On Fri 11-03-16 12:13:04, Vladimir Davydov wrote: > On Fri, Mar 11, 2016 at 09:42:39AM +0100, Michal Hocko wrote: > > On Fri 11-03-16 11:34:40, Vladimir Davydov wrote: > > > On Thu, Mar 10, 2016 at 03:50:13PM -0500, Johannes Weiner wrote: > > > > When setting memory.high below usage, nothing happens until the next > > > > charge comes along, and then it will only reclaim its own charge and > > > > not the now potentially huge excess of the new memory.high. This can > > > > cause groups to stay in excess of their memory.high indefinitely. > > > > > > > > To fix that, when shrinking memory.high, kick off a reclaim cycle that > > > > goes after the delta. > > > > > > I agree that we should reclaim the high excess, but I don't think it's a > > > good idea to do it synchronously. Currently, memory.low and memory.high > > > knobs can be easily used by a single-threaded load manager implemented > > > in userspace, because it doesn't need to care about potential stalls > > > caused by writes to these files. After this change it might happen that > > > a write to memory.high would take long, seconds perhaps, so in order to > > > react quickly to changes in other cgroups, a load manager would have to > > > spawn a thread per each write to memory.high, which would complicate its > > > implementation significantly. > > > > Is the complication on the managing part really an issue though. Such a > > manager would have to spawn a process/thread to change the .max already. > > IMO memory.max is not something that has to be changed often. In most > cases it will be set on container start and stay put throughout > container lifetime. I can also imagine a case when memory.max will be > changed for all containers when a container starts or stops, so as to > guarantee that if <= N containers of M go mad, the system will survive. > In any case, memory.max is reconfigured rarely, it rather belongs to the > static configuration. I see > OTOH memory.low and memory.high are perfect to be changed dynamically, > basing on containers' memory demand/pressure. A load manager might want > to reconfigure these knobs say every 5 seconds. Spawning a thread per > each container that often would look unnecessarily overcomplicated IMO. The question however is whether we want to hide a potentially costly operation and have it unaccounted and hidden in the kworker context. I mean fork() + write() doesn't sound terribly complicated to me to have a rather subtle behavior in the kernel. -- Michal Hocko SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>