From owner-freebsd-arm@FreeBSD.ORG Sat Mar 14 03:25:11 2015 Return-Path: Delivered-To: freebsd-arm@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E56266FA; Sat, 14 Mar 2015 03:25:11 +0000 (UTC) Received: from wa3yre.wynn.com (wa3yre.wynn.com [199.89.147.3]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 9C7C9112; Sat, 14 Mar 2015 03:25:11 +0000 (UTC) Received: from ivory.wynn.com (mail.wynn.com [199.89.147.3]) (authenticated bits=0) by wa3yre.wynn.com (8.14.3/8.12.6) with ESMTP id t2E3OuKT070384; Fri, 13 Mar 2015 23:24:57 -0400 (EDT) (envelope-from freebsd-arm@wynn.com) Date: Fri, 13 Mar 2015 23:24:55 -0400 From: Brett Wynkoop To: Bernd Walter , "freebsd-arm@freebsd.org" Subject: Re: BeagleBone slow inbound net I/O Message-ID: <20150313232455.3f844d3e@ivory.wynn.com> In-Reply-To: <20150313235104.GJ34648@cicely7.cicely.de> References: <20150311165115.32327c5a@ivory.wynn.com> <20150312133433.GB28385@cicely7.cicely.de> <20150312232641.4365263d@ivory.wynn.com> <1426270714.19693.7.camel@freebsd.org> <20150313235104.GJ34648@cicely7.cicely.de> X-Mailer: Claws Mail 3.10.1 (GTK+ 2.24.25; x86_64-apple-darwin10.8.0) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Ian Lepore X-BeenThere: freebsd-arm@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: "Porting FreeBSD to ARM processors." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 14 Mar 2015 03:25:12 -0000 On Sat, 14 Mar 2015 00:51:04 +0100 Bernd Walter wrote: > On Fri, Mar 13, 2015 at 12:18:34PM -0600, Ian Lepore wrote: > > On Thu, 2015-03-12 at 23:26 -0400, Brett Wynkoop wrote: > > > Greeting- > > > > > > It is confirmed, the net I/O is much slower than reading from the > > > SD card. Here is another run of tar - pipe - tar, but this time > > > the source is the sd card and the destination is still the USB > > > zfs. > > [...] > > > > > > > You're not actually testing network performance, you're testing a > > confusing mashup of overall system performance. > > Ian your point is well taken, but one can have a system where each part works fine on it's own, but when working in concert there is a breakdown. I believe that is what I have observed. Reading from sd card and writing to usb was many times faster than reading from ethernet and writing to usb. I would say I am testing the case where the source of the data is over the ethernet port and the destination is on the USB Flash. I will try grabbing data over the net and sending it to /dev/null, but if we have trouble moving bits from ethernet to USB I would say that is something that we might want to investigate. -Brett -- wynkoop@wynn.com http://prd4.wynn.com/wynkoop/pgp-keys.txt 917-642-6925 929-272-0000 Amendment VII In Suits at common law, where the value in controversy shall exceed twenty dollars, the right of trial by jury shall be preserved, and no fact tried by a jury, shall be otherwise re-examined in any Court of the United States, than according to the rules of the common law.