From owner-freebsd-performance@freebsd.org Tue Mar 7 07:10:21 2017 Return-Path: Delivered-To: freebsd-performance@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 90B66CFB408 for ; Tue, 7 Mar 2017 07:10:21 +0000 (UTC) (envelope-from slw@zxy.spb.ru) Received: from zxy.spb.ru (zxy.spb.ru [195.70.199.98]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 538781505 for ; Tue, 7 Mar 2017 07:10:21 +0000 (UTC) (envelope-from slw@zxy.spb.ru) Received: from slw by zxy.spb.ru with local (Exim 4.86 (FreeBSD)) (envelope-from ) id 1cl9GE-000ORn-VF; Tue, 07 Mar 2017 10:10:18 +0300 Date: Tue, 7 Mar 2017 10:10:18 +0300 From: Slawa Olhovchenkov To: Miroslav Lachman <000.fbsd@quip.cz> Cc: "freebsd-performance@freebsd.org" Subject: Re: Network performance comparison of DragonflyBSD, FreeBSD and Linux Message-ID: <20170307071018.GP15630@zxy.spb.ru> References: <58BE0984.4070208@quip.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <58BE0984.4070208@quip.cz> User-Agent: Mutt/1.5.24 (2015-08-30) X-SA-Exim-Connect-IP: X-SA-Exim-Mail-From: slw@zxy.spb.ru X-SA-Exim-Scanned: No (on zxy.spb.ru); SAEximRunCond expanded to false X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 07 Mar 2017 07:10:21 -0000 On Tue, Mar 07, 2017 at 02:14:44AM +0100, Miroslav Lachman wrote: > There is some comparison of DragonflyBSD, FreeBSD and two versions of > Linux in specific network benchmark - HTTP/1.1 short lived connections. > FreeBSD is the worst in this test. > > https://www.dragonflydigest.com/2017/03/06/19425.html > > https://leaf.dragonflybsd.org/~sephe/perfcomp/1K.png > https://leaf.dragonflybsd.org/~sephe/perfcomp/8K.png > https://leaf.dragonflybsd.org/~sephe/perfcomp/16K.png > > https://leaf.dragonflybsd.org/~sephe/perf_cmp.pdf Is this you test? I mean some congestion in file/page access layer on FreeBSD, can you re-test w/ about 1000 different files? I.e. every client request http://server/X_K.bin~1 http://server/X_K.bin~2 .... http://server/X_K.bin~1000 not just http://server/X_K.bin