Date: Fri, 30 Apr 1999 11:38:58 -0700 (PDT) From: Doug White <dwhite@resnet.uoregon.edu> To: Bryce Newall <data@dreamhaven.net> Cc: FreeBSD Questions List <freebsd-questions@FreeBSD.ORG> Subject: Re: No buffer space Message-ID: <Pine.BSF.4.03.9904301137000.16807-100000@resnet.uoregon.edu> In-Reply-To: <Pine.NEB.4.10.9904281457520.608-100000@ds9.dreamhaven.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 28 Apr 1999, Bryce Newall wrote: > I've been running into a problem lately one one of my servers. This > particular machine hosts several web sites, some of which are pretty > high-volume. The problem lately is that many network operations are > getting "No buffer space available" messages. This happens when using > traceroute and ping (that's when I actually notice the error message), but > I've been noticing it other times, too. In particular, this log entry: > > Apr 28 15:20:01 calico named[13140]: socket(SOCK_RAW): No buffer space > available > > This is starting to worry me, because it's causing things to not work at > random. A friend of mine suggested that I'd need to recompile the network > card driver with more buffer space. That's not the problem. This means that one of your routes is stuffed up and is holding packets as it figures out where to send them. Try running 'netstat -a' and see what's backed up. Pinging a dead address will often get these messages. Be careful playing with NMBCLUSTERS, you can cause odd panics and other problems if you put them too high and run the kernel out of memory. 6000 is a little high for a normal server. Doug White Internet: dwhite@resnet.uoregon.edu | FreeBSD: The Power to Serve http://gladstone.uoregon.edu/~dwhite | www.freebsd.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.03.9904301137000.16807-100000>