nfs4: serialize layoutcommit
Current pnfs_layoutcommit_inode can not handle parallel layoutcommit.
And as Trond suggested , there is no need for client to optimize for
parallel layoutcommit. So add NFS_INO_LAYOUTCOMMITTING flag to
mark inflight layoutcommit and serialize lalyoutcommit with it.
Also mark_inode_dirty_sync if pnfs_layoutcommit_inode fails to issue
layoutcommit.
Reported-by: Vitaliy Gusev <gusev.vitaliy@nexenta.com>
Signed-off-by: Peng Tao <peng_tao@emc.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d2ae413..b60fddf 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5950,6 +5950,7 @@
{
struct nfs4_layoutcommit_data *data = calldata;
struct pnfs_layout_segment *lseg, *tmp;
+ unsigned long *bitlock = &NFS_I(data->args.inode)->flags;
pnfs_cleanup_layoutcommit(data);
/* Matched by references in pnfs_set_layoutcommit */
@@ -5959,6 +5960,11 @@
&lseg->pls_flags))
put_lseg(lseg);
}
+
+ clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+
put_rpccred(data->cred);
kfree(data);
}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index ee73d9a..a2478bc 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1443,17 +1443,31 @@
/* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
data = kzalloc(sizeof(*data), GFP_NOFS);
if (!data) {
- mark_inode_dirty_sync(inode);
status = -ENOMEM;
goto out;
}
+ if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+ goto out_free;
+
+ if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
+ if (!sync) {
+ status = -EAGAIN;
+ goto out_free;
+ }
+ status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (status)
+ goto out_free;
+ }
+
INIT_LIST_HEAD(&data->lseg_list);
spin_lock(&inode->i_lock);
if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
+ clear_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags);
spin_unlock(&inode->i_lock);
- kfree(data);
- goto out;
+ wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING);
+ goto out_free;
}
pnfs_list_write_lseg(inode, &data->lseg_list);
@@ -1475,6 +1489,11 @@
status = nfs4_proc_layoutcommit(data, sync);
out:
+ if (status)
+ mark_inode_dirty_sync(inode);
dprintk("<-- %s status %d\n", __func__, status);
return status;
+out_free:
+ kfree(data);
+ goto out;
}
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 60a137b..ab2c634 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -229,6 +229,7 @@
#define NFS_INO_COMMIT (7) /* inode is committing unstable writes */
#define NFS_INO_PNFS_COMMIT (8) /* use pnfs code for commit */
#define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */
+#define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */
static inline struct nfs_inode *NFS_I(const struct inode *inode)
{