From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933143AbcFISHh (ORCPT ); Thu, 9 Jun 2016 14:07:37 -0400 Received: from outbound-smtp05.blacknight.com ([81.17.249.38]:59810 "EHLO outbound-smtp05.blacknight.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932220AbcFISHb (ORCPT ); Thu, 9 Jun 2016 14:07:31 -0400 From: Mel Gorman To: Andrew Morton , Linux-MM Cc: Rik van Riel , Vlastimil Babka , Johannes Weiner , LKML , Mel Gorman Subject: [PATCH 15/27] mm, page_alloc: Consider dirtyable memory in terms of nodes Date: Thu, 9 Jun 2016 19:04:31 +0100 Message-Id: <1465495483-11855-16-git-send-email-mgorman@techsingularity.net> X-Mailer: git-send-email 2.6.4 In-Reply-To: <1465495483-11855-1-git-send-email-mgorman@techsingularity.net> References: <1465495483-11855-1-git-send-email-mgorman@techsingularity.net> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Historically dirty pages were spread among zones but now that LRUs are per-node it is more appropriate to consider dirty pages in a node. Signed-off-by: Mel Gorman Signed-off-by: Johannes Weiner --- include/linux/mmzone.h | 12 +++--- include/linux/writeback.h | 2 +- mm/page-writeback.c | 94 ++++++++++++++++++++++++----------------------- mm/page_alloc.c | 26 ++++++------- 4 files changed, 67 insertions(+), 67 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 19a7adf0a734..5de2fc2dd0e6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -358,12 +358,6 @@ struct zone { struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; - /* - * This is a per-zone reserve of pages that are not available - * to userspace allocations. - */ - unsigned long totalreserve_pages; - #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. @@ -682,6 +676,12 @@ typedef struct pglist_data { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; #endif + /* + * This is a per-node reserve of pages that are not available + * to userspace allocations. + */ + unsigned long totalreserve_pages; + /* Write-intensive fields used from the page allocator */ ZONE_PADDING(_pad1_) spinlock_t lru_lock; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d0b5ca5d4e08..44b4422ae57f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long data); static inline void laptop_sync_completion(void) { } #endif void throttle_vm_writeout(gfp_t gfp_mask); -bool zone_dirty_ok(struct zone *zone); +bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3ddfa0b48436..4db3be44bb1d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -267,26 +267,35 @@ static void wb_min_max_ratio(struct bdi_writeback *wb, */ /** - * zone_dirtyable_memory - number of dirtyable pages in a zone - * @zone: the zone + * node_dirtyable_memory - number of dirtyable pages in a node + * @pgdat: the node * - * Returns the zone's number of pages potentially available for dirty - * page cache. This is the base value for the per-zone dirty limits. + * Returns the node's number of pages potentially available for dirty + * page cache. This is the base value for the per-node dirty limits. */ -static unsigned long zone_dirtyable_memory(struct zone *zone) +static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { - unsigned long nr_pages; + unsigned long nr_pages = 0; + int z; + + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + nr_pages += zone_page_state(zone, NR_FREE_PAGES); + } - nr_pages = zone_page_state(zone, NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ - nr_pages -= min(nr_pages, zone->totalreserve_pages); + nr_pages -= min(nr_pages, pgdat->totalreserve_pages); - nr_pages += node_page_state(zone->zone_pgdat, NR_INACTIVE_FILE); - nr_pages += node_page_state(zone->zone_pgdat, NR_ACTIVE_FILE); + nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); + nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } @@ -294,29 +303,13 @@ static unsigned long zone_dirtyable_memory(struct zone *zone) static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM - int node; unsigned long x = 0; - int i; - - for_each_node_state(node, N_HIGH_MEMORY) { - for (i = 0; i < MAX_NR_ZONES; i++) { - struct zone *z = &NODE_DATA(node)->node_zones[i]; - if (is_highmem(z)) - x += zone_dirtyable_memory(z); - } - } /* - * Unreclaimable memory (kernel memory or anonymous memory - * without swap) can bring down the dirtyable pages below - * the zone's dirty balance reserve and the above calculation - * will underflow. However we still want to add in nodes - * which are below threshold (negative values) to get a more - * accurate calculation but make sure that the total never - * underflows. + * LRU lists are per-node so