From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gate.crashing.org (gate.crashing.org [63.228.1.57]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3vDS5y5kdhzDqHH for ; Thu, 2 Feb 2017 15:42:30 +1100 (AEDT) Message-ID: <1486010533.4850.26.camel@kernel.crashing.org> Subject: Re: [RFC] implement QUEUED spinlocks on powerpc From: Benjamin Herrenschmidt To: Eric Dumazet , Michael Ellerman Cc: Eric Dumazet , Paul Mackerras , linuxppc-dev@lists.ozlabs.org, Kevin Hao , Torsten Duwe , Pan Xinhui Date: Thu, 02 Feb 2017 15:42:13 +1100 In-Reply-To: References: <1485968734.6360.154.camel@edumazet-glaptop3.roam.corp.google.com> <1485981445.4850.8.camel@kernel.crashing.org> <87y3xpb5li.fsf@concordia.ellerman.id.au> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Wed, 2017-02-01 at 20:40 -0800, Eric Dumazet wrote: > A typical benchmark would be to use 200 concurrent netperf -t TCP_RR, > through a single qdisc (protected by a spinlock) > > Non ticket/queued spinlocks behave quite bad in this scenario. > > I can try this next week if you want. That would be great ! Cheers, Ben.