On Feb 24, 2011, at 5:41 PM, 朱韬 wrote:
> Hi,guys:
> To meet the needs of the current project, I have to modify the policy of
> scheduler. So I checked out the source code
> fromhttp://svn.apache.org/repos/asf/hadoop/mapreduce/trunk/. Then I modified
> some code and compiled using this scr
(Removing common-dev, because this isn't a dev question.)
On Mar 1, 2011, at 6:13 AM, bikash sharma wrote:
> Hi,
> Is there a way to disable the use of pipelining , i.e., the reduce phase is
> started only after the map phase is completed?
Set mapred.reduce.slowstart.completed.maps to 1.
Be aw
If your cluster is heterogeneous like that, the you will most likely need to
have different configurations per node. In other words, not every node needs
to use the same mapred-site.xml.
On Mar 12, 2011, at 9:34 AM, xi yang wrote:
> Thanks, Harsh.
> I need to set node-A with 4 slots for map
Thanks, Harsh.
I need to set node-A with 4 slots for map tasks, and node-B with 3 ... I
mean I want to specify different map task capacity for different nodes, how
to distinguish different nodes can we do that ?
2011/3/12 Harsh J
> Q: Can we specify the map task capacity value for each nod
Q: Can we specify the map task capacity value for each node
A: Yes, they are task-tracker properties after all.
--
Harsh J
www.harshj.com
Thanks in advance
xyang
(Removing common-dev, because this isn't really a dev question)
On Feb 25, 2011, at 5:52 AM, bikash sharma wrote:
> Hi,
> How is task slot in Hadoop defined with respect to scheduling a map/reduce
> task on such slots available on TaskTrackers?
On a TaskTracker, one sets how many maps
(Removing common-dev, because this isn't a dev question)
On Feb 26, 2011, at 7:25 AM, bikash sharma wrote:
> Hi,
> I have a 10 nodes Hadoop cluster, where I am running some benchmarks for
> experiments.
> Surprisingly, when I initialize the Hadoop cluster
> (hadoop/bin/start-mapred.sh), in many
ERROR streaming.StreamJob: Error Launching job : Input path does not exist
--
Key: HADOOP-7185
URL: https://issues.apache.org/jira/browse/HADOOP-7185
Project: Hadoop Common
Hi
I followed these instructions to install hadoop-0.20-secure branch:
http://hbaseblog.com/2010/07/21/up-and-running-with-secure-hadoop/
The KDC starts correctly and kinit issues tickets without any
problems.Also if security option is disabled, all the hadoop daemons start
correctly.But if the
10 matches
Mail list logo