On Sat, Oct 13, 2018 at 08:31:37AM +0000, Song Liu wrote: > The only suggestion I have right now is on which struct owns which > data: > > 1. perf_cpu_context owns two perf_event_context: ctx and *task_ctx. > This is the same as right now.
> 2. perf_event_context owns multiple perf_event_pmu_context: > One perf_event_pmu_context for software groups; > One perf_event_pmu_context for each hardware PMU. It does now already, right? Through the pmu_ctx_list we can, given an perf_event_context, find all associated perf_event_pmu_context's. > 3. perf_event_pmu_context owns RB tree of events. Since we don't > need rotation across multiple hardware PMUs, the rotation is > within same perf_event_pmu_context. By keeping the RB trees in perf_event_context, we get bigger trees, which is more efficient (log(n+m) < log(n) + log(m)) Also, specifically, it means we only need a single merge sort / iteration to schedule in a full context, instead of (again) doing 'n' of them. Also, given a context and a pmu, it is cheaper for finding the relevant events; this is needed for big.little for instance. Something the proposed patch doesn't fully flesh out. > 4. perf_cpu_context owns multiple perf_cpu_pmu_context: > One perf_cpu_pmu_context for each hardware PMU. What would we need that relation for? > perf_cpu_pmu_context is tot needed for software only groups(?). Yes, that is a very good question; it mostly centers around what we want to do with perf_event_attr::exclusive for software events -- which is currently dodgy at best. Also, allocating the structure and keeping it around is probably less code than explicitly not doing it. > 5. perf_cpu_pmu_context has two pointers of perf_event_pmu_context. Instead of embedding the thing? Yeah, not sure. Either way around we'd not want to free the CPU perf_event_pmu_context that is associated with the perf_cpu_pmu_context, and embedding it saves a pointer chase. Not sure it actually makes a lot of difference either way around.
