You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-dev@hadoop.apache.org by "Chris Douglas (JIRA)" <ji...@apache.org> on 2008/01/24 22:20:35 UTC
[jira] Created: (HADOOP-2705) io.file.buffer.size should default to
a value larger than 4k
io.file.buffer.size should default to a value larger than 4k
------------------------------------------------------------
Key: HADOOP-2705
URL: https://issues.apache.org/jira/browse/HADOOP-2705
Project: Hadoop Core
Issue Type: Improvement
Components: conf
Reporter: Chris Douglas
Priority: Minor
Fix For: 0.16.0
Attachments: 2705-0.patch
Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (HADOOP-2705) io.file.buffer.size should default to
a value larger than 4k
Posted by "Nigel Daley (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Nigel Daley updated HADOOP-2705:
--------------------------------
Resolution: Fixed
Assignee: Chris Douglas
Status: Resolved (was: Patch Available)
I just committed this. Thanks Chris!
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Hadoop QA (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562372#action_12562372 ]
Hadoop QA commented on HADOOP-2705:
-----------------------------------
-1 overall. Here are the results of testing the latest attachment
http://issues.apache.org/jira/secure/attachment/12373968/2705-0.patch
against trunk revision 614721.
@author +1. The patch does not contain any @author tags.
javadoc +1. The javadoc tool did not generate any warning messages.
javac +1. The applied patch does not generate any new compiler warnings.
findbugs +1. The patch does not introduce any new Findbugs warnings.
core tests -1. The patch failed core unit tests.
contrib tests +1. The patch passed contrib unit tests.
Test results: http://hudson.zones.apache.org/hudson/job/Hadoop-Patch/1670/testReport/
Findbugs warnings: http://hudson.zones.apache.org/hudson/job/Hadoop-Patch/1670/artifact/trunk/build/test/findbugs/newPatchFindbugsWarnings.html
Checkstyle results: http://hudson.zones.apache.org/hudson/job/Hadoop-Patch/1670/artifact/trunk/build/test/checkstyle-errors.html
Console output: http://hudson.zones.apache.org/hudson/job/Hadoop-Patch/1670/console
This message is automatically generated.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Doug Cutting (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562757#action_12562757 ]
Doug Cutting commented on HADOOP-2705:
--------------------------------------
I think it is too late in the 0.16 cycle for this change. We should make it in 0.17, since it is not a bug fix, but a potentially incompatible, minor performance enhancement. In my original comment, above, I did not notice that it was targetted at 0.16.0. I should have commented then. Sorry!
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Nigel Daley (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562225#action_12562225 ]
Nigel Daley commented on HADOOP-2705:
-------------------------------------
+1 code review
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Doug Cutting (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562766#action_12562766 ]
Doug Cutting commented on HADOOP-2705:
--------------------------------------
> In my personal opinion, this config change was useful and extremely unlikely to break anything.
But that's not the criteria we've agreed on for stuff that goes in after the freeze. The criteria is blockers and documentation changes. This is neither.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Hudson (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562859#action_12562859 ]
Hudson commented on HADOOP-2705:
--------------------------------
Integrated in Hadoop-trunk #380 (See [http://hudson.zones.apache.org/hudson/job/Hadoop-trunk/380/])
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Raghu Angadi (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562235#action_12562235 ]
Raghu Angadi commented on HADOOP-2705:
--------------------------------------
The real issue might be overloaded use of "io.file.buffer.size". If a particular compression has a more optimal buffer size, shouldn't it use that , or somthing like max(io.buffer.size, more_optimal_than_default)? There are many other places this might need to be fixed. I think Konstantin filed another jira that propose a different buffer size for Datanode node disk (and may be network). I think io.file.buffer.size can't be tweaked be decent for so many different contexts.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (HADOOP-2705) io.file.buffer.size should default to
a value larger than 4k
Posted by "Chris Douglas (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Chris Douglas updated HADOOP-2705:
----------------------------------
Status: Patch Available (was: Open)
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Doug Cutting (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562229#action_12562229 ]
Doug Cutting commented on HADOOP-2705:
--------------------------------------
This could have a significant impact on heap size for applications that keep lots of files open. For example, Nutch and HBase. So, if we do commit this, we should list it as an incompatible change and suggest that folks who are short on RAM might use the prior value.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Chris Douglas (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562336#action_12562336 ]
Chris Douglas commented on HADOOP-2705:
---------------------------------------
My mistake: the difference on a single node is very slight, typically around 5% on reads for most cases. Lzo doesn't distinguish itself as was suspected (following the write tests, the first read test is significantly slower; I'm not sure why).
