Re: CONFIG_PREEMPT and server workloads

[Takashi Iwai <tiwai@suse.de>]

At Thu, 18 Mar 2004 22:10:06 -0800,
Andrew Morton wrote:
> 
> Takashi Iwai <tiwai@suse.de> wrote:
> >
> > BTW, i had the worst latency in sis900's timer handler.
> >  it takes 3ms, and hard to fix, too :-<
> 
> It's all coming back to me now.
> 
> The worst-case latency is during umount, fs/inode.c:invalidate_list() when
> the filesystem has a zillion inodes in icache.  Measured 250 milliseconds
> on a 256MB 2.7GHz P4 here.   OK, so don't do that.
 
also that's not included in my test case :)

> The unavoidable worst case is in the RCU callbacks for dcache shrinkage -
> I've seen 25 millisecond holdoffs on the above machine during filesystem
> stresstests when RCU is freeing a huge number of dentries in softirq
> context.

hmm, this wasn't also evaluated in my tests.
it's worthy to try.  thanks for the info.

> This if Hard To Fix.  Dipankar spent quite some time looking into it and
> had patches, but I lost track of where they're at.

couldn't this tasklet be replaced with workqueue or such?


Takashi