[OpenAFS-devel] Very simple patch for libafs CPU hog on signal

[Matt Peterson]

Right.

Thanks.


On Tuesday 29 January 2002 11:31 am, Derek Atkins wrote:
> Matt Peterson <matt@caldera.com> writes:
> > Also, can someone explain what is meant by the following?
> >
> > Nickolai Zeldovich <kolya@MIT.EDU> wrote:
> > > Unfortunately, this has the side effect of artificially increasing the
> > > system load to ~4 when AFS is idle, because the background daemons
> > > block waiting for requests.
> >
> > Is Nickolai is right on this one?  Tasks with a state of
> > TASK_INTERRUPTIBLE do not appear to increase the system load.  If they
> > did, you'd already see an increase of 4 as the daemon syscalls currently
> > spend most of their time in interruptable_sleep_on() (even without
> > Nickolai's patch).  Basically, I don't see how Nickolai's patch would
> > change system load.
>
> This was in reference to using a non-interruptible sleep, which does
> have the affect of increasing the load.
>
> -derek

-- 
Matt Peterson
Sr. Software Engineer
Caldera, Inc
matt@caldera.com