From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Howells Subject: Re: [RFC] sched: implement the exclusive wait queue as a LIFO queue Date: Wed, 28 Apr 2010 16:00:06 +0100 Message-ID: <14370.1272466806@redhat.com> References: <1272430986-20436-1-git-send-email-xiaosuo@gmail.com> <8526.1272447122@redhat.com> <6096.1272463619@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: dhowells@redhat.com, Ingo Molnar , Alexander Viro , Andrew Morton , "Eric W. Biederman" , Davide Libenzi , Roland Dreier , Stefan Richter , Peter Zijlstra , "David S. Miller" , Eric Dumazet , Christoph Lameter , Andreas Herrmann , Thomas Gleixner , Takashi Iwai , linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org To: Changli Gao Return-path: In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org Changli Gao wrote: > > How often do the two actually mix? =A0And if they do, is that reall= y an > > error? >=20 > The sock.sk_sleep is used by exclusive and non-exclusive wait queues. > exclusive and non-exclusive is identified by wait queues, not wait > queue heads. Maybe there is a historical reason. It is much like a > hack. But is it actually used in both modes at the same time? David