psi: Add PSI_CPU_FULL state

The FULL state doesn't exist for the CPU resource at the system level,
but exist at the cgroup level, means all non-idle tasks in a cgroup are
delayed on the CPU resource which used by others outside of the cgroup
or throttled by the cgroup cpu.max configuration.

Co-developed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20210303034659.91735-2-zhouchengming@bytedance.com

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index b95f3211566a22c88c53154cb8f7085d026ba98a..0a23300d49af74be5887d2c57352e362fdcf18e1 100644 (file)
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -50,9 +50,10 @@ enum psi_states {
        PSI_MEM_SOME,
        PSI_MEM_FULL,
        PSI_CPU_SOME,
+       PSI_CPU_FULL,
        /* Only per-CPU, to weigh the CPU in the global average: */
        PSI_NONIDLE,
-       NR_PSI_STATES = 6,
+       NR_PSI_STATES = 7,
 };
 
 enum psi_aggregators {

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 967732c0766c567d2fc1523c900c976d18ac1acf..2293c45d289dca898bdcdc759ef71c21d4fa9427 100644 (file)
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -34,7 +34,10 @@
  * delayed on that resource such that nobody is advancing and the CPU
  * goes idle. This leaves both workload and CPU unproductive.
  *
- * (Naturally, the FULL state doesn't exist for the CPU resource.)
+ * Naturally, the FULL state doesn't exist for the CPU resource at the
+ * system level, but exist at the cgroup level, means all non-idle tasks
+ * in a cgroup are delayed on the CPU resource which used by others outside
+ * of the cgroup or throttled by the cgroup cpu.max configuration.
  *
  *     SOME = nr_delayed_tasks != 0
  *     FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0
@@ -225,6 +228,8 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
                return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
        case PSI_CPU_SOME:
                return tasks[NR_RUNNING] > tasks[NR_ONCPU];
+       case PSI_CPU_FULL:
+               return tasks[NR_RUNNING] && !tasks[NR_ONCPU];
        case PSI_NONIDLE:
                return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
                        tasks[NR_RUNNING];
@@ -678,8 +683,11 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
                }
        }
 
-       if (groupc->state_mask & (1 << PSI_CPU_SOME))
+       if (groupc->state_mask & (1 << PSI_CPU_SOME)) {
                groupc->times[PSI_CPU_SOME] += delta;
+               if (groupc->state_mask & (1 << PSI_CPU_FULL))
+                       groupc->times[PSI_CPU_FULL] += delta;
+       }
 
        if (groupc->state_mask & (1 << PSI_NONIDLE))
                groupc->times[PSI_NONIDLE] += delta;
@@ -1018,7 +1026,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
                group->avg_next_update = update_averages(group, now);
        mutex_unlock(&group->avgs_lock);
 
-       for (full = 0; full < 2 - (res == PSI_CPU); full++) {
+       for (full = 0; full < 2; full++) {
                unsigned long avg[3];
                u64 total;
                int w;