[x264-devel] Updated (and hopefully final) threaded slicetype patch

[Leon Woestenberg]

Hello,

On Tue, Apr 7, 2009 at 6:43 PM, David DeHaven <dave at sagetv.com> wrote:
>
>>>>> Here's a decent article on the Linux 2.6 scheduler:
>>>>> http://www.ibm.com/developerworks/linux/library/l-scheduler/
>>>>
>>>> That article is 3 years old.
>>>
>>> Has it really changed that much? I'll admit the last time I bashed on
>>> the kernel significantly was well... three years ago.
>>
>> I don't remember when the tickless option was introduced.  I may have
>> been in the last three years.
>
> Looks like it started with 2.6.17, which was almost three years ago but
> still after I was messing around in it. Interesting stuff.
>
Tickless has *nothing* to do with this. (Tickless merely means there
is no periodic hardware timer, it's an implementation issue).


> One signal per frame isn't a high load so I can't see why the slowdown in
> performance, unless it's a flaw in the condition implementation or how it's

Exactly; this is what we need to find out.

> It seems *marginally* faster running on a 1.66 GHz Core Duo Mac Mini with
> Mac OS X 10.5.6. I used the arguments used for the regression test with
>
Sorry, such a test is burried by the background noise.

> The low anomalies (17.9x fps) were from Apple Mail checking mail in the
> background. This wasn't an ideal setup by any means, but it would be
> representative of a normal user system.
>
> If there's a better way to benchmark, let me know. I'll try it on the Linux
> box when I get the time.
>
the "time" command is a good start. The scheduler keeps CPU time for
each thread, this includes system time.

Note that under most Linux systems, pthread calls can sometimes by
fully handled in userspace (google for glibc futex).

Regards,
-- 
Leon