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 "Doug Cutting (JIRA)" <ji...@apache.org> on 2007/09/06 22:29:28 UTC
[jira] Created: (HADOOP-1850) eliminate parameters that must change
with cluster size
eliminate parameters that must change with cluster size
-------------------------------------------------------
Key: HADOOP-1850
URL: https://issues.apache.org/jira/browse/HADOOP-1850
Project: Hadoop
Issue Type: Improvement
Components: mapred
Reporter: Doug Cutting
Fix For: 0.15.0
As far as possible, configurations should be independent of cluster size. The cluster size is a parameter that the system knows and should thus be used to size things accordingly. Currently we know that the following parameters must be adjusted to non-default values for large clusters:
- mapred.job.tracker.handler.count
- mapred.reduce.parallel.copies
- tasktracker.http.threads
We should attempt to make each of these either set to something proportional to cluster size or (harder) dynamically sized based on load.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Updated: (HADOOP-1850) eliminate parameters that must change
with cluster size
Posted by "Doug Cutting (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-1850?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Doug Cutting updated HADOOP-1850:
---------------------------------
Description:
As far as possible, configurations should be independent of cluster size. The cluster size is a parameter that the system knows and should thus be used to size things accordingly. Currently we know that the following parameters must be adjusted to non-default values for large clusters:
- mapred.job.tracker.handler.count
- mapred.reduce.parallel.copies
- tasktracker.http.threads
We should attempt to make each of these either set to something proportional to cluster size or (harder) dynamically sized based on load.
was:
As far as possible, configurations should be independent of cluster size. The cluster size is a parameter that the system knows and should thus be used to size things accordingly. Currently we know that the following parameters must be adjusted to non-default values for large clusters:
- mapred.job.tracker.handler.count
- mapred.reduce.parallel.copies
- tasktracker.http.threads
We should attempt to make each of these either set to something proportional to cluster size or (harder) dynamically sized based on load.
> eliminate parameters that must change with cluster size
> -------------------------------------------------------
>
> Key: HADOOP-1850
> URL: https://issues.apache.org/jira/browse/HADOOP-1850
> Project: Hadoop
> Issue Type: Improvement
> Components: mapred
> Reporter: Doug Cutting
> Fix For: 0.15.0
>
>
> As far as possible, configurations should be independent of cluster size. The cluster size is a parameter that the system knows and should thus be used to size things accordingly. Currently we know that the following parameters must be adjusted to non-default values for large clusters:
> - mapred.job.tracker.handler.count
> - mapred.reduce.parallel.copies
> - tasktracker.http.threads
> We should attempt to make each of these either set to something proportional to cluster size or (harder) dynamically sized based on load.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
[jira] Commented: (HADOOP-1850) eliminate parameters that must
change with cluster size
Posted by "Doug Cutting (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/HADOOP-1850?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12528140 ]
Doug Cutting commented on HADOOP-1850:
--------------------------------------
Discussion in HADOOP-1874 indicates that the DFS heartbeat interval should also be adjusted for cluster size.
> eliminate parameters that must change with cluster size
> -------------------------------------------------------
>
> Key: HADOOP-1850
> URL: https://issues.apache.org/jira/browse/HADOOP-1850
> Project: Hadoop
> Issue Type: Improvement
> Components: mapred
> Reporter: Doug Cutting
> Fix For: 0.15.0
>
>
> As far as possible, configurations should be independent of cluster size. The cluster size is a parameter that the system knows and should thus be used to size things accordingly. Currently we know that the following parameters must be adjusted to non-default values for large clusters:
> - mapred.job.tracker.handler.count
> - mapred.reduce.parallel.copies
> - tasktracker.http.threads
> We should attempt to make each of these either set to something proportional to cluster size or (harder) dynamically sized based on load.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.