From ec8acf20afb8534ed511f6613dd2226b9e301010 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 22 Feb 2013 16:34:38 -0800 Subject: swap: add per-partition lock for swapfile swap_lock is heavily contended when I test swap to 3 fast SSD (even slightly slower than swap to 2 such SSD). The main contention comes from swap_info_get(). This patch tries to fix the gap with adding a new per-partition lock. Global data like nr_swapfiles, total_swap_pages, least_priority and swap_list are still protected by swap_lock. nr_swap_pages is an atomic now, it can be changed without swap_lock. In theory, it's possible get_swap_page() finds no swap pages but actually there are free swap pages. But sounds not a big problem. Accessing partition specific data (like scan_swap_map and so on) is only protected by swap_info_struct.lock. Changing swap_info_struct.flags need hold swap_lock and swap_info_struct.lock, because scan_scan_map() will check it. read the flags is ok with either the locks hold. If both swap_lock and swap_info_struct.lock must be hold, we always hold the former first to avoid deadlock. swap_entry_free() can change swap_list. To delete that code, we add a new highest_priority_index. Whenever get_swap_page() is called, we check it. If it's valid, we use it. It's a pity get_swap_page() still holds swap_lock(). But in practice, swap_lock() isn't heavily contended in my test with this patch (or I can say there are other much more heavier bottlenecks like TLB flush). And BTW, looks get_swap_page() doesn't really need the lock. We never free swap_info[] and we check SWAP_WRITEOK flag. The only risk without the lock is we could swapout to some low priority swap, but we can quickly recover after several rounds of swap, so sounds not a big deal to me. But I'd prefer to fix this if it's a real problem. "swap: make each swap partition have one address_space" improved the swapout speed from 1.7G/s to 2G/s. This patch further improves the speed to 2.3G/s, so around 15% improvement. It's a multi-process test, so TLB flush isn't the biggest bottleneck before the patches. [arnd@arndb.de: fix it for nommu] [hughd@google.com: add missing unlock] [minchan@kernel.org: get rid of lockdep whinge on sys_swapon] Signed-off-by: Shaohua Li Cc: Hugh Dickins Cc: Rik van Riel Cc: Minchan Kim Cc: Greg Kroah-Hartman Cc: Seth Jennings Cc: Konrad Rzeszutek Wilk Cc: Xiao Guangrong Cc: Dan Magenheimer Cc: Stephen Rothwell Signed-off-by: Arnd Bergmann Signed-off-by: Hugh Dickins Signed-off-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index 235c039892ee..a3e22d357e91 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -202,6 +202,18 @@ struct swap_info_struct { unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ #endif + spinlock_t lock; /* + * protect map scan related fields like + * swap_map, lowest_bit, highest_bit, + * inuse_pages, cluster_next, + * cluster_nr, lowest_alloc and + * highest_alloc. other fields are only + * changed at swapon/swapoff, so are + * protected by swap_lock. changing + * flags need hold this lock and + * swap_lock. If both locks need hold, + * hold swap_lock first. + */ }; struct swap_list_t { @@ -209,9 +221,6 @@ struct swap_list_t { int next; /* swapfile to be used next */ }; -/* Swap 50% full? Release swapcache more aggressively.. */ -#define vm_swap_full() (nr_swap_pages*2 < total_swap_pages) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; @@ -347,8 +356,20 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); /* linux/mm/swapfile.c */ -extern long nr_swap_pages; +extern atomic_long_t nr_swap_pages; extern long total_swap_pages; + +/* Swap 50% full? Release swapcache more aggressively.. */ +static inline bool vm_swap_full(void) +{ + return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; +} + +static inline long get_nr_swap_pages(void) +{ + return atomic_long_read(&nr_swap_pages); +} + extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); extern swp_entry_t get_swap_page_of_type(int); @@ -381,9 +402,10 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) #else /* CONFIG_SWAP */ -#define nr_swap_pages 0L +#define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL +#define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) -- cgit v1.2.3