mm: don't wait on congested zones in balance_pgdat()

From: Zlatko Calusic <zlatko.calusic@iskon.hr>

Commit 92df3a723f84 ("mm: vmscan: throttle reclaim if encountering too
many dirty pages under writeback") introduced waiting on congested zones
based on a sane algorithm in shrink_inactive_list().

What this means is that there's no more need for throttling and
additional heuristics in balance_pgdat().  So, let's remove it and tidy
up the code.

Signed-off-by: Zlatko Calusic <zlatko.calusic@iskon.hr>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index fce0a27..bd6cf61 100644 (file)
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -36,7 +36,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
                PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
                KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
-               KSWAPD_SKIP_CONGESTION_WAIT,
                PAGEOUTRUN, ALLOCSTALL, PGROTATED,
 #ifdef CONFIG_NUMA_BALANCING
                NUMA_PTE_UPDATES,

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8fde2fc..b93968b 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2617,7 +2617,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
                                                        int *classzone_idx)
 {
        bool pgdat_is_balanced = false;
-       struct zone *unbalanced_zone;
        int i;
        int end_zone = 0;       /* Inclusive.  0 = ZONE_DMA */
        unsigned long total_scanned;
@@ -2648,9 +2647,6 @@ loop_again:
 
        do {
                unsigned long lru_pages = 0;
-               int has_under_min_watermark_zone = 0;
-
-               unbalanced_zone = NULL;
 
                /*
                 * Scan in the highmem->dma direction for the highest
@@ -2790,17 +2786,7 @@ loop_again:
                                continue;
                        }
 
-                       if (!zone_balanced(zone, testorder, 0, end_zone)) {
-                               unbalanced_zone = zone;
-                               /*
-                                * We are still under min water mark.  This
-                                * means that we have a GFP_ATOMIC allocation
-                                * failure risk. Hurry up!
-                                */
-                               if (!zone_watermark_ok_safe(zone, order,
-                                           min_wmark_pages(zone), end_zone, 0))
-                                       has_under_min_watermark_zone = 1;
-                       } else {
+                       if (zone_balanced(zone, testorder, 0, end_zone))
                                /*
                                 * If a zone reaches its high watermark,
                                 * consider it to be no longer congested. It's
@@ -2809,8 +2795,6 @@ loop_again:
                                 * speculatively avoid congestion waits
                                 */
                                zone_clear_flag(zone, ZONE_CONGESTED);
-                       }
-
                }
 
                /*
@@ -2828,17 +2812,6 @@ loop_again:
                }
 
                /*
-                * OK, kswapd is getting into trouble.  Take a nap, then take
-                * another pass across the zones.
-                */
-               if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) {
-                       if (has_under_min_watermark_zone)
-                               count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
-                       else if (unbalanced_zone)
-                               wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10);
-               }
-
-               /*
                 * We do this so kswapd doesn't build up large priorities for
                 * example when it is freeing in parallel with allocators. It
                 * matches the direct reclaim path behaviour in terms of impact

diff --git a/mm/vmstat.c b/mm/vmstat.c
index c9d1f68..57f02fd 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -770,7 +770,6 @@ const char * const vmstat_text[] = {
        "kswapd_inodesteal",
        "kswapd_low_wmark_hit_quickly",
        "kswapd_high_wmark_hit_quickly",
-       "kswapd_skip_congestion_wait",
        "pageoutrun",
        "allocstall",