SCIENTIFIC-LINUX-USERS Archives

February 2007

SCIENTIFIC-LINUX-USERS@LISTSERV.FNAL.GOV

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Devin Bougie <[log in to unmask]>
Reply To:
Devin Bougie <[log in to unmask]>
Date:
Fri, 9 Feb 2007 17:16:10 -0500
Content-Type:
text/plain
Parts/Attachments:
text/plain (19 lines)
On Feb 5, 2007, at 10:39 AM, Devin Bougie wrote:
> We use 3ware 9500S-12 RAID controllers with 750G disks in a RAID5  
> configuration.  The 3ware controller splits this 6.82TB RAID volume  
> into 2TB devices (sd[c-f]) that we combine into one volume group.

These 2TB devices created by the 3ware controller are 2147450880K  
(which is below the maximum pv size of 2147483647K).  However, we  
found that we could reliably trigger the "attempt to acess beyond end  
of device" error by creating two 1TB volumes that completely use up  
one pv, and formatting them with mkfs.ext3.  (if we make them xfs  
instead of ext3, we only see the error after actually filling up the  
volumes)

It looks like we are able to avoid this by using the maximum VGDA  
kernel size for our 2TB physical volumes (`pvcreate --size  
2147418112K /dev/sdc` instead of just `pvcreate /dev/sdc`).

Devin

ATOM RSS1 RSS2