From owner-freebsd-current Sun Jun 7 04:07:33 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id EAA11754 for freebsd-current-outgoing; Sun, 7 Jun 1998 04:07:33 -0700 (PDT) (envelope-from owner-freebsd-current@FreeBSD.ORG) Received: from kremvax.demos.su (kremvax.demos.su [194.87.0.20]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id EAA11730 for ; Sun, 7 Jun 1998 04:07:17 -0700 (PDT) (envelope-from sinbin.demos.su!bag@kremvax.demos.su) Received: by kremvax.demos.su (8.6.13/D) from 0@sinbin.demos.su [194.87.5.31] with ESMTP id PAA07026; Sun, 7 Jun 1998 15:06:18 +0400 Received: by sinbin.demos.su id PAA17878; (8.6.12/D) Sun, 7 Jun 1998 15:05:36 +0400 From: bag@sinbin.demos.su (Alex G. Bulushev) Message-Id: <199806071105.PAA17878@sinbin.demos.su> Subject: Re: mbuf cluster problem continues!! In-Reply-To: <19980602192424.02082@demos.su> from "Mikhail A. Sokolov" at "Jun 2, 98 07:24:24 pm" X-ELM-OSV: (Our standard violations) no-mime=1; no-hdr-encoding=1 To: mishania@demos.su (Mikhail A. Sokolov) Date: Sun, 7 Jun 1998 15:05:35 +0400 (MSD) Cc: wollman@khavrinen.lcs.mit.edu, dg@root.com, freebsd-current@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL32 (25)] Content-Type: text Sender: owner-freebsd-current@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > Hello, > > On Mon, Jun 01, 1998 at 12:26:41PM -0400, Garrett Wollman wrote: > # < said: > > # > I've seen several reports of mbuf leaks in the specific case of running > # > squid proxy servers. > > # Not seen here. > > # root@xyz(4)$ netstat -m > # 825/1408 mbufs in use: > > Oh well, it's not squid what is definite culprit here, not closing tcp > connections: let's take a machine, which is attacked by clients, is being > agressively used nfs server and doesn't even have any services besides nfs, > which could leave tcp connections not closed: > > {zz}~/# netstat -m > 10577/10688 mbufs in use: > 10057 mbufs allocated to data > 520 mbufs allocated to packet headers > 451/728 mbuf clusters in use > 2792 Kbytes allocated to network (79% in use) > 0 requests for memory denied > 0 requests for memory delayed > 0 calls to protocol drain routines > {zz}~/# uptime > 6:44ÐÐ up 1 day, 8:57, 21 users, load averages: 1.85, 1.80, 1.62 > > NMBCLUSTERS are 24k, and still the machine will leak mbuf's once a week. > it is intresting than in the case of nfs server (with mbuf's leak's) it is no problems with number of mbuf claster's, only number of mbuf's increased, for example: 4:29 up 6:42, 19 users, load averages: 1.06, 1.23, 1.48 ^^^^ after reboot > netstat -m 3609/3744 mbufs in use: ^^^^^^^^^ 3084 mbufs allocated to data 525 mbufs allocated to packet headers 485/660 mbuf clusters in use ^^^^^^^ 1788 Kbytes allocated to network (79% in use) 0 requests for memory denied 0 requests for memory delayed 0 calls to protocol drain routines so 485 mbuf clusters and 3600 mbuf's allocated and after several day's: 1:56 up 6 days, 4:09, 14 users, load averages: 0.58, 0.77, 0.84 ^^^^^^^^^^^^^ > netstat -m 34613/34752 mbufs in use: ^^^^^^^^^^^ 34393 mbufs allocated to data 220 mbufs allocated to packet headers 260/818 mbuf clusters in use ^^^^^^^ 5980 Kbytes allocated to network (81% in use) 0 requests for memory denied 0 requests for memory delayed 0 calls to protocol drain routines only 260 mbuf clusters allocated, but 34613 mbufs !!! so this nfs server state is "before crash" Alex. > > My 2 kopeks. > > -- > -mishania > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-current" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message