> On Wed, Nov 11, 1998 at 02:03:19AM +0100, Kurt Garloff wrote:
> > Nov 11 01:46:30 kg1 kernel: Networking buffers in use : 144
> > Nov 11 01:46:30 kg1 kernel: Total network buffer allocations : 16120011
> > Nov 11 01:46:30 kg1 kernel: Total failed network buffer allocs : 2
> > Nov 11 01:46:30 kg1 kernel: IP fragment buffer size : 0
> > root@kg1:~ # uptime
> > 1:52am up 4 days, 8:28, 2 users, load average: 3.66, 3.85, 3.86
> > ...
> > Kernel is 2.1.125ac3, SMP (Dual PII-350), w/ HZ = 400, scheduler bigpatch 4
> > from Rik and compiled with egcs-1.1a (-O2, -march=pentiumpro -fschedule-insns2).
>
> Recompiled w/ -O2 -mpentiumpro -fschedule-insns2: No change.
>
> When I go single user (runlevel S), the leakage stops. (I can see it with
> Shift-Scroll and issueing klogd -o -f -.) As soon as I start the syslogd
> (1.3.30), the leakage goes on! So it must be somewhere in the socket or
> the surrounding layers.
Uhhh...You realize that "Networking buffers in use" is the thing you
should be looking at? "Total network buffer allocations" is merely a
counter for allocations as is the "Total failed network buffer allocs" for
failed allocations.
I don't see any leak here.
Simon-
| Simon Kirby | Systems Administration |
| mailto:sim@netnation.com | NetNation Communications |
| http://www.netnation.com/ | Tech: (604) 684-6892 |
-
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/