Robert Love wrote:
>On Wed, 2002-07-10 at 09:54, William Lee Irwin III wrote:
>
>
>
>>Examine the avenrun array declared in kernel/timer.c in a manner similar
>>to how loadavg_read_proc() in fs/proc/proc_misc.c does.
>>
>>
>
>David, I wanted to add that we formalized the locking rules on
>avenrun[3] a couple kernel revisions ago.
>
>In 2.4, I believe it is implicitly assumed you will do a cli() before
>accessing the data (if you want all 3 values to be in sync you need the
>read to be safe).
>
>In 2.5, grab a read_lock on xtime_lock and go at it.
>
> Robert Love
>
>
Thanks for your information. I think having a generic interface to
deterining CPU load of the system can help developers to determine some
task schdeuling policy to make the system more efficient utilise the
systems processing power. For example, I would not want to do some
intensive processing job when CPU load is high, but I can leaving this
work util the CPU load is not high (for non-urgent tasks).
regards,
David
regards,
David
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Jul 30 2002 - 14:00:24 EST