call for testers: altq in current

[Nate Lawson]

Max Laier wrote:
> On Saturday 07 April 2007 19:23, Nate Lawson wrote:
>> A few weeks ago, I committed a change to ALTQ that I was only able to
>> compile-test.  What I need is someone with a laptop or other
>> cpufreq-capable system that is also using ALTQ to verify that with
>> powerd running, the queuing timing is now reliable.
>>
>> Previously, altq would just cache the first value of the CPU freq it
>> saw (based on tsc_freq) and use that forever.  Now it gets updated each
>> time the freq changes.  I want to make sure the edge cases (i.e., freq
>> changes while a packet is being timed) work ok.
> 
> I will try to give it a spin over the long weekend.  Other testers please 
> note that you should test this without ALTQ_NOPCC.  Looking at the patch 
> now, it seems that the eventhandler should take this into account, too.  
> i.e. when ALTQ_NOPCC is defined we emulate a 256Mhz clock with 
> microtime - this shouldn't be dependent on the real cpu frequency 
> (eventhough things will get strange when the clockspeed drops below 
> 256Mhz).  Sorry for not paying attention when you posted the patch.
> 
> CC'ing freebsd-pf@ ... laptop anyone?

Thanks Max.  Yes, the microtime clock will be mostly unaffected by the
CPU frequency.  However, we may need to look into that case.

-- 
Nate