Skip to contentSkip to conversation

nfs: add 'noalignwrite' option for lock-less 'lost writes' prevention

PATCH In review Dan Aloni 3 participants 4 messages Jun 27, 2024 – Jul 11, 2024

Subsystems (2)
lore
Share & tools
lore

Dan Aloni

author
#0 lore raw

PATCH 1/1 nfs: add 'noalignwrite' option for lock-less 'lost writes' prevention

There are some applications that write to predefined non-overlapping file offsets from multiple clients and therefore don't need to rely on file locking. However, if these applications want non-aligned offsets and sizes they need to either use locks or risk data corruption, as the NFS client defaults to extending writes to whole pages.

This commit adds a new mount option noalignwrite, which allows to turn that off and avoid the need of locking, as long as these applications don't overlap on offsets.

---
 fs/nfs/fs_context.c       | 8 ++++++++
 fs/nfs/super.c            | 3 +++
 fs/nfs/write.c            | 3 +++
 include/linux/nfs_fs_sb.h | 1 +
 4 files changed, 15 insertions(+)
fs/nfs/fs_context.c +8 -0
index 6c9f3f6645dd..7e000d782e28 100644
@@ -49,6 +49,7 @@ enum nfs_param {
 	Opt_bsize,
 	Opt_clientaddr,
 	Opt_cto,
+	Opt_alignwrite,
 	Opt_fg,
 	Opt_fscache,
 	Opt_fscache_flag,
@@ -149,6 +150,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_u32   ("bsize",		Opt_bsize),
 	fsparam_string("clientaddr",	Opt_clientaddr),
 	fsparam_flag_no("cto",		Opt_cto),
+	fsparam_flag_no("alignwrite",	Opt_alignwrite),
 	fsparam_flag  ("fg",		Opt_fg),
 	fsparam_flag_no("fsc",		Opt_fscache_flag),
 	fsparam_string("fsc",		Opt_fscache),
@@ -592,6 +594,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		else
 			ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY;
 		break;
+	case Opt_alignwrite:
+		if (result.negated)
+			ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE;
+		else
+			ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE;
+		break;
 	case Opt_ac:
 		if (result.negated)
 			ctx->flags |= NFS_MOUNT_NOAC;
fs/nfs/super.c +3 -0
index cbbd4866b0b7..1382ae19bba4 100644
@@ -549,6 +549,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	else
 		seq_puts(m, ",local_lock=posix");
 
+	if (nfss->flags & NFS_MOUNT_NO_ALIGNWRITE)
+		seq_puts(m, ",noalignwrite");
+
 	if (nfss->flags & NFS_MOUNT_WRITE_EAGER) {
 		if (nfss->flags & NFS_MOUNT_WRITE_WAIT)
 			seq_puts(m, ",write=wait");
fs/nfs/write.c +3 -0
index 2329cbb0e446..cfe8061bf005 100644
@@ -1315,7 +1315,10 @@ static int nfs_can_extend_write(struct file *file, struct folio *folio,
 	struct file_lock_context *flctx = locks_inode_context(inode);
 	struct file_lock *fl;
 	int ret;
+	unsigned int mntflags = NFS_SERVER(inode)->flags;
 
+	if (mntflags & NFS_MOUNT_NO_ALIGNWRITE)
+		return 0;
 	if (file->f_flags & O_DSYNC)
 		return 0;
 	if (!nfs_folio_write_uptodate(folio, pagelen))
include/linux/nfs_fs_sb.h +1 -0
index 92de074e63b9..4d28b4a328a7 100644
@@ -157,6 +157,7 @@ struct nfs_server {
 #define NFS_MOUNT_WRITE_WAIT		0x02000000
 #define NFS_MOUNT_TRUNK_DISCOVERY	0x04000000
 #define NFS_MOUNT_SHUTDOWN			0x08000000
+#define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
 
 	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
Signature · 1 line
2.39.3
maintainer Reviewed-by on v1 1/1
#1 lore raw
Quoted 97 lines · Dan Aloni

There are some applications that write to predefined non-overlapping file offsets from multiple clients and therefore don't need to rely on
file locking. However, if these applications want non-aligned offsets and sizes they need to either use locks or risk data corruption, as the
NFS client defaults to extending writes to whole pages.

This commit adds a new mount option noalignwrite, which allows to turn
that off and avoid the need of locking, as long as these applications don't overlap on offsets.

