From owner-freebsd-stable Fri Jun 12 06:19:45 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id GAA07359 for freebsd-stable-outgoing; Fri, 12 Jun 1998 06:19:45 -0700 (PDT) (envelope-from owner-freebsd-stable@FreeBSD.ORG) Received: from assurance ([206.29.49.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id GAA07347 for ; Fri, 12 Jun 1998 06:19:37 -0700 (PDT) (envelope-from vshah@rstcorp.com) Received: (from uucp@localhost) by assurance (8.7.5/8.6.9) id JAA17445; Fri, 12 Jun 1998 09:19:04 -0400 Received: from sandbox.rstcorp.com(206.29.49.63) by assurance.rstcorp.com via smap (V2.0) id xma017439; Fri, 12 Jun 98 09:18:07 -0400 Received: from fault.rstcorp.com (fault [206.29.49.18]) by sandbox.rstcorp.com (8.8.8/8.8.8) with ESMTP id JAA08098; Fri, 12 Jun 1998 09:18:05 -0400 (EDT) Received: (from vshah@localhost) by fault.rstcorp.com (8.8.8/8.8.8) id JAA09212; Fri, 12 Jun 1998 09:16:20 -0400 (EDT) Date: Fri, 12 Jun 1998 09:16:20 -0400 (EDT) Message-Id: <199806121316.JAA09212@fault.rstcorp.com> From: "Viren R. Shah" To: Wes Peters Cc: freebsd-stable@FreeBSD.ORG, Robert Du Gaue , Doug Russell Subject: Re: NFS server performance (was: NFS performance benchmarks?) In-Reply-To: <358225EE.783ED931@softweyr.com> References: <358225EE.783ED931@softweyr.com> X-Mailer: VM 6.40 under 19.16 "Lille" XEmacs Lucid Reply-To: "Viren R. Shah" X-Face: )~y+U*K:yzjz{q<5lzpI_SVef'U.])9g[C9`1N@]u3,MHY7f*l7C)[_NjM4y4K8$uIUh|\u (K&&HS6,M!61&GMTk'mqmB/Qg]]X}"?TzsFl]"2v!bl8']dma.:^IY^a[lbOI>U:b<~FyK3q-p{HmZ mn~g.`~BE!5{2D:}Yi+\_KkWe?XaHj9$ko1k8iKLYv5*_2c8"G=?Up[}hn+7RNM(bzBZ_wWk6!Pf&B ?3Tcm7M7B~W%K/I0aX3]*=jP?aM]H6HBPT`oLk+0n^_;N\2\%|Rhy;p}34Q.jEsM\qtnxcm;ag%Nq Mime-Version: 1.0 (generated by tm-edit 7.106) Content-Type: text/plain; charset=US-ASCII Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG >>>>> "Wes" == Wes Peters writes: [Thanks a lot for the responses.] Doug> There must be some time of flakiness occuring here. (Perhaps Doug> some strange incompatibility due to the SunOS client??) I have Doug> used iozone to test Robert> I would look at your NIC cards, the HUB/Switch (if any), Wes> I agree. Have you read the FAQs about NFS server with Sun clients? Yes. The FreeBSD Server only accepts NFSv2 mounts (using the -2 flag on mountd). NFSv3 was said to be too unstable to use in a production system. The system specs are as follows: PII-300 w/ 128M RAM Adaptec aic7880 Ultra SCSI host adapter Intel EtherExpress PRO/100+ card. 3COM hub The card is: fxp0: flags=8843 mtu 1500 inet 206.29.49.78 netmask 0xffffff80 broadcast 206.29.49.127 ether 00:a0:c9:ce:ea:4a media: autoselect The one problem seems to be: [vshah@hal] ~/extraspace> netstat -i | more Name Mtu Network Address Ipkts Ierrs Opkts Oerrs Coll fxp0 1500 00.a0.c9.ce.ea.4a 43972311 183 43193398 2 1842570 fxp0 1500 206.29.49/25 hal.rstcorp.com 43972311 183 43193398 2 1842570 There seem to be a lot of collisions on the card. Is this indicative of anything? Should the NIC be forced into 100baseT/full-duplex mode? The 100Mb segment only has a couple of Ultras, the FreeBSD server and a couple of NT boxes on there (basically all the different server type boxen). Wes> By the way, I expect a Solaris server running on SMP hardware to out- Wes> perform a FreeBSD server; their threaded NFS server is quite fast. The Solaris server is an Ultra-1 without any RAID. Wes> Wes Peters Softweyr LLC Thanks Viren -- Viren R. Shah {viren @ rstcorp . com} Names : Vanadium(23) Iodine(53) RhEnium(75) Nitrogen(7) Density(g/mL): 5.8 4.92 21 0.0001251 Average Density: 7.93003 g/mL To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message