On Fri, 2005-11-04 at 15:37, Andrei Dorofeev wrote:
> On 11/4/05, Peter Tribble <[EMAIL PROTECTED]> wrote:
> > However, there is one case in which prstat could be improved. While
> > the prstat -a output simply adds the memory of each process, if you
> > use prstat -aL it simply adds things up by LWP so the memory usage
> > gets multiplied by the number of LWPs in the process. eg:
> >
> > NPROC USERNAME SIZE RSS MEMORY TIME
> > CPU
> > 2 apache 708M 534M 5.0% 1:27:31 6.7%
> > 30 oracle 11G 9915M 93% 0:11:31 6.0%
> > 50 root 138M 84M 0.7% 8:18:21 0.7%
> >
> > NLWP USERNAME SIZE RSS MEMORY TIME
> > CPU
> > 123 apache 84G 63G 55% 0:50:06 7.1%
> > 156 oracle 59G 52G 45% 0:11:16 5.7%
> > 122 root 447M 323M 0.3% 8:18:16 0.7%
> >
> > In this case the apache user is running a single, but rather large,
> > java process.
>
> The SIZE/RSS bug was fixed in S10. See
> http://bugs.opensolaris.org/bugdatabase/view_bug.do?bug_id=4983833
You're right, of course. That was on an S9 box. Actually, though,
it only appears to be partially fixed (I thought it was still true
for S10, I just wasn't looking closely enough). So, on my S10
machine I see:
NPROC USERNAME SIZE RSS MEMORY TIME CPU
172 ptribble 4118M 3033M 74% 11:31:00 7.0%
12 xsuser 396M 226M 5.5% 0:51:36 0.1%
34 root 108M 42M 1.0% 0:23:43 0.0%
NLWP USERNAME SIZE RSS MEMORY TIME CPU
220 ptribble 4118M 3033M 58% 11:30:47 7.1%
73 xsuser 396M 226M 41% 0:26:34 0.1%
140 root 108M 42M 0.8% 0:23:11 0.0%
As you can see, the numbers are better but the percentages
don't match up. (This is a 4G machine so the first set of
numbers from prstat -a look right to me, whereas the second set
from prstat -aL look very bogus.)
> > (Just looking at this, I'm not sure why the TIME is so different.)
>
> That could be 4481976 which was fixed a long time ago in S8 and S9.
> So, on what Solaris release was this prstat snapshot taken from?
I see the TIME discrepancy on both S9 and S10. In both cases
the LWP view comes up with lower TIME values.
--
-Peter Tribble
L.I.S., University of Hertfordshire - http://www.herts.ac.uk/
http://www.petertribble.co.uk/ - http://ptribble.blogspot.com/
_______________________________________________
perf-discuss mailing list
[email protected]
