Date: Tue, 27 Oct 1998 22:30:23 -0800 (PST) From: Marc Slemko <marcs@znep.com> To: Mike Smith <mike@smith.net.au> Cc: Steven Yang <syang@directhit.com>, "'freebsd-hackers@freebsd.org'" <freebsd-hackers@FreeBSD.ORG> Subject: Re: FW: Can't get rid of my mbufs. Message-ID: <Pine.BSF.4.03.9810272224160.20832-100000@alive.znep.com> In-Reply-To: <199810280158.RAA02572@dingo.cdrom.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 27 Oct 1998, Mike Smith wrote: > > Thanks for the info. One question remains. Suppose netstat -m tells me > > that 7900/8050 mbuf clusters are in use. Now suppose I stop all of the > > important processes and let the machine stay idle for 2 hours. Why does > > netstat -m still tell me that 7900/8050 mbuf clusters are in use? > > Basically, I'd wish it would say something like 99/8050 mbuf clusters in > > use instead. I already have MAXUSERS set to 512. > > You have an mbuf leak somewhere, where mbufs are being allocated to > contain data but never being freed. > > I'm not aware of any known mbuf leaks in 2.2.7, however you might He isn't using 2.2.7, he is using 2.2.6 plus an old verison of Apache. My first recommendation would be to upgrade both. I don't really see that the sort of volume being moved is that huge (it is trivial to do 100 hits/sec on a 20k file on my little p166 using well under 500 mbuf clusters), but a _lot_ can depend on the exact benchmark setup. eg. 5000 simultaneous clients will use a heck of a lot more mbufs than 5 simultaneous clients will, yet both could get similar throughput. SUre, the FastCGI stuff is probably doing something more complex than static files and it does double the total transfered (from fastcgi to the server, from the server to the client), but still... To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" 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.4.03.9810272224160.20832-100000>