54ceac4515
The attached patch makes NFS share superblocks between mounts from the same
server and FSID over the same protocol.
It does this by creating each superblock with a false root and returning the
real root dentry in the vfsmount presented by get_sb(). The root dentry set
starts off as an anonymous dentry if we don't already have the dentry for its
inode, otherwise it simply returns the dentry we already have.
We may thus end up with several trees of dentries in the superblock, and if at
some later point one of anonymous tree roots is discovered by normal filesystem
activity to be located in another tree within the superblock, the anonymous
root is named and materialises attached to the second tree at the appropriate
point.
Why do it this way? Why not pass an extra argument to the mount() syscall to
indicate the subpath and then pathwalk from the server root to the desired
directory? You can't guarantee this will work for two reasons:
(1) The root and intervening nodes may not be accessible to the client.
With NFS2 and NFS3, for instance, mountd is called on the server to get
the filehandle for the tip of a path. mountd won't give us handles for
anything we don't have permission to access, and so we can't set up NFS
inodes for such nodes, and so can't easily set up dentries (we'd have to
have ghost inodes or something).
With this patch we don't actually create dentries until we get handles
from the server that we can use to set up their inodes, and we don't
actually bind them into the tree until we know for sure where they go.
(2) Inaccessible symbolic links.
If we're asked to mount two exports from the server, eg:
mount warthog:/warthog/aaa/xxx /mmm
mount warthog:/warthog/bbb/yyy /nnn
We may not be able to access anything nearer the root than xxx and yyy,
but we may find out later that /mmm/www/yyy, say, is actually the same
directory as the one mounted on /nnn. What we might then find out, for
example, is that /warthog/bbb was actually a symbolic link to
/warthog/aaa/xxx/www, but we can't actually determine that by talking to
the server until /warthog is made available by NFS.
This would lead to having constructed an errneous dentry tree which we
can't easily fix. We can end up with a dentry marked as a directory when
it should actually be a symlink, or we could end up with an apparently
hardlinked directory.
With this patch we need not make assumptions about the type of a dentry
for which we can't retrieve information, nor need we assume we know its
place in the grand scheme of things until we actually see that place.
This patch reduces the possibility of aliasing in the inode and page caches for
inodes that may be accessed by more than one NFS export. It also reduces the
number of superblocks required for NFS where there are many NFS exports being
used from a server (home directory server + autofs for example).
This in turn makes it simpler to do local caching of network filesystems, as it
can then be guaranteed that there won't be links from multiple inodes in
separate superblocks to the same cache file.
Obviously, cache aliasing between different levels of NFS protocol could still
be a problem, but at least that gives us another key to use when indexing the
cache.
This patch makes the following changes:
(1) The server record construction/destruction has been abstracted out into
its own set of functions to make things easier to get right. These have
been moved into fs/nfs/client.c.
All the code in fs/nfs/client.c has to do with the management of
connections to servers, and doesn't touch superblocks in any way; the
remaining code in fs/nfs/super.c has to do with VFS superblock management.
(2) The sequence of events undertaken by NFS mount is now reordered:
(a) A volume representation (struct nfs_server) is allocated.
(b) A server representation (struct nfs_client) is acquired. This may be
allocated or shared, and is keyed on server address, port and NFS
version.
(c) If allocated, the client representation is initialised. The state
member variable of nfs_client is used to prevent a race during
initialisation from two mounts.
(d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find
the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we
are given the root FH in advance.
(e) The volume FSID is probed for on the root FH.
(f) The volume representation is initialised from the FSINFO record
retrieved on the root FH.
(g) sget() is called to acquire a superblock. This may be allocated or
shared, keyed on client pointer and FSID.
(h) If allocated, the superblock is initialised.
(i) If the superblock is shared, then the new nfs_server record is
discarded.
(j) The root dentry for this mount is looked up from the root FH.
(k) The root dentry for this mount is assigned to the vfsmount.
(3) nfs_readdir_lookup() creates dentries for each of the entries readdir()
returns; this function now attaches disconnected trees from alternate
roots that happen to be discovered attached to a directory being read (in
the same way nfs_lookup() is made to do for lookup ops).
The new d_materialise_unique() function is now used to do this, thus
permitting the whole thing to be done under one set of locks, and thus
avoiding any race between mount and lookup operations on the same
directory.
(4) The client management code uses a new debug facility: NFSDBG_CLIENT which
is set by echoing 1024 to /proc/net/sunrpc/nfs_debug.
(5) Clone mounts are now called xdev mounts.
(6) Use the dentry passed to the statfs() op as the handle for retrieving fs
statistics rather than the root dentry of the superblock (which is now a
dummy).
