| clear query|facets|time |
Search criteria: .
Results from 31 to 40 from
62 (0.075s).
|
|
|
Loading phrases to help you
refine your search...
|
|
[HDFS-2290] Block with corrupt replica is not getting replicated - HDFS - [issue]
|
|
...A block has one replica marked as corrupt and two good ones. countNodes() correctly detects that there are only 2 live replicas, and fsck reports the block as under-replicated. But Replicati...
|
|
|
http://issues.apache.org/jira/browse/HDFS-2290
Author: Konstantin Shvachko,
2012-06-04, 17:30
|
|
|
[HDFS-3462] TestDFSClientRetries.busyTest() should restore default xceiver count in the config. - HDFS - [issue]
|
|
...TestDFSClientRetries.busyTest() sets maximum xceiver count in the config to a small value, but does not restore it back to the default. As the result subsequent tests can fail, especially on...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3462
Author: Konstantin Shvachko,
2012-05-31, 14:06
|
|
|
[HDFS-3463] DFSTestUtil.waitCorruptReplicas() should not use file reading time as a timeout measure. - HDFS - [issue]
|
|
...Tests fail because DFSTestUtil.waitCorruptReplicas() does not wait long enough....
|
|
|
http://issues.apache.org/jira/browse/HDFS-3463
Author: Konstantin Shvachko,
2012-05-30, 19:27
|
|
|
[HDFS-535] TestFileCreation occasionally fails because of an exception in DataStreamer. - HDFS - [issue]
|
|
...One of test cases, namely testFsCloseAfterClusterShutdown(), of TestFileCreation fails occasionally....
|
|
|
http://issues.apache.org/jira/browse/HDFS-535
Author: Konstantin Shvachko,
2012-05-21, 18:26
|
|
|
[HDFS-119] logSync() may block NameNode forever. - HDFS - [issue]
|
|
...FSEditLog.logSync() first waits until isSyncRunning is false and then performs syncing to file streams by calling EditLogOutputStream.flush().If an exception is thrown after isSyncRunning is...
|
|
|
http://issues.apache.org/jira/browse/HDFS-119
Author: Konstantin Shvachko,
2012-04-24, 21:54
|
|
|
Re: [DISCUSS] Remove append? - HDFS - [mail # dev]
|
|
...Eli, I went over the entire discussion on the topic, and did not get it. Is there a problem with append? We know it does not work in hadoop-1, only flush() does. Is there anything wron...
|
|
|
Author: Konstantin Shvachko,
2012-03-22, 08:26
|
|
|
Re: [DISCUSS] Remove append? - HDFS - [mail # dev]
|
|
...Hi Dave, Your opinion is very much appreciated. Thanks, On Wed, Mar 21, 2012 at 5:36 AM, Dave Shine wrote: y opinion carries. But I have been hoping to see append be...
|
|
|
Author: Konstantin Shvachko,
2012-03-22, 08:11
|
|
|
[HDFS-107] Data-nodes should be formatted when the name-node is formatted. - HDFS - [issue]
|
|
...The upgrade feature HADOOP-702 requires data-nodes to store persistently the namespaceID in their version files and verify during startup that it matches the one stored on the name-node.When...
|
|
|
http://issues.apache.org/jira/browse/HDFS-107
Author: Konstantin Shvachko,
2012-03-10, 18:43
|
|
|
Re: Review request: trunk->HDFS-1623 merge - HDFS - [mail # dev]
|
|
...Ok I misunderstood the current direction of the merge. On the review request: I intentionally did not remove handling of new files with blocks (non empty). The reason is potenti...
|
|
|
Author: Konstantin Shvachko,
2012-02-09, 20:54
|
|
|
Re: Review request: trunk->HDFS-1623 merge - HDFS - [mail # dev]
|
|
...I was wondering 1. What was the test plan that has been executed for testing this implementation of HA? Besides unit tests. 2. Have you done any benchmarks, comparing current cluster perform...
|
|
|
Author: Konstantin Shvachko,
2012-02-09, 18:54
|
|
|
|
