Re: [PATCH] mm: move pcp and lru-pcp drainging into single wq

[Mel Gorman]

On Tue, Mar 07, 2017 at 02:17:51PM +0100, Michal Hocko wrote:
> From: Michal Hocko <mhocko@xxxxxxxx>
> 
> We currently have 2 specific WQ_RECLAIM workqueues in the mm code.
> vmstat_wq for updating pcp stats and lru_add_drain_wq dedicated to drain
> per cpu lru caches. This seems more than necessary because both can run
> on a single WQ. Both do not block on locks requiring a memory allocation
> nor perform any allocations themselves. We will save one rescuer thread
> this way.
> 
> On the other hand drain_all_pages() queues work on the system wq which
> doesn't have rescuer and so this depend on memory allocation (when all
> workers are stuck allocating and new ones cannot be created). This is
> not critical as there should be somebody invoking the OOM killer (e.g.
> the forking worker) and get the situation unstuck and eventually
> performs the draining. Quite annoying though. This worker should be
> using WQ_RECLAIM as well. We can reuse the same one as for lru draining
> and vmstat.
> 
> Changes since v1
> - rename vmstat_wq to mm_percpu_wq - per Mel
> - make sure we are not trying to enqueue anything while the WQ hasn't
>   been intialized yet. This shouldn't happen because the initialization
>   is done from an init code but some init section might be triggering
>   those paths indirectly so just warn and skip the draining in that case
>   per Vlastimil
> - do not propagate error from setup_vmstat to keep the previous behavior
>   per Mel
> 
> Suggested-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
> Signed-off-by: Michal Hocko <mhocko@xxxxxxxx>

Acked-by: Mel Gorman <mgorman@xxxxxxx>
> +struct workqueue_struct *mm_percpu_wq;
> +
>  static int __init setup_vmstat(void)
>  {
> -#ifdef CONFIG_SMP
> -	int ret;
> +	int ret __maybe_unused;
>  
> +	mm_percpu_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
> +
> +#ifdef CONFIG_SMP
>  	ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
>  					NULL, vmstat_cpu_dead);
>  	if (ret < 0)

Should the workqueue also have been renamed to mm_percpu_wq?

-- 
Mel Gorman
SUSE Labs