From: Johannes Weiner <hannes@xxxxxxxxxxx>
Subject: mm/page-writeback.c: do not count anon pages as dirtyable memory
The VM is currently heavily tuned to avoid swapping. Whether that is good
or bad is a separate discussion, but as long as the VM won't swap to make
room for dirty cache, we can not consider anonymous pages when calculating
the amount of dirtyable memory, the baseline to which
dirty_background_ratio and dirty_ratio are applied.
A simple workload that occupies a significant size (40+%, depending on
memory layout, storage speeds etc.) of memory with anon/tmpfs pages and
uses the remainder for a streaming writer demonstrates this problem. In
that case, the actual cache pages are a small fraction of what is
considered dirtyable overall, which results in an relatively large portion
of the cache pages to be dirtied. As kswapd starts rotating these, random
tasks enter direct reclaim and stall on IO.
Only consider free pages and file pages dirtyable.
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reported-by: Tejun Heo <tj@xxxxxxxxxx>
Tested-by: Tejun Heo <tj@xxxxxxxxxx>
Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Reviewed-by: Michal Hocko <mhocko@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/vmstat.h | 2 --
mm/internal.h | 1 -
mm/page-writeback.c | 6 ++++--
mm/vmscan.c | 23 +----------------------
4 files changed, 5 insertions(+), 27 deletions(-)
diff -puN include/linux/vmstat.h~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory include/linux/vmstat.h
--- a/include/linux/vmstat.h~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory
+++ a/include/linux/vmstat.h
@@ -142,8 +142,6 @@ static inline unsigned long zone_page_st
return x;
}
-extern unsigned long global_reclaimable_pages(void);
-
#ifdef CONFIG_NUMA
/*
* Determine the per node value of a stat item. This function
diff -puN mm/internal.h~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory mm/internal.h
--- a/mm/internal.h~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory
+++ a/mm/internal.h
@@ -83,7 +83,6 @@ extern unsigned long highest_memmap_pfn;
*/
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
extern bool zone_reclaimable(struct zone *zone);
/*
diff -puN mm/page-writeback.c~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory mm/page-writeback.c
--- a/mm/page-writeback.c~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory
+++ a/mm/page-writeback.c
@@ -205,7 +205,8 @@ static unsigned long zone_dirtyable_memo
nr_pages = zone_page_state(zone, NR_FREE_PAGES);
nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
- nr_pages += zone_reclaimable_pages(zone);
+ nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
+ nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
return nr_pages;
}
@@ -258,7 +259,8 @@ static unsigned long global_dirtyable_me
x = global_page_state(NR_FREE_PAGES);
x -= min(x, dirty_balance_reserve);
- x += global_reclaimable_pages();
+ x += global_page_state(NR_INACTIVE_FILE);
+ x += global_page_state(NR_ACTIVE_FILE);
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
diff -puN mm/vmscan.c~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory mm/vmscan.c
--- a/mm/vmscan.c~mm-page-writebackc-do-not-count-anon-pages-as-dirtyable-memory
+++ a/mm/vmscan.c
@@ -147,7 +147,7 @@ static bool global_reclaim(struct scan_c
}
#endif
-unsigned long zone_reclaimable_pages(struct zone *zone)
+static unsigned long zone_reclaimable_pages(struct zone *zone)
{
int nr;
@@ -3315,27 +3315,6 @@ void wakeup_kswapd(struct zone *zone, in
wake_up_interruptible(&pgdat->kswapd_wait);
}
-/*
- * The reclaimable count would be mostly accurate.
- * The less reclaimable pages may be
- * - mlocked pages, which will be moved to unevictable list when encountered
- * - mapped pages, which may require several travels to be reclaimed
- * - dirty pages, which is not "instantly" reclaimable
- */
-unsigned long global_reclaimable_pages(void)
-{
- int nr;
-
- nr = global_page_state(NR_ACTIVE_FILE) +
- global_page_state(NR_INACTIVE_FILE);
-
- if (get_nr_swap_pages() > 0)
- nr += global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_INACTIVE_ANON);
-
- return nr;
-}
-
#ifdef CONFIG_HIBERNATION
/*
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
_
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html