If this is worthwhile, it won't be clear from the results I have. My apologies.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Doug Cutting (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562726#action_12562726 ]
Doug Cutting commented on HADOOP-2705:
--------------------------------------
I'm confused too. This is an incompatible, non-blocker, performance improvement, filed long after the freeze. Why is it included in 0.16.0? I interpreted Chris' last comment to say that the performance improvement offered by this patch was actually moderate. In any case, the measured performance improvement is limited to a single place (lzo) while io.file.buffer.size is used widely throughout the system, and the impact of the change might thus be great.
I don't mean to make too big of a deal about this, since anyone who suffers from this change has an easy workaround, namely to reset the value back to 4k. But I don't follow the process here.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Chris Douglas (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562722#action_12562722 ]
Chris Douglas commented on HADOOP-2705:
---------------------------------------
bq. To be clear, this patch improves reads by 5% for single nodes only but by 40% when > a single node?
No, the patch has a measured 5% single-node improvement on reads. The 40% was an artifact of the benchmark and not a real result. Specifically: the 4k baseline was collected in the same run as a series of write benchmarks. Running without the write benchmarks improves the first read benchmark significantly, in that case the lzo, block compressed SequenceFiles. This was wrongly attributed to the buffer size; runs directly comparing reads and varying only the buffer size confirmed the more modest improvement.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "stack (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562764#action_12562764 ]
stack commented on HADOOP-2705:
-------------------------------
+1 on reverting. 5% improvement on reads is always nice but cost looks too high at least from the hbase perspecitve (logs of open files) and in advance of our runing evaluation tests. Thanks.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (HADOOP-2705) io.file.buffer.size should default to
a value larger than 4k
Posted by "Owen O'Malley (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Owen O'Malley updated HADOOP-2705:
----------------------------------
Fix Version/s: (was: 0.16.0)
0.17.0
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.17.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "stack (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562719#action_12562719 ]
stack commented on HADOOP-2705:
-------------------------------
Description says upping buffer size improves read times by 40% but later, says "...typically around 5% on reads for most cases" with a 'single node' qualifier.
To be clear, this patch improves reads by 5% for single nodes only but by 40% when > a single node? Thanks.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Doug Cutting (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12562740#action_12562740 ]
Doug Cutting commented on HADOOP-2705:
--------------------------------------
Nutch applications can easily keep hundreds of files open, and each file has multiple layers of buffers. With 1000 files, each with say 5 buffers, this would add 160MB of heap, which should not be done lightly.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Reopened: (HADOOP-2705) io.file.buffer.size should default
to a value larger than 4k
Posted by "Owen O'Malley (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Owen O'Malley reopened HADOOP-2705:
-----------------------------------
Doug feels like process has been violated by this patch, so I'll roll it back. In my personal opinion, this config change was useful and extremely unlikely to break anything.
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Assignee: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (HADOOP-2705) io.file.buffer.size should default to
a value larger than 4k
Posted by "Chris Douglas (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-2705?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Chris Douglas updated HADOOP-2705:
----------------------------------
Attachment: 2705-0.patch
> io.file.buffer.size should default to a value larger than 4k
> ------------------------------------------------------------
>
> Key: HADOOP-2705
> URL: https://issues.apache.org/jira/browse/HADOOP-2705
> Project: Hadoop Core
> Issue Type: Improvement
> Components: conf
> Reporter: Chris Douglas
> Priority: Minor
> Fix For: 0.16.0
>
> Attachments: 2705-0.patch
>
>
> Tests using HADOOP-2406 suggest that increasing this to 32k from 4k improves read times for block, lzo compressed SequenceFiles by over 40%; 32k is a relatively conservative bump.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.