Return-path: Received: from crystal.sipsolutions.net ([195.210.38.204]:39898 "EHLO sipsolutions.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756419AbYBAXaM (ORCPT ); Fri, 1 Feb 2008 18:30:12 -0500 Subject: Re: mac80211 QoS/aggregation questions, thoughts From: Johannes Berg To: Tomas Winkler Cc: Ron Rindjunsky , linux-wireless , Jouni Malinen , Ivo van Doorn , Patrick McHardy In-Reply-To: <1ba2fa240802011524g38a9583fs7c4b792bda844327@mail.gmail.com> (sfid-20080201_232419_709731_495E9739) References: <1201882512.4188.66.camel@johannes.berg> <1201902217.4188.82.camel@johannes.berg> <1ba2fa240802011524g38a9583fs7c4b792bda844327@mail.gmail.com> (sfid-20080201_232419_709731_495E9739) Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-Uxi+pqI7sb4Nv3FxpLpm" Date: Sat, 02 Feb 2008 00:30:03 +0100 Message-Id: <1201908603.4188.97.camel@johannes.berg> (sfid-20080201_233017_535795_91C74BED) Mime-Version: 1.0 Sender: linux-wireless-owner@vger.kernel.org List-ID: --=-Uxi+pqI7sb4Nv3FxpLpm Content-Type: text/plain Content-Transfer-Encoding: quoted-printable > 4965 has 4 queues which are used for regular WMM. Only 11 queues > might be used for aggregation, but in AP mode we might map one of the > queues to after beacon multicast traffic. > One queue is reserved for communicating with FW. The number my differ > on further NICs. Ok, makes sense. > All the traffic queues 4 WMM + 11 AGG are served according regular WMM > policy, 4 AC - these are configured by conf_tx. The aggregation > queues are needed for handling ordering of frames correctly and not > for on media prioritizing Yeah I realise those are just for the right ordering (which is interesting btw, Broadcom gets away without extra queues, not sure yet how), but I those have to have media access too and I wonder how that is configured. But it's not too important right now. I'm trying to grasp the qdisc/multiqueue netdev stuff right now, it's proving harder than I expected :) > Sorry but I have to review your patch later No worries, I just whipped that up as proof-of-concept. johannes --=-Uxi+pqI7sb4Nv3FxpLpm Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Comment: Johannes Berg (powerbook) iQIVAwUAR6OreqVg1VMiehFYAQJOdg//UQ5NK5DRfEl23nDw/ZkMbBl/3sFRGHbH 5p21+w2XIeK4FZGGx8KSLafTpDryWcnGUzT8U4bgNqBX+jS5KgBeneDUS4ye8/jz nRrMoxj04hhUz3XV8LaYrf1nseulhXu6L/r9Xp5dtzSb533vZ4mKyG4R86yjFw34 qlbe1Vl8tnwOcTrOQlSwTysus+k+SfCsE4iXKEa9Apemb0nJtonMW1QDWiV8YxZP lnx/ZJbGkowNlKS6hh0jpfyza7qG2Glj7uvleCT50d0KgH8sM4Cl3ZKZe/Z1Q+TX 7/NRDj5pJ9zJ4ZsPcdI4oFPDSaWfpW8UnSuXaIKpcJdZ9PQUVXr5IqHP1A1Yix9T CIy9jo9/3EBbIiVAFawtnDILYpdXphi2whzqrzgRQk+iPlpASA4bzbhr67QJT0Ro 8t+XJSiO2oVupeNPXHTSgjc1feSse5kgTQk9eIFsofMUqchL7TeDCRuCwMS82Hq/ NcirzaGvu4t7xCMUYPWQDf4e5vBtHjDDu/ru7x50EF05iD3t9YvI5jwBAJGXJ2MX DJg2yc2ZZ41Iq6iowq+GNviqltcGcvN9VX/LIsjFIQAQMkw2s4CaV6QJ8heJMly/ SZTgAyr0qNkUHj3fV4tw0s3yuFuq+Kktqxsx/Filo4NVxVATD97aTUzzr7mPkhO6 G8SboKtBwYw= =Nwel -----END PGP SIGNATURE----- --=-Uxi+pqI7sb4Nv3FxpLpm--