On Sun, Oct 06, 2002 at 12:59:17PM +0200, Thomas Langås wrote:
> jw schultz:
> > I stand corrected. The load average reported will reflect
> > them. The D-state processes, however, will have nearly zero
> > effect on the system performance, yes? So in this case the
> > load average reported is simply an infated number.
>
> They won't have any effect on the system, but the load number is
> insane (we have a 2 CPU intel-boks with a load number of 480)
> and there's like 200-300 (or more) processes hanging in D-state
> with they're FD's and stuff. There _really_ should be a way
> to remove all theese processes, Solaris does this nicely.
That you have that many processes hanging in the D-state is
a concern. That the load number is inflated is telling you
something is wrong. If not then the logic feeding the load
number needs changing.
Are all those processes hanging because of NFS? If so, i'd
start by looking at the mount options as i said before. I'd
also look into the network and fileserver because something
is wrong. In my experience Solaris behaved the same way.
-- ________________________________________________________________ J.W. Schultz Pegasystems Technologies email address: jw@pegasys.wsRemember Cernan and Schmitt - 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/
This archive was generated by hypermail 2b29 : Mon Oct 07 2002 - 22:00:53 EST