[Gluster-devel] Small File Performance - Strange results

[Raghavendra Talur]

----- Original Message -----

> From: "Hafeez Bana" <hafeez.bana at gmail.com>
> To: gluster-devel at gluster.org
> Sent: Tuesday, August 4, 2015 10:25:46 PM
> Subject: [Gluster-devel] Small File Performance - Strange results

> All,

> We've been evaluating glusterfs 3.2.7 on ubuntu 14.04 LTS. All tests were run
> with event-thread matching cpu-cores and lookup-unhashed turned off

Is it really GlusterFS 3.2.7? That is pretty old version. Upgrade is highly recommended. 

> We noted a couple of issues and some interesting results which might be of
> benefit to the developers

> Setup
> - bare metal machine with SSD running ZFS - 2 LXC container running glusterd
> and another running a samba instance which is serving a share backed by a
> fuse mounted volume.

> Observations
> 1 ) the fuse mounted volume has to be done in the host and LXC run on top of
> it. If you try to fuse mount within in LXC - posix acls group persmissions
> are not respected completed by gluster

If you use -oacl option then it should work whether within LXC or not. 
Logs would be useful to debug this issue more. 

> 2) small file performance - tests were run unzipping from a windows box a 45M
> and 150M (expanded size - contains 8000 files) archive. 45M performance is
> reasonable. 150M tests takes 10 times as long(about 18 minutes) as the same
> samba instance serving of a straight zfs filesystem

We have seen that time required for creation of new files increases exponentially when the number of existing files in the parent folder is increased. It is fixed in 3.7 version of Gluster if you use the VFS plugin integration between Samba and Gluster instead of FUSE mount. 

> 3) As a whim we logged into the container containing the samba instance and
> copied files from the ZFS folder to the folder under gluster. 14seconds for
> the same transfer of 8000 files!!

> We don't know if there is a mismatch in the config of samba that is causing
> issues with gluster. Any ideas? And also is the issue with posix acls groups
> being broken if you fuse_mount a gluster volume within LXC known?

> Finally, are there any gluster developers in the UK - we would love to talk
> to them.

> Thanks,
> Hafeez

> _______________________________________________
> Gluster-devel mailing list
> Gluster-devel at gluster.org
> http://www.gluster.org/mailman/listinfo/gluster-devel

-- 

Thanks! 
Raghavendra Talur | Red Hat Storage Developer | Bangalore | +918039245176 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-devel/attachments/20150804/666cca90/attachment.html>