What's all this in syslog? I don't remember ever seeing it there before.
...
Apr 14 13:58:31 foo kernel: Disorder0 3 5 f0 s2 rr1
Apr 14 13:58:32 foo kernel: Disorder0 3 5 f0 s1 rr1
Apr 14 13:58:41 foo kernel: Disorder0 3 8 f0 s0 rr1
Apr 14 13:58:44 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:58:45 foo kernel: Disorder0 3 4 f0 s0 rr1
Apr 14 13:58:47 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:58:55 foo kernel: Disorder3 1 5 f5 s2 rr0
Apr 14 13:58:59 foo kernel: Undo Hoe 145.236.164.120/2007 c3 l0 ss2/2 p3
Apr 14 13:59:00 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:59:01 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:59:02 foo kernel: Undo Hoe 145.236.164.120/2007 c3 l0 ss2/2 p2
Apr 14 13:59:02 foo kernel: Disorder0 3 4 f0 s0 rr1
Apr 14 13:59:03 foo kernel: Undo Hoe 145.236.164.120/2007 c3 l0 ss2/2 p1
Apr 14 13:59:04 foo kernel: Undo retrans 145.236.164.120/2007 c2 l0 ss2/2
p0
Apr 14 13:59:11 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:59:15 foo kernel: Disorder0 3 4 f0 s0 rr1
Apr 14 13:59:17 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:59:19 foo kernel: Disorder0 3 4 f0 s0 rr1
Apr 14 13:59:21 foo kernel: Disorder0 3 4 f0 s0 rr1
Apr 14 13:59:24 foo kernel: Disorder0 3 7 f0 s0 rr1
Apr 14 13:59:25 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:59:37 foo kernel: Disorder0 3 5 f0 s0 rr1
Apr 14 13:59:57 foo kernel: Disorder3 1 5 f5 s2 rr0
...
What kernel are you running? This is disabled by default. search for
where FASTRETRANS_DEBUG is enabled (should be in linux/include/net/tcp.h
and set it someting low (like 1 which is the default. The actual error
message comes up in tcp_input.c (search fro FASTRETRANS_DEBUG).
Regards,
Bart.
On Sat, 14 Apr 2001, George Bonser wrote:
> What's all this in syslog? I don't remember ever seeing it there before.
>
> ...
> Apr 14 13:58:31 foo kernel: Disorder0 3 5 f0 s2 rr1
> Apr 14 13:58:32 foo kernel: Disorder0 3 5 f0 s1 rr1
> Apr 14 13:58:41 foo kernel: Disorder0 3 8 f0 s0 rr1
> Apr 14 13:58:44 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:58:45 foo kernel: Disorder0 3 4 f0 s0 rr1
> Apr 14 13:58:47 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:58:55 foo kernel: Disorder3 1 5 f5 s2 rr0
> Apr 14 13:58:59 foo kernel: Undo Hoe 145.236.164.120/2007 c3 l0 ss2/2 p3
> Apr 14 13:59:00 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:59:01 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:59:02 foo kernel: Undo Hoe 145.236.164.120/2007 c3 l0 ss2/2 p2
> Apr 14 13:59:02 foo kernel: Disorder0 3 4 f0 s0 rr1
> Apr 14 13:59:03 foo kernel: Undo Hoe 145.236.164.120/2007 c3 l0 ss2/2 p1
> Apr 14 13:59:04 foo kernel: Undo retrans 145.236.164.120/2007 c2 l0 ss2/2
> p0
> Apr 14 13:59:11 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:59:15 foo kernel: Disorder0 3 4 f0 s0 rr1
> Apr 14 13:59:17 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:59:19 foo kernel: Disorder0 3 4 f0 s0 rr1
> Apr 14 13:59:21 foo kernel: Disorder0 3 4 f0 s0 rr1
> Apr 14 13:59:24 foo kernel: Disorder0 3 7 f0 s0 rr1
> Apr 14 13:59:25 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:59:37 foo kernel: Disorder0 3 5 f0 s0 rr1
> Apr 14 13:59:57 foo kernel: Disorder3 1 5 f5 s2 rr0
> ...
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
WebSig: http://www.jukie.net/~bart/sig/
>
> What kernel are you running?
That is 2.4.4-pre3
> This is disabled by default. search for
> where FASTRETRANS_DEBUG is enabled (should be in linux/include/net/tcp.h
> and set it someting low (like 1 which is the default. The actual error
> message comes up in tcp_input.c (search fro FASTRETRANS_DEBUG).
>
> Regards,
> Bart.
Thanks, Bart. Looks like it was set to 2. I have set it to 1 and will build
it again. I am trying to figure out why 2.4.4 (or to be more accurate
2.4.>1) dies on me when running in my web farm. This last time I tried
running top in the background with:
top -b -i -d10 >crap &
And it has run like a champ! First time I have ever been able to run it
with good performance for more than 15 minutes. Maybe I will just
substitute /dev/null for crap and that will fix it :-/