test results. Benchmakring
work for other systems (e.g., file systems) is probably helpful for you as well.
Wantao
-- Original --
From: "Marcos Ortiz";
Date: Sun, May 8, 2011 02:14 PM
To: "stanley.shi";
Cc: "mapreduce-user";
I guess the property is "mapreduce.job.maxtaskfailures.per.tracker", and the
default value is 4.
Wantao
-- Original --
From: "Jeff Zhang";
Date: Tue, May 10, 2011 04:32 PM
To: "mapreduce-user";
Subject: What is the prop
"org.apache.hadoop.mapred" is the package for old API and
"org.apache.hadoop.mapreduce" is the package for new API. Although the two APIs
have similar functionality, the implementation is different. Hadoop is
migrating from the old API to the new API.
Wantao
---
ystem
mapreduce.cluster.temp.dir
file:///pvfs/hadoop/mapred/temp
mapreduce.jobtracker.staging.root.dir
file:///pvfs/hadoop/mapred/staging
mapreduce.cluster.local.dir
/root/hadoop_local
Does anybody know how to fix this problem?
Thanks for any advice.
Wantao
Hi all,
I did not find where Mapper and Reducer are set in source code of the Terasort
example in Hadoop 0.21.0. So I guess default Mapper and Reducer are used. If
so, what are the classes names for them?
Thanks for any advice.
Wantao
