From cda73a10eb3f493871ed39f468db50a65ebeddce Mon Sep 17 00:00:00 2001 From: Zlatko Calusic Date: Thu, 20 Dec 2012 00:25:13 +0100 Subject: mm: do not sleep in balance_pgdat if there's no i/o congestion On a 4GB RAM machine, where Normal zone is much smaller than DMA32 zone, the Normal zone gets fragmented in time. This requires relatively more pressure in balance_pgdat to get the zone above the required watermark. Unfortunately, the congestion_wait() call in there slows it down for a completely wrong reason, expecting that there's a lot of writeback/swapout, even when there's none (much more common). After a few days, when fragmentation progresses, this flawed logic translates to a very high CPU iowait times, even though there's no I/O congestion at all. If THP is enabled, the problem occurs sooner, but I was able to see it even on !THP kernels, just by giving it a bit more time to occur. The proper way to deal with this is to not wait, unless there's congestion. Thanks to Mel Gorman, we already have the function that perfectly fits the job. The patch was tested on a machine which nicely revealed the problem after only 1 day of uptime, and it's been working great. Signed-off-by: Zlatko Calusic Acked-by: Mel Gorman Signed-off-by: Linus Torvalds --- mm/vmscan.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index 828530e2794a..adc7e9058181 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2570,7 +2570,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, static unsigned long balance_pgdat(pg_data_t *pgdat, int order, int *classzone_idx) { - int all_zones_ok; + struct zone *unbalanced_zone; unsigned long balanced; int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ @@ -2604,7 +2604,7 @@ loop_again: unsigned long lru_pages = 0; int has_under_min_watermark_zone = 0; - all_zones_ok = 1; + unbalanced_zone = NULL; balanced = 0; /* @@ -2743,7 +2743,7 @@ loop_again: } if (!zone_balanced(zone, testorder, 0, end_zone)) { - all_zones_ok = 0; + unbalanced_zone = zone; /* * We are still under min water mark. This * means that we have a GFP_ATOMIC allocation @@ -2776,7 +2776,7 @@ loop_again: pfmemalloc_watermark_ok(pgdat)) wake_up(&pgdat->pfmemalloc_wait); - if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx))) + if (!unbalanced_zone || (order && pgdat_balanced(pgdat, balanced, *classzone_idx))) break; /* kswapd: all done */ /* * OK, kswapd is getting into trouble. Take a nap, then take @@ -2786,7 +2786,7 @@ loop_again: if (has_under_min_watermark_zone) count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT); else - congestion_wait(BLK_RW_ASYNC, HZ/10); + wait_iff_congested(unbalanced_zone, BLK_RW_ASYNC, HZ/10); } /* @@ -2805,7 +2805,7 @@ out: * high-order: Balanced zones must make up at least 25% of the node * for the node to be balanced */ - if (!(all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))) { + if (unbalanced_zone && (!order || !pgdat_balanced(pgdat, balanced, *classzone_idx))) { cond_resched(); try_to_freeze(); -- cgit v1.2.1