Re: Datanodes optimizations

2012-03-05 Thread Hairong Kuang
+ Peter and hdfs-dev Awesome, Siying! I am so impressed by the amount of work that you've done to improve HDFS I/O. Could you please revert r23326 r23292 and r23290? I do not think that they will be useful for the warehouse use case. Thanks! Hairong From: Siying Dong mailto:siyin...@fb.com>>

Re: Review Request: ByteBuffer-based read API for DFSInputStream

2012-03-05 Thread Todd Lipcon
--- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/4184/#review5622 --- Ship it! first pass looks good. A few questions: - do you have before

[jira] [Created] (HDFS-3050) refactor OEV to share more code with the NameNode

2012-03-05 Thread Colin Patrick McCabe (Created) (JIRA)
refactor OEV to share more code with the NameNode - Key: HDFS-3050 URL: https://issues.apache.org/jira/browse/HDFS-3050 Project: Hadoop HDFS Issue Type: Improvement Reporter: Colin

[jira] [Created] (HDFS-3049) During the normal loading NN startup process, fall back on a different image or EditLog if we see one that is corrupt

2012-03-05 Thread Colin Patrick McCabe (Created) (JIRA)
During the normal loading NN startup process, fall back on a different image or EditLog if we see one that is corrupt - Key: HDFS-3049 URL: https:/

Review Request: ByteBuffer-based read API for DFSInputStream

2012-03-05 Thread Todd Lipcon
--- This is an automatically generated e-mail. To reply, visit: https://reviews.apache.org/r/4184/ --- Review request for hadoop-hdfs and Todd Lipcon. Summary --- Posting patch t

[jira] [Created] (HDFS-3048) Small race in BlockManager#close

2012-03-05 Thread Eli Collins (Created) (JIRA)
Small race in BlockManager#close Key: HDFS-3048 URL: https://issues.apache.org/jira/browse/HDFS-3048 Project: Hadoop HDFS Issue Type: Bug Components: name-node Affects Versions: 0.23.2

[jira] [Created] (HDFS-3047) DU usage in FSDataset should use a single thread, instead of thread per directory

2012-03-05 Thread Suresh Srinivas (Created) (JIRA)
DU usage in FSDataset should use a single thread, instead of thread per directory - Key: HDFS-3047 URL: https://issues.apache.org/jira/browse/HDFS-3047 Project: Hadoop HD

[jira] [Created] (HDFS-3046) We should test fsck failures for files in /lost+found

2012-03-05 Thread Eli Collins (Created) (JIRA)
We should test fsck failures for files in /lost+found -- Key: HDFS-3046 URL: https://issues.apache.org/jira/browse/HDFS-3046 Project: Hadoop HDFS Issue Type: Bug Components: name

[jira] [Created] (HDFS-3044) fsck move should be non-destructive by default

2012-03-05 Thread Eli Collins (Created) (JIRA)
fsck move should be non-destructive by default -- Key: HDFS-3044 URL: https://issues.apache.org/jira/browse/HDFS-3044 Project: Hadoop HDFS Issue Type: Improvement Components: name-node

[jira] [Created] (HDFS-3045) fsck move should bail on a file if it can't create a block file

2012-03-05 Thread Eli Collins (Created) (JIRA)
fsck move should bail on a file if it can't create a block file --- Key: HDFS-3045 URL: https://issues.apache.org/jira/browse/HDFS-3045 Project: Hadoop HDFS Issue Type: Improvement