@@ -36,6 +36,7 @@
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
+#include "pnfs.h"
#include "nfstrace.h"
@@ -323,10 +324,18 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
static int nfs_want_read_modify_write(struct file *file, struct page *page,
loff_t pos, unsigned len)
{
+ struct nfs_server *server = NFS_SERVER(file->f_mapping->host);
unsigned int pglen = nfs_page_length(page);
unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
unsigned int end = offset + len;
+ if (server->pnfs_curr_ld &&
+ (server->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE)) {
+ if (!PageUptodate(page))
+ return 1;
+ return 0;
+ }
+
if ((file->f_mode & FMODE_READ) && /* open for read? */
!PageUptodate(page) && /* Uptodate? */
!PagePrivate(page) && /* i/o request already? */
@@ -71,6 +71,7 @@ enum layoutdriver_policy_flags {
/* Should the pNFS client commit and return the layout upon a setattr */
PNFS_LAYOUTRET_ON_SETATTR = 1 << 0,
PNFS_LAYOUTRET_ON_ERROR = 1 << 1,
+ PNFS_READ_WHOLE_PAGE = 1 << 2,
};
struct nfs4_deviceid_node;
Like all block based filesystems, the pNFS block layout driver can't read or write at a byte granularity and thus has to perform read-modify-write cycles on writes smaller than this granularity. Add a flag so that the core NFS code always reads a whole page when starting a smaller write, so that we can do it in the place where the VFS expects it instead of doing in very deadlock prone way in the writeback handler. Note that in theory we could do less than page size reads here for disks that have a smaller sector size which are server by a server with a smaller pnfs block size. But so far that doesn't seem like a worthwhile optimization. Signed-off-by: Christoph Hellwig <hch@lst.de> --- fs/nfs/file.c | 9 +++++++++ fs/nfs/pnfs.h | 1 + 2 files changed, 10 insertions(+)