From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ian Campbell Subject: Re: [PATCH Remus v5 2/2] libxc/restore: implement Remus checkpointed restore Date: Fri, 15 May 2015 10:09:58 +0100 Message-ID: <1431680998.8943.22.camel@citrix.com> References: <1431597974-15624-1-git-send-email-yanghy@cn.fujitsu.com> <1431597974-15624-3-git-send-email-yanghy@cn.fujitsu.com> <1431608716.13579.78.camel@citrix.com> <55554CAD.6060206@cn.fujitsu.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <55554CAD.6060206@cn.fujitsu.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Yang Hongyang Cc: wei.liu2@citrix.com, eddie.dong@intel.com, wency@cn.fujitsu.com, andrew.cooper3@citrix.com, yunhong.jiang@intel.com, ian.jackson@eu.citrix.com, xen-devel@lists.xen.org, guijianfeng@cn.fujitsu.com, rshriram@cs.ubc.ca List-Id: xen-devel@lists.xenproject.org On Fri, 2015-05-15 at 09:32 +0800, Yang Hongyang wrote: > > On 05/14/2015 09:05 PM, Ian Campbell wrote: > > On Thu, 2015-05-14 at 18:06 +0800, Yang Hongyang wrote: > >> With Remus, the restore flow should be: > >> the first full migration stream -> { periodically restore stream } > >> > >> Signed-off-by: Yang Hongyang > >> Signed-off-by: Andrew Cooper > >> CC: Ian Campbell > >> CC: Ian Jackson > >> CC: Wei Liu > >> --- > >> tools/libxc/xc_sr_common.h | 14 ++++++ > >> tools/libxc/xc_sr_restore.c | 113 ++++++++++++++++++++++++++++++++++++++++---- > >> 2 files changed, 117 insertions(+), 10 deletions(-) > >> > >> diff --git a/tools/libxc/xc_sr_common.h b/tools/libxc/xc_sr_common.h > >> index f8121e7..3bf27f1 100644 > >> --- a/tools/libxc/xc_sr_common.h > >> +++ b/tools/libxc/xc_sr_common.h > >> @@ -208,6 +208,20 @@ struct xc_sr_context > >> /* Plain VM, or checkpoints over time. */ > >> bool checkpointed; > >> > >> + /* Currently buffering records between a checkpoint */ > >> + bool buffer_all_records; > >> + > >> +/* > >> + * With Remus, we buffer the records sent by the primary at checkpoint, > >> + * in case the primary will fail, we can recover from the last > >> + * checkpoint state. > >> + * This should be enough because primary only send dirty pages at > >> + * checkpoint. > > > > I'm not sure how it then follows that 1024 buffers is guaranteed to be > > enough, unless there is something on the sending side arranging it to be > > so? > > There are only few records at every checkpoint in my test, mostly under 10, > probably because I don't do much operations in the Guest. I thought This limit > can be adjusted later by further testing. For some reason I thought these buffers included the page data, is that not true? I was expecting the bulk of the records to be dirty page data. > Since you and Andy both have doubts on this, I have to reconsider on this, > perhaps there should be no limit. Even if the 1024 limit works for > most of the cases, there might be cases that exceed the limit. So I will > add another member 'allocated_rec_num' in the context, when the > 'buffered_rec_num' exceed the 'allocated_rec_num', I will reallocate the buffer. > The initial buffer size will be 1024 records which will work for most cases. That seems easy enough to be worth doing even if I was wrong about paged data.