[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>
diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
index 2a0a9ef..2e10458 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 @@
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;