[XFS] Introduce two new mount options (nolargeio/largeio) to allow
filesystems to expose the filesystem stripe width in stat(2) rather than
the page cache size. This allows applications requiring high bandwidth to
easily determine the optimum I/O size for the underlying filesystem. The
default is to report the page cache size (i.e. "nolargeio").
SGI-PV: 942818
SGI-Modid: xfs-linux:xfs-kern:23830a
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Nathan Scott <nathans@sgi.com>
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index e2bf2ef..8221b11 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -181,40 +181,7 @@
vap->va_rdev = 0;
if (!(ip->i_d.di_flags & XFS_DIFLAG_REALTIME)) {
-
-#if 0
- /* Large block sizes confuse various
- * user space programs, so letting the
- * stripe size through is not a good
- * idea for now.
- */
- vap->va_blocksize = mp->m_swidth ?
- /*
- * If the underlying volume is a stripe, then
- * return the stripe width in bytes as the
- * recommended I/O size.
- */
- (mp->m_swidth << mp->m_sb.sb_blocklog) :
- /*
- * Return the largest of the preferred buffer
- * sizes since doing small I/Os into larger
- * buffers causes buffers to be decommissioned.
- * The value returned is in bytes.
- */
- (1 << (int)MAX(mp->m_readio_log,
- mp->m_writeio_log));
-
-#else
- vap->va_blocksize =
- /*
- * Return the largest of the preferred buffer
- * sizes since doing small I/Os into larger
- * buffers causes buffers to be decommissioned.
- * The value returned is in bytes.
- */
- 1 << (int)MAX(mp->m_readio_log,
- mp->m_writeio_log);
-#endif
+ vap->va_blocksize = xfs_preferred_iosize(mp);
} else {
/*