From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp201.iad.emailsrvr.com (smtp201.iad.emailsrvr.com [207.97.245.201]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 1BB48202224 for ; Sat, 23 Jun 2012 12:29:03 -0700 (PDT) Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp30.relay.iad1a.emailsrvr.com (SMTP Server) with ESMTP id 8DBDA201F1; Sat, 23 Jun 2012 15:29:02 -0400 (EDT) X-Virus-Scanned: OK Received: from legacy5.wa-web.iad1a (legacy5.wa-web.iad1a.rsapps.net [192.168.2.221]) by smtp30.relay.iad1a.emailsrvr.com (SMTP Server) with ESMTP id 72355201ED; Sat, 23 Jun 2012 15:29:02 -0400 (EDT) Received: from reed.com (localhost [127.0.0.1]) by legacy5.wa-web.iad1a (Postfix) with ESMTP id 5FA6F2E9802E; Sat, 23 Jun 2012 15:29:02 -0400 (EDT) Received: by apps.rackspace.com (Authenticated sender: dpreed@reed.com, from: dpreed@reed.com) with HTTP; Sat, 23 Jun 2012 15:29:02 -0400 (EDT) Date: Sat, 23 Jun 2012 15:29:02 -0400 (EDT) From: dpreed@reed.com To: "Robert Bradley" MIME-Version: 1.0 Content-Type: text/plain;charset=UTF-8 Content-Transfer-Encoding: quoted-printable Importance: Normal X-Priority: 3 (Normal) X-Type: plain In-Reply-To: <4FE4D882.50308@gmail.com> References: <1340395875.353911244@apps.rackspace.com> <4FE4D882.50308@gmail.com> Message-ID: <1340479742.390625935@apps.rackspace.com> X-Mailer: webmail7.0 Cc: cerowrt-devel@lists.bufferbloat.net Subject: Re: [Cerowrt-devel] Fwd: [PATCH] ag71xx: Added support for baby-jumbo packets. X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 23 Jun 2012 19:29:04 -0000 I find it curious that packet aggregation is done in 802.11n standards, but= that the packets are limited to 1540. I bet that limit may not be there = in all Atheros NICs, and maybe not in this one. Will investigate now that = I'm curious.=0A=0A-----Original Message-----=0AFrom: "Robert Bradley" =0ASent: Friday, June 22, 2012 4:41pm=0ATo: cerowrt-d= evel@lists.bufferbloat.net=0ASubject: Re: [Cerowrt-devel] Fwd: [PATCH] ag71= xx: Added support for baby-jumbo packets.=0A=0AOn 22/06/12 21:11, dpreed@re= ed.com wrote:=0A> Good step. Why not allow 9K byte jumbos when one's packe= ts traverse a path that is internal to the local area, and all the 1 GigE l= inks support 9K?=0A>=0A=0AAll the posts I could see claim that the System-o= n-Chip NIC (Atheros =0AAR7161) cannot handle packets greater than 1540 octe= ts, so routing 9k =0Apackets from wired->wireless or wired->WAN would not b= e an option. If I =0Aunderstood Dave's previous post correctly, though, th= e built-in switch =0Aallows jumbo packets, so wired->wired internal traffic= should work fine =0Awith 9K packets already.=0A=0AThe only issue with that= setup is that with mismatched MTUs, it might be =0Aimpossible to communica= te with the router and the 9k-friendly nodes at =0Athe same time. Thankful= ly, on Linux at least, you can set per-route =0AMTUs (http://lartc.org/howt= o/lartc.cookbook.mtu-discovery.html), so it =0Amight be possible to exploit= that to do what you want. Maybe something =0Alike this would work?=0A=0Ai= p route add default via 172.30.42.1 mtu 1500=0Aip route add 172.30.42.1/32 = dev eth0 mtu 1500=0Aip route add 172.30.42.1/27 dev eth0 mtu 9000=0A=0A-- = =0ARobert Bradley=0A_______________________________________________=0ACerow= rt-devel mailing list=0ACerowrt-devel@lists.bufferbloat.net=0Ahttps://lists= .bufferbloat.net/listinfo/cerowrt-devel=0A