Messages in this thread |  | | | Date | Tue, 20 Jan 2009 19:42:49 +0100 | | From | Ingo Molnar <> | | Subject | Re: [Bug #12465] KVM guests stalling on 2.6.28 (bisected) |
| |
* Kevin Shanahan <kmshanah@ucwb.org.au> wrote:
> Running the ping test with without apache2 running in the guest: > > --- hermes-old.wumi.org.au ping statistics --- > 900 packets transmitted, 900 received, 0% packet loss, time 902740ms > rtt min/avg/max/mdev = 0.568/3.745/272.558/16.990 ms > > And with apache2 running: > > --- hermes-old.wumi.org.au ping statistics --- > 900 packets transmitted, 900 received, 0% packet loss, time 902758ms > rtt min/avg/max/mdev = 0.625/25.634/852.739/76.586 ms > > In both cases it's quite variable, but the max latency is still not as > bad as when running with the irq chip enabled.
So the worst-case ping latency is more than 10 times lower?
I'd say this points in the direction of some sort of KVM-internal wakeup/signalling latency that happens if KVM does not deschedule. For example it could be a bug like this: if a guest image runs at 100% CPU time for a long time, IRQ injections might not propagate up until the preemption callbacks run. (but i'm just speculating here)
Ingo
|  |