Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754620Ab0LILS1 (ORCPT ); Thu, 9 Dec 2010 06:18:27 -0500 Received: from gir.skynet.ie ([193.1.99.77]:47696 "EHLO gir.skynet.ie" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753859Ab0LILSY (ORCPT ); Thu, 9 Dec 2010 06:18:24 -0500 From: Mel Gorman To: Simon Kirby Cc: KOSAKI Motohiro , Shaohua Li , Dave Hansen , Johannes Weiner , Andrew Morton , linux-mm , linux-kernel , Mel Gorman Subject: [PATCH 6/6] mm: kswapd: Use the classzone idx that kswapd was using for sleeping_prematurely() Date: Thu, 9 Dec 2010 11:18:20 +0000 Message-Id: <1291893500-12342-7-git-send-email-mel@csn.ul.ie> X-Mailer: git-send-email 1.7.1 In-Reply-To: <1291893500-12342-1-git-send-email-mel@csn.ul.ie> References: <1291893500-12342-1-git-send-email-mel@csn.ul.ie> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4240 Lines: 120 When kswapd is woken up for a high-order allocation, it takes account of the highest usable zone by the caller (the classzone idx). During allocation, this index is used to select the lowmem_reserve[] that should be applied to the watermark calculation in zone_watermark_ok(). When balancing a node, kswapd considers the highest unbalanced zone to be the classzone index. This will always be at least be the callers classzone_idx and can be higher. However, sleeping_prematurely() always considers the lowest zone (e.g. ZONE_DMA) to be the classzone index. This means that sleeping_prematurely() can consider a zone to be balanced that is unusable by the allocation request that originally woke kswapd. This patch changes sleeping_prematurely() to use a classzone_idx matching the value it used in balance_pgdat(). Signed-off-by: Mel Gorman --- mm/vmscan.c | 19 +++++++++++-------- 1 files changed, 11 insertions(+), 8 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index d7b0a3c..e25b3ac 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2132,7 +2132,8 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced) } /* is kswapd sleeping prematurely? */ -static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) +static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, + int classzone_idx) { int i; unsigned long balanced = 0; @@ -2140,7 +2141,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) /* If a direct reclaimer woke kswapd within HZ/10, it's premature */ if (remaining) - return 1; + return true; /* Check the watermark levels */ for (i = 0; i < pgdat->nr_zones; i++) { @@ -2161,7 +2162,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) } if (!zone_watermark_ok(zone, order, high_wmark_pages(zone), - 0, 0)) + classzone_idx, 0)) all_zones_ok = false; else balanced += zone->present_pages; @@ -2199,7 +2200,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining) * of pages is balanced across the zones. */ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, - int classzone_idx) + int *classzone_idx) { int all_zones_ok; unsigned long balanced; @@ -2262,6 +2263,7 @@ loop_again: if (!zone_watermark_ok(zone, order, high_wmark_pages(zone), 0, 0)) { end_zone = i; + *classzone_idx = i; break; } } @@ -2346,7 +2348,7 @@ loop_again: * spectulatively avoid congestion waits */ zone_clear_flag(zone, ZONE_CONGESTED); - if (i <= classzone_idx) + if (i <= *classzone_idx) balanced += zone->present_pages; } @@ -2441,6 +2443,7 @@ out: * if another caller entered the allocator slow path while kswapd * was awake, order will remain at the higher level */ + *classzone_idx = end_zone; return order; } @@ -2514,7 +2517,7 @@ static int kswapd(void *p) long remaining = 0; /* Try to sleep for a short interval */ - if (!sleeping_prematurely(pgdat, order, remaining)) { + if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { remaining = schedule_timeout(HZ/10); finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); @@ -2525,7 +2528,7 @@ static int kswapd(void *p) * premature sleep. If not, then go fully * to sleep until explicitly woken up */ - if (!sleeping_prematurely(pgdat, order, remaining)) { + if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); schedule(); } else { @@ -2553,7 +2556,7 @@ static int kswapd(void *p) */ if (!ret) { trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - order = balance_pgdat(pgdat, order, classzone_idx); + order = balance_pgdat(pgdat, order, &classzone_idx); } } return 0; -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/