"David S. Miller" <davem@redhat.com> writes:
> Can people test out this patch? Especially people who see
> the kernel go deeply into swap and never come fully out of it.
I have my machine running with -pre6 and this patch applied. I don't
see any swap use anymore. I'm not sure whether this attributable to
the changes which went in the mm code after -pre6-5 or to Dave's
patch.
But this does not mean that I think everything works flawless. Under
heavy compilation applications still seem to suffer a lot. Just start
several big interfactive applications (netscape, Emacs, acrobat in my
case) and compile something big (mozilla, glibc). If you don't touch
the applications for a few seconds they are not as responsive as one
wants once you get back to them.
Also, as other have reported, the kswapd accumulates quite some
runtime. On my system with almost two days uptime it has 16min58sec
(getting about 10 seconds for every 3 minutes I compile). The X
server has only about 3.5 times more. If you look at the load you'll
also see that compiling with -j4 produces a load of 4.65, all of which
I can only attribute to the kswapd since I've never seen this before.
-- ---------------. drepper at gnu.org ,-. 1325 Chesapeake Terrace Ulrich Drepper \ ,-------------------' \ Sunnyvale, CA 94089 USA Red Hat `--' drepper at redhat.com `------------------------- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun May 07 2000 - 21:00:10 EST