Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1259931

Re: [RFC 1/3] mm, oom: refactor oom detection

Show all headers | View raw

> On Fri 30-10-15 09:36:26, Michal Hocko wrote:
> > On Fri 30-10-15 12:10:15, Hillf Danton wrote:
> > [...]
> > > > +	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, ac->nodemask) {
> > > > +		unsigned long free = zone_page_state(zone, NR_FREE_PAGES);
> > > > +		unsigned long reclaimable;
> > > > +		unsigned long target;
> > > > +
> > > > +		reclaimable = zone_reclaimable_pages(zone) +
> > > > +			      zone_page_state(zone, NR_ISOLATED_FILE) +
> > > > +			      zone_page_state(zone, NR_ISOLATED_ANON);
> > > > +		target = reclaimable;
> > > > +		target -= stall_backoff * (1 + target/MAX_STALL_BACKOFF);
> > >
> > > 		target = reclaimable - stall_backoff * (1 + target/MAX_STALL_BACKOFF);
> > > 		             = reclaimable - stall_backoff - stall_backoff  * (target/MAX_STALL_BACKOFF);
> > >
> > > then the first stall_backoff looks unreasonable.
> >
> > First stall_backoff is off by 1 but that shouldn't make any difference.
> >
> > > I guess you mean
> > > 		target	= reclaimable - target * (stall_backoff/MAX_STALL_BACKOFF);
> > > 			= reclaimable - stall_back * (target/MAX_STALL_BACKOFF);
> >
> > No the reason I used the bias is to converge for MAX_STALL_BACKOFF. If
> > you have target which is not divisible by MAX_STALL_BACKOFF then the
> > rounding would get target > 0 and so we wouldn't converge. With the +1
> > you underflow which is MAX_STALL_BACKOFF in maximum which should be
> > fixed up by the free memory. Maybe a check for free < MAX_STALL_BACKOFF
> > would be good but I didn't get that far with this.
> 
> I've ended up with the following after all. It uses ceiling for the
> division this should be underflow safe albeit less readable (at least
> for me).

Looks good, thanks.

Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>

> ---
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 0dc1ca9b1219..c9a4e62f234e 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3176,7 +3176,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
>  			      zone_page_state(zone, NR_ISOLATED_FILE) +
>  			      zone_page_state(zone, NR_ISOLATED_ANON);
>  		target = reclaimable;
> -		target -= stall_backoff * (1 + target/MAX_STALL_BACKOFF);
> +		target -= (stall_backoff * target + MAX_STALL_BACKOFF - 1) / MAX_STALL_BACKOFF;
>  		target += free;
> 
>  		/*
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index bc14217acd47..0b3ec972ec7a 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2672,7 +2672,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
>  	int initial_priority = sc->priority;
>  	unsigned long total_scanned = 0;
>  	unsigned long writeback_threshold;
> -	bool zones_reclaimable;
>  retry:
>  	delayacct_freepages_start();
> 
> @@ -2683,7 +2682,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
>  		vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
>  				sc->priority);
>  		sc->nr_scanned = 0;
> -		zones_reclaimable = shrink_zones(zonelist, sc);
> +		shrink_zones(zonelist, sc);
> 
>  		total_scanned += sc->nr_scanned;
>  		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
> --
> Michal Hocko
> SUSE Labs

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

RFC: OOM detection rework v1 mhocko@kernel.org - 2015-10-29 16:20 +0100
  [RFC 3/3] mm: use watermak checks for __GFP_REPEAT high order allocations mhocko@kernel.org - 2015-10-29 16:20 +0100
  [RFC 1/3] mm, oom: refactor oom detection mhocko@kernel.org - 2015-10-29 16:20 +0100
    Re: [RFC 1/3] mm, oom: refactor oom detection "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2015-10-30 05:20 +0100
      Re: [RFC 1/3] mm, oom: refactor oom detection Michal Hocko <mhocko@kernel.org> - 2015-10-30 09:40 +0100
        Re: [RFC 1/3] mm, oom: refactor oom detection Michal Hocko <mhocko@kernel.org> - 2015-10-30 11:20 +0100
          Re: [RFC 1/3] mm, oom: refactor oom detection Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> - 2015-10-30 14:40 +0100
            Re: [RFC 1/3] mm, oom: refactor oom detection Michal Hocko <mhocko@kernel.org> - 2015-10-30 16:00 +0100
          Re: [RFC 1/3] mm, oom: refactor oom detection "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2015-10-31 05:00 +0100
    Re: [RFC 1/3] mm, oom: refactor oom detection Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> - 2015-10-30 06:30 +0100
      Re: [RFC 1/3] mm, oom: refactor oom detection Michal Hocko <mhocko@kernel.org> - 2015-10-30 09:30 +0100
        Re: [RFC 1/3] mm, oom: refactor oom detection Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> - 2015-10-30 10:50 +0100
          Re: [RFC 1/3] mm, oom: refactor oom detection Michal Hocko <mhocko@kernel.org> - 2015-10-30 11:20 +0100
    Re: [RFC 1/3] mm, oom: refactor oom detection Michal Hocko <mhocko@kernel.org> - 2015-11-12 13:40 +0100
  [RFC 2/3] mm: throttle on IO only when there are too many dirty and writeback pages mhocko@kernel.org - 2015-10-29 16:20 +0100
    Re: [RFC 2/3] mm: throttle on IO only when there are too many dirty and writeback pages "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2015-10-30 05:30 +0100
      Re: [RFC 2/3] mm: throttle on IO only when there are too many dirty  and writeback pages Michal Hocko <mhocko@kernel.org> - 2015-10-30 09:40 +0100
    Re: [RFC 2/3] mm: throttle on IO only when there are too many dirty  and writeback pages Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> - 2015-10-30 06:50 +0100
      Re: [RFC 2/3] mm: throttle on IO only when there are too many dirty  and writeback pages Michal Hocko <mhocko@kernel.org> - 2015-10-30 09:40 +0100
  Re: RFC: OOM detection rework v1 Michal Hocko <mhocko@kernel.org> - 2015-11-12 13:50 +0100

csiph-web