From 1a4a8153e0df1705397aa3ff561dd8fdc2e6fc23 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 20 May 2022 10:21:00 -0700 Subject: rcu-tasks: Stop RCU Tasks Trace from scanning full tasks list This commit takes off the training wheels and relies only on scanning currently running tasks and tasks that have blocked or been preempted within their current RCU Tasks Trace read-side critical section. Before this commit, the time complexity of an RCU Tasks Trace grace period is O(T), where T is the number of tasks. After this commit, this time complexity is O(C+B), where C is the number of CPUs and B is the number of tasks that have blocked (or been preempted) at least once during their current RCU Tasks Trace read-side critical sections. Of course, if all tasks have blocked (or been preempted) at least once during their current RCU Tasks Trace read-side critical sections, this is still O(T), but current expectations are that RCU Tasks Trace read-side critical section will be short and that there will normally not be large numbers of tasks blocked within such a critical section. Dave Marchevsky kindly measured the effects of this commit on the RCU Tasks Trace grace-period latency and the rcu_tasks_trace_kthread task's CPU consumption per RCU Tasks Trace grace period over the course of a fixed test, all in milliseconds: Before After GP latency 22.3 ms stddev > 0.1 17.0 ms stddev < 0.1 GP CPU 2.3 ms stddev 0.3 1.1 ms stddev 0.2 This was on a system with 15,000 tasks, so it is reasonable to expect much larger savings on the systems on which this issue was first noted, given that they sport well in excess of 100,000 tasks. CPU consumption was measured using profiling techniques. Signed-off-by: Paul E. McKenney Cc: Neeraj Upadhyay Cc: Eric Dumazet Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Martin KaFai Lau Cc: KP Singh Tested-by: Dave Marchevsky --- kernel/rcu/tasks.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 272c905995e5..fe0552086ccf 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -670,10 +670,12 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) * and make a list of them in holdouts. */ set_tasks_gp_state(rtp, RTGS_SCAN_TASKLIST); - rcu_read_lock(); - for_each_process_thread(g, t) - rtp->pertask_func(t, &holdouts); - rcu_read_unlock(); + if (rtp->pertask_func) { + rcu_read_lock(); + for_each_process_thread(g, t) + rtp->pertask_func(t, &holdouts); + rcu_read_unlock(); + } set_tasks_gp_state(rtp, RTGS_POST_SCAN_TASKLIST); rtp->postscan_func(&holdouts); @@ -1746,7 +1748,6 @@ static int __init rcu_spawn_tasks_trace_kthread(void) rcu_tasks_trace.init_fract = 1; } rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step; - rcu_tasks_trace.pertask_func = rcu_tasks_trace_pertask; rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan; rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace; rcu_tasks_trace.postgp_func = rcu_tasks_trace_postgp; -- cgit v1.2.3-59-g8ed1b