From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <toke@toke.dk>
Received: from mail.toke.dk (mail.toke.dk [52.28.52.200])
 (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits))
 (No client certificate requested)
 by lists.bufferbloat.net (Postfix) with ESMTPS id 1E9083B29E
 for <cake@lists.bufferbloat.net>; Fri,  1 Jun 2018 13:46:42 -0400 (EDT)
From: Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=toke.dk; s=20161023;
 t=1527875201; bh=rhyJHO3GIgTvbHgCQQUE5B8yiyarDSHwlfLXwIlBjeM=;
 h=From:To:Subject:Date:From;
 b=LTb7tdIHFaru6wekfywlxPJ+a3LOMtB1LMxqmIP32rqsKDNGovsSl/KhMvpVGXycN
 NIOVvIuvFCWriDwLIm9XuK9ZIVlvZ+OB4qeejtB6m9pBIe1WJeasRLTRjm5uGHWdrH
 DZs9z8oSNsCaryQIVllRfdyK340D3W6D9DOAk1oG2+pCqCQfaeaVg35SCGhZFqzlw1
 3TKpQFJpNoUGcsGqTSjTvOOiMdvbjwnMcDbqqZ47KqSkCYisfKtqVAJQ4UDvy1RoAe
 +YSFmVp8D3FXt/D3Xl6GM0q1QYc6GiCm2KFGLPed4jn+NjDWxBecHqt2QcGGv2F/QL
 aYRqZhIWFWuog==
To: cake@lists.bufferbloat.net
Date: Fri, 01 Jun 2018 19:46:40 +0200
X-Clacks-Overhead: GNU Terry Pratchett
Message-ID: <87muwe9z7j.fsf@toke.dk>
MIME-Version: 1.0
Content-Type: text/plain
Subject: [Cake] Lockup at high speeds
X-BeenThere: cake@lists.bufferbloat.net
X-Mailman-Version: 2.1.20
Precedence: list
List-Id: Cake - FQ_codel the next generation <cake.lists.bufferbloat.net>
List-Unsubscribe: <https://lists.bufferbloat.net/options/cake>,
 <mailto:cake-request@lists.bufferbloat.net?subject=unsubscribe>
List-Archive: <https://lists.bufferbloat.net/pipermail/cake>
List-Post: <mailto:cake@lists.bufferbloat.net>
List-Help: <mailto:cake-request@lists.bufferbloat.net?subject=help>
List-Subscribe: <https://lists.bufferbloat.net/listinfo/cake>,
 <mailto:cake-request@lists.bufferbloat.net?subject=subscribe>
X-List-Received-Date: Fri, 01 Jun 2018 17:46:42 -0000

As you may have seen, I hit a lockup bug when testing Cake at high
speeds. I am not quite sure what is happening, but we seem to be looping
forever either in cake_dequeue() or cake_enqueue(), causing deadlocks.

Unfortunately, I have no more time to debug this for now. As far as I
can tell, it only seems to be happening as the shaped rate approaches or
exceeds the link speed, or when running in unlimited mode. So for all I
know it might be possible to trigger it at lower speeds as well...

Anyone with any bright ideas?

-Toke

P.S. While testing this, I did manage to get some high speed results
before everything blew up on me:

Summary of tcp_4up test run 'Cake 40gbps' (at 2018-06-01 17:36:19.216149):

                           avg       median          # data pts
 Ping (ms) ICMP :         0.36         0.12 ms              197
 TCP upload avg :      9563.03      9563.95 Mbits/s         151
 TCP upload sum :     38252.11     38255.80 Mbits/s         151
 TCP upload::1  :      9686.85      9674.40 Mbits/s         150
 TCP upload::2  :      9444.94      9460.09 Mbits/s         150
 TCP upload::3  :      9438.95      9461.36 Mbits/s         150
 TCP upload::4  :      9681.37      9675.69 Mbits/s         150