@@ -1118,6 +1118,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
int may_enter_fs;
enum page_references references = PAGEREF_RECLAIM_CLEAN;
bool dirty, writeback;
+ unsigned int nr_pages;
cond_resched();
@@ -1129,6 +1130,13 @@ static unsigned long shrink_page_list(struct list_head *page_list,
VM_BUG_ON_PAGE(PageActive(page), page);
+ nr_pages = 1 << compound_order(page);
+
+ /*
+ * Accounted one page for THP for now. If THP gets swapped
+ * out in a whole, will account all tail pages later to
+ * avoid accounting tail pages twice.
+ */
sc->nr_scanned++;
if (unlikely(!page_evictable(page)))
@@ -1250,7 +1258,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
case PAGEREF_ACTIVATE:
goto activate_locked;
case PAGEREF_KEEP:
- stat->nr_ref_keep++;
+ stat->nr_ref_keep += nr_pages;
goto keep_locked;
case PAGEREF_RECLAIM:
case PAGEREF_RECLAIM_CLEAN:
@@ -1292,7 +1300,9 @@ static unsigned long shrink_page_list(struct list_head *page_list,
#endif
if (!add_to_swap(page))
goto activate_locked;
- }
+ } else
+ /* Account tail pages for THP */
+ sc->nr_scanned += nr_pages - 1;
may_enter_fs = 1;
@@ -1315,7 +1325,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
if (unlikely(PageTransHuge(page)))
flags |= TTU_SPLIT_HUGE_PMD;
if (!try_to_unmap(page, flags)) {
- stat->nr_unmap_fail++;
+ stat->nr_unmap_fail += nr_pages;
goto activate_locked;
}
}
@@ -1442,7 +1452,11 @@ static unsigned long shrink_page_list(struct list_head *page_list,
unlock_page(page);
free_it:
- nr_reclaimed++;
+ /*
+ * THP may get swapped out in a whole, need account
+ * all base pages.
+ */
+ nr_reclaimed += (1 << compound_order(page));
/*
* Is there need to periodically free_page_list? It would
@@ -1464,7 +1478,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
if (!PageMlocked(page)) {
int type = page_is_file_cache(page);
SetPageActive(page);
- pgactivate++;
stat->nr_activate[type] += hpage_nr_pages(page);
count_memcg_page_event(page, PGACTIVATE);
}
@@ -1475,6 +1488,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
}
+ pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
+
mem_cgroup_uncharge_list(&free_pages);
try_to_unmap_flush();
free_unref_page_list(&free_pages);
@@ -1646,10 +1661,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
LIST_HEAD(pages_skipped);
isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED);
+ total_scan = 0;
scan = 0;
- for (total_scan = 0;
- scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src);
- total_scan++) {
+ while (scan < nr_to_scan && !list_empty(src)) {
struct page *page;
page = lru_to_page(src);
@@ -1657,9 +1671,12 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
VM_BUG_ON_PAGE(!PageLRU(page), page);
+ nr_pages = 1 << compound_order(page);
+ total_scan += nr_pages;
+
if (page_zonenum(page) > sc->reclaim_idx) {
list_move(&page->lru, &pages_skipped);
- nr_skipped[page_zonenum(page)]++;
+ nr_skipped[page_zonenum(page)] += nr_pages;
continue;
}
@@ -1668,11 +1685,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
* return with no isolated pages if the LRU mostly contains
* ineligible pages. This causes the VM to not reclaim any
* pages, triggering a premature OOM.
+ *
+ * Account all tail pages of THP. This would not cause
+ * premature OOM since __isolate_lru_page() returns -EBUSY
+ * only when the page is being freed somewhere else.
*/
- scan++;
+ scan += nr_pages;
switch (__isolate_lru_page(page, mode)) {
case 0:
- nr_pages = hpage_nr_pages(page);
nr_taken += nr_pages;
nr_zone_taken[page_zonenum(page)] += nr_pages;
list_move(&page->lru, dst);
Since commit bd4c82c22c36 ("mm, THP, swap: delay splitting THP after swapped out"), THP can be swapped out in a whole. But, nr_reclaimed and some other vm counters still get inc'ed by one even though a whole THP (512 pages) gets swapped out. This doesn't make too much sense to memory reclaim. For example, direct reclaim may just need reclaim SWAP_CLUSTER_MAX pages, reclaiming one THP could fulfill it. But, if nr_reclaimed is not increased correctly, direct reclaim may just waste time to reclaim more pages, SWAP_CLUSTER_MAX * 512 pages in worst case. And, it may cause pgsteal_{kswapd|direct} is greater than pgscan_{kswapd|direct}, like the below: pgsteal_kswapd 122933 pgsteal_direct 26600225 pgscan_kswapd 174153 pgscan_direct 14678312 nr_reclaimed and nr_scanned must be fixed in parallel otherwise it would break some page reclaim logic, e.g. vmpressure: this looks at the scanned/reclaimed ratio so it won't change semantics as long as scanned & reclaimed are fixed in parallel. compaction/reclaim: compaction wants a certain number of physical pages freed up before going back to compacting. kswapd priority raising: kswapd raises priority if we scan fewer pages than the reclaim target (which itself is obviously expressed in order-0 pages). As a result, kswapd can falsely raise its aggressiveness even when it's making great progress. Other than nr_scanned and nr_reclaimed, some other counters, e.g. pgactivate, nr_skipped, nr_ref_keep and nr_unmap_fail need to be fixed too since they are user visible via cgroup, /proc/vmstat or trace points, otherwise they would be underreported. When isolating pages from LRUs, nr_taken has been accounted in base page, but nr_scanned and nr_skipped are still accounted in THP. It doesn't make too much sense too since this may cause trace point underreport the numbers as well. So accounting those counters in base page instead of accounting THP as one page. nr_dirty, nr_unqueued_dirty, nr_congested and nr_writeback are used by file cache, so they are not impacted by THP swap. This change may result in lower steal/scan ratio in some cases since THP may get split during page reclaim, then a part of tail pages get reclaimed instead of the whole 512 pages, but nr_scanned is accounted by 512, particularly for direct reclaim. But, this should be not a significant issue. Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com> --- v5: Fixed sc->nr_scanned double accounting per Huang Ying Added some comments to address the concern about premature OOM per Hillf Danton v4: Fixed the comments from Johannes and Huang Ying v3: Removed Shakeel's Reviewed-by since the patch has been changed significantly Switched back to use compound_order per Matthew Fixed more counters per Johannes v2: Added Shakeel's Reviewed-by Use hpage_nr_pages instead of compound_order per Huang Ying and William Kucharski mm/vmscan.c | 42 +++++++++++++++++++++++++++++++----------- 1 file changed, 31 insertions(+), 11 deletions(-)