From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: [RFC PATCH] Introduce RCU-enabled DQs (v2) Date: Tue, 27 Aug 2013 00:23:16 +0200 Message-ID: <521BD554.4010806@redhat.com> References: <1377371209-2017-1-git-send-email-ncmike@ncultra.org> <20130825191835.GA1073@Krystal> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org Sender: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org To: Mike Day Cc: rp@svcs.cs.pdx.edu, qemu-devel@nongnu.org, lttng-dev@lists.lttng.org, Mathieu Desnoyers , Anthony Liguori , Paul Mckenney List-Id: lttng-dev@lists.lttng.org Il 26/08/2013 23:48, Mike Day ha scritto: > > > Mathieu - Thanks for the review! And thanks for the code, I'm working > with it right now. I like the idea of using a flag to provide a form of > atomicity for the doubly-linked list elements. I'm also planning on > running some timing tests to see of the additional memory barriers and > atomic accesses make *any* difference whatsoever. We probably have already too many queue/list variations (a relic of the BSD queue.h headers). Linux does not need RCU-friendly reverse iteration at all, do we really need it? In other words, I think your v2 was really close to mergeable state... Paolo