[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] Re: [Xen-users] Not good performance on Xen
On Mon, 2017-10-23 at 17:18 +0200, Berillions wrote: > Hi, > Hi, > I remarked something between Xen and Bare Metal. > - During the test #2 (Syria) i have slowdown on Xen. But not on BM. > - During the test #3 (Geothermal Valley), there are missing texture > on Xen and not on BM > > To have early the same perf, no slowdown and missing texture, i must > to set 8 vcpus to the Guest > Ah, interesting! So if the guest has 16 vCPUs, perf is bad, if it has 8 perf is good, is this correct? Could you, perhaps, execute, on the host, while the benchmark is running, the following command: # xl vcpu-list in both cases (i.e., one time when the guest has 16 vCPUs, and another when it has 8)? Also, still while running the benchmark, can you run `xentop' (still on the host), let it run for a few seconds, check how much CPU % both the guest and the host are consuming, and repot it here? Regards, Dario -- <<This happens because I choose it to happen!>> (Raistlin Majere) ----------------------------------------------------------------- Dario Faggioli, Ph.D, http://about.me/dario.faggioli Attachment:
signature.asc _______________________________________________ Xen-users mailing list Xen-users@xxxxxxxxxxxxx https://lists.xen.org/xen-users
|
Lists.xenproject.org is hosted with RackSpace, monitoring our |