~kihwal] and [~mingma], thank you for the addit
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14290453#comment-14290453
]
Ted Yu commented on HDFS-7609:
--
If PriorityQueue.remove() took much time, can we utilize
Prio
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14289642#comment-14289642
]
Ming Ma commented on HDFS-7609:
---
Yeah, we also had this issue. It appears somehow an entry wi
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14289533#comment-14289533
]
Kihwal Lee commented on HDFS-7609:
--
Compared to 0.23, edit replaying in 2.x is 5x-10x slow
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14278877#comment-14278877
]
Daryn Sharp commented on HDFS-7609:
---
I think there be a separate option to disable popula
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14278085#comment-14278085
]
Carrey Zhan commented on HDFS-7609:
---
Yes you are right. I know the meaning of retry cache
[
https://issues.apache.org/jira/browse/HDFS-7609?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14277507#comment-14277507
]
Daryn Sharp commented on HDFS-7609:
---
We've also noticed a huge performance degradation (1
27 matches
Mail list logo