[Linux-cluster] Directories with >100K files

[nick at javacat.f2s.com]

Hi Jeff

thanks for taking the time to reply :)
Please see my comments below -

Quoting Jeff Sturm <jeff.sturm at eprize.com>:

> > -----Original Message-----
> > From: linux-cluster-bounces at redhat.com
> > [mailto:linux-cluster-bounces at redhat.com] On Behalf Of
> > nick at javacat.f2s.com
> > Sent: Tuesday, January 20, 2009 5:19 AM
> > To: linux-cluster at redhat.com
> > Subject: [Linux-cluster] Directories with >100K files
> >
> > We have a GFS filesystem mounted over iSCSI. When doing an
> > 'ls' on directories with several thousand files it takes
> > around 10 minutes to get a response back -
>
> You don't say how many nodes you have, or anything about your
> networking.

4 nodes. Each node has 2 x 1GB NIC's dedicated to iSCSI. Each NIC is on a dedicated iSCSI VLAN on a 1GB switch. The storage is on a Dell MD3000i.

>
> Some general pointers:
>
> - A plain "ls" is probably much faster any variant that fetches inode
> metatdata, e.g. "ls -l".  The latter performs a stat() on each
> individual file which in turn triggers locking activity of some sort.
> This is known to be slow on GFS1.  (I've heard reports that GFS2 is/will
> be better.)
>
> - You want a fast, reliable low-latency network for your cluster.  Intel
> GigE cards and a fast switch are a good bet.
>
> - Unless your application needs access times or quota support, mounting
> with "noquota,noatime" is a good idea.  Maybe also "nodiratime".

I have remounted with "noquota,noatime,nodiratime" with no performance increase.


> > Can anyone recommend any GFS tunables to help us out here ?
>
> You could try bumping demote_secs up from its default of 5 minutes.
> That'll cause locks to be held longer so they may not need to be
> reacquired so often.  It won't help with the initial directory listing,
> but should help on subsequent invocations.

I will investigate demote_secs, thankyou.


> In your case, with "ls" taking 8 minutes to run, some locks initially
> acuired during execution of the command have already been demoted once
> complete.
>
> > Should we set statfs_fast to 1 ?
>
> Probably good to set this, regardless.

Done.

>
> > What about glock_purge ?
>
> Glock_purge helps limit CPU time consumed by gfs_scand when a large
> number of unused glocks are present.  See
> http://people.redhat.com/wcheng/Patches/GFS/readme.gfs_glock_trimming.R4
> .  This may make your system run better but I'm not sure it's going to
> help with listing your giant directories.
>
> > Here is the fstab entry for the GFS filesystem:
> > /dev/vggfs/lvol00       /apps                   gfs
> > _netdev         1 2
>
> Try "noatime,noquota" here.
>
> Jeff
>

Here is what I have so far -

fstab: noatime,nodiratime,noquota
statfs_fast 1
statfs_slots 128
glock_purge 50
directio and inherit_directio set on the files/dirs that are taking a long time to 'ls'.

I will continue investigations and get back to the list shortly.

Many thanks
Nick.