hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Michael Thomas <tho...@hep.caltech.edu>
Subject Re: Disk configuration.:1
Date Mon, 13 Jul 2009 20:57:26 GMT
On 07/13/2009 01:01 PM, Todd Troxell wrote:
> Hello,
> On Mon, Jul 13, 2009 at 11:50:45AM -0700, Dmitry Pushkarev wrote:
>> How do people usually setup drives? For example will it be better to mount
>> them to two separate folders and feed these folder to both tasktracker and
>> datanode? Or setup LVM with raid 0 to maximize bandwidth.
> Related to this, I've been searching for details on large data nodes,
> specifically 4x2T -- primary use case is low hit data archiving.
> Any known issue with running such large (8T) data nodes?

We have 4 x 6TB, 2 x 13TB, and 2 x 42TB datanodes.  The smaller ones run 
xfs and the larger ones run solaris + zfs.  Decommissioning these large 
datanodes takes quite a bit longer than it does for our smaller (2TB) 
datanodes, but fortunately we don't have to do it very often.


View raw message