| clear query|facets|time |
Search criteria: .
Results from 131 to 140 from
491 (0.06s).
|
|
|
Loading phrases to help you
refine your search...
|
|
[HDFS-3726] QJM: if a logger misses an RPC, don't retry that logger until next segment - HDFS - [issue]
|
|
...Currently, if a logger misses an RPC in the middle of a log segment, or misses the startLogSegment RPC (eg it was down or network was disconnected during that time period), then it will thro...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3726
Author: Todd Lipcon,
2012-09-06, 18:00
|
|
|
[HDFS-3891] QJM: SBN fails if selectInputStreams throws RTE - HDFS - [issue]
|
|
...Currently, QJM's selectInputStream method throws an RTE if a quorum cannot be reached. This propagates into the Standby Node and causes the whole node to crash. It should handle this error a...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3891
Author: Todd Lipcon,
2012-09-06, 17:32
|
|
|
[HDFS-3867] QJM: Support rolling restart of JNs - HDFS - [issue]
|
|
...In order to perform upgrades or other maintenance, it is useful to be able to perform a rolling restart of the journal nodes while the NameNode is active.Currently, this does not work, becau...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3867
Author: Todd Lipcon,
2012-09-06, 01:19
|
|
|
[HDFS-3876] NN should not RPC to self to find trash defaults (causes deadlock) - HDFS - [issue]
|
|
...When transitioning a SBN to active, I ran into the following situation: the TrashPolicy first gets loaded by an IPC Server Handler thread. The initialize function then tries to make an RPC t...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3876
Author: Todd Lipcon,
2012-09-05, 19:31
|
|
|
[HDFS-3870] QJM: add metrics to JournalNode - HDFS - [issue]
|
|
...The JournalNode should expose some basic metrics through the usual interface. In particular: the writer epoch, accepted epoch, the last written transaction ID and last committed txid (which ...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3870
Author: Todd Lipcon,
2012-09-05, 05:31
|
|
|
[HDFS-3884] QJM: Journal format() should reset cached values - HDFS - [issue]
|
|
...Simple bug in the JournalNode: it caches certain values (eg accepted epoch) in memory, and the cached values aren't reset when the journal is formatted. So, after a format, further calls to ...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3884
Author: Todd Lipcon,
2012-09-05, 05:29
|
|
|
[HDFS-3869] QJM: expose non-file journal manager details in web UI - HDFS - [issue]
|
|
...Currently, the NN web UI only contains NN storage directories on local disk. It should also include details about any non-file JournalManagers in use.This JIRA targets the QJM branch, but wi...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3869
Author: Todd Lipcon,
2012-09-05, 05:16
|
|
|
[HDFS-3863] QJM: track last "committed" txid - HDFS - [issue]
|
|
...Per some discussion with Chao Shi here, we should keep track of the "last committed txid" on each JournalNode. Then during any recovery operation, we can sanity-check that we aren't asked to...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3863
Author: Todd Lipcon,
2012-09-05, 05:13
|
|
|
[HDFS-3862] QJM: don't require a fencer to be configured if shared storage has built-in single-writer semantics - HDFS - [issue]
|
|
...Currently, NN HA requires that the administrator configure a fencing method to ensure that only a single NameNode may write to the shared storage at a time. Some shared edits storage impleme...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3862
Author: Todd Lipcon,
2012-09-01, 19:55
|
|
|
[HDFS-3872] Store block ID in block metadata header - HDFS - [issue]
|
|
...We recently had an interesting local filesystem corruption in one cluster, which caused a block and its associated metadata file to get replaced with a data/meta pair from an entirely differ...
|
|
|
http://issues.apache.org/jira/browse/HDFS-3872
Author: Todd Lipcon,
2012-08-30, 17:52
|
|
|
|
