[Linux-cluster] GFS Tuning - it's just slow, to slow for production

Alan A alan.zg at gmail.com
Tue Mar 16 20:01:28 UTC 2010


I rebuild the share as GFS2, and mounted GFS2 instead of GFS.

In /etc/fstab I am mounting with:

/dev/mapper/vg_acct10-lv_acct10 /acct10 gfs2 defaults 1 2

I tried mounting:
/dev/mapper/vg_acct10-lv_acct10 /acct10 gfs2 -o reltime 1 2

and
/dev/mapper/vg_acct10-lv_acct10 /acct10 gfs2  -o notime 1 2

It complained about /etc/fstab not having valid arguments. I also got  very
different parameters with gfs2_tool gettune /mountpoint then what I saw in
gfs:

[root at fenclxmrcati11 bin]# gfs2_tool gettune /acct10
new_files_directio = 0
new_files_jdata = 0
quota_scale = 1.0000   (1, 1)
logd_secs = 1
recoverd_secs = 60
statfs_quantum = 30
stall_secs = 600
quota_cache_secs = 300
quota_simul_sync = 64
statfs_slow = 0
complain_secs = 10
max_readahead = 262144
quota_quantum = 60
quota_warn_period = 10
jindex_refresh_secs = 60
log_flush_secs = 60
incore_log_blocks = 1024



My question - how do I mount the volume via /etc/fstab with -o noatime or -o
reltime?
For quota management - Documentation suggests mounting with mount -o
quota=account options, is this necessary if I set the quotas with gfs2_quota
command?







On Thu, Mar 4, 2010 at 11:25 AM, Gordan Bobic <gordan at bobich.net> wrote:

> Are you concurrently accessing same directories from multiple nodes? If so,
> re-arrange the access pattern so each node is accessing independent
> subtrees. Otherwise you'll have massive lock churn and very poor latencies.
>
> Gordan
>
> "Alan A" <alan.zg at gmail.com> wrote:
>
> >We are trying to deploy GFS in production, and are experiencing major
> >performance issues. What parameters in GFS settune can be changed to
> >increase I/O, to better tune performance? Application we run utilizes a
> lot
> >of I/O, please advise.
> >
> >We experience OK performance when starting, but as things ramp up and we
> get
> >few processes going GFS slows dramatically.
> >
> >--
> >Alan A.
> >--
> >Linux-cluster mailing list
> >Linux-cluster at redhat.com
> >https://www.redhat.com/mailman/listinfo/linux-cluster
> --
> Sent from my Android phone with K-9 Mail. Please excuse my brevity.
> --
> Linux-cluster mailing list
> Linux-cluster at redhat.com
> https://www.redhat.com/mailman/listinfo/linux-cluster
>



-- 
Alan A.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listman.redhat.com/archives/linux-cluster/attachments/20100316/d6d169a4/attachment.htm>


More information about the Linux-cluster mailing list