hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Todd Lipcon <t...@cloudera.com>
Subject Re: Why does the default HEARTBEAT_INTERVAL value is 3?
Date Wed, 10 Feb 2010 06:35:45 GMT
On Tue, Feb 9, 2010 at 10:22 PM, Tomer Shiran <tshiran@maprtech.com> wrote:

> Just curious. What limit are you referring to?
>

See the JIRA:

https://issues.apache.org/jira/browse/MAPREDUCE-1266

The limit is the HEARTBEAT_SCALING_FACTOR stuff, and the clusterSize factor
(second comment down)

-Todd


> On Tue, Feb 9, 2010 at 11:42 AM, Todd Lipcon <todd@cloudera.com> wrote:
>
> > On Tue, Feb 9, 2010 at 11:37 AM, Edward Capriolo <edlinuxguru@gmail.com>
> > wrote:
> >
> > > With the setting of 5 each tasktracker checks into the jobtracker
> > > every 5 seconds. The concept is that with enough TaskTrackers , say a
> > > 1000 node cluster 1000/5= 200 will be checking in at and given second.
> >
> > Actually there's already a limit that automatically scales up the
> > heartbeat interval as the cluster size increases. So reducing the
> > minimum won't break scalability on large clusters in any way.
> >
> > -Todd
> >
>
>
>
> --
> Tomer Shiran
> Director of Product Management | MapR Technologies (www.mapr.com) |
> 650-804-8657
>

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