From d7d9d9a9f7788444bd8663a8e05276548adc7d3f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 8 Jul 2011 15:39:40 -0700 Subject: [PATCH] mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit BugLink: http://bugs.launchpad.net/bugs/808509 During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman Reported-by: Pádraig Brady Tested-by: Pádraig Brady Tested-by: Andrew Lutomirski Acked-by: Rik van Riel Cc: Minchan Kim Cc: KOSAKI Motohiro Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 215ddd6664ced067afca7eebd2d1eb83f064ff5a) Acked-by: Stefan Bader Acked-by: Leann Ogasawara Signed-off-by: Tim Gardner Signed-off-by: Andy Whitcroft --- mm/vmscan.c | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 136dc5e..4b8b37c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2381,7 +2381,6 @@ loop_again: if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), 0, 0)) { end_zone = i; - *classzone_idx = i; break; } } @@ -2458,8 +2457,11 @@ loop_again: total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) sc.may_writepage = 1; - if (zone->all_unreclaimable) + if (zone->all_unreclaimable) { + if (end_zone && end_zone == i) + end_zone--; continue; + } if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), end_zone, 0)) { @@ -2639,8 +2641,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) */ static int kswapd(void *p) { - unsigned long order; - int classzone_idx; + unsigned long order, new_order; + int classzone_idx, new_classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -2670,17 +2672,23 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - order = 0; - classzone_idx = MAX_NR_ZONES - 1; + order = new_order = 0; + classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; for ( ; ; ) { - unsigned long new_order; - int new_classzone_idx; int ret; - new_order = pgdat->kswapd_max_order; - new_classzone_idx = pgdat->classzone_idx; - pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = MAX_NR_ZONES - 1; + /* + * If the last balance_pgdat was unsuccessful it's unlikely a + * new request of a similar or harder type will succeed soon + * so consider going to sleep on the basis we reclaimed at + */ + if (classzone_idx >= new_classzone_idx && order == new_order) { + new_order = pgdat->kswapd_max_order; + new_classzone_idx = pgdat->classzone_idx; + pgdat->kswapd_max_order = 0; + pgdat->classzone_idx = pgdat->nr_zones - 1; + } + if (order < new_order || classzone_idx > new_classzone_idx) { /* * Don't sleep if someone wants a larger 'order' @@ -2693,7 +2701,7 @@ static int kswapd(void *p) order = pgdat->kswapd_max_order; classzone_idx = pgdat->classzone_idx; pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = MAX_NR_ZONES - 1; + pgdat->classzone_idx = pgdat->nr_zones - 1; } ret = try_to_freeze(); -- 1.7.10.4