From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tom Evans Subject: Re: Fwd: Querying current tx_queue usage of a SocketCAN interface Date: Fri, 03 Apr 2015 12:35:56 +1100 Message-ID: <551DEE7C.6040202@optusnet.com.au> References: <55187FF1.7020701@optusnet.com.au> <5519E5A9.7080104@optusnet.com.au> <551A0FF3.4070400@optusnet.com.au> <551C7D79.50906@optusnet.com.au> <551CE5C9.6020600@pengutronix.de> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mail110.syd.optusnet.com.au ([211.29.132.97]:57694 "EHLO mail110.syd.optusnet.com.au" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753007AbbDCBgE (ORCPT ); Thu, 2 Apr 2015 21:36:04 -0400 In-Reply-To: Sender: linux-can-owner@vger.kernel.org List-ID: To: Paarvai Naai , Marc Kleine-Budde Cc: Dan Egnor , linux-can@vger.kernel.org On 3/04/2015 5:28 AM, Paarvai Naai wrote: > Ironically, that brings us full-circle back to my original reason for > this thread, but we went off on a tangent in the meantime (partly my > fault!). Querying the tx_queue usage has multiple benefits. Is there > some way we can address that easier issue first? Didn't I already answer that question a few days ago? I found something in /proc or /sys (details in my mailbox at work) That looked like the interface to qdisc to allow inspection of the queue depths. Thanks to google that's: cat /sys/class/net/can0/queues/tx-0/byte_queue_limits/inflight drivers/net/core/net-sysfs.c /lib/dynamic_queue_limits.c Did you investigate that at all, or are you waiting for someone else to do this for you? Can anyone else comment on that apparent interface? Is "dql" part of "qdisc" or something else? How is it enabled? --- Before using google I just spent 30 minutes trying to quote my previous reply from: http://dir.gmane.org/gmane.linux.can Can anyone else get to the above URL today? It crashes Firefox every time I go there, locks up IE solidly, and I gave up on lynx after it started running GZIP and pulling down about 10 MEGS of data without displaying anything. It is now spitting "fopen()", "feof()" and "fgets()" PHP errors at me, so it looks like gmane is broken for Easter. Tom