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

Groups > linux.kernel > #1447904 > unrolled thread

[PATCH 5/5] mm, vmscan: Account for skipped pages as a partial scan

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial scan Mel Gorman <mgorman@techsingularity.net> - 2016-07-21 16:20 +0200
    Re: [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial  scan Johannes Weiner <hannes@cmpxchg.org> - 2016-07-22 18:10 +0200
    Re: [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial  scan Minchan Kim <minchan@kernel.org> - 2016-07-25 10:40 +0200
      Re: [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial  scan Mel Gorman <mgorman@techsingularity.net> - 2016-07-25 12:00 +0200

#1447904 — [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial scan

Page reclaim determines whether a pgdat is unreclaimable by examining how
many pages have been scanned since a page was freed and comparing that to
the LRU sizes. Skipped pages are not reclaim candidates but contribute to
scanned. This can prematurely mark a pgdat as unreclaimable and trigger
an OOM kill.

This patch accounts for skipped pages as a partial scan so that an
unreclaimable pgdat will still be marked as such but by scaling the cost
of a skip, it'll avoid the pgdat being marked prematurely.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/vmscan.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6810d81f60c7..e5af357dd4ac 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1424,7 +1424,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	LIST_HEAD(pages_skipped);
 
 	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
-					!list_empty(src); scan++) {
+					!list_empty(src);) {
 		struct page *page;
 
 		page = lru_to_page(src);
@@ -1438,6 +1438,12 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			continue;
 		}
 
+		/*
+		 * Account for scanned and skipped separetly to avoid the pgdat
+		 * being prematurely marked unreclaimable by pgdat_reclaimable.
+		 */
+		scan++;
+
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
 			nr_pages = hpage_nr_pages(page);
@@ -1465,14 +1471,24 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	 */
 	if (!list_empty(&pages_skipped)) {
 		int zid;
+		unsigned long total_skipped = 0;
 
-		list_splice(&pages_skipped, src);
 		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 			if (!nr_skipped[zid])
 				continue;
 
 			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
+			total_skipped += nr_skipped[zid];
 		}
+
+		/*
+		 * Account skipped pages as a partial scan as the pgdat may be
+		 * close to unreclaimable. If the LRU list is empty, account
+		 * skipped pages as a full scan.
+		 */
+		scan += list_empty(src) ? total_skipped : total_skipped >> 2;
+
+		list_splice(&pages_skipped, src);
 	}
 	*nr_scanned = scan;
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
-- 
2.6.4

[toc] | [next] | [standalone]

#1448660 — Re: [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial scan

On Thu, Jul 21, 2016 at 03:11:01PM +0100, Mel Gorman wrote:
> Page reclaim determines whether a pgdat is unreclaimable by examining how
> many pages have been scanned since a page was freed and comparing that to
> the LRU sizes. Skipped pages are not reclaim candidates but contribute to
> scanned. This can prematurely mark a pgdat as unreclaimable and trigger
> an OOM kill.
> 
> This patch accounts for skipped pages as a partial scan so that an
> unreclaimable pgdat will still be marked as such but by scaling the cost
> of a skip, it'll avoid the pgdat being marked prematurely.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

[toc] | [prev] | [next] | [standalone]

#1449361 — Re: [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial scan

On Thu, Jul 21, 2016 at 03:11:01PM +0100, Mel Gorman wrote:
> Page reclaim determines whether a pgdat is unreclaimable by examining how
> many pages have been scanned since a page was freed and comparing that to
> the LRU sizes. Skipped pages are not reclaim candidates but contribute to
> scanned. This can prematurely mark a pgdat as unreclaimable and trigger
> an OOM kill.
> 
> This patch accounts for skipped pages as a partial scan so that an
> unreclaimable pgdat will still be marked as such but by scaling the cost
> of a skip, it'll avoid the pgdat being marked prematurely.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
> ---
>  mm/vmscan.c | 20 ++++++++++++++++++--
>  1 file changed, 18 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 6810d81f60c7..e5af357dd4ac 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1424,7 +1424,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
>  	LIST_HEAD(pages_skipped);
>  
>  	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
> -					!list_empty(src); scan++) {
> +					!list_empty(src);) {
>  		struct page *page;
>  
>  		page = lru_to_page(src);
> @@ -1438,6 +1438,12 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
>  			continue;
>  		}
>  
> +		/*
> +		 * Account for scanned and skipped separetly to avoid the pgdat
> +		 * being prematurely marked unreclaimable by pgdat_reclaimable.
> +		 */
> +		scan++;
> +
>  		switch (__isolate_lru_page(page, mode)) {
>  		case 0:
>  			nr_pages = hpage_nr_pages(page);
> @@ -1465,14 +1471,24 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
>  	 */
>  	if (!list_empty(&pages_skipped)) {
>  		int zid;
> +		unsigned long total_skipped = 0;
>  
> -		list_splice(&pages_skipped, src);
>  		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
>  			if (!nr_skipped[zid])
>  				continue;
>  
>  			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
> +			total_skipped += nr_skipped[zid];
>  		}
> +
> +		/*
> +		 * Account skipped pages as a partial scan as the pgdat may be
> +		 * close to unreclaimable. If the LRU list is empty, account
> +		 * skipped pages as a full scan.
> +		 */

node-lru made OOM detection lengthy because a freeing of any zone will
reset NR_PAGES_SCANNED easily so that it's hard to meet a situation
pgdat_reclaimable returns *false*.

When I perform stress test, it seems I encounter the situation easily
although I have no number now.

Anyway, this patch makes sense to me because it's better than now.
About accounting scan, I supports this idea.

But still, I doubt it's okay to continue skipping pages under
irq-disabled-spin lock without any condition.

[toc] | [prev] | [next] | [standalone]

#1449409 — Re: [PATCH 5/5] mm, vmscan: Account for skipped pages as a partial scan

On Mon, Jul 25, 2016 at 05:39:13PM +0900, Minchan Kim wrote:
> > @@ -1465,14 +1471,24 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
> >  	 */
> >  	if (!list_empty(&pages_skipped)) {
> >  		int zid;
> > +		unsigned long total_skipped = 0;
> >  
> > -		list_splice(&pages_skipped, src);
> >  		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
> >  			if (!nr_skipped[zid])
> >  				continue;
> >  
> >  			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
> > +			total_skipped += nr_skipped[zid];
> >  		}
> > +
> > +		/*
> > +		 * Account skipped pages as a partial scan as the pgdat may be
> > +		 * close to unreclaimable. If the LRU list is empty, account
> > +		 * skipped pages as a full scan.
> > +		 */
> 
> node-lru made OOM detection lengthy because a freeing of any zone will
> reset NR_PAGES_SCANNED easily so that it's hard to meet a situation
> pgdat_reclaimable returns *false*.
> 

Your patch should go a long way to addressing that as it checks the zone
counters first before conducting the scan. Remember as well that the longer
detection of OOM only applies to zone-constrained allocations and there
is always the possibility that highmem shrinking of pages frees lowmem
memory if buffers are used.

-- 
Mel Gorman
SUSE Labs

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web