On Mon, 7 Nov 2016 17:55:47 +0100 (CET) Thomas Gleixner <t...@linutronix.de> wrote:
> On Sat, 5 Nov 2016, Chris Metcalf wrote: > > == Remote statistics == > > > > We discussed the possibility of remote statistics gathering, i.e. load > > average etc. The idea would be that we could have housekeeping > > core(s) periodically iterate over the nohz cores to load their rq > > remotely and do update_current etc. Presumably it should be possible > > for a single housekeeping core to handle doing this for all the > > nohz_full cores, as we only need to do it quite infrequently. > > > > Thomas suggested that this might be the last remaining thing that > > needed to be done to allow disabling the current behavior of falling > > back to a 1 Hz clock in nohz_full. > > > > I believe Thomas said he had a patch to do this already. > > No, Riek was working on that. Rik series made it possible to have remote tick sampling. That is, calling account_process_tick(cpu) from a housekeeping CPU, so that tick accounting is done for a remote "cpu". The series was intended to improve overhead on nohz_full CPUs. However, to get rid of the 1Hz tick, we need to do the same thing for scheduler_tick(). I'm not sure if this has been attempted yet, and if it's at all possible. > > == Remote LRU cache drain == > > > > One of the issues with task isolation currently is that the LRU cache > > drain must be done prior to entering userspace, but it requires > > interrupts enabled and thus can't be done atomically. My previous > > patch series have handled this by checking with interrupts disabled, > > but then looping around with interrupts enabled to try to drain the > > LRU pagevecs. Experimentally this works, but it's not provable that > > it terminates, which is worrisome. Andy suggested adding a percpu > > flag to disable creation of deferred work like LRU cache pages. > > > > Thomas suggested using an RT "local lock" to guard the LRU cache > > flush; he is planning on bringing the concept to mainline in any case. > > However, after some discussion we converged on simply using a spinlock > > to guard the appropriate resources. As a result, the > > lru_add_drain_all() code that currently queues work on each remote cpu > > to drain it, can instead simply acquire the lock and drain it remotely. > > This means that a task isolation task no longer needs to worry about > > being interrupted by SMP function call IPIs, so we don't have to deal > > with this in the task isolation framework any more. > > > > I don't recall anyone else volunteering to tackle this, so I will plan > > to look at it. The patch to do that should be orthogonal to the > > revised task isolation patch series. > > I offered to clean up the patch from RT. I'll do that in the next days. Yes, the RT kernel got a patch that fixes this. I wonder if the same idea could work for vm_stat (that is, gathering those stats from housekeeping CPUs vs. having to queue deferrable work to do it).
