summaryrefslogtreecommitdiff
path: root/include/linux/nfs_fs.h
diff options
context:
space:
mode:
authorTrond Myklebust <Trond.Myklebust@netapp.com>2006-03-20 21:44:36 +0300
committerTrond Myklebust <Trond.Myklebust@netapp.com>2006-03-20 21:44:36 +0300
commitfad61490419b3e494f300e9b2579810ef3bcda31 (patch)
tree1bca68921a83d4dc0219aa8d46c3c8e8313965c2 /include/linux/nfs_fs.h
parente17b1fc4b35399935f00a635206e183d9292fe4f (diff)
downloadlinux-fad61490419b3e494f300e9b2579810ef3bcda31.tar.xz
nfs: Use UNSTABLE + COMMIT for NFS O_DIRECT writes
Currently NFS O_DIRECT writes use FILE_SYNC so that a COMMIT is not necessary. This simplifies the internal logic, but this could be a difficult workload for some servers. Instead, let's send UNSTABLE writes, and after they all complete, send a COMMIT for the dirty range. After the COMMIT returns successfully, then do the wake_up or fire off aio_complete(). Test plan: Async direct I/O tests against Solaris (or any server that requires committed unstable writes). Reboot server during test. Based on an earlier patch by Chuck Lever <cel@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Diffstat (limited to 'include/linux/nfs_fs.h')
-rw-r--r--include/linux/nfs_fs.h1
1 files changed, 1 insertions, 0 deletions
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 423f202b881c..9f84c8a5ea43 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -422,6 +422,7 @@ void nfs_commit_free(struct nfs_write_data *p);
extern int nfs_sync_inode(struct inode *, unsigned long, unsigned int, int);
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
extern int nfs_commit_inode(struct inode *, int);
+extern void nfs_commit_release(void *wdata);
#else
static inline int
nfs_commit_inode(struct inode *inode, int how)