Re: [Networker] Performance issues with large file systems
2006-03-01 06:56:58
On Wed, 1 Mar 2006 11:51:08 +0100, Maarten Boot wrote:
>If I get it right you backup the 4 groups at the same time and they are
on the same (super sized) disk.
Yep.
But we do NOT have ANY influence how the "application owner"
uses the disk - and they don't care about backup speeds :-(
It's very conventient for the Notes guys to go with on large filesystem.
>
>is that a raid5 by any chance?
>
Yes, this a "metaLUN" created from two RAID-5 luns,
which are 4+1 each on Clariion. So the filesystem spans 10 disks 2x(4+1)
and the CX700 should be powerfull enough to handle sequential I/Os
with some kind of "read ahead".
Not worth to mention that the spindles uses different I/O pathes
inside the box.
>if so your paralell datastreams may interfere on the disk level.
Yes, good point.
But our 1st problem was very poor performance WITHOUT the parallelism of
the four groups --> i.e. one group, some clients, saveset=All
(no conflicting I/O at all), so I don't feel that's the point right now.
I still thinking in
- IP issues
- file system issues
Thanks again anybody who replied ... -sg-
To sign off this list, send email to listserv AT listserv.temple DOT edu and
type "signoff networker" in the
body of the email. Please write to networker-request AT listserv.temple DOT edu
if you have any problems
wit this list. You can access the archives at
http://listserv.temple.edu/archives/networker.html or
via RSS at http://listserv.temple.edu/cgi-bin/wa?RSS&L=NETWORKER
|
|
|