From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wei Wang Subject: Re: [PATCH v20 4/7] virtio-balloon: VIRTIO_BALLOON_F_SG Date: Wed, 03 Jan 2018 17:00:28 +0800 Message-ID: <5A4C9BAC.3040808__49431.9455967799$1514969803$gmane$org@intel.com> References: <1513685879-21823-5-git-send-email-wei.w.wang@intel.com> <20171224032121.GA5273@bombadil.infradead.org> <201712241345.DIG21823.SLFOOJtQFOMVFH@I-love.SAKURA.ne.jp> <5A3F5A4A.1070009@intel.com> <20180102132419.GB8222@bombadil.infradead.org> <201801031129.JFC18298.FJMHtOFLVSQOFO@I-love.SAKURA.ne.jp> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <201801031129.JFC18298.FJMHtOFLVSQOFO@I-love.SAKURA.ne.jp> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org To: Tetsuo Handa , willy@infradead.org Cc: aarcange@redhat.com, virtio-dev@lists.oasis-open.org, riel@redhat.com, quan.xu0@gmail.com, kvm@vger.kernel.org, mst@redhat.com, qemu-devel@nongnu.org, amit.shah@redhat.com, liliang.opensource@gmail.com, mawilcox@microsoft.com, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, linux-mm@kvack.org, yang.zhang.wz@gmail.com, nilal@redhat.com, cornelia.huck@de.ibm.com, pbonzini@redhat.com, akpm@linux-foundation.org, mhocko@kernel.org, mgorman@techsingularity.net List-Id: virtualization@lists.linuxfoundation.org On 01/03/2018 10:29 AM, Tetsuo Handa wrote: > Matthew Wilcox wrote: >> The radix tree convention is objectively awful, which is why I'm working >> to change it. Specifying the GFP flags at radix tree initialisation time >> rather than allocation time leads to all kinds of confusion. The preload >> API is a pretty awful workaround, and it will go away once the XArray >> is working correctly. That said, there's no alternative to it without >> making XBitmap depend on XArray, and I don't want to hold you up there. >> So there's an xb_preload for the moment. > I'm ready to propose cvbmp shown below as an alternative to xbitmap (but > specialized for virtio-balloon case). Wei, can you do some benchmarking > between xbitmap and cvbmp? > ---------------------------------------- > cvbmp: clustered values bitmap I don't think we need to replace xbitmap, at least at this stage. The new implementation doesn't look simpler at all, and virtio-balloon has worked well with xbitmap. I would suggest you to send out the new implementation for discussion after this series ends, and justify with better performance results if you could get. Best, Wei