lkml.org 
[lkml]   [2009]   [May]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [GIT PULL] cputime patch for 2.6.30-rc6
On Mon, 18 May 2009, Peter Zijlstra wrote:
> On Mon, 2009-05-18 at 16:09 +0200, Martin Schwidefsky wrote:
> > Hi Linus,
> >
> > please pull from 'cputime' branch of
> >
> > git://git390.marist.edu/pub/scm/linux-2.6.git cputime
> >
> > to receive the following updates:
> >
> > Michael Abbott (1):
> > Fix idle time field in /proc/uptime
> >
> > fs/proc/uptime.c | 8 +++++++-
> > 1 files changed, 7 insertions(+), 1 deletions(-)
> >
> > diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
> > index 0c10a0b..c0ac0d7 100644
> > --- a/fs/proc/uptime.c
> > +++ b/fs/proc/uptime.c
> > @@ -4,13 +4,19 @@
> > #include <linux/sched.h>
> > #include <linux/seq_file.h>
> > #include <linux/time.h>
> > +#include <linux/kernel_stat.h>
> > #include <asm/cputime.h>
> >
> > static int uptime_proc_show(struct seq_file *m, void *v)
> > {
> > struct timespec uptime;
> > struct timespec idle;
> > - cputime_t idletime = cputime_add(init_task.utime, init_task.stime);
> > + int len, i;
> > + cputime_t idletime = 0;
>
> cputime_zero, I guess..
>
> > + for_each_possible_cpu(i)
> > + idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle);
> > + idletime = cputime64_to_clock_t(idletime);
> >
> > do_posix_clock_monotonic_gettime(&uptime);
> > monotonic_to_bootbased(&uptime);
>
> This is a world readable proc file, adding a for_each_possible_cpu() in
> there scares me a little (this wouldn't be the first and only such case
> though).
>
> Suppose you have lots of cpus, and all those cpus are dirtying those
> cachelines (who's updating idle time when they're idle?), then this loop
> can cause a massive cacheline bounce fest.
>
> Then think about userspace doing:
> while :; do cat /proc/uptime > /dev/null; done

Well, the offending code derives pretty well directly from /proc/stat,
which is used, for example, by top. So if there is an issue then I guess
it already exists.

There is a pending problem in this code: for a multiple cpu system we'll
end up with more idle time than elapsed time, which is not really very
nice. Unfortunately *something* has to be done here, as it looks as if
.utime and .stime (at least for init_task) have lost any meaning. I sort
of though of dividing by number of cpus, but that's not going to work very
well..

I came to this problem from a uni-processor instrument which uses
/proc/uptime to determine whether the system is overloaded (and discovers
on the current kernel that it is, permanently!). This fix is definitely
imperfect, but I think a better fix will require rather deeper knowledge
of kernel time accounting than I can offer.


\
 
 \ /
  Last update: 2009-05-18 18:31    [W:0.711 / U:0.492 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site