there is no fast and accurate means of + * calculating dirtyable memory in the highmem zone. */ - if ((long)x < 0) - x = 0; + x = totalhigh_pages; /* * Make sure that the number of highmem pages is never larger @@ -442,23 +435,23 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) } /** - * zone_dirty_limit - maximum number of dirty pages allowed in a zone - * @zone: the zone + * node_dirty_limit - maximum number of dirty pages allowed in a node + * @pgdat: the node * - * Returns the maximum number of dirty pages allowed in a zone, based - * on the zone's dirtyable memory. + * Returns the maximum number of dirty pages allowed in a node, based + * on the node's dirtyable memory. */ -static unsigned long zone_dirty_limit(struct zone *zone) +static unsigned long node_dirty_limit(struct pglist_data *pgdat) { - unsigned long zone_memory = zone_dirtyable_memory(zone); + unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * - zone_memory / global_dirtyable_memory(); + node_memory / global_dirtyable_memory(); else - dirty = vm_dirty_ratio * zone_memory / 100; + dirty = vm_dirty_ratio * node_memory / 100; if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) dirty += dirty / 4; @@ -467,19 +460,30 @@ static unsigned long zone_dirty_limit(struct zone *zone) } /** - * zone_dirty_ok - tells whether a zone is within its dirty limits - * @zone: the zone to check + * node_dirty_ok - tells whether a node is within its dirty limits + * @pgdat: the node to check * - * Returns %true when the dirty pages in @zone are within the zone's + * Returns %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ -bool zone_dirty_ok(struct zone *zone) +bool node_dirty_ok(struct pglist_data *pgdat) { - unsigned long limit = zone_dirty_limit(zone); + int z; + unsigned long limit = node_dirty_limit(pgdat); + unsigned long nr_pages = 0; + + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + nr_pages += zone_page_state(zone, NR_FILE_DIRTY); + nr_pages += zone_page_state(zone, NR_UNSTABLE_NFS); + nr_pages += zone_page_state(zone, NR_WRITEBACK); + } - return zone_page_state(zone, NR_FILE_DIRTY) + - zone_page_state(zone, NR_UNSTABLE_NFS) + - zone_page_state(zone, NR_WRITEBACK) <= limit; + return nr_pages <= limit; } int dirty_background_ratio_handler(struct ctl_table *table, int write, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fc5bad895732..37e7b909ba48 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2917,31 +2917,24 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, } /* * When allocating a page cache page for writing, we - * want to get it from a zone that is within its dirty - * limit, such that no single zone holds more than its + * want to get it from a node that is within its dirty + * limit, such that no single node holds more than its * proportional share of globally allowed dirty pages. - * The dirty limits take into account the zone's + * The dirty limits take into account the node's * lowmem reserves and high watermark so that kswapd * should be able to balance it without having to * write pages from its LRU list. * - * This may look like it could increase pressure on - * lower zones by failing allocations in higher zones - * before they are full. But the pages that do spill - * over are limited as the lower zones are protected - * by this very same mechanism. It should not become - * a practical burden to them. - * * XXX: For now, allow allocations to potentially - * exceed the per-zone dirty limit in the slowpath + * exceed the per-node dirty limit in the slowpath * (spread_dirty_pages unset) before going into reclaim, * which is important when on a NUMA setup the allowed - * zones are together not big enough to reach the + * nodes are together not big enough to reach the * global limit. The proper fix for these situations - * will require awareness of zones in the + * will require awareness of nodes in the * dirty-throttling and the flusher threads. */ - if (ac->spread_dirty_pages && !zone_dirty_ok(zone)) + if (ac->spread_dirty_pages && !node_dirty_ok(zone->zone_pgdat)) continue; mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; @@ -6701,6 +6694,9 @@ static void calculate_totalreserve_pages(void) enum zone_type i, j; for_each_online_pgdat(pgdat) { + + pgdat->totalreserve_pages = 0; + for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; long max = 0; @@ -6717,7 +6713,7 @@ static void calculate_totalreserve_pages(void) if (max > zone->managed_pages) max = zone->managed_pages; - zone->totalreserve_pages = max; + pgdat->totalreserve_pages += max; reserve_pages += max; } -- 2.6.4