From: Vivek Goyal Subject: Re: [PATCHSET] blk-throttle: implement proper hierarchy support Date: Thu, 2 May 2013 14:59:52 -0400 Message-ID: <20130502185952.GJ30020@redhat.com> References: <1367455189-6957-1-git-send-email-tj@kernel.org> <20130502173428.GA4771@redhat.com> <20130502180815.GG30020@redhat.com> <20130502184426.GO19814@mtj.dyndns.org> Mime-Version: 1.0 Return-path: Content-Disposition: inline In-Reply-To: <20130502184426.GO19814-9pTldWuhBndy/B6EtB590w@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Tejun Heo Cc: axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org, containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org On Thu, May 02, 2013 at 11:44:26AM -0700, Tejun Heo wrote: [..] > Also, if you're actually thinking about reimplementing blk-throttle, > please do consider the followings. > > * Currently, blk-throttle doesn't throttle the number of bios being > queued. Note that this breaks the basic back-pressure mechanism > where IO pressure is propagated back to the issuer by throttling the > issuing task. blk-throttle breaks that link and converts it to a > memory pressure. Agreed. Implementing something along the lines of per group nr_requests is needed. > > * It's almost inherently unscalable with highops devices. Given that > IO limiting doesn't require very fine granularity, I think doing > this per-cpu shouldn't be too hard. e.g. build a per-cpu token > distributing hierarchy with rebalancing across CPUs happening > periodically. Interesting. I thought for highops devices we will these multi queue patches from jens and there we can probably implement per queue tokens and rebalance tokens across queues periodically. > > In short, right now, the goal is getting the hierarchy support > acceptably working ASAP and yeap we wanna get the nested limits and at > least certain level of fairness, but let's please implement something > simple for now and strive for sophistification later because it's > holding back everyone else. I am fine with this. Having some hierarchical algorithm and not blocking full hierarchical support for cgroup is better than not having any hierachical support and wait for better implementation. Thanks Vivek