Return-path: Received: from mail.atheros.com ([12.36.123.2]:39660 "EHLO mail.atheros.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752106AbYIRWBR (ORCPT ); Thu, 18 Sep 2008 18:01:17 -0400 Date: Thu, 18 Sep 2008 15:01:02 -0700 From: "Luis R. Rodriguez" To: Steven Noonan CC: Luis Rodriguez , Ingo Molnar , "ath9k-devel@lists.ath9k.org" , linux-wireless , LKML Subject: Re: [ath9k-devel] ath9k: massive unexplained latency in 2.6.27 (rc5, rc6, probably others) Message-ID: <20080918220102.GE7408@tesla> (sfid-20080919_000121_634216_693751B0) References: <43e72e890809181134ybbec8fdxcb2a466aa17fe390@mail.gmail.com> <43e72e890809181142n7738cd99g522e6688e68d11ce@mail.gmail.com> <43e72e890809181344q416b5944w3332ee5a33db048c@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" In-Reply-To: Sender: linux-wireless-owner@vger.kernel.org List-ID: On Thu, Sep 18, 2008 at 02:49:45PM -0700, Steven Noonan wrote: > > No, it's in hex. 0x17 = 23, 0x11 = 17. IRQ 17 is the one that pooped > in my case, which is my wireless chipset. Ah - boo. > If I do, I'll need to know what precisely to do about it. What debug > info should I collect before rebooting? Sure, OK so in ath9k's core.h we have a macro used to indicate what type of debugging stuff gets print out. By default we only leave enabled the fatal stuff. #define DBG_DEFAULT (ATH_DBG_FATAL ) You want to add to this ATH_DBG_INTERRUPT as follows: #define DBG_DEFAULT (ATH_DBG_FATAL | ATH_DBG_INTERRUPT) Then since the issue seems to come up when you rmmod, simply try to download do some large RXing or TXing or both and then rmmod. Capture the output and send along. > > Patches speak more than words, but yeah sorry, we should have > > addressed this there. I've personally have just been busy with > > tackling aggregation. > > > > Which is far more important, I agree. It's annoying to get speeds > <802.11b on my pre-802.11n capable chipset and network. ;) Yeah exactly, I hope the work we do will get in for 27. We'll see. Luis