[Gluster-users] Lower IO performance with 3.7.x than with 3.5.x

[Krutika Dhananjay]

CC'ing distribute component owners. 

-Krutika 
----- Original Message -----

> From: "Geoffrey Letessier" <geoffrey.letessier at cnrs.fr>
> To: gluster-users at gluster.org
> Sent: Thursday, August 13, 2015 5:39:47 PM
> Subject: [Gluster-users] Lower IO performance with 3.7.x than with 3.5.x

> Hi,

> Previously we used GlusterFS v3.5.3 and we could achieve around 1.1GBs for
> read/write in plain distributed volume.
> Now, since I have upgraded GlusterFS to 3.7.3, i can only achieve around
> 700MBs (max).

> Here some additional information concerning my volume.

> # gluster volume info vol_workdir_amd

> Volume Name: vol_workdir_amd
> Type: Distribute
> Volume ID: 42d8f9fa-3b24-414f-a275-dadcfdd8d3db
> Status: Started
> Number of Bricks: 4
> Transport-type: tcp,rdma
> Bricks:
> Brick1: ib-storage1:/export/brick_workdir/brick1/data
> Brick2: ib-storage3:/export/brick_workdir/brick1/data
> Brick3: ib-storage1:/export/brick_workdir/brick2/data
> Brick4: ib-storage3:/export/brick_workdir/brick2/data
> Options Reconfigured:
> client.event-threads: 4
> performance.readdir-ahead: on
> auth.allow: 10.0.*
> cluster.min-free-disk: 5%
> performance.cache-size: 1GB
> performance.io-thread-count: 32
> diagnostics.brick-log-level: CRITICAL
> nfs.disable: on
> performance.read-ahead: on

> and the status is OK for all bricks in.

> Thanks in advance,
> Geoffrey
> ------------------------------------------------------
> Geoffrey Letessier
> Responsable informatique & ingénieur système
> UPR 9080 - CNRS - Laboratoire de Biochimie Théorique
> Institut de Biologie Physico-Chimique
> 13, rue Pierre et Marie Curie - 75005 Paris
> Tel: 01 58 41 50 93 - eMail: geoffrey.letessier at ibpc.fr

> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://www.gluster.org/mailman/listinfo/gluster-users
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20150814/6eddc05a/attachment.html>