[ 
http://issues.apache.org/jira/browse/HADOOP-195?page=comments#action_12378342 ] 

paul sutter commented on HADOOP-195:
------------------------------------


dominek,

if you're not moving gigabytes of data, its unlikely that you need to worry 
about one or two buffer copies.

if an application does move gigabytes of data, and you have some other use for 
the CPU while you're moving data, you definitely dont want that data flowing 
through the file cache because you are incurring a buffer copy and the data 
volumes are too large to get any benefit from the file cache. 

but it feels like there are a few too many if's for our discussion to be of 
much importance ;) its definitely a fun area of work!

paul



> transfer map output transfer with http instead of rpc
> -----------------------------------------------------
>
>          Key: HADOOP-195
>          URL: http://issues.apache.org/jira/browse/HADOOP-195
>      Project: Hadoop
>         Type: Improvement

>   Components: mapred
>     Versions: 0.2
>     Reporter: Owen O'Malley
>     Assignee: Owen O'Malley
>      Fix For: 0.3

>
> The data transfer of the map output should be transfered via http instead 
> rpc, because rpc is very slow for this application and the timeout behavior 
> is suboptimal. (server sends data and client ignores it because it took more 
> than 10 seconds to be received.)

-- 
This message is automatically generated by JIRA.
-
If you think it was sent incorrectly contact one of the administrators:
   http://issues.apache.org/jira/secure/Administrators.jspa
-
For more information on JIRA, see:
   http://www.atlassian.com/software/jira

Reply via email to