On Tue, Aug 6, 2019 at 11:29 PM Daniel Jordan <daniel.m.jordan@xxxxxxxxxx> wrote: > > On Tue, Aug 06, 2019 at 04:23:29PM +0800, Yafang Shao wrote: > > On Tue, Aug 6, 2019 at 3:35 PM Michal Hocko <mhocko@xxxxxxxxxx> wrote: > > > Considering that this is a long term behavior of a rarely used node > > > reclaim I would rather not touch it unless some _real_ workload suffers > > > from this behavior. Or is there any reason to fix this even though there > > > is no evidence of real workloads suffering from the current behavior? > > > -- > > > > When we do performance tuning on some workloads(especially if this > > workload is NUMA sensitive), sometimes we may enable it on our test > > environment and then do some benchmark to dicide whether or not > > applying it on the production envrioment. Although the result is not > > good enough as expected, it is really a performance tuning knob. > > So am I understanding correctly that you sometimes enable node reclaim in > production workloads when you find the numbers justify it? If so, which ones? We used to enable it on production environment, but it caused some latency spike(because of memory pressure), so we have to disable it now. BTW, do you plan to enable it for your workload ? Thanks Yafang
