On Tue 18-10-16 20:04:20, Tetsuo Handa wrote:
[...]
> @@ -1697,11 +1697,25 @@ static bool inactive_reclaimable_pages(struct lruvec 
> *lruvec,
>       int file = is_file_lru(lru);
>       struct pglist_data *pgdat = lruvec_pgdat(lruvec);
>       struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
> +     unsigned long wait_start = jiffies;
> +     unsigned int wait_timeout = 10 * HZ;
> +     long last_diff = 0;
> +     long diff;
>  
>       if (!inactive_reclaimable_pages(lruvec, sc, lru))
>               return 0;
>  
> -     while (unlikely(too_many_isolated(pgdat, file, sc))) {
> +     while (unlikely((diff = too_many_isolated(pgdat, file, sc)) > 0)) {
> +             if (diff < last_diff) {
> +                     wait_start = jiffies;
> +                     wait_timeout = 10 * HZ;
> +             } else if (time_after(jiffies, wait_start + wait_timeout)) {
> +                     warn_alloc(sc->gfp_mask,
> +                                "shrink_inactive_list() stalls for %ums",
> +                                jiffies_to_msecs(jiffies - wait_start));
> +                     wait_timeout += 10 * HZ;
> +             }
> +             last_diff = diff;
>               congestion_wait(BLK_RW_ASYNC, HZ/10);
>  
>               /* We are about to die and free our memory. Return now. */
> ----------
[...]
> So, how can we make warn_alloc() reliable?

This is not about warn_alloc reliability but more about
too_many_isolated waiting for an unbounded amount of time. And that
should be fixed. I do not have a good idea how right now.
-- 
Michal Hocko
SUSE Labs

Reply via email to