From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mike Snitzer Subject: Re: dm-log-userspace: Allow mark requests to piggyback on flush requests Date: Mon, 13 Jan 2014 21:59:37 -0500 Message-ID: <20140114025937.GA5816@redhat.com> References: <1389666600.12232.2.camel@f16> Reply-To: device-mapper development Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <1389666600.12232.2.camel@f16> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: Jonathan Brassow Cc: dm-devel@redhat.com, dmzhang@suse.de List-Id: dm-devel.ids On Mon, Jan 13 2014 at 9:30pm -0500, Jonathan Brassow wrote: > dm-log-userspace: Allow mark requests to piggyback on flush requests > > In the cluster evironment, cluster write has poor performance. > Because userspace_flush has to contact userspace program(cmirrord) > in clear/mark/flush request. But both mark and flush requests > require cmirrord to circle message to all the cluster nodes in each > flush call. This behave is realy slow. So the idea is merging > mark and flush request together to reduce the kernel-userspace-kernel > time. Allow a new directive, "integrated_flush" that can be used to > instruct the kernel log code to combine flush and mark requests when > directed by userspace. Additionlly, flush requests are performed > lazily when only clear requests exist. > > Signed-off-by: dongmao zhang > Signed-off-by: Jonathan Brassow Hey Jon, Thanks for following through with this. Should it be attributed to dongmao as the author?