[Ocfs2-devel] [PATCH 1/2] Ocfs2: Add a mount option "coherency=*" for O_DIRECT writes.

[Tristan Ye]

Currently, default behavior of O_DIRECT writes was allowing
concurrent writing among nodes, no cluster coherency guaranteed
(no EX locks was taken), it hurts buffered reads on other nodes
by reading stale data from cache.

The new mount option introduce a chance to choose two different
behaviors for O_DIRECT writes:

    * coherency=full, as the default value, will disallow
		      concurrent O_DIRECT writes by taking
		      EX locks.

    * coherency=buffered, allow concurrent O_DIRECT writes
			  without EX lock among nodes, which
			  gains high performance at risk of
			  getting stale data on other nodes.

Signed-off-by: Tristan Ye <tristan.ye at oracle.com>
---
 Documentation/filesystems/ocfs2.txt |    7 +++++++
 fs/ocfs2/ocfs2.h                    |    3 +++
 fs/ocfs2/super.c                    |   23 +++++++++++++++++++++++
 3 files changed, 33 insertions(+), 0 deletions(-)

diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index 1f7ae14..5393e66 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -87,3 +87,10 @@ dir_resv_level=	(*)	By default, directory reservations will scale with file
 			reservations - users should rarely need to change this
 			value. If allocation reservations are turned off, this
 			option will have no effect.
+coherency=full  (*)	Disallow concurrent O_DIRECT writes, cluster inode
+			lock will be taken to force other nodes drop cache,
+			therefore full cluster coherency is guaranteed even
+			for O_DIRECT writes.
+coherency=buffered	Allow concurrent O_DIRECT writes without EX lock among
+			nodes, which gains high performance at risk of getting
+			stale data on other nodes.
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index c67003b..2b987be 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -256,6 +256,9 @@ enum ocfs2_mount_options
 						   control lists */
 	OCFS2_MOUNT_USRQUOTA = 1 << 10, /* We support user quotas */
 	OCFS2_MOUNT_GRPQUOTA = 1 << 11, /* We support group quotas */
+
+	OCFS2_MOUNT_COHERENCY_BUFFERED = 1 << 12 /* Allow concurrent O_DIRECT
+						    writes */
 };
 
 #define OCFS2_OSB_SOFT_RO			0x0001
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index fa1be1b..36ee274 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -177,6 +177,8 @@ enum {
 	Opt_noacl,
 	Opt_usrquota,
 	Opt_grpquota,
+	Opt_coherency_buffered,
+	Opt_coherency_full,
 	Opt_resv_level,
 	Opt_dir_resv_level,
 	Opt_err,
@@ -205,6 +207,8 @@ static const match_table_t tokens = {
 	{Opt_noacl, "noacl"},
 	{Opt_usrquota, "usrquota"},
 	{Opt_grpquota, "grpquota"},
+	{Opt_coherency_buffered, "coherency=buffered"},
+	{Opt_coherency_full, "coherency=full"},
 	{Opt_resv_level, "resv_level=%u"},
 	{Opt_dir_resv_level, "dir_resv_level=%u"},
 	{Opt_err, NULL}
@@ -631,6 +635,14 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
 		goto out;
 	}
 
+	if ((osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED) !=
+	    (parsed_options.mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED)) {
+		ret = -EINVAL;
+		mlog(ML_ERROR, "Cannot change cluster coherency mode on "
+		     "remount\n");
+		goto out;
+	}
+
 	/* Probably don't want this on remount; it might
 	 * mess with other nodes */
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64) &&
@@ -1438,6 +1450,12 @@ static int ocfs2_parse_options(struct super_block *sb,
 		case Opt_grpquota:
 			mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA;
 			break;
+		case Opt_coherency_buffered:
+			mopt->mount_opt |= OCFS2_MOUNT_COHERENCY_BUFFERED;
+			break;
+		case Opt_coherency_full:
+			mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED;
+			break;
 		case Opt_acl:
 			mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL;
 			mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL;
@@ -1536,6 +1554,11 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 	if (opts & OCFS2_MOUNT_GRPQUOTA)
 		seq_printf(s, ",grpquota");
 
+	if (opts & OCFS2_MOUNT_COHERENCY_BUFFERED)
+		seq_printf(s, ",coherency=buffered");
+	else
+		seq_printf(s, ",coherency=full");
+
 	if (opts & OCFS2_MOUNT_NOUSERXATTR)
 		seq_printf(s, ",nouser_xattr");
 	else
-- 
1.5.5