On Monday, 23 April 2007 at 4:06:10 -0700, Jeremy Chadwick wrote:
On Sat, Apr 07, 2007 at 08:20:58PM -0300, Marc G. Fournier wrote:
- --On Saturday, April 07, 2007 20:12:00 +0100 Chris [EMAIL PROTECTED]
wrote:
Also to add I now have a 2nd box using 6.2 STABLE few days old code,
had to use it because of broadcom 5755 nic card, I plan to use large
tcp window sizes so will be interesting to see if this also suffers
from the problem.
I've got 8 servers on the same network, 3 are almost identical, but one of
them
(the one with the problem) is using software RAID vs hardware ... but, if
you
are seeing it without using software RAID, then that is obviously not the
culprit :(
May be a red herring...
I'm able to reproduce the No buffer space available message when
setting net.inet.tcp.(send|recv)space to non-default values. All I've
tried is the following, with a kernel dated 2007/04/22:
# sysctl net.inet.tcp.sendspace=131072
# sysctl net.inet.tcp.recvspace=262144
Example session:
$ su2
# sysctl net.inet.tcp.sendspace=131072
net.inet.tcp.sendspace: 32768 - 131072
# sysctl net.inet.tcp.recvspace=262144
net.inet.tcp.recvspace: 65536 - 262144
# logout
$ ssh medusa
socket: No buffer space available
ssh: connect to host medusa port 22: No buffer space available
$ su2
# sysctl net.inet.tcp.sendspace=32768
net.inet.tcp.sendspace: 131072 - 32768
# sysctl net.inet.tcp.recvspace=65536
net.inet.tcp.recvspace: 262144 - 65536
# logout
$ ssh medusa
Last login: Mon Apr 23 03:45:45 2007 from ...
I assume this is because the maximum size of a TCP datagram is 65536
bytes, but as I'm not familiar enough with TCP on such a low level,
this may be speculation on my part.
Just something worth checking/tinkering with.
Try to adjust kern.ipc.maxsockbuf value.
--
==
- Best regards, Nikolay Pavlov. ---
==
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]