Return-path: Received: from wa-out-1112.google.com ([209.85.146.177]:55876 "EHLO wa-out-1112.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755211AbYF3L31 (ORCPT ); Mon, 30 Jun 2008 07:29:27 -0400 Received: by wa-out-1112.google.com with SMTP id j37so1159215waf.23 for ; Mon, 30 Jun 2008 04:29:26 -0700 (PDT) Message-ID: <1ba2fa240806300429l679f1568k584143b448455594@mail.gmail.com> (sfid-20080630_132930_015153_3D838E92) Date: Mon, 30 Jun 2008 14:29:26 +0300 From: "Tomas Winkler" To: "Johannes Berg" Subject: Re: compat-wireless high packet loss. Cc: "Guy Cohen" , "David Miller" , "John W. Linville" , "Luis R. Rodriguez" , "Linux Wireless" , "Emmanuel Grumbach" , "Patrick McHardy" In-Reply-To: <1214824149.5507.36.camel@johannes.berg> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 References: <1ba2fa240806261603g30c3e757y9166c2f9e05f7666@mail.gmail.com> <247d6d340806282323v3192ead8v149359e482375991@mail.gmail.com> <1214824149.5507.36.camel@johannes.berg> Sender: linux-wireless-owner@vger.kernel.org List-ID: On Mon, Jun 30, 2008 at 2:09 PM, Johannes Berg wrote: > On Sun, 2008-06-29 at 09:23 +0300, Guy Cohen wrote: >> More info on the issue.. The problem is with TX of unrestrained UDP >> stream, when the traffic generated at the application layer is larger >> than the link can pass. With kernel 2.6.26-* the traffic is restrained >> when the TX FIFOs gets full while in 2.6.25.* frames are dropped at >> some layer. It seems that the drop happens after the IP fragmentation >> step at the stack. > > does compat use multiqueue now? if not, look in the mac80211 fake mq > code. 2.6.25 has a real mq Thanks Tomas