* Performance Analysis - EMUL_MTSPR: Increased counts
@ 2013-05-13 8:32 nitesh narayan lal
2013-05-14 10:27 ` tiejun.chen
0 siblings, 1 reply; 4+ messages in thread
From: nitesh narayan lal @ 2013-05-13 8:32 UTC (permalink / raw)
To: kvm
Hi,
I am doing the virtio performance analysis on PowerPC,with the updated
QEMU I had observed that the EMUL_MTSPR instruction counts in KVM Exit
count is going really high when I send packets from Guest with respect
to without sending network packets from Guest.
I had added few prints and found that special register number 336
which corresponds to TSR:Timer Status is been called number of times
which I think could result in a higher CPU Utilization.
I would be thankful if I could get some opinions about this observation.
Regards
Nitesh Narayan Lal
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Performance Analysis - EMUL_MTSPR: Increased counts
2013-05-13 8:32 Performance Analysis - EMUL_MTSPR: Increased counts nitesh narayan lal
@ 2013-05-14 10:27 ` tiejun.chen
0 siblings, 0 replies; 4+ messages in thread
From: tiejun.chen @ 2013-05-14 10:27 UTC (permalink / raw)
To: nitesh narayan lal; +Cc: kvm, kvm-ppc@vger.kernel.org
On 05/13/2013 04:32 PM, nitesh narayan lal wrote:
> Hi,
> I am doing the virtio performance analysis on PowerPC,with the updated
> QEMU I had observed that the EMUL_MTSPR instruction counts in KVM Exit
Sounds you are saying this behaviour is only reproduced after you update QEMU.
If so, you can use 'git bisect' easily to figure out this issued commit.
> count is going really high when I send packets from Guest with respect
> to without sending network packets from Guest.
> I had added few prints and found that special register number 336
> which corresponds to TSR:Timer Status is been called number of times
Which platform? Which CPU core?
> which I think could result in a higher CPU Utilization.
How many processes else are running except for KVM guest?
Tiejun
> I would be thankful if I could get some opinions about this observation.
> Regards
> Nitesh Narayan Lal
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Performance Analysis - EMUL_MTSPR: Increased counts
@ 2013-05-14 10:27 ` tiejun.chen
0 siblings, 0 replies; 4+ messages in thread
From: tiejun.chen @ 2013-05-14 10:27 UTC (permalink / raw)
To: nitesh narayan lal; +Cc: kvm, kvm-ppc@vger.kernel.org
On 05/13/2013 04:32 PM, nitesh narayan lal wrote:
> Hi,
> I am doing the virtio performance analysis on PowerPC,with the updated
> QEMU I had observed that the EMUL_MTSPR instruction counts in KVM Exit
Sounds you are saying this behaviour is only reproduced after you update QEMU.
If so, you can use 'git bisect' easily to figure out this issued commit.
> count is going really high when I send packets from Guest with respect
> to without sending network packets from Guest.
> I had added few prints and found that special register number 336
> which corresponds to TSR:Timer Status is been called number of times
Which platform? Which CPU core?
> which I think could result in a higher CPU Utilization.
How many processes else are running except for KVM guest?
Tiejun
> I would be thankful if I could get some opinions about this observation.
> Regards
> Nitesh Narayan Lal
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Performance Analysis - EMUL_MTSPR: Increased counts
2013-05-14 10:27 ` tiejun.chen
(?)
@ 2013-05-15 4:15 ` nitesh narayan lal
-1 siblings, 0 replies; 4+ messages in thread
From: nitesh narayan lal @ 2013-05-15 4:15 UTC (permalink / raw)
To: tiejun.chen; +Cc: kvm
Hi Tiejun,
It was just an observation made by me, but I checked it again and I
observed that its not consistent. I didn't get the same thing what I
had observed earlier in the next trial.
Although right now I will keep my analysis going and will keep the
list updated as I will find something.
Regards
Nitesh Narayan Lal
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2013-05-15 4:15 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-05-13 8:32 Performance Analysis - EMUL_MTSPR: Increased counts nitesh narayan lal
2013-05-14 10:27 ` tiejun.chen
2013-05-14 10:27 ` tiejun.chen
2013-05-15 4:15 ` nitesh narayan lal
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.