Date: Mon, 01 Jun 1998 02:12:01 -0700 From: David Greenman <dg@root.com> To: John Hay <jhay@mikom.csir.co.za> Cc: andrew@iaccess.com.au, freebsd-current@FreeBSD.ORG Subject: Re: mbuf cluster problem continues!! Message-ID: <199806010912.CAA09919@implode.root.com> In-Reply-To: Your message of "Sat, 01 Jun 1998 08:54:17 %2B0200." <199806010654.IAA16317@zibbi.mikom.csir.co.za>
next in thread | previous in thread | raw e-mail | index | archive | help
>> I've seen several reports of mbuf leaks in the specific case of running >> squid proxy servers. As I don't have anything remotely resembling that in any >> configuration I have here, someone else will have to troubleshoot this one. >> It's possible that this might actually be a bug in squid rather than in >> FreeBSD. I have really no idea; I've not seen any mbuf leaks in any other >> networking use of FreeBSD so it is surprising that one would show up when >> doing this. > >Isn't it just the various TCP wait states for old connections that still >have to timeout that look like mbuf leaks? Even on my not-so-very-busy >squid server there is always some of them hanging around. You can easily >see that with "netstat -an". That could be...certainly something to check out. I seem to recall that the previous report of this problem was with a machine that had a very light proxy load, so it seemed unlikely that old connections could be a serious problem. ...but perhaps either the load wasn't as light as thought or perhaps there were very few mbuf clusters configured (or both). -DG David Greenman Co-founder/Principal Architect, The FreeBSD Project To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199806010912.CAA09919>