On Mon, Jul 18, 2016 at 01:11:22PM +0100, Mel Gorman wrote:
> The all_unreclaimable logic is related to the number of pages scanned
> but currently pages skipped contributes to pages scanned. That is one
> possibility. The other is that if all pages scanned are skipped then the
> OOM killer can believe there is zero progress.
>
> Try this to start with;
>
And if that fails, try this heavier handed version that will scan the full
LRU potentially to isolate at least a single page if it's available for
zone-constrained allocations. It's compile-tested only
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a6f31617a08c..6a35691c8b94 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1408,14 +1408,14 @@ static unsigned long isolate_lru_pages(unsigned long
nr_to_scan,
isolate_mode_t mode, enum lru_list lru)
{
struct list_head *src = &lruvec->lists[lru];
- unsigned long nr_taken = 0;
+ unsigned long nr_taken = 0, total_skipped = 0;
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
unsigned long scan, nr_pages;
LIST_HEAD(pages_skipped);
for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
- !list_empty(src); scan++) {
+ !list_empty(src) && scan == total_skipped; scan++) {
struct page *page;
page = lru_to_page(src);
@@ -1426,6 +1426,7 @@ static unsigned long isolate_lru_pages(unsigned long
nr_to_scan,
if (page_zonenum(page) > sc->reclaim_idx) {
list_move(&page->lru, &pages_skipped);
nr_skipped[page_zonenum(page)]++;
+ total_skipped++;
continue;
}
@@ -1465,7 +1466,7 @@ static unsigned long isolate_lru_pages(unsigned long
nr_to_scan,
__count_zid_vm_events(PGSCAN_SKIP, zid,
nr_skipped[zid]);
}
}
- *nr_scanned = scan;
+ *nr_scanned = scan - total_skipped;
trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
scan,
nr_taken, mode, is_file_lru(lru));
update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken);
--
Mel Gorman
SUSE Labs
