| clear query|facets|time |
Search criteria: .
Results from 161 to 170 from
488 (0.09s).
|
|
|
Loading phrases to help you
refine your search...
|
|
[HDFS-3725] Fix QJM startup when individual JNs have gaps - HDFS - [issue]
|
|
...This fixes a bug in the HDFS-3077 branch:If one of the JNs goes down and comes back up, it may have a discontiguous set of logs in its storage directories. This means that a future getEditLo...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3725
Author: Todd Lipcon,
2012-07-30, 23:36
|
|
|
Re: Test failed when compiling Trunk - HDFS - [mail # user]
|
|
...Hi Clement, Can you try boosting the timeout for this test case to a higher value? I wonder if your machine is just slower than the ones which we developed the test on originally? &nbs...
|
|
|
Author: Todd Lipcon,
2012-07-29, 20:53
|
|
|
[HDFS-2533] Remove needless synchronization on FSDataSet.getBlockFile - HDFS - [issue]
|
|
...HDFS-1148 discusses lock contention issues in FSDataset. It provides a more comprehensive fix, converting it all to RWLocks, etc. This JIRA is for one very specific fix which gives a decent ...
|
|
|
http://issues.apache.org/jira/browse/HDFS-2533
Author: Todd Lipcon,
2012-07-26, 04:50
|
|
|
[HDFS-3693] QJM: JNStorage should read its storage info even before a writer becomes active - HDFS - [issue]
|
|
...In order for QJM to work with HA, the standby needs to be able to read from a JournalNode even when no active has written to it. In the current code, it reads the StorageInfo only when newEp...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3693
Author: Todd Lipcon,
2012-07-25, 21:47
|
|
|
[HDFS-3692] QJM: support purgeEditLogs() call to remotely purge logs - HDFS - [issue]
|
|
...This API is currently marked TODO. We need it to maintain bounded disk space usage on the JournalNode storage....
|
|
|
http://issues.apache.org/jira/browse/HDFS-3692
Author: Todd Lipcon,
2012-07-25, 21:46
|
|
|
[HDFS-3694] QJM: Fix getEditLogManifest to fetch httpPort if necessary - HDFS - [issue]
|
|
...This is necessary for QJM to work with HA. When the NNs start up, they start in standby state and try to read from the JournalNodes. So they call getEditLogManifest(). But they don't call ge...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3694
Author: Todd Lipcon,
2012-07-25, 21:40
|
|
|
Re: How to rebuild the shared edits directory - HDFS - [mail # user]
|
|
...Hi Jeff, I don't know the HP offerings very well myself, but I know some of our customers are successfully using lower end NetApp devices. You should also be aware that work on t...
|
|
|
Author: Todd Lipcon,
2012-07-25, 18:51
|
|
|
Re: testing HDFS-3077 on branch-2 - HDFS - [mail # dev]
|
|
...Hey Andy Really glad you'll be testing this! We should sync up on IRC - I can point you in the right direction as to what should and shouldn't yet work, etc. Of course, sam...
|
|
|
Author: Todd Lipcon,
2012-07-24, 05:33
|
|
|
[HDFS-3685] IPC server logs a useless message when shutting down socket - HDFS - [issue]
|
|
...I occasionally see this WARN message out of the NameNode:12/07/19 10:37:37 WARN ipc.Server: Ignoring socket shutdown exceptionwith no further details. This message isn't useful - it either n...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3685
Author: Todd Lipcon,
2012-07-19, 17:44
|
|
|
[HDFS-3644] OEV should recognize and deal with 0.20.20x opcode versions - HDFS - [issue]
|
|
...We have some opcode conflicts for edit logs between 0.20.20x (LV -19, -31) vs newer versions. For edit log loading, we dealt with this by forcing users to save namespace on an earlier versio...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3644
Author: Todd Lipcon,
2012-07-16, 23:14
|
|
|
|
