[Beowulf] Rackable / SGI

Andrew M.A. Cater amacater at galactic.demon.co.uk
Sat Apr 4 06:38:45 PDT 2009


On Fri, Apr 03, 2009 at 08:15:06PM -0400, Joe Landman wrote:
> Mark Hahn wrote:
>
>> from my position, XFS was a semi-fringe option for people who 
>> distrusted ext3 for some reason.  (and there were a few solid ones, 
>> mainly just  >8TB.)  going forward, I expect to use ext4
>
> I wouldn't use ext3 for anything other than small partitions (100 GB or  
> so).  Too many cases seeing the fsck need to get triggered for some  
> reason ... the wait is horrible.
>

Interesting. Since I'm stuck using Red Hat and IBM, I've been hit by 
this on a 10TB storage shelf. Red Hat will only offer me ext3 and 8TB.
IBM storage on a Megaraid card which handles the disks as one physical 
volume

[Debian would offer me more, since Debian 5 will format to greater than 
8TB - and other file systems.]

I just want a 10TB "bucket" in which to store slowly changing/increasing 
files and I'm in a datacentre with UPS so I'm not too worried about the 
fsck - until it happens of course.
>
> I don't see many people moving hundreds of TB off XFS onto something  
> without a really good reason (and other people running into the other  
> things bugs).
>
> Zfs is not the revealed word of some deity, in file systems.  This mind  
> set is painful to deal with, and often winds up with people having  
> *very* unrealistic expectations of what it is, what it can do, and how  
> it performs.  Our experience in speaking to customers about it, suggests  
> that the primary reason why there is interest in it, is ease of  
> management.  There are some who are interested in the data integrity  
> bits.  This said, it ain't perfect.  It has bugs, and people have been  
> bitten by them.

Amen, brother :)

Andy

> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf




More information about the Beowulf mailing list