On Mon, Feb 08, 2016 at 11:59:00AM -0800, Hollis Blanchard wrote:
> On 02/08/2016 07:30 AM, Stefan Hajnoczi wrote:
> >On Wed, Jan 13, 2016 at 03:13:02PM -0800, Hollis Blanchard wrote:
> >>The event timestamps are host time (get_clock()). I'm correlating qemu
> >>events with other logs (using icount
On 02/08/2016 07:30 AM, Stefan Hajnoczi wrote:
On Wed, Jan 13, 2016 at 03:13:02PM -0800, Hollis Blanchard wrote:
The event timestamps are host time (get_clock()). I'm correlating qemu
events with other logs (using icount), so host time is unhelpful. Could we
use cpu_get_clock() instead? (Trace e
Alex Bennée writes:
> Hollis Blanchard writes:
>
>> Hi Stefan, I've been starting to use qemu tracing and found it quite
>> useful. I have a couple comments about the trace events in general:
>>
>
>> Right now, the simple tracepoint backend creates a trace file even when
>> no events are activ
Hollis Blanchard writes:
> Hi Stefan, I've been starting to use qemu tracing and found it quite
> useful. I have a couple comments about the trace events in general:
>
> Right now, the simple tracepoint backend creates a trace file even when
> no events are active and no -trace options are pres
Stefan Hajnoczi writes:
> On Wed, Jan 13, 2016 at 03:13:02PM -0800, Hollis Blanchard wrote:
>> Hi Stefan, I've been starting to use qemu tracing and found it quite useful.
>> I have a couple comments about the trace events in general:
> Sorry for the late reply.
>> The event timestamps are host
On Wed, Jan 13, 2016 at 03:13:02PM -0800, Hollis Blanchard wrote:
> Hi Stefan, I've been starting to use qemu tracing and found it quite useful.
> I have a couple comments about the trace events in general:
Sorry for the late reply.
> The event timestamps are host time (get_clock()). I'm correlat
Hi Stefan, I've been starting to use qemu tracing and found it quite
useful. I have a couple comments about the trace events in general:
The event timestamps are host time (get_clock()). I'm correlating qemu
events with other logs (using icount), so host time is unhelpful. Could
we use cpu_get