From owner-freebsd-net@freebsd.org Mon Oct 22 07:49:00 2018 Return-Path: Delivered-To: freebsd-net@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 8B4EFFED55B for ; Mon, 22 Oct 2018 07:49:00 +0000 (UTC) (envelope-from evidence@nitrology.com) Received: from nitrology.com (nitrology.com [69.28.128.160]) by mx1.freebsd.org (Postfix) with ESMTP id 2B1DF8D098; Mon, 22 Oct 2018 07:49:00 +0000 (UTC) (envelope-from evidence@nitrology.com) Received: by nitrology.com (Postfix, from userid 1001) id 484525D458; Mon, 22 Oct 2018 00:48:53 -0700 (MST) Date: Mon, 22 Oct 2018 00:48:53 -0700 From: Jason Wolfe To: Lev Serebryakov Cc: Eugene Grosbein , freebsd-net@freebsd.org Subject: Re: What is best TCP throughput benchmarking tool? Message-ID: <20181022074853.GA31987@nitrology.com> References: <650aa1c7-26db-f463-cb59-8dfe1886c764@grosbein.net> <1743704969.20181019235034@serebryakov.spb.ru> <04f00191-78b8-6c9f-4b6b-fb11d10f91ea@grosbein.net> <876446461.20181020020328@serebryakov.spb.ru> <78b23b34-7c47-30a1-4386-405ec90fa76d@grosbein.net> <926143031.20181020175438@serebryakov.spb.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <926143031.20181020175438@serebryakov.spb.ru> User-Agent: Mutt/1.10.1 (2018-07-13) X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 22 Oct 2018 07:49:00 -0000 Lev Serebryakov wrote on Sat, Oct 20, 2018 at 05:54:38PM +0300: > Hello Eugene, > > Saturday, October 20, 2018, 2:23:29 AM, you wrote: > > > You do not need to micro-control this. The wrk provides you with nice stats > > plus you have counters of "systat -ifstat 1" during long test. > > >> All these tools ? wrk, nginx ? are optimized for many concurrent > >> connections on powerful hardware and looks like overkill to test one > >> connection bandwidth on Atom CPU. > > You can choose number of concurrent connections yourself while running wrk. > One. I need one :-) > > >> BTW, how to configure nginx to server 16G+ file without any disk access? > >> One big hole on tmpfs? :) > > You do not need large disk file in case of wrk+nginx. Make small-sized tmpfs > > with single several megabytes-sized file, and that's all. > I want to run multi-minute streams. On gigabit network. Without any time > spent on connections, requests, TCP windows scaling, etc. As I said, it is > complete opposite to what nginx+wrk does well. nginx will happily serve sparse files: # touch internets.bff; time truncate -s 30T internets.bff; ls -ls # internets.bff real 0m0.001s user 0m0.000s sys 0m0.000s 224 -rw-r--r-- 1 root wheel 32985348833280 Oct 22 00:37 internets.bff HTTP request sent, awaiting response... 200 OK Length: 32985348833280 (30T) [application/octet-stream] Jason