On Tue, Nov 9, 2010 at 3:11 PM, Lluís wrote:
> Stefan Hajnoczi writes:
>
>> On Mon, Nov 8, 2010 at 2:35 PM, Lluís wrote:
>>> Another important change would be to provide a generic interface inside
>>> QEMU that provides a programmatic control of the tracing state of all
>>> events (both per-cpu a
On Mon, Nov 8, 2010 at 2:35 PM, Lluís wrote:
> As more and more tracing backends appear (right now: nop, simple, ust
> and the new dtrace), it is harder to provide a tracetool where these
> backends can be efficiently used without being aware of per-CPU tracing
> state.
Per-CPU as in per-vcpu or
Stefan Hajnoczi writes:
> On Mon, Nov 8, 2010 at 2:35 PM, Lluís wrote:
>> As more and more tracing backends appear (right now: nop, simple, ust
>> and the new dtrace), it is harder to provide a tracetool where these
>> backends can be efficiently used without being aware of per-CPU tracing
>> sta
As more and more tracing backends appear (right now: nop, simple, ust
and the new dtrace), it is harder to provide a tracetool where these
backends can be efficiently used without being aware of per-CPU tracing
state.
What I have now is basically:
* trace.h : trace_##name
Backend-specific decla