From owner-freebsd-net@freebsd.org  Fri Oct 27 20:34:36 2017
Return-Path: <owner-freebsd-net@freebsd.org>
Delivered-To: freebsd-net@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 0958CE508A9
 for <freebsd-net@mailman.ysv.freebsd.org>;
 Fri, 27 Oct 2017 20:34:36 +0000 (UTC) (envelope-from aspam@cox.net)
Received: from fed1rmfepi106.cox.net (fed1rmfepi106.cox.net [68.230.241.137])
 by mx1.freebsd.org (Postfix) with ESMTP id D834A767DA
 for <freebsd-net@freebsd.org>; Fri, 27 Oct 2017 20:34:35 +0000 (UTC)
 (envelope-from aspam@cox.net)
Received: from eastrmimpo305.cox.net ([68.230.241.237])
 by eastrmfepo103.cox.net
 (InterMail vM.8.01.05.28 201-2260-151-171-20160122) with ESMTP
 id <20171027203411.YOXV4084.eastrmfepo103.cox.net@eastrmimpo305.cox.net>
 for <freebsd-net@freebsd.org>; Fri, 27 Oct 2017 16:34:11 -0400
Received: from thunder.sweets ([68.100.138.62])
 by eastrmimpo305.cox.net with cox
 id SkaB1w0091LxgH801kaB5X; Fri, 27 Oct 2017 16:34:11 -0400
X-CT-Class: Clean
X-CT-Score: 0.00
X-CT-RefID: str=0001.0A020201.59F39843.00AA, ss=1, re=0.000, recu=0.000,
 reip=0.000, cl=1, cld=1, fgs=0
X-CT-Spam: 0
X-Authority-Analysis: v=2.2 cv=ENB26xRC c=1 sm=1 tr=0
 a=3mkzfl4ircflX6G+lDqBYw==:117 a=3mkzfl4ircflX6G+lDqBYw==:17
 a=IkcTkHD0fZMA:10 a=x7bEGLp0ZPQA:10 a=02M-m0pO-4AA:10
 a=kFlFZXso1ko05N4mdaoA:9 a=QEXdDO2ut3YA:10
X-CM-Score: 0.00
Authentication-Results: cox.net; none
Received: from [10.10.10.15] (thunder.sweets [10.10.10.15])
 (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits))
 (No client certificate requested)
 by thunder.sweets (Postfix) with ESMTP id 92DAC113FC;
 Fri, 27 Oct 2017 16:34:10 -0400 (EDT)
Message-ID: <59F39841.1070601@cox.net>
Date: Fri, 27 Oct 2017 16:34:09 -0400
From: Joe Buehler <aspam@cox.net>
User-Agent: Thunderbird 1.5.0.12 (X11/20120201)
MIME-Version: 1.0
To: Vincenzo Maffione <v.maffione@gmail.com>
CC: FreeBSD Net <freebsd-net@freebsd.org>
Subject: Re: virtio_net / netmap RX dropping frames
References: <59F0FBEE.6030008@cox.net> <59F1F1BA.3020608@cox.net>
 <59F214F6.9060905@cox.net> <59F223C3.5040907@cox.net>
 <SWyy1w0133ngQoH01Wyyg8>
In-Reply-To: <SWyy1w0133ngQoH01Wyyg8>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.23
Precedence: list
List-Id: Networking and TCP/IP with FreeBSD <freebsd-net.freebsd.org>
List-Unsubscribe: <https://lists.freebsd.org/mailman/options/freebsd-net>,
 <mailto:freebsd-net-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-net/>
List-Post: <mailto:freebsd-net@freebsd.org>
List-Help: <mailto:freebsd-net-request@freebsd.org?subject=help>
List-Subscribe: <https://lists.freebsd.org/mailman/listinfo/freebsd-net>,
 <mailto:freebsd-net-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Fri, 27 Oct 2017 20:34:36 -0000

Vincenzo Maffione wrote:

> You need to figure out who is dropping the RX packets and why. This
> seems to happen before the packets really make their way to the
> virtio-net RX ring. So it must be some queue overflow in the macvtap or
> your ixgbe device.

I cranked up the qlen on macvtap1 (100,000) and that fixed the drops but
the resulting latency is horrible, increasing with test length, as is
the jitter.  Given the low RX thread CPU it would appear that there is
eomething wrong between macvtap and my code.  I will have to chew on
this a bit.

Joe Buehler