From: Huang Ying <ying.huang@xxxxxxxxx> Subject: mm, swap: use offset of swap entry as key of swap cache This patch is to improve the performance of swap cache operations when the type of the swap device is not 0. Originally, the whole swap entry value is used as the key of the swap cache, even though there is one radix tree for each swap device. If the type of the swap device is not 0, the height of the radix tree of the swap cache will be increased unnecessary, especially on 64bit architecture. For example, for a 1GB swap device on the x86_64 architecture, the height of the radix tree of the swap cache is 11. But if the offset of the swap entry is used as the key of the swap cache, the height of the radix tree of the swap cache is 4. The increased height causes unnecessary radix tree descending and increased cache footprint. This patch reduces the height of the radix tree of the swap cache via using the offset of the swap entry instead of the whole swap entry value as the key of the swap cache. In 32 processes sequential swap out test case on a Xeon E5 v3 system with RAM disk as swap, the lock contention for the spinlock of the swap cache is reduced from 20.15% to 12.19%, when the type of the swap device is 1. Use the whole swap entry as key, perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list: 10.37, perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_node_memcg: 9.78, Use the swap offset as key, perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list: 6.25, perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_node_memcg: 5.94, Link: http://lkml.kernel.org/r/1473270649-27229-1-git-send-email-ying.huang@xxxxxxxxx Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx> Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> Cc: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx> Cc: Minchan Kim <minchan@xxxxxxxxxx> Cc: Aaron Lu <aaron.lu@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/mm.h | 8 ++++---- mm/memcontrol.c | 5 +++-- mm/mincore.c | 5 +++-- mm/swap_state.c | 8 ++++---- mm/swapfile.c | 4 ++-- 5 files changed, 16 insertions(+), 14 deletions(-) diff -puN include/linux/mm.h~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache include/linux/mm.h --- a/include/linux/mm.h~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache +++ a/include/linux/mm.h @@ -1048,19 +1048,19 @@ struct address_space *page_file_mapping( return page->mapping; } +extern pgoff_t __page_file_index(struct page *page); + /* * Return the pagecache index of the passed page. Regular pagecache pages - * use ->index whereas swapcache pages use ->private + * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) - return page_private(page); + return __page_file_index(page); return page->index; } -extern pgoff_t __page_file_index(struct page *page); - /* * Return the file index of the page. Regular pagecache pages use ->index * whereas swapcache pages use swp_offset(->private) diff -puN mm/memcontrol.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache mm/memcontrol.c --- a/mm/memcontrol.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache +++ a/mm/memcontrol.c @@ -4408,7 +4408,7 @@ static struct page *mc_handle_swap_pte(s * Because lookup_swap_cache() updates some statistics counter, * we call find_get_page() with swapper_space directly. */ - page = find_get_page(swap_address_space(ent), ent.val); + page = find_get_page(swap_address_space(ent), swp_offset(ent)); if (do_memsw_account()) entry->val = ent.val; @@ -4446,7 +4446,8 @@ static struct page *mc_handle_file_pte(s swp_entry_t swp = radix_to_swp_entry(page); if (do_memsw_account()) *entry = swp; - page = find_get_page(swap_address_space(swp), swp.val); + page = find_get_page(swap_address_space(swp), + swp_offset(swp)); } } else page = find_get_page(mapping, pgoff); diff -puN mm/mincore.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache mm/mincore.c --- a/mm/mincore.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache +++ a/mm/mincore.c @@ -66,7 +66,8 @@ static unsigned char mincore_page(struct */ if (radix_tree_exceptional_entry(page)) { swp_entry_t swp = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swp), swp.val); + page = find_get_page(swap_address_space(swp), + swp_offset(swp)); } } else page = find_get_page(mapping, pgoff); @@ -150,7 +151,7 @@ static int mincore_pte_range(pmd_t *pmd, } else { #ifdef CONFIG_SWAP *vec = mincore_page(swap_address_space(entry), - entry.val); + swp_offset(entry)); #else WARN_ON(1); *vec = 1; diff -puN mm/swap_state.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache mm/swap_state.c --- a/mm/swap_state.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache +++ a/mm/swap_state.c @@ -94,7 +94,7 @@ int __add_to_swap_cache(struct page *pag address_space = swap_address_space(entry); spin_lock_irq(&address_space->tree_lock); error = radix_tree_insert(&address_space->page_tree, - entry.val, page); + swp_offset(entry), page); if (likely(!error)) { address_space->nrpages++; __inc_node_page_state(page, NR_FILE_PAGES); @@ -145,7 +145,7 @@ void __delete_from_swap_cache(struct pag entry.val = page_private(page); address_space = swap_address_space(entry); - radix_tree_delete(&address_space->page_tree, page_private(page)); + radix_tree_delete(&address_space->page_tree, swp_offset(entry)); set_page_private(page, 0); ClearPageSwapCache(page); address_space->nrpages--; @@ -283,7 +283,7 @@ struct page * lookup_swap_cache(swp_entr { struct page *page; - page = find_get_page(swap_address_space(entry), entry.val); + page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (page) { INC_CACHE_INFO(find_success); @@ -310,7 +310,7 @@ struct page *__read_swap_cache_async(swp * called after lookup_swap_cache() failed, re-calling * that would confuse statistics. */ - found_page = find_get_page(swapper_space, entry.val); + found_page = find_get_page(swapper_space, swp_offset(entry)); if (found_page) break; diff -puN mm/swapfile.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache mm/swapfile.c --- a/mm/swapfile.c~mm-swap-use-offset-of-swap-entry-as-key-of-swap-cache +++ a/mm/swapfile.c @@ -105,7 +105,7 @@ __try_to_reclaim_swap(struct swap_info_s struct page *page; int ret = 0; - page = find_get_page(swap_address_space(entry), entry.val); + page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (!page) return 0; /* @@ -1005,7 +1005,7 @@ int free_swap_and_cache(swp_entry_t entr if (p) { if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) { page = find_get_page(swap_address_space(entry), - entry.val); + swp_offset(entry)); if (page && !trylock_page(page)) { put_page(page); page = NULL; _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html