Re: [PATCH] sched/fair: Fix CPU bandwidth limit bypass during CPU hotplug

[Madadi Vineeth Reddy <vineethr@linux.ibm.com>]

Hi Vishal,

On 26/11/24 12:18, Vishal Chourasia wrote:
> CPU controller limits are not properly enforced during CPU hotplug operations,
> particularly during CPU offline. When a CPU goes offline, throttled
> processes are unintentionally being unthrottled across all CPUs in the system,
> allowing them to exceed their assigned quota limits.
> 
> Assigning 6.25% bandwidth limit to a cgroup in a 8 CPU system, where, workload
> is running 8 threads for 20 seconds at 100% CPU utilization,
> expected (user+sys) time = 10 seconds.
> 
> # cat /sys/fs/cgroup/test/cpu.max
> 50000 100000
> 
> # ./ebizzy -t 8 -S 20        // non-hotplug case
> real 20.00 s
> user 10.81 s                 // intented behaviour
> sys   0.00 s
> 
> # ./ebizzy -t 8 -S 20        // hotplug case
> real 20.00 s
> user 14.43 s                 // Workload is able to run for 14 secs
> sys   0.00 s                 // when it should have only run for 10 secs
> 
> During CPU hotplug, scheduler domains are rebuilt and cpu_attach_domain
> is called for every active CPU to update the root domain. That ends up
> calling rq_offline_fair which un-throttles any throttled hierarchies.
> 
> Unthrottling should only occur for the CPU being hotplugged to allow its
> throttled processes to become runnable and get migrated to other CPUs.
> 
> With current patch applied,
> # ./ebizzy -t 8 -S 20        // hotplug case
> real 21.00 s
> user 10.16 s                 // intented behaviour
> sys   0.00 s
> 
> Note: hotplug operation (online, offline) was performed in while(1) loop

Tested with and without this patch for the ebizzy workload as mentioned.

Without the patch:
------------------
19376 records/s
real 20.00 s
user 12.49 s
sys   0.00 s

With the patch:
---------------
17708 records/s
real 20.00 s
user 10.07 s
sys   0.00 s

Hence,
Tested-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>

Thanks,
Madadi Vineeth Reddy

> 
> Signed-off-by: Vishal Chourasia <vishalc@linux.ibm.com>
> ---
>  kernel/sched/fair.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index fbdca89c677f..c436e2307e6f 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6684,7 +6684,8 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
>  	list_for_each_entry_rcu(tg, &task_groups, list) {
>  		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
>  
> -		if (!cfs_rq->runtime_enabled)
> +		/* Don't unthrottle an active cfs_rq unnecessarily */
> +		if (!cfs_rq->runtime_enabled || cpumask_test_cpu(cpu_of(rq), cpu_active_mask))
>  			continue;
>  
>  		/*