Re: [PATCH] x86_64: fix delayed signals

[Arjan van de Ven <arjan@infradead.org>]

On Sat, 12 Jul 2008 16:42:13 +0300
Török Edwin <edwintorok@gmail.com> wrote:

> On 2008-07-12 13:32, Török Edwin wrote:
> > I haven't yet tried ftrace on this box, and neither did I try
> > Roland's patch yet. I will try that now, and hopefuly come back
> > with some numbers shortly.
> >   
> 
> tip/master of today already includes Roland's patch, so I have tested
> it without even knowing on the 64-bit box.
> [After gathering all the traces, I wanted to repeat everything with
> the patch applied, but there was no need since its already there].
> I can say that I didn't notice any difference in the delays (I still
> get 24 - 30 second delays).
> I also tried Linus's readdir patch, the latency is around 27 seconds
> (was 30 before). I am not sure if it is an improvement, or measurement
> noise.
> 
> Also I wasn't able to reproduce the  'Ctrl+Z works faster than Ctrl+C'
> symptom, perhaps it is just a coincidence: by the time I press Ctrl+Z
> to interrupt, enough time has passed (30+ secs), that the same effect
> would have been obtained by another Ctrl+C, or by just waiting.
> 
> On 32-bit, I think the 2-3 seconds latency can be attributed to I/O
> delays, and I think its acceptable given the slow disk (5k4 rpm sata).

I see really bad delays on 32 bit as well, but they go away for me if I
do
echo 4096 > /sys/block/sda/queue/nr_requests



-- 
If you want to reach me at my work email, use arjan@linux.intel.com
For development, discussion and tips for power savings, 
visit http://www.lesswatts.org