Commit 9bf87482 authored by Peng Tao's avatar Peng Tao Committed by Tom Haynes

nfs41: serialize first layoutget of a file

Per RFC 5661 Errata 3208:
| A client MAY always forget its layout state and associated
| layout stateid at any time (See also section 12.5.5.1).
| In such case, the client MUST use a non-layout stateid for the next
| LAYOUTGET operation. This will signal the server that the client has
| no more layouts on the file and its respective layout state can be
| released before issuing a new layout in response to LAYOUTGET.

In order to make such a signal unique to server, client needs to serialize
all layoutgets using non-layout stateid. We implement this by serializing
layoutgets when client has no layout segments at hand.
Signed-off-by: default avatarPeng Tao <tao.peng@primarydata.com>
Signed-off-by: default avatarTom Haynes <Thomas.Haynes@primarydata.com>
parent abb9a007
...@@ -1288,6 +1288,7 @@ pnfs_update_layout(struct inode *ino, ...@@ -1288,6 +1288,7 @@ pnfs_update_layout(struct inode *ino,
struct nfs_client *clp = server->nfs_client; struct nfs_client *clp = server->nfs_client;
struct pnfs_layout_hdr *lo; struct pnfs_layout_hdr *lo;
struct pnfs_layout_segment *lseg = NULL; struct pnfs_layout_segment *lseg = NULL;
bool first;
if (!pnfs_enabled_sb(NFS_SERVER(ino))) if (!pnfs_enabled_sb(NFS_SERVER(ino)))
goto out; goto out;
...@@ -1295,6 +1296,8 @@ pnfs_update_layout(struct inode *ino, ...@@ -1295,6 +1296,8 @@ pnfs_update_layout(struct inode *ino,
if (pnfs_within_mdsthreshold(ctx, ino, iomode)) if (pnfs_within_mdsthreshold(ctx, ino, iomode))
goto out; goto out;
lookup_again:
first = false;
spin_lock(&ino->i_lock); spin_lock(&ino->i_lock);
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
if (lo == NULL) { if (lo == NULL) {
...@@ -1312,10 +1315,27 @@ pnfs_update_layout(struct inode *ino, ...@@ -1312,10 +1315,27 @@ pnfs_update_layout(struct inode *ino,
if (pnfs_layout_io_test_failed(lo, iomode)) if (pnfs_layout_io_test_failed(lo, iomode))
goto out_unlock; goto out_unlock;
/* Check to see if the layout for the given range already exists */ first = list_empty(&lo->plh_segs);
if (first) {
/* The first layoutget for the file. Need to serialize per
* RFC 5661 Errata 3208.
*/
if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
&lo->plh_flags)) {
spin_unlock(&ino->i_lock);
wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
TASK_UNINTERRUPTIBLE);
pnfs_put_layout_hdr(lo);
goto lookup_again;
}
} else {
/* Check to see if the layout for the given range
* already exists
*/
lseg = pnfs_find_lseg(lo, &arg); lseg = pnfs_find_lseg(lo, &arg);
if (lseg) if (lseg)
goto out_unlock; goto out_unlock;
}
if (pnfs_layoutgets_blocked(lo, 0)) if (pnfs_layoutgets_blocked(lo, 0))
goto out_unlock; goto out_unlock;
...@@ -1343,6 +1363,13 @@ pnfs_update_layout(struct inode *ino, ...@@ -1343,6 +1363,13 @@ pnfs_update_layout(struct inode *ino,
lseg = send_layoutget(lo, ctx, &arg, gfp_flags); lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
atomic_dec(&lo->plh_outstanding); atomic_dec(&lo->plh_outstanding);
out_put_layout_hdr: out_put_layout_hdr:
if (first) {
unsigned long *bitlock = &lo->plh_flags;
clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock);
smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET);
}
pnfs_put_layout_hdr(lo); pnfs_put_layout_hdr(lo);
out: out:
dprintk("%s: inode %s/%llu pNFS layout segment %s for " dprintk("%s: inode %s/%llu pNFS layout segment %s for "
......
...@@ -95,6 +95,7 @@ enum { ...@@ -95,6 +95,7 @@ enum {
NFS_LAYOUT_ROC, /* some lseg had roc bit set */ NFS_LAYOUT_ROC, /* some lseg had roc bit set */
NFS_LAYOUT_RETURN, /* Return this layout ASAP */ NFS_LAYOUT_RETURN, /* Return this layout ASAP */
NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */
NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */
}; };
enum layoutdriver_policy_flags { enum layoutdriver_policy_flags {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment