* VM behaviour under 2.4.5-ac21
@ 2001-06-29 14:50 Martin Knoblauch
2001-06-29 23:20 ` J . A . Magallon
0 siblings, 1 reply; 3+ messages in thread
From: Martin Knoblauch @ 2001-06-29 14:50 UTC (permalink / raw)
To: linux-kernel
Hi,
just something positive for the weekend. With 2.4.5-ac21, the behaviour
on my laptop (128MB plus twice the sapw) seems a bit more sane. When I
start new large applications now, the "used" portion of VM actually
pushes against the cache instead of forcing stuff into swap. It is still
using swap, but the effects on interactivity are much lighter.
So, if this is a preview of 2.4.6 bahaviour, there may be a light at
the end of the tunnel.
Have a good weekend
Martin
--
------------------------------------------------------------------
Martin Knoblauch | email: Martin.Knoblauch@TeraPort.de
TeraPort GmbH | Phone: +49-89-510857-309
C+ITS | Fax: +49-89-510857-111
http://www.teraport.de | Mobile: +49-170-4904759
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: VM behaviour under 2.4.5-ac21
2001-06-29 14:50 VM behaviour under 2.4.5-ac21 Martin Knoblauch
@ 2001-06-29 23:20 ` J . A . Magallon
2001-06-30 15:33 ` Marcelo Tosatti
0 siblings, 1 reply; 3+ messages in thread
From: J . A . Magallon @ 2001-06-29 23:20 UTC (permalink / raw)
To: Martin Knoblauch; +Cc: linux-kernel @ vger . kernel . org
On 20010629 Martin Knoblauch wrote:
>Hi,
>
> just something positive for the weekend. With 2.4.5-ac21, the behaviour
>on my laptop (128MB plus twice the sapw) seems a bit more sane. When I
>start new large applications now, the "used" portion of VM actually
>pushes against the cache instead of forcing stuff into swap. It is still
>using swap, but the effects on interactivity are much lighter.
>
I was just going to say the same. After ac20, I think, the kernel stopped
pre-allocating swap.
Before I had always some swap used even if I was only using half my core memory
(256Mb). And growing. I have not seen the box touch the swap since ac20.
It uses all the ram it can get for cache, but does not send anything to swap
to use its ram for cache.
Now running ac21 while building ac22, and state is:
werewolf:/usr/src# free
total used free shared buffers cached
Mem: 255588 241044 14544 2168 8836 153752
-/+ buffers/cache: 78456 177132
Swap: 152576 0 152576
werewolf:/usr/src# vmstat
procs memory swap io system cpu
r b w swpd free buff cache si so bi bo in cs us sy id
1 0 0 0 6944 8836 153868 0 0 16 12 95 385 17 3 80
--
J.A. Magallon # Let the source be with you...
mailto:jamagallon@able.es
Mandrake Linux release 8.1 (Cooker) for i586
Linux werewolf 2.4.5-ac21 #1 SMP Fri Jun 29 16:02:22 CEST 2001 i686
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: VM behaviour under 2.4.5-ac21
2001-06-29 23:20 ` J . A . Magallon
@ 2001-06-30 15:33 ` Marcelo Tosatti
0 siblings, 0 replies; 3+ messages in thread
From: Marcelo Tosatti @ 2001-06-30 15:33 UTC (permalink / raw)
To: J . A . Magallon; +Cc: Martin Knoblauch, linux-kernel @ vger . kernel . org
On Sat, 30 Jun 2001, J . A . Magallon wrote:
>
> On 20010629 Martin Knoblauch wrote:
> >Hi,
> >
> > just something positive for the weekend. With 2.4.5-ac21, the behaviour
> >on my laptop (128MB plus twice the sapw) seems a bit more sane. When I
> >start new large applications now, the "used" portion of VM actually
> >pushes against the cache instead of forcing stuff into swap. It is still
> >using swap, but the effects on interactivity are much lighter.
> >
>
> I was just going to say the same. After ac20, I think, the kernel stopped
> pre-allocating swap.
> Before I had always some swap used even if I was only using half my core memory
> (256Mb). And growing. I have not seen the box touch the swap since ac20.
> It uses all the ram it can get for cache, but does not send anything to swap
> to use its ram for cache.
> Now running ac21 while building ac22, and state is:
> werewolf:/usr/src# free
> total used free shared buffers cached
> Mem: 255588 241044 14544 2168 8836 153752
> -/+ buffers/cache: 78456 177132
> Swap: 152576 0 152576
> werewolf:/usr/src# vmstat
> procs memory swap io system cpu
> r b w swpd free buff cache si so bi bo in cs us sy id
> 1 0 0 0 6944 8836 153868 0 0 16 12 95 385 17 3 80
>
Weird: there is no VM change between ac20 and 21.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2001-06-30 17:06 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2001-06-29 14:50 VM behaviour under 2.4.5-ac21 Martin Knoblauch
2001-06-29 23:20 ` J . A . Magallon
2001-06-30 15:33 ` Marcelo Tosatti
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).