On Tue, Jan 17, 2017 at 09:38:39AM -0800, David Carrillo-Cisneros wrote: > This is a low-hanging fruit optimization. It replaces the iteration over > the "pmus" list in cgroup switch by an iteration over a new list that > contains only cpuctxs with at least one cgroup event. > > This is necessary because the number of pmus have increased over the years > e.g modern x86 server systems have well above 50 pmus. > The iteration over the full pmu list is unneccessary and can be costly in > heavy cache contention scenarios.
While I haven't done any measurement of the overhead, this looks like a nice rework/cleanup. Since this is only changing the management of cpu contexts, this shouldn't adversely affect systems with heterogeneous CPUs. I've also given this a spin on such a system, to no ill effect. I have one (very minor) comment below, but either way: Acked-by: Mark Rutland <[email protected]> Tested-by: Mark Rutland <[email protected]> > @@ -889,6 +876,7 @@ list_update_cgroup_event(struct perf_event *event, > struct perf_event_context *ctx, bool add) > { > struct perf_cpu_context *cpuctx; > + struct list_head *lentry; It might be worth calling this cpuctx_entry, so that it's clear which list element it refers to. I can imagine we'll add more list manipulation in this path in future. Thanks, Mark.
