Re: [PATCH 9/9] sched/psi: add PSI_IRQ to track IRQ/SOFTIRQ pressure

[Chengming Zhou]

On 2022/7/26 02:26, Johannes Weiner wrote:
> On Thu, Jul 21, 2022 at 12:04:39PM +0800, Chengming Zhou wrote:
>> Now PSI already tracked workload pressure stall information for
>> CPU, memory and IO. Apart from these, IRQ/SOFTIRQ could have
>> obvious impact on some workload productivity, such as web service
>> workload.
>>
>> When CONFIG_IRQ_TIME_ACCOUNTING, we can get IRQ/SOFTIRQ delta time
>> from update_rq_clock_task(), in which we can record that delta
>> to CPU curr task's cgroups as PSI_IRQ_FULL status.
>>
>> Note we don't use PSI_IRQ_SOME since IRQ/SOFTIRQ always happen in
>> the current task on the CPU, make nothing productive could run
>> even if it were runnable, so we only use PSI_IRQ_FULL.
> 
> That sounds reasonable.
> 
>> For performance impact consideration, this is enabled by default when
>> CONFIG_IRQ_TIME_ACCOUNTING, but can be disabled by kernel cmdline
>> parameter "psi_irq=".
> 
> If there isn't a concrete usecase already, let's not add another
> commandline parameter for now.
> 
>> @@ -63,9 +64,11 @@ enum psi_states {
>>  	PSI_MEM_FULL,
>>  	PSI_CPU_SOME,
>>  	PSI_CPU_FULL,
>> +	PSI_IRQ_SOME,
>> +	PSI_IRQ_FULL,
>>  	/* Only per-CPU, to weigh the CPU in the global average: */
>>  	PSI_NONIDLE,
>> -	NR_PSI_STATES = 7,
>> +	NR_PSI_STATES = 9,
>>  };
> 
> Unfortunately, this grows the psi state touched by the scheduler into
> a second cacheline. :( Please reclaim space first.
> 
> I think we can remove the NR_CPU task count, which frees up one
> u32. Something like the below diff should work (untested!)

Hi, I tested ok, would you mind if I put this patch in this series?


Subject: [PATCH] sched/psi: remove NR_ONCPU task accounting

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 TSK_ONCPU in state_mask to track instead.

Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reviewed-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
Tested-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>


> 
> And you should be able to remove PSI_IRQ_SOME, since it's not used
> anyway. Then we'd be good to go.
> 
> diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
> index c7fe7c089718..31dc76e2d8ea 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.
> @@ -39,9 +32,11 @@ enum psi_task_count {
>  #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,
> diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> index a4fa3aadfcba..232e1dbfad46 100644
> --- a/kernel/sched/psi.c
> +++ b/kernel/sched/psi.c
> @@ -215,7 +215,7 @@ 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:
> @@ -228,9 +228,9 @@ 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];
> @@ -692,9 +692,9 @@ 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);
>  
> @@ -710,6 +710,26 @@ 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 = TSK_ONCPU;
> +		set &= ~TSK_ONCPU;
> +	} else {
> +		state_mask = groupc->state_mask & TSK_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;
> @@ -729,9 +749,8 @@ 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 & TSK_ONCPU))
>  			state_mask |= (1 << s);
>  	}
>  
> @@ -743,7 +762,7 @@ 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 & TSK_ONCPU) && cpu_curr(cpu)->in_memstall))
>  		state_mask |= (1 << PSI_MEM_FULL);
>  
>  	groupc->state_mask = state_mask;
> @@ -847,7 +866,8 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
>  		iter = NULL;
>  		while ((group = iterate_groups(next, &iter))) {
>  			if (identical_state &&
> -			    per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
> +			    (per_cpu_ptr(group->pcpu, cpu)->state_mask &
> +			     TSK_ONCPU)) {
>  				common = group;
>  				break;
>  			}