From owner-freebsd-net@freebsd.org  Sat Jan 23 19:17:14 2016
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 A168FA8E805
 for <freebsd-net@mailman.ysv.freebsd.org>;
 Sat, 23 Jan 2016 19:17:14 +0000 (UTC)
 (envelope-from cenzatti@hush.com)
Received: from smtp1.hushmail.com (smtp1a.hushmail.com [65.39.178.236])
 (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits))
 (Client CN "smtp.hushmail.com", Issuer "smtp.hushmail.com" (not verified))
 by mx1.freebsd.org (Postfix) with ESMTPS id 85EB71A56
 for <freebsd-net@freebsd.org>; Sat, 23 Jan 2016 19:17:14 +0000 (UTC)
 (envelope-from cenzatti@hush.com)
Received: from smtp1.hushmail.com (smtp1a.hushmail.com [65.39.178.236])
 by smtp1.hushmail.com (Postfix) with SMTP id 14F5340297
 for <freebsd-net@freebsd.org>; Sat, 23 Jan 2016 18:43:21 +0000 (UTC)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed; d=hush.com;
 h=date:to:subject:from; s=hush;
 bh=nAfv2av4gUYI09ULdiJAiY5Bbtn+vPFXBwyrnm5KEjY=;
 b=lBz1NXai+xJr0+gDVEfkL8SV2nS6CNDmo3k4JdKbuSlH73A5pNN1J7uh455tZQw5FlliMvUAXx0OogKXrTsncgicAsGwOXQ51H9FrW/svmumQMl0hcPoebmoyurJGYf1n4vrOxEjoBvqlwldto2/R7l8j5MoA75cHu7qmuWyndw+aKC2puoh30ZP3TFABRO6FzbOuuexONed4a5INBWjnV+7sA0pH2XmpudkISwHwzXB2d6e3dSRM43TD+UdXmX0PJfbs5yzRN143sz34qVw/0N9+fk2MPE369UDcVEBMI5Zy9jlNi8pr+Iwauja7Sm9mFiI6GM0giqW4pc+fEYdOQ==
Received: from smtp.hushmail.com (w5.hushmail.com [65.39.178.80])
 by smtp1.hushmail.com (Postfix) with ESMTP;
 Sat, 23 Jan 2016 18:43:20 +0000 (UTC)
Received: by smtp.hushmail.com (Postfix, from userid 99)
 id CA903A0126; Sat, 23 Jan 2016 18:43:20 +0000 (UTC)
MIME-Version: 1.0
Date: Sat, 23 Jan 2016 16:43:20 -0200
To: "Adrian Chadd" <adrian.chadd@gmail.com>,
 "Pavel Odintsov" <pavel.odintsov@gmail.com>
Cc: freebsd-net@freebsd.org, "Eduardo Meyer" <dudu.meyer@gmail.com>
Subject: Re: netmap design question - accessing netmap:X-n individual queues
 on FreeBSD
From: "Marcus Cenzatti" <cenzatti@hush.com>
In-Reply-To: <CAJ-VmokP2f5Uv5ubn2Cico_iXN20jL9tPuYHE2gomGLWkPLsUA@mail.gmail.com>
References: <CAEqdE_4ANVrGP2hKA4nT=AJqJ5M80A+Hy2srjoe8wfugvmbypg@mail.gmail.com>
 <CALgsdbe7W2fPEWMnobXWebn63J9kYhupE-C=JM2xfQKBfnQwaw@mail.gmail.com>
 <CAJ-VmonCizOxfsV7kH_7GTHYXW8FgvjEV-8zt7qxE6b5tUadxg@mail.gmail.com>
 <CALgsdbdZOkpX-hzLVkLxz=1kGOjnNCNSZz4B1HfJy2hART4+0w@mail.gmail.com>
 <CAJ-VmokP2f5Uv5ubn2Cico_iXN20jL9tPuYHE2gomGLWkPLsUA@mail.gmail.com> 
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="UTF-8"
Message-Id: <20160123184320.CA903A0126@smtp.hushmail.com>
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.20
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: Sat, 23 Jan 2016 19:17:14 -0000



On 1/23/2016 at 1:31 PM, "Adrian Chadd" <adrian.chadd@gmail.com> wrote:
>
>For random src/dst ports and IPs and on the chelsio t5 40gig 
>hardware,
>I was getting what, uhm, 40mil tx pps and around 25ish mil rx pps?
>
>The chelsio rx path really wants to be coalescing rx buffers, which
>the netmap API currently doesn't support. I've no idea if luigi has
>plans to add that. So, it has the hilarious side effect of "adding
>more RX queues" translates to "drops in RX performance." :(
>
>Thanks,

hello,

I am sorry, are you saying intel and chelsio distribute RX packet load differently? If I am not mistaken intel will distributed traffic among queues based on ip addresses flow/hashes/whatever, does chelsio make it per packet or somethig other?

how does this behavior you noticed could affect single queue (or applications on netmap:if0 and not netmap:if0-n) on chelsio?

thanks