Currently, if zone is short on free pages, refill_inactive_zone() starts moving pages from active_list to inactive_list, rotating active_list as it goes. That is, pages from the tail of active_list are transferred to its head, thus destroying lru ordering, exactly when we need it most --- when system is low on free memory and page replacement has to be performed. This patch modifies refill_inactive_zone() so that it scans active_list without rotating it. To achieve this, special dummy page zone->scan_page is maintained for each zone. This page marks a place in the active_list reached during scanning. As an additional bonus, if memory pressure is not so big as to start swapping mapped pages (reclaim_mapped == 0 in refill_inactive_zone()), then not referenced mapped pages can be left behind zone->scan_page instead of moving them to the head of active_list. When reclaim_mapped mode is activated, zone->scan_page is reset back to the tail of active_list so that these pages can be re-scanned. include/linux/mmzone.h | 6 ++ mm/page_alloc.c | 20 +++++++ mm/vmscan.c | 134 ++++++++++++++++++++++++++++++++----------------- 3 files changed, 114 insertions(+), 46 deletions(-) diff -puN include/linux/mmzone.h~dont-rotate-active-list include/linux/mmzone.h --- bk-linux/include/linux/mmzone.h~dont-rotate-active-list 2004-11-08 15:08:20.164977040 +0300 +++ bk-linux-nikita/include/linux/mmzone.h 2004-11-08 15:08:20.175975368 +0300 @@ -210,6 +210,12 @@ struct zone { unsigned long present_pages; /* amount of memory (excluding holes) */ /* + * dummy page used as place holder during scanning of + * active_list in refill_inactive_zone() + */ + struct page *scan_page; + + /* * rarely used fields: */ char *name; diff -puN mm/page_alloc.c~dont-rotate-active-list mm/page_alloc.c --- bk-linux/mm/page_alloc.c~dont-rotate-active-list 2004-11-08 15:08:20.168976432 +0300 +++ bk-linux-nikita/mm/page_alloc.c 2004-11-08 15:08:20.178974912 +0300 @@ -1472,6 +1472,9 @@ void zone_init_free_lists(struct pglist_ memmap_init_zone((size), (nid), (zone), (start_pfn)) #endif +/* dummy pages used to scan active lists */ +static struct page scan_pages[MAX_NUMNODES][MAX_NR_ZONES]; + /* * Set up the zone data structures: * - mark all pages reserved @@ -1493,6 +1496,7 @@ static void __init free_area_init_core(s struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize; unsigned long batch; + struct page *scan_page; zone_table[NODEZONE(nid, j)] = zone; realsize = size = zones_size[j]; @@ -1552,6 +1556,22 @@ static void __init free_area_init_core(s zone->nr_scan_inactive = 0; zone->nr_active = 0; zone->nr_inactive = 0; + + /* initialize dummy page used for scanning */ + scan_page = &scan_pages[nid][j]; + zone->scan_page = scan_page; + memset(scan_page, 0, sizeof *scan_page); + scan_page->flags = + (1 << PG_locked) | + (1 << PG_error) | + (1 << PG_lru) | + (1 << PG_active) | + (1 << PG_reserved); + set_page_zone(scan_page, j); + page_cache_get(scan_page); + INIT_LIST_HEAD(&scan_page->lru); + list_add(&scan_page->lru, &zone->active_list); + if (!size) continue; diff -puN mm/vmscan.c~dont-rotate-active-list mm/vmscan.c --- bk-linux/mm/vmscan.c~dont-rotate-active-list 2004-11-08 15:08:20.172975824 +0300 +++ bk-linux-nikita/mm/vmscan.c 2004-11-08 15:08:20.179974760 +0300 @@ -647,6 +647,39 @@ done: pagevec_release(&pvec); } + +/* move pages from @page_list to the @spot, that should be somewhere on the + * @zone->active_list */ +static int +spill_on_spot(struct zone *zone, + struct list_head *page_list, struct list_head *spot, + struct pagevec *pvec) +{ + struct page *page; + int moved; + + moved = 0; + while (!list_empty(page_list)) { + page = lru_to_page(page_list); + prefetchw_prev_lru_page(page, page_list, flags); + if (TestSetPageLRU(page)) + BUG(); + BUG_ON(!PageActive(page)); + list_move(&page->lru, spot); + moved++; + if (!pagevec_add(pvec, page)) { + zone->nr_active += moved; + moved = 0; + spin_unlock_irq(&zone->lru_lock); + __pagevec_release(pvec); + spin_lock_irq(&zone->lru_lock); + } + } + return