[XFS] On machines with more than 8 cpus, when running parallel I/O

threads, the incore superblock lock becomes the limiting factor for
buffered write throughput. Make the contended fields in the incore
superblock use per-cpu counters so that there is no global lock to limit
scalability.

SGI-PV: 946630
SGI-Modid: xfs-linux-melb:xfs-kern:25106a

Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Nathan Scott <nathans@sgi.com>

1 files changed, 2 insertions, 1 deletions

diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
index 2a0a9efb8ccb..2e1045837881 100644
--- a/fs/xfs/xfs_vfsops.c
+++ b/fs/xfs/xfs_vfsops.c
@@ -55,7 +55,7 @@
 #include "xfs_clnt.h"
 #include "xfs_fsops.h"
 
-STATIC int xfs_sync(bhv_desc_t *, int, cred_t *);
+STATIC int      xfs_sync(bhv_desc_t *, int, cred_t *);
 
 int
 xfs_init(void)
@@ -807,6 +807,7 @@ xfs_statvfs(
 
         statp->f_type = XFS_SB_MAGIC;
 
+        xfs_icsb_sync_counters_lazy(mp);
         s = XFS_SB_LOCK(mp);
         statp->f_bsize = sbp->sb_blocksize;
         lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;