Wei Wang wrote: > 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. I'm VMware Workstation Player user, and I don't have environment for doing performance test using virtio-balloon. Thus, I need to ask you. Also, please look at http://lkml.kernel.org/r/1514904621-39186-1-git-send-email-penguin-kernel@xxxxxxxxxxxxxxxxxxx .
