[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <8D11C01F3154466-1620-15304@webmail-vd015.sysops.aol.com>
Date: Tue, 1 Apr 2014 16:41:53 -0400 (EDT)
From: Pietro Paolini <pulsarpietro@....com>
To: linux-kernel@...r.kernel.org
Subject: nf_conntrack: table full
Hello,
I am doing some investigation regarding an error I am experiencing
using my linux embedded device as router in my home network.
If I try to push the number the connections to around 20K I will se a
lot of messages from the kernel saying :
nf_conntrack: table full, dropping packet.
nf_conntrack: table full, dropping packet.
nf_conntrack: table full, dropping packet.
nf_conntrack: table full, dropping packet.
nf_conntrack: table full, dropping packet.
nf_conntrack: table full, dropping packet.
nf_conntrack: table full, dropping packet.
Actually this is fine for me since the number of allowed conntrack is
/proc/sys/net/netfilter/nf_conntrack_max is around 7844, the
strange thing is that the device will reboot after a while - actually
my watchdog reboots the device since is not able to allocate memory -
I have a try with slabtop running and I have seen that but monitoring
the /proc/slabinfo:
3968 nf_conntrack_c0d4eacc
4392 size-8192
6360 skbuff_head_cache
15356 size-4096
31808 size-1024
Well size-1024 is quite high, do you know where is that from and how is
that related to the packets coming in ? Even point me at the right
folder in the source code could be great since I am really lost here.
Thanks in advance,
Pietro.
"And therefore never send to know for whom the bell tolls"
pulsarpietro@....com
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists