From mboxrd@z Thu Jan 1 00:00:00 1970 From: KAMEZAWA Hiroyuki Subject: Re: [PATCH 9/9] ext3: do not throttle metadata and journal IO Date: Thu, 23 Apr 2009 11:54:19 +0900 Message-ID: <20090423115419.c493266a.kamezawa.hiroyu__11913.267200771$1240455520$gmane$org@jp.fujitsu.com> References: <20090421163537.GI19186@mit.edu> <20090421172317.GM19637@balbir.in.ibm.com> <20090421174620.GD15541@mit.edu> <20090421181429.GO19637@balbir.in.ibm.com> <20090421191401.GF15541@mit.edu> <20090421204905.GA5573@linux> <20090422093349.1ee9ae82.kamezawa.hiroyu@jp.fujitsu.com> <20090422102153.9aec17b9.kamezawa.hiroyu@jp.fujitsu.com> <20090422102239.GA1935@linux> <20090423090535.ec419269.kamezawa.hiroyu@jp.fujitsu.com> <20090423012254.GZ15541@mit.edu> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20090423012254.GZ15541-3s7WtUTddSA@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: containers-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Errors-To: containers-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org To: Theodore Tso Cc: randy.dunlap-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org, dradford-cT2on/YLNlBWk0Htik3J/w@public.gmane.org, akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org, ngupta-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org, subrata-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org, fernando-gVGce1chcLdL9jVzuh4AOg@public.gmane.org, agk-9JcytcrH/bA+uJoB2kUjGw@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Henrik Lunde , dave-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org, roberto-5KDOxZqKugI@public.gmane.org, Carl-FOgKQjlUJ6BQetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, Jens Axboe , matt-cT2on/YLNlBWk0Htik3J/w@public.gmane.org, containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, Paul Menage , Balbir Singh , Gui-FOgKQjlUJ6BQetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, eric.rannaud-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org, Andrea Righi List-Id: containers.vger.kernel.org On Wed, 22 Apr 2009 21:22:54 -0400 Theodore Tso wrote: > On Thu, Apr 23, 2009 at 09:05:35AM +0900, KAMEZAWA Hiroyuki wrote: > > So, current status is. > > > > A. memcg should support dirty_ratio for its own memory reclaim. > > in plan. > > > > B. another cgroup can be implemnted to support cgroup_dirty_limit(). > > But relationship with "A" should be discussed. > > no plan yet. > > > > C. I/O cgroup and bufferred I/O tracking system. > > Now under patch review. > > > > And this I/O throttle is mainly for "C" discussion. > > How much testing has been done in terms of whether the I/O throttling > actually works? Not just, "the kernel doesn't crash", but that where > you have one process generating a large amount of I/O load, in various > different ways, and whether the right things happens? If so, how has > this been measured? I/O control people should prove it. And they do, I think. > > I'm really concerned that given some of the ways that I/O will "leak" > out --- the via pdflush, swap writeout, etc., that without the rest of > the pieces in place, I/O throttling by itself might not prove to be > very effective. Sure, if the workload is only doing direct I/O, life > is pretty easy and it shouldn't be hard to throttle the cgroup. > It's just a problem of "what we do and what we don't, now". Andrea, Vivek, could you clarify ? As other project, I/O controller will not be 100% at first implementation. > But in the case where there is bufferred I/O, without write > throttling, it's hard to see how well the I/O controller will work in > practice. In fact, I wouldn't be that surprised if it's possible to > trigger the OOM killer....... > yes, then, memcg should have dirty_ratio handler. And, we may have to implement dirty-ratio controller. So, please don't merge memcg discussion and I/O BW throttoling. It's related to each other but different problem. Thanks, -Kame