From owner-freebsd-xen@FreeBSD.ORG  Thu Jan 27 14:32:55 2011
Return-Path: <owner-freebsd-xen@FreeBSD.ORG>
Delivered-To: freebsd-xen@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id 4404B1065674
	for <freebsd-xen@freebsd.org>; Thu, 27 Jan 2011 14:32:55 +0000 (UTC)
	(envelope-from sysconfig@ossafe.org)
Received: from mx2.the-ally.co.uk (mx2.the-ally.co.uk [95.154.227.236])
	by mx1.freebsd.org (Postfix) with ESMTP id 0B84A8FC12
	for <freebsd-xen@freebsd.org>; Thu, 27 Jan 2011 14:32:54 +0000 (UTC)
Received: from [10.2.2.20] (unknown [10.2.2.20])
	by mx2.the-ally.co.uk (Postfix) with ESMTP id 4FF35ED0418;
	Thu, 27 Jan 2011 14:01:13 +0000 (GMT)
Mime-Version: 1.0 (Apple Message framework v1082)
Content-Type: text/plain; charset=us-ascii
From: Carsten Heesch <sysconfig@ossafe.org>
In-Reply-To: <alpine.BSF.2.00.1101260038310.20212@tiktik.epipe.com>
Date: Thu, 27 Jan 2011 14:01:25 +0000
Content-Transfer-Encoding: quoted-printable
Message-Id: <0F524D72-3752-47FD-9234-ED009009B0A0@ossafe.org>
References: <AANLkTink37iAtMeNZ5NEhgKwPFOgXOVr4epSFxp=7Kmr@mail.gmail.com>
	<AANLkTink=S9WxJCVT+AOaMjiLPLg9gtSwF1VwdzexFG+@mail.gmail.com>
	<alpine.BSF.2.00.1101251425320.20212@tiktik.epipe.com>
	<1295969742.3187.48.camel@pow>
	<alpine.BSF.2.00.1101260038310.20212@tiktik.epipe.com>
To: Janne Snabb <snabb@epipe.com>
X-Mailer: Apple Mail (2.1082)
Cc: freebsd-xen@freebsd.org, luke@hybrid-logic.co.uk
Subject: Re: I have a problem with iSCSI on AMD64 Xen HVM
X-BeenThere: freebsd-xen@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Discussion of the freebsd port to xen - implementation and usage
	<freebsd-xen.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-xen>,
	<mailto:freebsd-xen-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-xen>
List-Post: <mailto:freebsd-xen@freebsd.org>
List-Help: <mailto:freebsd-xen-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-xen>,
	<mailto:freebsd-xen-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Thu, 27 Jan 2011 14:32:55 -0000



>> 	int max =3D 24 /* MAX_SKB_FRAGS + (rx->status <=3D =
RX_COPY_THRESHOLD) */;

I've just recompiled XENHVM setting this for a quick test:

> int max =3D MAX_SKB_FRAGS;


Before, I was receiving said error message a lot; now it's gone. Also, =
throughput has massively increased!

My test setup was:

2x FreeBSD/amd64 8.2-RC2 (compiled about a week ago), XENHVM kernel.
Both DomU's were running on the same physical machine (CentOS 5.5 x86_64 =
with Xen 4.3.3 on Intel i7), their xn0 NICs are using the same bridge on =
Dom0.

I was able to trigger the error message on the receiving side by doing a =
simple "scp test.bin <target>:/dev/null" from one DomU to the other. =
Throughput dropped within seconds from ~40MB/sec below 2MB/sec.

Now, with that change in place, throughput remains well above 50MB/sec! =
(approximates actual disk read speed minus SSH compression/encryption =
overhead)=20


Which would be the right value for max? This was obviously only a quick, =
dirty test. I haven't got a clue either, where the max=3D5 came from, =
but it doesn't seem to be a reasonable value.


Cheers
Carsten