From owner-freebsd-net Fri Sep 21 1: 0: 1 2001 Delivered-To: freebsd-net@freebsd.org Received: from silby.com (cb34181-a.mdsn1.wi.home.com [24.14.173.39]) by hub.freebsd.org (Postfix) with ESMTP id 943A237B421 for ; Fri, 21 Sep 2001 00:59:56 -0700 (PDT) Received: (qmail 68964 invoked by uid 1000); 21 Sep 2001 07:59:56 -0000 Received: from localhost (sendmail-bs@127.0.0.1) by localhost with SMTP; 21 Sep 2001 07:59:56 -0000 Date: Fri, 21 Sep 2001 02:59:56 -0500 (CDT) From: Mike Silbersack To: Cc: Subject: Re: TCP performance question In-Reply-To: <200109210746.QAA09541@const.kawasaki.flab.fujitsu.co.jp> Message-ID: <20010921025715.U68923-100000@achilles.silby.com> 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 Fri, 21 Sep 2001 tsuchiya@flab.fujitsu.co.jp wrote: > and we changed the size from 1 to 10000 byte and measured the time of > read/write pair on the server. Usually the measured time is > around or less than 1 msec, however it is always 100msec when the size is > between 2049 and 2919 byte or between 4381 and 5839 byte or > between 7301 and 8751 byte. 100 times slower. Try disabling delayed ACKs and see how that affects your results. The default delay for delayed acks is 100ms. sysctl -w net.inet.tcp.delayed_ack=0 Actually, come to think of it, I think Jonathan Lemon fixed issues related to this with delayed acks sometime between 4.2 and 4.4. For this (and many other reasons), you should consider upgrading before you continue your performance tests. Mike "Silby" Silbersack To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message