* /proc/slabinfo reports excessive size-64 objects
@ 2004-01-07 1:15 Alex Buell
2004-01-07 5:26 ` Andrew Morton
0 siblings, 1 reply; 3+ messages in thread
From: Alex Buell @ 2004-01-07 1:15 UTC (permalink / raw)
To: Mailing List - Linux Kernel
Both of my 2.4.23 boxes reports excessive size-64 objects
1) on my 512MB box, it's 3176370 3176442 64 53838 53838 1
2) on my 128MB box, it's 1223329 1223365 64 20735 20735 1
Is this really normal? Both boxes have been up for 2 days, but the 128MB
box is starting to show signs of getting slower and slower the more the
size-64 cache increases.
--
http://www.munted.org.uk
Your mother cooks socks in hell
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: /proc/slabinfo reports excessive size-64 objects
2004-01-07 1:15 /proc/slabinfo reports excessive size-64 objects Alex Buell
@ 2004-01-07 5:26 ` Andrew Morton
2004-01-07 9:58 ` Alex Buell
0 siblings, 1 reply; 3+ messages in thread
From: Andrew Morton @ 2004-01-07 5:26 UTC (permalink / raw)
To: Alex Buell; +Cc: linux-kernel
Alex Buell <alex.buell@munted.org.uk> wrote:
>
> Both of my 2.4.23 boxes reports excessive size-64 objects
>
> 1) on my 512MB box, it's 3176370 3176442 64 53838 53838 1
> 2) on my 128MB box, it's 1223329 1223365 64 20735 20735 1
>
> Is this really normal? Both boxes have been up for 2 days, but the 128MB
> box is starting to show signs of getting slower and slower the more the
> size-64 cache increases.
It looks unusual. Are you running any less popular device drivers or
networking configurations?
We had a couple of ext3/htree leaks which did this in 2.6. Nothing else
comes to mind.
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: /proc/slabinfo reports excessive size-64 objects
2004-01-07 5:26 ` Andrew Morton
@ 2004-01-07 9:58 ` Alex Buell
0 siblings, 0 replies; 3+ messages in thread
From: Alex Buell @ 2004-01-07 9:58 UTC (permalink / raw)
To: Andrew Morton; +Cc: Mailing List - Linux Kernel
On Tue, 6 Jan 2004, Andrew Morton wrote:
> Alex Buell <alex.buell@munted.org.uk> wrote:
> >
> > Both of my 2.4.23 boxes reports excessive size-64 objects
> >
> > 1) on my 512MB box, it's 3176370 3176442 64 53838 53838 1
> > 2) on my 128MB box, it's 1223329 1223365 64 20735 20735 1
> >
> > Is this really normal? Both boxes have been up for 2 days, but the 128MB
> > box is starting to show signs of getting slower and slower the more the
> > size-64 cache increases.
>
> It looks unusual. Are you running any less popular device drivers or
> networking configurations?
>
> We had a couple of ext3/htree leaks which did this in 2.6. Nothing else
> comes to mind.
Yup, it was an ext3/htree leak. I've been given a patch to test.
--
http://www.munted.org.uk
Your mother cooks socks in hell
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2004-01-07 9:58 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2004-01-07 1:15 /proc/slabinfo reports excessive size-64 objects Alex Buell
2004-01-07 5:26 ` Andrew Morton
2004-01-07 9:58 ` Alex Buell
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).