similar to: dbench strange results

trying to check gluster performance with dbench I'm using a replica 3 with a bonded dual gigabit (balance-alb) on all servers and shard (64M) enabled. I'm unable to over 3MB (three) MB/s from *inside* VM, thus I think there isn't any small file issue, as from inside VM there isn't any metadata operation for gluster. Any advice ?

I try to use dbench to test HVM domain. Now I use the parameters as below: #./dbench -c client.txt 64 I am wondering if these parameters make sense. Anyone like to give me some suggestions? Thanks and best regards Alex shi _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

hi everybody would a tool such as dbench be a valid bechmark for gluster? and, most importantly, is there any formula to estimate raw fs to gluster performance ratio for different setups? for instance: having a replicated volume, two bricks, fuse mountpoint to volume via non-congested 1Gbps or even a volume on single brick with fuse client mountpoing locally what percentage/fraction of raw

I saw the presentation "Virtualization of Linux Servers" at OLS last month and it had some nice comparisons of Xen performance vs a lot of other virtualization/container technologies: http://ols.fedoraproject.org/OLS/Reprints-2008/camargos-reprint.pdf As always with benchmarks, there are questions to ask and points to quibble, but overall Xen looks quite good... except on Dbench. Has

To test gluster's behavior under heavy load, I'm currently doing this on two machines sharing a common /mnt/gfs gluster mount: ssh bal-6.example.com apt-get install dbench && dbench 6 -t 60 -D /mnt/gfs ssh bal-7.example.com apt-get install dbench && dbench 6 -t 60 -D /mnt/gfs One of the processes usually dies pretty quickly like this: [608] open