Hi Bharata Thanks for this, very useful. Would you be able to specify tests with mainly reads and writes. As far as I know there is a big hit and poor performance on writes in normal fuse mounts. Are you using IOmeter or bonnie ?
Seems the results with fuse and the native qemu-glusterfs are pretty similar, am I right ? Regards, Fernando -----Original Message----- From: Bharata B Rao [mailto:bharata....@gmail.com] Sent: 03 September 2012 06:54 To: Fernando Frediani (Qube) Cc: gluster-users@gluster.org Subject: Re: [Gluster-users] QEMU-GlusterFS native integration demo video On Tue, Aug 28, 2012 at 3:04 PM, Fernando Frediani (Qube) <fernando.fredi...@qubenet.net> wrote: > Thanks for sharing it with us Bharata. > > I saw you have two nodes. Have you done any performance tests and if so how > they compare with creating normal .qcow2 or .raw files on the filesystem, > specially for the writes ? Fernando, In the video I was using a single node system (local brick). However I have tested QEMU-GlusterFS with 2 node scenario too. I have some performance numbers that compare the QEMU-GlusterFS native integration with QEMU-GlusterFS FUSE mount. Were you looking for anything different ? I don't have numbers for qcow2 or for create, but have numbers for reads for raw files. FIO numbers for read can be found here: http://lists.nongnu.org/archive/html/qemu-devel/2012-07/msg02718.html http://lists.gnu.org/archive/html/gluster-devel/2012-08/msg00063.html I am planning to publish more numbers for other scenarios (qcow2 and writes etc) in future. Regards, Bharata. _______________________________________________ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
