diff options
| author | Shaohua Li <shli@kernel.org> | 2013-02-22 16:34:37 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-02-23 17:50:17 -0800 |
| commit | 33806f06da654092182410d974b6d3c5396ea3eb (patch) | |
| tree | 7f7da99d94481a1d4c78ebf05b410fc8ba654a39 /mm/swapfile.c | |
| parent | 9800339b5e0f0e24ab3dac349e0de80d2018832e (diff) | |
| download | linux-3.10-33806f06da654092182410d974b6d3c5396ea3eb.tar.gz linux-3.10-33806f06da654092182410d974b6d3c5396ea3eb.tar.bz2 linux-3.10-33806f06da654092182410d974b6d3c5396ea3eb.zip | |
swap: make each swap partition have one address_space
When I use several fast SSD to do swap, swapper_space.tree_lock is
heavily contended. This makes each swap partition have one
address_space to reduce the lock contention. There is an array of
address_space for swap. The swap entry type is the index to the array.
In my test with 3 SSD, this increases the swapout throughput 20%.
[akpm@linux-foundation.org: revert unneeded change to __add_to_swap_cache]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/swapfile.c')
| -rw-r--r-- | mm/swapfile.c | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c index e97a0e5aea9..e51864e6fe8 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -79,7 +79,7 @@ __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) struct page *page; int ret = 0; - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), entry.val); if (!page) return 0; /* @@ -699,7 +699,8 @@ int free_swap_and_cache(swp_entry_t entry) p = swap_info_get(entry); if (p) { if (swap_entry_free(p, entry, 1) == SWAP_HAS_CACHE) { - page = find_get_page(&swapper_space, entry.val); + page = find_get_page(swap_address_space(entry), + entry.val); if (page && !trylock_page(page)) { page_cache_release(page); page = NULL; |