hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Matthew John <tmatthewjohn1...@gmail.com>
Subject When is Map <Node, TaskInProgress> updated for a Job
Date Thu, 05 May 2011 02:50:56 GMT
Hi all,

I went down the lines of figuring out how the JobTracker, JobInProgress and
TaskScheduler combined works out the problem of giving a Task (corresponding
to an InputSplit) to a Node (corresponding to a TaskTracker in the node). I
understand that a set of methods in JobInProgress like obtainLocalMapTask
(first tries to give a local node for running the Map task) do the required
when TaskScheduler tries to give a Task to a free TaskTracker. And this
finally goes down to going  through a mapping Map <Node, TaskInProgress> and
allotting a TaskInProgress (corresponding to a InputSplit/Task) to the

My question when is this Map<Node, TaskInProgress> updated? Is it done along
with the createNewSplits performed by the JobClient ? Where can I find the
code for these Mappings getting initialized and populated/updated ?


Matthew John

  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message