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
147 lines
4.7 KiB
C
147 lines
4.7 KiB
C
/*
|
|
* fs/nfs/nfs4renewd.c
|
|
*
|
|
* Copyright (c) 2002 The Regents of the University of Michigan.
|
|
* All rights reserved.
|
|
*
|
|
* Kendrick Smith <kmsmith@umich.edu>
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
*
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
* 3. Neither the name of the University nor the names of its
|
|
* contributors may be used to endorse or promote products derived
|
|
* from this software without specific prior written permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
|
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
|
* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
* DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
|
|
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
|
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
|
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*
|
|
* Implementation of the NFSv4 "renew daemon", which wakes up periodically to
|
|
* send a RENEW, to keep state alive on the server. The daemon is implemented
|
|
* as an rpc_task, not a real kernel thread, so it always runs in rpciod's
|
|
* context. There is one renewd per nfs_server.
|
|
*
|
|
* TODO: If the send queue gets backlogged (e.g., if the server goes down),
|
|
* we will keep filling the queue with periodic RENEW requests. We need a
|
|
* mechanism for ensuring that if renewd successfully sends off a request,
|
|
* then it only wakes up when the request is finished. Maybe use the
|
|
* child task framework of the RPC layer?
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/smp_lock.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/sunrpc/sched.h>
|
|
#include <linux/sunrpc/clnt.h>
|
|
|
|
#include <linux/nfs.h>
|
|
#include <linux/nfs4.h>
|
|
#include <linux/nfs_fs.h>
|
|
#include "nfs4_fs.h"
|
|
#include "delegation.h"
|
|
|
|
#define NFSDBG_FACILITY NFSDBG_PROC
|
|
|
|
void
|
|
nfs4_renew_state(void *data)
|
|
{
|
|
struct nfs_client *clp = (struct nfs_client *)data;
|
|
struct rpc_cred *cred;
|
|
long lease, timeout;
|
|
unsigned long last, now;
|
|
|
|
down_read(&clp->cl_sem);
|
|
dprintk("%s: start\n", __FUNCTION__);
|
|
/* Are there any active superblocks? */
|
|
if (list_empty(&clp->cl_superblocks))
|
|
goto out;
|
|
spin_lock(&clp->cl_lock);
|
|
lease = clp->cl_lease_time;
|
|
last = clp->cl_last_renewal;
|
|
now = jiffies;
|
|
timeout = (2 * lease) / 3 + (long)last - (long)now;
|
|
/* Are we close to a lease timeout? */
|
|
if (time_after(now, last + lease/3)) {
|
|
cred = nfs4_get_renew_cred(clp);
|
|
if (cred == NULL) {
|
|
set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
|
|
spin_unlock(&clp->cl_lock);
|
|
nfs_expire_all_delegations(clp);
|
|
goto out;
|
|
}
|
|
spin_unlock(&clp->cl_lock);
|
|
/* Queue an asynchronous RENEW. */
|
|
nfs4_proc_async_renew(clp, cred);
|
|
put_rpccred(cred);
|
|
timeout = (2 * lease) / 3;
|
|
spin_lock(&clp->cl_lock);
|
|
} else
|
|
dprintk("%s: failed to call renewd. Reason: lease not expired \n",
|
|
__FUNCTION__);
|
|
if (timeout < 5 * HZ) /* safeguard */
|
|
timeout = 5 * HZ;
|
|
dprintk("%s: requeueing work. Lease period = %ld\n",
|
|
__FUNCTION__, (timeout + HZ - 1) / HZ);
|
|
cancel_delayed_work(&clp->cl_renewd);
|
|
schedule_delayed_work(&clp->cl_renewd, timeout);
|
|
spin_unlock(&clp->cl_lock);
|
|
out:
|
|
up_read(&clp->cl_sem);
|
|
dprintk("%s: done\n", __FUNCTION__);
|
|
}
|
|
|
|
/* Must be called with clp->cl_sem locked for writes */
|
|
void
|
|
nfs4_schedule_state_renewal(struct nfs_client *clp)
|
|
{
|
|
long timeout;
|
|
|
|
spin_lock(&clp->cl_lock);
|
|
timeout = (2 * clp->cl_lease_time) / 3 + (long)clp->cl_last_renewal
|
|
- (long)jiffies;
|
|
if (timeout < 5 * HZ)
|
|
timeout = 5 * HZ;
|
|
dprintk("%s: requeueing work. Lease period = %ld\n",
|
|
__FUNCTION__, (timeout + HZ - 1) / HZ);
|
|
cancel_delayed_work(&clp->cl_renewd);
|
|
schedule_delayed_work(&clp->cl_renewd, timeout);
|
|
spin_unlock(&clp->cl_lock);
|
|
}
|
|
|
|
void
|
|
nfs4_renewd_prepare_shutdown(struct nfs_server *server)
|
|
{
|
|
flush_scheduled_work();
|
|
}
|
|
|
|
void
|
|
nfs4_kill_renewd(struct nfs_client *clp)
|
|
{
|
|
down_read(&clp->cl_sem);
|
|
cancel_delayed_work(&clp->cl_renewd);
|
|
up_read(&clp->cl_sem);
|
|
flush_scheduled_work();
|
|
}
|
|
|
|
/*
|
|
* Local variables:
|
|
* c-basic-offset: 8
|
|
* End:
|
|
*/
|