| clear query|facets|time |
Search criteria: .
Results from 1 to 10 from
19 (0.132s).
|
|
|
Loading phrases to help you
refine your search...
|
|
[HDFS-4239] Means of telling the datanode to stop using a sick disk - HDFS - [issue]
|
|
...If a disk has been deemed 'sick' – i.e. not dead but wounded, failing occasionally, or just exhibiting high latency – your choices are:1. Decommission the total datanode. I...
|
|
|
http://issues.apache.org/jira/browse/HDFS-4239
Author: stack,
2013-03-22, 09:55
|
|
|
[HDFS-4580] 0.95 site build failing with 'maven-project-info-reports-plugin: Could not find goal 'dependency-info'' - HDFS - [issue]
|
|
...Our report plugin is 2.4. Says that 'dependency-info' is new since 2.5 on the mvn report page:project-info-reports:dependency-info (new in 2.5> is used to generate code snippets to b...
|
|
|
http://issues.apache.org/jira/browse/HDFS-4580
Author: stack,
2013-03-08, 20:37
|
|
|
[HDFS-4203] After recoverFileLease, datanode gets stuck complaining block '...has out of data GS ....may already be committed' - HDFS - [issue]
|
|
...After calling recoverFileLease, an append to a file gets stuck retying this:2012-11-16 13:06:14,298 DEBUG [IPC Server handler 2 on 53224] namenode.PendingReplicationBlocks(92): Removing pend...
|
|
|
http://issues.apache.org/jira/browse/HDFS-4203
Author: stack,
2012-11-16, 22:32
|
|
|
[HDFS-2296] If read error while lease is being recovered, client reverts to stale view on block info - HDFS - [issue]
|
|
...We are seeing the following issue around recoverLease over in hbaselandia. DFSClient calls recoverLease to assume ownership of a file. The recoverLease returns to the client but ...
|
|
|
http://issues.apache.org/jira/browse/HDFS-2296
Author: stack,
2012-08-24, 07:46
|
|
|
Re: [VOTE CANCELLED] Commit hdfs-630 to 0.21? - HDFS - [mail # dev]
|
|
...Nicholas reviewed hdfs-630 patch and made some suggestions for improvements. Cosmin, the patch writer, obliged. After chatting with Nicholas and Cosmin, I will reverse the hdfs-6...
|
|
|
Author: stack,
2009-12-21, 00:49
|
|
|
[VOTE] Commit hdfs-630 to 0.21? - HDFS - [mail # dev]
|
|
...I'd like to propose a vote on having hdfs-630 committed to 0.21 (Its already been committed to TRUNK). hdfs-630 adds having the dfsclient pass the namenode the name of datanodes its de...
|
|
|
Author: stack,
2009-12-15, 05:56
|
|
|
Commit hdfs-630 to 0.21? - HDFS - [mail # dev]
|
|
...HDFS-630 is kinda critical to us over in hbase. We'd like to get it into 0.21 (Its been committed to TRUNK). Its probably hard to argue its a blocker for 0.21. We could run...
|
|
|
Author: stack,
2009-12-12, 23:54
|
|
|
Re: I just got "Cannot complete block: block has not been COMMITTED by the client" - HDFS - [mail # user]
|
|
...Follow up: This was not an hdfs-630 issue. It was caused by my not having the same patched jar everywhere across the cluster. Pardon the noise. St.Ack On Wed, Nov 11, 2009 ...
|
|
|
Author: stack,
2009-11-14, 21:34
|
|
|
Re: I just got "Cannot complete block: block has not been COMMITTED by the client" - HDFS - [mail # user]
|
|
...I removed HDFS-630 and this issue seems to go away. I haven't seen it over the last few restarts. St.Ack On Wed, Nov 11, 2009 at 3:46 PM, stack wrote: ...
|
|
|
Author: stack,
2009-11-12, 01:53
|
|
|
Small cluster, " Bad connect ack with firstBadLink as XX.XX.XX.140:51010" - HDFS - [mail # user]
|
|
...I'm testing flush. I'm using branch-0.21 hdfs. I run a write load and kill one of the members of my little 4-node hdfs cluster. 1 of the 4 datanodes being down does more damage t...
|
|
|
Author: stack,
2009-11-12, 00:37
|
|
|
|
