linux-kernel - Re: [PATCH 04/10] mm: vmscan: Decide whether to compact the pgdat based on reclaim progress

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20130321153231.GP6094@dhcp22.suse.cz>
Date:	Thu, 21 Mar 2013 16:32:31 +0100
From:	Michal Hocko <mhocko@...e.cz>
To:	Mel Gorman <mgorman@...e.de>
Cc:	Linux-MM <linux-mm@...ck.org>, Jiri Slaby <jslaby@...e.cz>,
	Valdis Kletnieks <Valdis.Kletnieks@...edu>,
	Rik van Riel <riel@...hat.com>,
	Zlatko Calusic <zcalusic@...sync.net>,
	Johannes Weiner <hannes@...xchg.org>,
	dormando <dormando@...ia.net>,
	Satoru Moriya <satoru.moriya@....com>,
	LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 04/10] mm: vmscan: Decide whether to compact the pgdat
 based on reclaim progress

On Sun 17-03-13 13:04:10, Mel Gorman wrote:
> In the past, kswapd makes a decision on whether to compact memory after the
> pgdat was considered balanced. This more or less worked but it is late to
> make such a decision and does not fit well now that kswapd makes a decision
> whether to exit the zone scanning loop depending on reclaim progress.
> 
> This patch will compact a pgdat if at least  the requested number of pages
> were reclaimed from unbalanced zones for a given priority. If any zone is
> currently balanced, kswapd will not call compaction as it is expected the
> necessary pages are already available.
> 
> Signed-off-by: Mel Gorman <mgorman@...e.de>
> ---
>  mm/vmscan.c | 52 +++++++++++++++++++++-------------------------------
>  1 file changed, 21 insertions(+), 31 deletions(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 279d0c2..7513bd1 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2694,8 +2694,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
>  
>  	do {
>  		unsigned long lru_pages = 0;
> +		unsigned long nr_to_reclaim = 0;
>  		unsigned long nr_reclaimed = sc.nr_reclaimed;
> +		unsigned long this_reclaimed;
>  		bool raise_priority = true;
> +		bool pgdat_needs_compaction = true;

I am confused. We don't want to compact for order == 0, do we?

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7513bd1..1b89c29 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2698,7 +2698,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 		unsigned long nr_reclaimed = sc.nr_reclaimed;
 		unsigned long this_reclaimed;
 		bool raise_priority = true;
-		bool pgdat_needs_compaction = true;
+		bool pgdat_needs_compaction = order > 0;
 
 		/*
 		 * Scan in the highmem->dma direction for the highest

Other than that it makes sense to me.

>  
>  		/*
>  		 * Scan in the highmem->dma direction for the highest
> @@ -2743,7 +2746,17 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
>  		for (i = 0; i <= end_zone; i++) {
>  			struct zone *zone = pgdat->node_zones + i;
>  
> +			if (!populated_zone(zone))
> +				continue;
> +
>  			lru_pages += zone_reclaimable_pages(zone);
> +
> +			/* Check if the memory needs to be defragmented */
> +			if (order && pgdat_needs_compaction &&
> +					zone_watermark_ok(zone, order,
> +						low_wmark_pages(zone),
> +						*classzone_idx, 0))
> +				pgdat_needs_compaction = false;
>  		}
>  
>  		/*
> @@ -2814,6 +2827,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
>  				 */
>  				if (kswapd_shrink_zone(zone, &sc, lru_pages))
>  					raise_priority = false;
> +
> +				nr_to_reclaim += sc.nr_to_reclaim;
>  			}
>  
>  			/*
> @@ -2864,46 +2879,21 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
>  		if (try_to_freeze() || kthread_should_stop())
>  			break;
>  
> -		/* If no reclaim progress then increase scanning priority */
> -		if (sc.nr_reclaimed - nr_reclaimed == 0)
> -			raise_priority = true;
> +		/* Compact if necessary and kswapd is reclaiming efficiently */
> +		this_reclaimed = sc.nr_reclaimed - nr_reclaimed;
> +		if (order && pgdat_needs_compaction &&
> +				this_reclaimed > nr_to_reclaim)
> +			compact_pgdat(pgdat, order);
>  
>  		/*
>  		 * Raise priority if scanning rate is too low or there was no
>  		 * progress in reclaiming pages
>  		 */
> -		if (raise_priority || sc.nr_reclaimed - nr_reclaimed == 0)
> +		if (raise_priority || !this_reclaimed)
>  			sc.priority--;
>  	} while (sc.priority >= 0 &&
>  		 !pgdat_balanced(pgdat, order, *classzone_idx));
>  
> -	/*
> -	 * If kswapd was reclaiming at a higher order, it has the option of
> -	 * sleeping without all zones being balanced. Before it does, it must
> -	 * ensure that the watermarks for order-0 on *all* zones are met and
> -	 * that the congestion flags are cleared. The congestion flag must
> -	 * be cleared as kswapd is the only mechanism that clears the flag
> -	 * and it is potentially going to sleep here.
> -	 */
> -	if (order) {
> -		int zones_need_compaction = 1;
> -
> -		for (i = 0; i <= end_zone; i++) {
> -			struct zone *zone = pgdat->node_zones + i;
> -
> -			if (!populated_zone(zone))
> -				continue;
> -
> -			/* Check if the memory needs to be defragmented. */
> -			if (zone_watermark_ok(zone, order,
> -				    low_wmark_pages(zone), *classzone_idx, 0))
> -				zones_need_compaction = 0;
> -		}
> -
> -		if (zones_need_compaction)
> -			compact_pgdat(pgdat, order);
> -	}
> -
>  out:
>  	/*
>  	 * Return the order we were reclaiming at so prepare_kswapd_sleep()
> -- 
> 1.8.1.4
> 

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