From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga18.intel.com (mga18.intel.com [134.134.136.126]) by dpdk.org (Postfix) with ESMTP id 66B1137B0; Thu, 17 May 2018 14:12:37 +0200 (CEST) X-Amp-Result: UNSCANNABLE X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by orsmga106.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 17 May 2018 05:12:36 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.49,410,1520924400"; d="scan'208";a="225015130" Received: from debian.sh.intel.com (HELO debian) ([10.67.104.203]) by orsmga005.jf.intel.com with ESMTP; 17 May 2018 05:12:35 -0700 Date: Thu, 17 May 2018 20:13:01 +0800 From: Tiwei Bie To: Maxime Coquelin Cc: dev@dpdk.org, mst@redhat.com, stable@dpdk.org Message-ID: <20180517121301.GA22907@debian> References: <20180517114447.28205-1-maxime.coquelin@redhat.com> <81a73714-9a7f-0b64-d508-2eb03422fe06@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <81a73714-9a7f-0b64-d508-2eb03422fe06@redhat.com> User-Agent: Mutt/1.9.5 (2018-04-13) Subject: Re: [dpdk-dev] [PATCH v4] vhost: improve dirty pages logging performance X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 17 May 2018 12:12:38 -0000 On Thu, May 17, 2018 at 02:01:52PM +0200, Maxime Coquelin wrote: > Hi Tiwei, > > On 05/17/2018 01:44 PM, Maxime Coquelin wrote: > > This patch caches all dirty pages logging until the used ring index > > is updated. > > > > The goal of this optimization is to fix a performance regression > > introduced when the vhost library started to use atomic operations > > to set bits in the shared dirty log map. While the fix was valid > > as previous implementation wasn't safe against concurrent accesses, > > contention was induced. > > > > With this patch, during migration, we have: > > 1. Less atomic operations as only a single atomic OR operation > > per 32 or 64 (depending on CPU) pages. > > 2. Less atomic operations as during a burst, the same page will > > be marked dirty only once. > > 3. Less write memory barriers. > > > > Fixes: 897f13a1f726 ("vhost: make page logging atomic") > > > > Cc:stable@dpdk.org > > > > Cc: Tiwei Bie > > Suggested-by: Michael S. Tsirkin > > Signed-off-by: Maxime Coquelin > > I missed to add your: > Reviewed-by: Tiwei Bie > > that you replied to v3, and since the changes in v4 were suggested by > you, I guess it still applies. Yeah. Thanks! :) Best regards, Tiwei Bie