mm: don't use radix tree writeback tags for pages in swap cache

File pages use a set of radix tree tags (DIRTY, TOWRITE, WRITEBACK,
etc.) to accelerate finding the pages with a specific tag in the radix
tree during inode writeback.  But for anonymous pages in the swap cache,
there is no inode writeback.  So there is no need to find the pages with
some writeback tags in the radix tree.  It is not necessary to touch
radix tree writeback tags for pages in the swap cache.

Per Rik van Riel's suggestion, a new flag AS_NO_WRITEBACK_TAGS is
introduced for address spaces which don't need to update the writeback
tags.  The flag is set for swap caches.  It may be used for DAX file
systems, etc.

With this patch, the swap out bandwidth improved 22.3% (from ~1.2GB/s to
~1.48GBps) in the vm-scalability swap-w-seq test case with 8 processes.
The test is done on a Xeon E5 v3 system.  The swap device used is a RAM
simulated PMEM (persistent memory) device.  The improvement comes from
the reduced contention on the swap cache radix tree lock.  To test
sequential swapping out, the test case uses 8 processes, which
sequentially allocate and write to the anonymous pages until RAM and
part of the swap device is used up.

Details of comparison is as follow,

base             base+patch
---------------- --------------------------
         %stddev     %change         %stddev
             \          |                \
   2506952 ±  2%     +28.1%    3212076 ±  7%  vm-scalability.throughput
   1207402 ±  7%     +22.3%    1476578 ±  6%  vmstat.swap.so
     10.86 ± 12%     -23.4%       8.31 ± 16%  perf-profile.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list
     10.82 ± 13%     -33.1%       7.24 ± 14%  perf-profile.cycles-pp._raw_spin_lock_irqsave.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_zone_memcg
     10.36 ± 11%    -100.0%       0.00 ± -1%  perf-profile.cycles-pp._raw_spin_lock_irqsave.__test_set_page_writeback.bdev_write_page.__swap_writepage.swap_writepage
     10.52 ± 12%    -100.0%       0.00 ± -1%  perf-profile.cycles-pp._raw_spin_lock_irqsave.test_clear_page_writeback.end_page_writeback.page_endio.pmem_rw_page

Link: http://lkml.kernel.org/r/1472578089-5560-1-git-send-email-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Tejun Heo <tj@kernel.org>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 01e84436cddfec1da8b871b6343d72a2420ba070..48d9cf04337c783e9f2c85915e496603f6a5e0d0 100644 (file)
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -25,6 +25,8 @@ enum mapping_flags {
        AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */
        AS_UNEVICTABLE  = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */
        AS_EXITING      = __GFP_BITS_SHIFT + 4, /* final truncate in progress */
+       /* writeback related tags are not used */
+       AS_NO_WRITEBACK_TAGS = __GFP_BITS_SHIFT + 5,
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -64,6 +66,16 @@ static inline int mapping_exiting(struct address_space *mapping)
        return test_bit(AS_EXITING, &mapping->flags);
 }
 
+static inline void mapping_set_no_writeback_tags(struct address_space *mapping)
+{
+       set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
+}
+
+static inline int mapping_use_writeback_tags(struct address_space *mapping)
+{
+       return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
        return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5ed3381818ecd26c1187bba63308c710228e835f..439cc63ad903fb898192188367670efad4a2d1fa 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2716,7 +2716,7 @@ int test_clear_page_writeback(struct page *page)
        int ret;
 
        lock_page_memcg(page);
-       if (mapping) {
+       if (mapping && mapping_use_writeback_tags(mapping)) {
                struct inode *inode = mapping->host;
                struct backing_dev_info *bdi = inode_to_bdi(inode);
                unsigned long flags;
@@ -2759,7 +2759,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
        int ret;
 
        lock_page_memcg(page);
-       if (mapping) {
+       if (mapping && mapping_use_writeback_tags(mapping)) {
                struct inode *inode = mapping->host;
                struct backing_dev_info *bdi = inode_to_bdi(inode);
                unsigned long flags;

diff --git a/mm/swap_state.c b/mm/swap_state.c
index c8310a37be3abbcf267472f30bd0e3677c1336d4..268b8191982b245e2adb0c68d3518f173b012cb4 100644 (file)
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -37,6 +37,8 @@ struct address_space swapper_spaces[MAX_SWAPFILES] = {
                .page_tree      = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
                .i_mmap_writable = ATOMIC_INIT(0),
                .a_ops          = &swap_aops,
+               /* swap cache doesn't use writeback related tags */
+               .flags          = 1 << AS_NO_WRITEBACK_TAGS,
        }
 };