On Tue, 10 Dec 2013 23:23:01 +0000 "Kotwani, Mukul" <[email protected]> wrote:
> As an example, for a specific test: > PUT for Ubuntu, default parameters: ~140 ops/sec > PUT for Ubuntu, disable_fallocate=true: ~100 ops/sec > PUT for Redhat 5.8, default parameters: ~15 ops/sec I suppose it should be trackable, although I'm far from expert on this. Since the RHEL 5.8 numbers are so low, the system must be doing something. You just need to find out what that is. For example, it may be trashing with writeouts and so you need to change the dirty memory ratio. It really is impossible to guess. Since it's an actual RHEL and not CentOS, did you try to ask your account rep about this? -- Pete _______________________________________________ Mailing list: http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack Post to : [email protected] Unsubscribe : http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack
