lkml.org 
[lkml]   [2006]   [Apr]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [patch][rfc] quell interactive feeding frenzy
Date
Con Kolivas wrote:
> On Friday 14 April 2006 13:16, Al Boldi wrote:
> > Can you try the attached mem-eater passing it the number of kb to be
> > eaten.
> >
> > i.e. '# while :; do ./eatm 9999 ; done'
> >
> > This will print the number of bytes eaten and the timing in ms.
> >
> > Assuming timeslice=100, adjust the number of kb to be eaten such that
> > the timing will be less than timeslice (something like 60ms). Switch to
> > another vt and start another eatm w/ the number of kb yielding more than
> > timeslice (something like 140ms). This eatm should starve completely
> > after exceeding timeslice.
> >
> > This problem also exists in mainline, but it is able to break out of it
> > to some extent. Setting eatm kb to a timing larger than timeslice does
> > not exhibit this problem.
>
> Thanks for bringing this to my attention. A while back I had different
> management of forked tasks and merged it with PF_NONSLEEP. Since then I've
> changed the management of NONSLEEP tasks and didn't realise it had
> adversely affected the accounting of forking tasks. This patch should
> rectify it.

Congrats!

Much smoother, but I still get this choke w/ 2 eatm 9999 loops running:

9 MB 783 KB eaten in 131 msec (74 MB/s)
9 MB 783 KB eaten in 129 msec (75 MB/s)
9 MB 783 KB eaten in 129 msec (75 MB/s)
9 MB 783 KB eaten in 131 msec (74 MB/s)
9 MB 783 KB eaten in 133 msec (73 MB/s)
9 MB 783 KB eaten in 132 msec (73 MB/s)
9 MB 783 KB eaten in 128 msec (76 MB/s)
9 MB 783 KB eaten in 133 msec (73 MB/s)
9 MB 783 KB eaten in 129 msec (75 MB/s)
9 MB 783 KB eaten in 130 msec (74 MB/s)
9 MB 783 KB eaten in 2416 msec (3 MB/s) <<<<<<<<<<<<<
9 MB 783 KB eaten in 197 msec (48 MB/s)
9 MB 783 KB eaten in 133 msec (73 MB/s)
9 MB 783 KB eaten in 132 msec (73 MB/s)
9 MB 783 KB eaten in 132 msec (73 MB/s)
9 MB 783 KB eaten in 126 msec (77 MB/s)
9 MB 783 KB eaten in 135 msec (72 MB/s)
9 MB 783 KB eaten in 132 msec (73 MB/s)
9 MB 783 KB eaten in 132 msec (73 MB/s)
9 MB 783 KB eaten in 134 msec (72 MB/s)
9 MB 783 KB eaten in 64 msec (152 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 64 msec (152 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 64 msec (152 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)
9 MB 783 KB eaten in 63 msec (154 MB/s)

You may have to adjust the kb to get the same effect.

Thanks!

--
Al

-
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/

\
 
 \ /
  Last update: 2006-04-15 22:50    [W:0.212 / U:0.080 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site