Thanks Sudhakara for your reply.
I did my experminets by varing number of reducers and made it double in
each experiments .I have a qustion regarding to the response time.Suppose
there is 6 cluster nodes and in first experminet i have 3 reducers and it
gets doubled (6 ) in second experiment and
See https://builds.apache.org/job/Hadoop-Mapreduce-trunk/1394/
###
## LAST 60 LINES OF THE CONSOLE
###
[...truncated 28876 lines...]
Tests run: 5, Failures: 0, Errors:
Thomas Graves created MAPREDUCE-5137:
Summary: AM web UI: clicking on Map Task results in 500 error
Key: MAPREDUCE-5137
URL: https://issues.apache.org/jira/browse/MAPREDUCE-5137
Project: Hadoop
Hi Samanesh,
Increasing the reducer for a job would not help as you excepting. In most
of MR jobs more then 60% time will spent in mapper phase(it depends upon
what type of operation performing on data in map and reducer phase).
Increasing the number of reduces increases the framework overhead,
Vinod Kumar Vavilapalli created MAPREDUCE-5138:
--
Summary: Fix LocalDistributedCacheManager after YARN-112
Key: MAPREDUCE-5138
URL: https://issues.apache.org/jira/browse/MAPREDUCE-5138
[
https://issues.apache.org/jira/browse/MAPREDUCE-5138?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Vinod Kumar Vavilapalli resolved MAPREDUCE-5138.
Resolution: Fixed
Fix Version/s: 2.0.5-beta
Hadoop
Sudhakara,thanks again for your information.
Actually the reason i am focused on response time is i am going to modify
hadoop to skip the sort phase in mapTask and run a sample like wordCount
example on modified hadoop (skipped sort in map task) and compare its
performance with unmodified hadoop
Hi guys :
Seems like it would be simpler if the existing mapreduce repo had a pom.xml
for building, rather than build.xml.
Could there be a JIRA made to this effect?
--
Jay Vyas
http://jayunit100.blogspot.com
By 'existing', did you mean branch 1 ?
Branch 2 and trunk already are using pom.xml
Cheers
On Tue, Apr 9, 2013 at 5:02 PM, Jay Vyas jayunit...@gmail.com wrote:
Hi guys :
Seems like it would be simpler if the existing mapreduce repo had a pom.xml
for building, rather than build.xml.
Could
Folks,
I've created a release candidate (rc0) for hadoop-2.0.4-alpha that I would like
to release.
This is a bug-fix release which solves a number of issues discovered during
integration testing of the full-stack.
The RC is available at:
Vinod Kumar Vavilapalli created MAPREDUCE-5139:
--
Summary: Update MR App after YARN-486
Key: MAPREDUCE-5139
URL: https://issues.apache.org/jira/browse/MAPREDUCE-5139
Project: Hadoop
Zhijie Shen created MAPREDUCE-5140:
--
Summary: The mapping between yarn and mapreduce states needs to be
updated when application store is delayed
Key: MAPREDUCE-5140
URL:
12 matches
Mail list logo