From owner-freebsd-net Tue Oct 15 18:17:58 2002 Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6A06C37B401 for ; Tue, 15 Oct 2002 18:17:57 -0700 (PDT) Received: from mail.deltanet.com (mail.deltanet.com [216.237.144.132]) by mx1.FreeBSD.org (Postfix) with ESMTP id F284543E77 for ; Tue, 15 Oct 2002 18:17:56 -0700 (PDT) (envelope-from pherman@frenchfries.net) Received: from mammoth.eat.frenchfries.net (da001d0174.lax-ca.osd.concentric.net [64.0.144.175]) by mail.deltanet.com (8.11.6/8.11.6) with ESMTP id g9G065c04297 for ; Tue, 15 Oct 2002 17:06:06 -0700 Received: by mammoth.eat.frenchfries.net (Postfix, from userid 1000) id E22644A22; Tue, 15 Oct 2002 17:25:42 -0700 (PDT) Received: from localhost (localhost [127.0.0.1]) by mammoth.eat.frenchfries.net (Postfix) with ESMTP id DE3764A20; Tue, 15 Oct 2002 17:25:42 -0700 (PDT) Date: Tue, 15 Oct 2002 17:25:42 -0700 (PDT) From: Paul Herman X-X-Sender: pherman@mammoth.eat.frenchfries.net To: Lars Eggert Cc: Steve Francis , Kirill Ponomarew , Subject: Re: delayed ACK In-Reply-To: <3DAC8206.1080604@isi.edu> Message-ID: <20021015162359.B8363-100000@mammoth.eat.frenchfries.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Tue, 15 Oct 2002, Lars Eggert wrote: > Paul Herman wrote: > > > > Not true. Although some bugs have been fixed in 4.3, FreeBSD's > > delayed ACKs will still degrade your performance dramatically in > > some cases. > > I'm sorry, but such statements without a packet trace that exhibits the > problem are just not useful. Aha! Another victim who is willing to take a look at this! :-) It's an issue that was left unresolved in kern/24645. Bruce Evans brought this to my attention back during the unrelated "I have delayed ACK problems" thread on -net in January of 2001 and I then passed it on to jlemon. If you need a packet trace, let me know, but you should be able to reproduce it yourself. Even today on my 4.7-PRERELEASE I still get: mammoth# sysctl net.inet.tcp.delayed_ack=0 net.inet.tcp.delayed_ack: 1 -> 0 mammoth# time tar cf 127.0.0.1:/tmp/foo /kernel 0.000u 0.041s 0:00.33 12.1% 350+300k 0+0io 0pf+0w mammoth# sysctl net.inet.tcp.delayed_ack=1 net.inet.tcp.delayed_ack: 0 -> 1 mammoth# time tar cf 127.0.0.1:/tmp/foo /kernel 0.014u 0.033s 0:45.90 0.0% 700+600k 0+0io 0pf+0w ^^^^^^^ It seems that lowering lo0 mtu to 1500 makes this particular problem go away. The magic mtu size is 2100. This makes me think that this is a big problem across GigE using 8K jumbo frames, not sure. Also, taring over the IPv6 lo0 interface seems to work OK. No idea what causes this. -Paul. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message