From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:43148) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UTv5g-0001Uk-EM for qemu-devel@nongnu.org; Sun, 21 Apr 2013 10:18:06 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1UTv5e-00008N-4U for qemu-devel@nongnu.org; Sun, 21 Apr 2013 10:18:04 -0400 Received: from mx1.redhat.com ([209.132.183.28]:20997) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UTv5d-00008F-RS for qemu-devel@nongnu.org; Sun, 21 Apr 2013 10:18:02 -0400 Date: Sun, 21 Apr 2013 17:17:46 +0300 From: "Michael S. Tsirkin" Message-ID: <20130421141746.GB13512@redhat.com> References: <1366240040-10730-1-git-send-email-mrhines@linux.vnet.ibm.com> <1366240040-10730-8-git-send-email-mrhines@linux.vnet.ibm.com> <51706E9C.9@redhat.com> <20130420170240.GA16115@redhat.com> <5173E759.5080906@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <5173E759.5080906@redhat.com> Subject: Re: [Qemu-devel] [PULL v4 07/11] rdma: introduce capability for chunk registration List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Paolo Bonzini Cc: aliguori@us.ibm.com, quintela@redhat.com, qemu-devel@nongnu.org, mrhines@linux.vnet.ibm.com, owasserm@redhat.com, abali@us.ibm.com, mrhines@us.ibm.com, gokul@us.ibm.com On Sun, Apr 21, 2013 at 03:19:21PM +0200, Paolo Bonzini wrote: > Il 20/04/2013 19:02, Michael S. Tsirkin ha scritto: > >> > I guess the opposite sense could be named 'x-rdma-pin-all'; default > >> > false means to do chunk registration and release, > > chunk release only happens after migration is complete unfortunately. > > This means that eventually all initialized memory is pinned, regardless > > of the setting (this is fixable but there's no plan to fix this, at this > > point). So pin-all might be misleading to some. > > > > I agree 'chunk' is unnecessarily low level though. > > The only difference ATM is pinning of uninitialized memory so I think a > > better name would be 'x-rdma-pin-uninitialized' or some such. > > > > x-rdma-pin-all is a better choice. x-rdma-pin-uninitialized is also too > low level. > > Since this series is likely to miss 1.5 at this point, we could > implement the unregistration part of the protocol in the destination. > This way, any heuristic we add to the source will not break backwards > compatibility. > > Paolo To test, you'll have to implement it in the source too. That's probably a good idea anyway, though doing this efficiently might need more thought, and some of the tricks I described earlier (pipelining, registration cache) might be needed. Though I'm curious what the performance impact would be even without these tricks. -- MST