Date: Mon, 15 Jul 1996 03:08:39 -0700 From: David Greenman <davidg@root.com> To: bill@twwells.com (T. William Wells) Cc: freebsd-questions@FreeBSD.ORG Subject: Re: system hangs? after resetting rtq_reallyold Message-ID: <199607151008.DAA02851@root.com> In-Reply-To: Your message of "15 Jul 1996 05:17:43 EDT." <4sd2bn$47f@twwells.com>
next in thread | previous in thread | raw e-mail | index | archive | help
>In article <199607150758.AAA02464@root.com>, >David Greenman <davidg@Root.COM> wrote: >: It shouldn't be necessary to set NMBCLUSTERS that high on most "normal" >: systems. It would take several hundred TCP connections to exhaust 2000 mbuf >: clusters. > >The machine in question is our main shell account server, which >also hosts our Web server. A netstat shows the following. At 5AM. > > 169 CLOSING > 65 ESTABLISHED > 15 FIN_WAIT_1 > 5 FIN_WAIT_2 > 16 LAST_ACK > 2 SYN_RCVD > 2 SYN_SENT > 34 TIME_WAIT > >During peak hours, I expect two or three times those numbers. >The machine hasn't been rebooted in a month; it's used a maximum >of 2036 clusters. Yes, this is exactly what I was expecting. Thanks for the numbers to back this up. >Web servers in particular are going to want a large number of >mbufs..... Yes, absolutely. WWW servers are especially evil because of their transaction oriented nature. TCP was never designed for that. -DG David Greenman Core-team/Principal Architect, The FreeBSD Project
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199607151008.DAA02851>