moved; +} + + + /* * This moves pages from the active list to the inactive list. * @@ -673,42 +706,17 @@ refill_inactive_zone(struct zone *zone, int nr_pages = sc->nr_to_scan; LIST_HEAD(l_hold); /* The pages which were snipped off */ LIST_HEAD(l_inactive); /* Pages to go onto the inactive_list */ - LIST_HEAD(l_active); /* Pages to go onto the active_list */ + LIST_HEAD(l_ignore); /* Pages to be returned to the active_list */ + LIST_HEAD(l_active); /* Pages to go onto the head of the + * active_list */ struct page *page; + struct page *scan; struct pagevec pvec; int reclaim_mapped = 0; long mapped_ratio; long distress; long swap_tendency; - lru_add_drain(); - pgmoved = 0; - spin_lock_irq(&zone->lru_lock); - while (pgscanned < nr_pages && !list_empty(&zone->active_list)) { - page = lru_to_page(&zone->active_list); - prefetchw_prev_lru_page(page, &zone->active_list, flags); - if (!TestClearPageLRU(page)) - BUG(); - list_del(&page->lru); - if (get_page_testone(page)) { - /* - * It was already free! release_pages() or put_page() - * are about to remove it from the LRU and free it. So - * put the refcount back and put the page back on the - * LRU - */ - __put_page(page); - SetPageLRU(page); - list_add(&page->lru, &zone->active_list); - } else { - list_add(&page->lru, &l_hold); - pgmoved++; - } - pgscanned++; - } - zone->nr_active -= pgmoved; - spin_unlock_irq(&zone->lru_lock); - /* * `distress' is a measure of how much trouble we're having reclaiming * pages. 0 -> no problems. 100 -> great trouble. @@ -740,14 +748,62 @@ refill_inactive_zone(struct zone *zone, if (swap_tendency >= 100) reclaim_mapped = 1; + scan = zone->scan_page; + lru_add_drain(); + pgmoved = 0; + spin_lock_irq(&zone->lru_lock); + if (reclaim_mapped) { + /* + * When scanning active_list with !reclaim_mapped mapped + * inactive pages are left behind zone->scan_page. If zone is + * switched to reclaim_mapped mode reset zone->scan_page to + * the end of inactive list so that inactive mapped pages are + * re-scanned. + */ + list_move_tail(&scan->lru, &zone->active_list); + } + while (nr_pages && zone->active_list.prev != zone->active_list.next) { + /* + * if head of active list reached---wrap to the tail + */ + if (scan->lru.prev == &zone->active_list) + list_move_tail(&scan->lru, &zone->active_list); + page = lru_to_page(&scan->lru); + prefetchw_prev_lru_page(page, &zone->active_list, flags); + if (!TestClearPageLRU(page)) + BUG(); + list_del(&page->lru); + if (get_page_testone(page)) { + /* + * It was already free! release_pages() or put_page() + * are about to remove it from the LRU and free it. So + * put the refcount back and put the page back on the + * LRU + */ + __put_page(page); + SetPageLRU(page); + list_add(&page->lru, &zone->active_list); + } else { + list_add(&page->lru, &l_hold); + pgmoved++; + } + nr_pages--; + } + zone->nr_active -= pgmoved; + spin_unlock_irq(&zone->lru_lock); + while (!list_empty(&l_hold)) { page = lru_to_page(&l_hold); list_del(&page->lru); + /* + * probably it would be useful to transfer dirty bit from pte + * to the @page here. + */ if (page_mapped(page)) { if (!reclaim_mapped || (total_swap_pages == 0 && PageAnon(page)) || page_referenced(page, 0)) { - list_add(&page->lru, &l_active); + list_add(&page->lru, &l_ignore); continue; } } @@ -786,23 +842,9 @@ refill_inactive_zone(struct zone *zone, spin_lock_irq(&zone->lru_lock); } - pgmoved = 0; - while (!list_empty(&l_active)) { - page = lru_to_page(&l_active); - prefetchw_prev_lru_page(page, &l_active, flags); - if (TestSetPageLRU(page)) - BUG(); - BUG_ON(!PageActive(page)); - list_move(&page->lru, &zone->active_list); - pgmoved++; - if (!pagevec_add(&pvec, page)) { + pgmoved = spill_on_spot(zone, &l_active, &zone->active_list, &pvec); zone->nr_active += pgmoved; - pgmoved = 0; - spin_unlock_irq(&zone->lru_lock); - __pagevec_release(&pvec); - spin_lock_irq(&zone->lru_lock); - } - } + pgmoved = spill_on_spot(zone, &l_ignore, &scan->lru, &pvec); zone->nr_active += pgmoved; spin_unlock_irq(&zone->lru_lock); pagevec_release(&pvec); _