Messages in this thread | | | Date | Wed, 27 Feb 2008 17:09:45 +0900 | From | KAMEZAWA Hiroyuki <> | Subject | Re: [RFC][PATCH] page reclaim throttle take2 |
| |
On Tue, 26 Feb 2008 23:56:39 -0800 (PST) David Rientjes <rientjes@google.com> wrote:
> On Wed, 27 Feb 2008, KAMEZAWA Hiroyuki wrote: > > > Hmm, but kswapd, which is main worker of page reclaiming, is per-node. > > And reclaim is done based on zone. > > per-zone/per-node throttling seems to make sense. > > > > That's another argument for not introducing the sysctl; the number of > nodes and zones are a static property of the machine that cannot change > without a reboot (numa=fake, mem=, introducing movable zones, etc). We > don't have node hotplug that can suddenly introduce additional zones from > which to reclaim.
Hmm, do you know there is already zone-hotplug ? ;) (Means, onlining new memory in new zone increase the # of zones. Now, in our system, possible-node turns to be online nodes.)
> My point was that there doesn't appear to be any use case for tuning this > via a sysctl that isn't simply attempting to workaround some other reclaim > problem when the VM is stressed. If that's agreed upon, then deciding > between a config option that is either per-cpu or per-node should be based > on the benchmarks that you've run. At this time, it appears that per-node > is the more advantageous. > I agree that what is the best is based on benchmark. I like per-node, now. I believe there will be some change when RvR's spilit-LRU patches are applied.
> > I know his environment has 4cpus per node but throttle to 3 was the best > > number in his measurement. Then it seems num-per-cpu is excessive. > > (At least, ratio(%) is better.) > > That seems to indicate that the NUMA topology is more important than lock > contention for the reclaim throttle. > I hear that there is also I/O bottle-neck for page reclaiming, at last.
Thanks, -Kame
| |