[OpenAFS] cpu load
sabah
sabah@hep.man.ac.uk
Tue, 18 Nov 2003 21:48:45 +0000 (GMT)
Hi Steven,
Thank you so much.
On Tue, 18 Nov 2003, Jenkins, Steven wrote:
>
> Without knowing any details of your system, from your description, it
> appears that the software raid daemons are accounting for your CPU time.
>
> Without knowing how you've configured your disks (ie, devices,
> controllers, virtual devices, filesystems, mount points), I'd think it
> reasonable for your system, which is a fileserver (I'm assuming), to be
> spending a lot of time doing software raid. I'd also like to know:
/dev/md0 7.7G 6.2G 1.1G 85% /
/dev/hda1 99M 16M 77M 17% /boot
none 251M 0 251M 0% /dev/shm
/dev/md1 484M 149M 311M 33% /usr/vice/cache
/dev/md4 97G 33G 60G 35% /vicepg
/dev/md3 2.9G 33M 2.7G 2% /viceph
/dev/md2 2.9G 33M 2.7G 2% /vicepi
/dev/hdg1 113G 73G 34G 68% /bkupdsk
AFS 8.6G 0 8.5G 0% /afs
This is a copy of raidtab file
-------------------------------------------------------------------------
raiddev /dev/md0
raid-level 1
nr-raid-disks 2
chunk-size 64k
persistent-superblock 1
nr-spare-disks 0
device /dev/hda3
raid-disk 0
device /dev/hdc3
raid-disk 1
raiddev /dev/md1
raid-level 1
nr-raid-disks 2
chunk-size 64k
persistent-superblock 1
nr-spare-disks 0
device /dev/hda6
raid-disk 0
device /dev/hdc6
raid-disk 1
raiddev /dev/md4
raid-level 1
nr-raid-disks 2
chunk-size 64k
persistent-superblock 1
nr-spare-disks 0
device /dev/hda8
raid-disk 0
device /dev/hdc8
raid-disk 1
raiddev /dev/md3
raid-level 1
nr-raid-disks 2
chunk-size 64k
persistent-superblock 1
nr-spare-disks 0
device /dev/hda7
raid-disk 0
device /dev/hdc7
raid-disk 1
raiddev /dev/md2
raid-level 1
nr-raid-disks 2
chunk-size 64k
persistent-superblock 1
nr-spare-disks 0
device /dev/hda5
raid-disk 0
device /dev/hdc5
raid-disk 1
--------------------------------------------------------------------
>
> - is your system is doing anything else besides serving AFS
No
> - how many clients does your system have
90
> - are people doing I/O intensive work on files that reside on your
> fileserver
not always
> - are there any known issues with your combination of OS & raid software
>
I am not aware of any.
> For example, if there are many clients simultaneously doing lots of
> compiles of files in AFS, all of which are on this server, then it might
> be perfectly reasonable to see CPU utilization like you are seeing.
Is this mean even if I remove software raid. Users can not do lots of
compiles of files in AFS?
Many thanks, Sabah.
>
> Steven
>
> -----Original Message-----
> From: openafs-info-admin@openafs.org
> [mailto:openafs-info-admin@openafs.org] On Behalf Of sabah
> Sent: Tuesday, November 18, 2003 2:18 PM
> To: openafs-info@openafs.org
> Subject: [OpenAFS] cpu load
>
>
> Dear All,
> I have an AFS server running linux.
> "
> Linux version 2.4.18-3 (bhcompile@daffy.perf.redhat.com) (gcc version
> 2.96
> 20000731 (Red Hat Linux 7.3 2.96-110)) #1 Thu Apr 18 07:37:53 EDT 2002 "
> If one run "uptime" you get
>
> uptime
> 7:15pm up 11:11, 2 users, load average: 2.36, 2.59, 2.66
>
> Most of the load used by:
> 26 root 16 0 0 0 0 RW 32.0 0.0 161:09 raid1d
> 27 root 15 0 0 0 0 DW 11.5 0.0 67:12 raid1syncd
>
> does anyone know how to get the load down please?
>
> Thanks, Sabah.
>
>
--
***********************************************************************
* From Sabah Salih *
* Department of Physics and Astronomy, *
* The University of Manchester, Oxford Rd, Manchester M13 9PL *
* Tel: +44 1612754171 or x4171 Mobile: 07941344515 *
* E-mail: sabah@hep.man.ac.uk *
* Home: *
* 48 Danes Road, Fallowfield, Manchester *
* M14 5JS *
* *
***********************************************************************