On Saturday, November 17, 2007 2:15 AM, Eric Saxe wrote:
> Hi Aubrey,
>
> Li, Aubrey wrote:
>>> Yea, so the DTrace probe will only fire when a pstate transition
>>> happens...we need a way to query the current CPU P-states so we know
>>> what state we are in should the probe not fire at all during the
>>> sampling period. :)
>>>
>>>
>>
>> 1) probe not fire.
>> - We can query the current state from kstat. "current_clock_Hz"
>> in the module "cpu_info" contains the speed.
>>
> Agreed.
>
>> 2) probe fire only one time.
>> - we know the timestamp of the switching, but we don't know when
>> it is in the sampling period. So we are not able to get how
>> long P1 stays and how long P2 does.
>>
> How about we take an initial timestamp when the sampling
> period begins.
> If the probe doesn't
> fire, then we would report being in the state we read out of the kstat
> 100%. If it fires once during the
> sampling period, then we'll report how much time was spent in each of
> the two pstates during the sample period, etc.
Hi Eric,
If I understand correctly, we have to take the initial timestamp in the
loop as follows.
Which dtrace probe should we use to take the initial timestamp?
========
Prepare dtrace script, execute and go.
Loop() {
Take initial timestamp;
wait sampling period;
snap dtrace data;
}
========
Thanks,
-Aubrey