---
 fs/nfs/fs_context.c       | 8 ++++++++
 fs/nfs/super.c            | 3 +++
 fs/nfs/write.c            | 3 +++
 include/linux/nfs_fs_sb.h | 1 +

 4 files changed, 15 insertions(+)
fs/nfs/fs_context.c +2 -0
index 6c9f3f6645dd..7e000d782e28 100644
@@ -49,6 +49,7 @@ enum nfs_param {
  	Opt_bsize,
  	Opt_clientaddr,
  	Opt_cto,
+	Opt_alignwrite,
  	Opt_fg,
  	Opt_fscache,
  	Opt_fscache_flag,
@@ -149,6 +150,7 @@ static const struct fs_parameter_spec
 nfs_fs_parameters[] = {
  	fsparam_u32   ("bsize",		Opt_bsize),
  	fsparam_string("clientaddr",	Opt_clientaddr),
  	fsparam_flag_no("cto",		Opt_cto),
+	fsparam_flag_no("alignwrite",	Opt_alignwrite),
  	fsparam_flag  ("fg",		Opt_fg),
  	fsparam_flag_no("fsc",		Opt_fscache_flag),

  fsparam_string("fsc", Opt_fscache),

fs/nfs/fs_context.c +0 -0
@@ -592,6 +594,12 @@ static int nfs_fs_context_parse_param(struct
 fs_context *fc,

  else
  ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY; break;

fs/nfs/fs_context.c +6 -0
+	case Opt_alignwrite:
+		if (result.negated)
+			ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE;
+		else
+			ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE;
+		break;

  case Opt_ac:
  if (result.negated) ctx->flags |= NFS_MOUNT_NOAC;

fs/nfs/super.c +0 -0
index cbbd4866b0b7..1382ae19bba4 100644
@@ -549,6 +549,9 @@ static void nfs_show_mount_options(struct
 seq_file *m, struct nfs_server *nfss,

  else
  seq_puts(m, ",local_lock=posix");

fs/nfs/super.c +3 -0
+	if (nfss->flags & NFS_MOUNT_NO_ALIGNWRITE)
+		seq_puts(m, ",noalignwrite");
+

  if (nfss->flags & NFS_MOUNT_WRITE_EAGER) { if (nfss->flags & NFS_MOUNT_WRITE_WAIT) seq_puts(m, ",write=wait");

fs/nfs/write.c +0 -0
index 2329cbb0e446..cfe8061bf005 100644
@@ -1315,7 +1315,10 @@ static int nfs_can_extend_write(struct file
 *file, struct folio *folio,

  struct file_lock_context *flctx =
locks_inode_context(inode);
  struct file_lock *fl;
  int ret;

fs/nfs/write.c +1 -0
+	unsigned int mntflags = NFS_SERVER(inode)->flags;

fs/nfs/write.c +2 -0
+	if (mntflags & NFS_MOUNT_NO_ALIGNWRITE)
+		return 0;

  if (file->f_flags & O_DSYNC)
  return 0;
  if (!nfs_folio_write_uptodate(folio, pagelen))

include/linux/nfs_fs_sb.h +1 -0
index 92de074e63b9..4d28b4a328a7 100644
@@ -157,6 +157,7 @@ struct nfs_server {
  #define NFS_MOUNT_WRITE_WAIT		0x02000000
  #define NFS_MOUNT_TRUNK_DISCOVERY	0x04000000
  #define NFS_MOUNT_SHUTDOWN			0x08000000
+#define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
Quoted 5 lines


  unsigned int fattr_valid; /* Valid attributes
*/
  unsigned int caps; /* server
capabilities */

While I hate that we need a new mount option for this, I do understand the need. I do wonder if we'd be better served by a new fadvise64() flag or something. Either way, this would probably be needed in the interim, so...

Reviewed-by on v1 1/1
#2 lore raw
In reply to Dan Aloni
Quoted 11 lines · Dan Aloni

There are some applications that write to predefined non-overlapping file offsets from multiple clients and therefore don't need to rely on file locking. However, if these applications want non-aligned offsets and sizes they need to either use locks or risk data corruption, as the NFS client defaults to extending writes to whole pages.

This commit adds a new mount option noalignwrite, which allows to turn that off and avoid the need of locking, as long as these applications don't overlap on offsets.

The new name seems a better choice.
I'm also on Christoph's camp that having this behavior be the default makes sense given that we have large folios.

Trond, Anna,
What are your thoughts on this?

author
#3 lore raw
Quoted 19 lines · Sagi Grimberg
Quoted 11 lines · Dan Aloni

There are some applications that write to predefined non-overlapping file offsets from multiple clients and therefore don't need to rely on file locking. However, if these applications want non-aligned offsets and sizes they need to either use locks or risk data corruption, as the NFS client defaults to extending writes to whole pages.

This commit adds a new mount option noalignwrite, which allows to turn that off and avoid the need of locking, as long as these applications don't overlap on offsets.

The new name seems a better choice.
I'm also on Christoph's camp that having this behavior be the default makes sense given that we have large folios.

Quoted 5 lines

Trond, Anna,
What are your thoughts on this?

Pinging. Do we need to do anything further? I can prepare the nfs-utils patch too.

Signature · 1 line
Dan Aloni