Re: [PATCH v2 07/10] sched/psi: remove NR_ONCPU task accounting

From: Chengming Zhou
Date: Tue Aug 16 2022 - 07:26:52 EST


On 2022/8/8 19:03, Chengming Zhou wrote:
> From: Johannes Weiner <hannes@xxxxxxxxxxx>
>
> We put all fields updated by the scheduler in the first cacheline of
> struct psi_group_cpu for performance.
>
> Since we want add another PSI_IRQ_FULL to track IRQ/SOFTIRQ pressure,
> we need to reclaim space first. This patch remove NR_ONCPU task accounting
> in struct psi_group_cpu, use one bit in state_mask to track instead.
>
> Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
> Reviewed-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
> Tested-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
> ---
> include/linux/psi_types.h | 16 +++++++---------
> kernel/sched/psi.c | 36 ++++++++++++++++++++++++++++--------
> 2 files changed, 35 insertions(+), 17 deletions(-)
>
> diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
> index c7fe7c089718..54cb74946db4 100644
> --- a/include/linux/psi_types.h
> +++ b/include/linux/psi_types.h
> @@ -15,13 +15,6 @@ enum psi_task_count {
> NR_IOWAIT,
> NR_MEMSTALL,
> NR_RUNNING,
> - /*
> - * This can't have values other than 0 or 1 and could be
> - * implemented as a bit flag. But for now we still have room
> - * in the first cacheline of psi_group_cpu, and this way we
> - * don't have to special case any state tracking for it.
> - */
> - NR_ONCPU,
> /*
> * For IO and CPU stalls the presence of running/oncpu tasks
> * in the domain means a partial rather than a full stall.
> @@ -32,16 +25,18 @@ enum psi_task_count {
> * threads and memstall ones.
> */
> NR_MEMSTALL_RUNNING,
> - NR_PSI_TASK_COUNTS = 5,
> + NR_PSI_TASK_COUNTS = 4,
> };
>
> /* Task state bitmasks */
> #define TSK_IOWAIT (1 << NR_IOWAIT)
> #define TSK_MEMSTALL (1 << NR_MEMSTALL)
> #define TSK_RUNNING (1 << NR_RUNNING)
> -#define TSK_ONCPU (1 << NR_ONCPU)
> #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING)
>
> +/* Only one task can be scheduled, no corresponding task count */
> +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS)
> +
> /* Resources that workloads could be stalled on */
> enum psi_res {
> PSI_IO,
> @@ -68,6 +63,9 @@ enum psi_states {
> NR_PSI_STATES = 7,
> };
>
> +/* Use one bit in the state mask to track TSK_ONCPU */
> +#define PSI_ONCPU (1 << NR_PSI_STATES)
> +
> enum psi_aggregators {
> PSI_AVGS = 0,
> PSI_POLL,
> diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> index 595a6c8230b7..1c675715ed33 100644
> --- a/kernel/sched/psi.c
> +++ b/kernel/sched/psi.c
> @@ -216,7 +216,7 @@ void __init psi_init(void)
> group_init(&psi_system);
> }
>
> -static bool test_state(unsigned int *tasks, enum psi_states state)
> +static bool test_state(unsigned int *tasks, enum psi_states state, bool oncpu)
> {
> switch (state) {
> case PSI_IO_SOME:
> @@ -229,9 +229,9 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
> return unlikely(tasks[NR_MEMSTALL] &&
> tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]);
> case PSI_CPU_SOME:
> - return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]);
> + return unlikely(tasks[NR_RUNNING] > oncpu);
> case PSI_CPU_FULL:
> - return unlikely(tasks[NR_RUNNING] && !tasks[NR_ONCPU]);
> + return unlikely(tasks[NR_RUNNING] && !oncpu);
> case PSI_NONIDLE:
> return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
> tasks[NR_RUNNING];
> @@ -693,9 +693,9 @@ static void psi_group_change(struct psi_group *group, int cpu,
> bool wake_clock)
> {
> struct psi_group_cpu *groupc;
> - u32 state_mask = 0;
> unsigned int t, m;
> enum psi_states s;
> + u32 state_mask;
>
> groupc = per_cpu_ptr(group->pcpu, cpu);
>
> @@ -711,6 +711,26 @@ static void psi_group_change(struct psi_group *group, int cpu,
>
> record_times(groupc, now);
>
> + /*
> + * Start with TSK_ONCPU, which doesn't have a corresponding
> + * task count - it's just a boolean flag directly encoded in
> + * the state mask. Clear, set, or carry the current state if
> + * no changes are requested.
> + */
> + if (clear & TSK_ONCPU) {
> + state_mask = 0;
> + clear &= ~TSK_ONCPU;
> + } else if (set & TSK_ONCPU) {
> + state_mask = PSI_ONCPU;
> + set &= ~TSK_ONCPU;

These two conditions should use "unlikely()", which would be better
in the perf bench sched pipe testcase.


> + } else {
> + state_mask = groupc->state_mask & PSI_ONCPU;
> + }
> +
> + /*
> + * The rest of the state mask is calculated based on the task
> + * counts. Update those first, then construct the mask.
> + */
> for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
> if (!(m & (1 << t)))
> continue;
> @@ -730,9 +750,8 @@ static void psi_group_change(struct psi_group *group, int cpu,
> if (set & (1 << t))
> groupc->tasks[t]++;
>
> - /* Calculate state mask representing active states */
> for (s = 0; s < NR_PSI_STATES; s++) {
> - if (test_state(groupc->tasks, s))
> + if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU))
> state_mask |= (1 << s);
> }
>
> @@ -744,7 +763,7 @@ static void psi_group_change(struct psi_group *group, int cpu,
> * task in a cgroup is in_memstall, the corresponding groupc
> * on that cpu is in PSI_MEM_FULL state.
> */
> - if (unlikely(groupc->tasks[NR_ONCPU] && cpu_curr(cpu)->in_memstall))
> + if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall))
> state_mask |= (1 << PSI_MEM_FULL);
>
> groupc->state_mask = state_mask;
> @@ -835,7 +854,8 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
> */
> iter = NULL;
> while ((group = iterate_groups(next, &iter))) {
> - if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
> + if (per_cpu_ptr(group->pcpu, cpu)->state_mask &
> + PSI_ONCPU) {
> common = group;
> break;
> }