Re: Job scheduling

2011-06-07 Thread Ian Halperin
For the record, I figured this out. The default task scheduler just assigns tasks to trackers on a first come first served basis as trackers' heartbeats are received; although this might tend to favour data-local and then rack-local trackers at a large enough scale. I switched over to using FairS

Re: Job scheduling

2011-06-07 Thread Ian Halperin
I found from Googling around that I should probably be seeing messages like "Choosing data-local task" and "Choosing rack-local task" - from JobInProgress::addRunningTaskToTIP(). (e.g. here: http://mail-archives.apache.org/mod_mbox/hadoop-mapreduce-dev/201012.mbox/%3C2120373776.44711293532894724.Ja

Re: Job scheduling

2011-06-07 Thread Ian Halperin
Harsh, thanks for the clarification. But my mappers always seem to run elsewhere. Here's an example with 2 splits, both on rack1node1, but the 2 mappers get started on other nodes. Could the "choosing a non-local task" message be significant? I have actually read through the JobTracker source, bu

Re: Job scheduling

2011-06-06 Thread Harsh J
Ian, The reducer needn't run on the same TaskTracker as it does not work on local data. The mapper 21, however, should've run on node:/rack1/rack1node1.local. On Tue, Jun 7, 2011 at 5:09 AM, Ian Halperin wrote: > Hi, > > I might be misunderstanding how scheduling is supposed to work, or I mi

Job scheduling

2011-06-06 Thread Ian Halperin
Hi, I might be misunderstanding how scheduling is supposed to work, or I might have something misconfigured, but my Map/Reduce jobs don't seem to run where my data is located. I get a bunch of these messages: INFO org.apache.hadoop.mapred.JobInProgress: tip:task_201106062049_0001_ m_21 has sp

Re: job scheduling and task scheduling inin map reduce

2010-11-06 Thread Harsh J
Hi, On Sun, Nov 7, 2010 at 12:40 AM, nitin reddy wrote: > where in the source code i mean the class of map reduce the jobs are > mapped from the job scheduler to the task scheduler so that i could > plugin my trust concept to the tasks scheduler and increase the The task-scheduler in play is inv

job scheduling and task scheduling inin map reduce

2010-11-06 Thread nitin reddy
I am working on my cloud computing project, introducing the concept of trust for a node using some data mining techniques. I want to know where in the source code i mean the class of map reduce the jobs are mapped from the job scheduler to the task scheduler so that i could plugin my trust concept