Hi Avati,
I do not use RDMA for transport. I use tcp transport over the IPoIB interface.
I have already re-installed 3.2.7 on that server for shipping. I will install 3.4.1 on other servers and send you client logs, but please wait for a while.
Regards,
Cuong
On Wed, Dec 4, 2013 at 9:35 AM, Anand Avati <avati@xxxxxxxxxxx> wrote:
Nguyen,I did not realize you were using RDMA. Can you paste the gluster client logs as well?Thanks,AvatiOn Tue, Dec 3, 2013 at 4:16 PM, Nguyen Viet Cuong <mrcuongnv@xxxxxxxxx> wrote:
Hi Keithley,Please find the bug in the attached log file. I experienced this bug on both 3.4.0 and 3.4.1. There is no problem with GlusterFS 3.2.7.I use IOR 3.0.1 for the test. The connection is IBoIP. OFED is come from Mellanox (1.5.3). OS is CentOS 6.4.About the GlusterFS on RHEL 6.5, I wonder that why there is no glusterfs-server and glusterfs-geo-replication packages?--On Tue, Dec 3, 2013 at 1:03 AM, Kaleb S. KEITHLEY <kkeithle@xxxxxxxxxx> wrote:
On 12/02/2013 10:52 AM, Nguyen Viet Cuong wrote:Have you filed a bug?
Hi,
Actually, I have very bad experience with GlusterFS 3.3.x and 3.4.x
under very high pressure (> 64 processes write in parallel in more than
10 minutes, for example).
You can get the glusterfs RPMs that were built in the Fedora Koji build system at
GlusterFS 3.2.7 from EPEL is really stable and
we use it for production.
Unfortunately, there is no official built of GlusterFS 3.2.x on
Gluster's repo.
https://koji.fedoraproject.org/koji/packageinfo?packageID=5443
and in particular the 3.2.7 el6 RPMs are at
https://koji.fedoraproject.org/koji/buildinfo?buildID=323952
--
Kaleb
Nguyen Viet Cuong
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-users
Nguyen Viet Cuong
_______________________________________________ Gluster-users mailing list Gluster-users@xxxxxxxxxxx http://supercolony.gluster.org/mailman/listinfo/gluster-users
