On Tue, Jun 11, 2013 at 07:09:05AM -0400, Jeff Layton wrote:
> Currently, the hashing that the locking code uses to add these values
> to the blocked_hash is simply calculated using fl_owner field. That's
> valid in most cases except for server-side lockd, which validates the
> owner of a lock based on fl_owner and fl_pid.
>
> In the case where you have a small number of NFS clients doing a lot
> of locking between different processes, you could end up with all
> the blocked requests sitting in a very small number of hash buckets.
>
> Add a new lm_owner_key operation to the lock_manager_operations that
> will generate an unsigned long to use as the key in the hashtable.
> That function is only implemented for server-side lockd, and simply
> XORs the fl_owner and fl_pid.
Like I've said I think we should look into defining a lock_owner struct
that lockd can allocate as necessary so that the lock code can just do a
pointer comparison on struct lock_owner *'s. But maybe that doesn't
work out and in any case it can be future work, so looks fine, ACK.
--b.
>
> Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
> ---
> Documentation/filesystems/Locking | 18 +++++++++++-------
> fs/lockd/svclock.c | 12 ++++++++++++
> fs/locks.c | 12 ++++++++++--
> include/linux/fs.h | 1 +
> 4 files changed, 34 insertions(+), 9 deletions(-)
>
> diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
> index 13f91ab..ee351ac 100644
> --- a/Documentation/filesystems/Locking
> +++ b/Documentation/filesystems/Locking
> @@ -351,6 +351,7 @@ fl_release_private: maybe no
> ----------------------- lock_manager_operations ---------------------------
> prototypes:
> int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
> + unsigned long (*lm_owner_key)(struct file_lock *);
> void (*lm_notify)(struct file_lock *); /* unblock callback */
> int (*lm_grant)(struct file_lock *, struct file_lock *, int);
> void (*lm_break)(struct file_lock *); /* break_lease callback */
> @@ -360,18 +361,21 @@ locking rules:
>
> inode->i_lock file_lock_lock may block
> lm_compare_owner: yes maybe no
> +lm_owner_key yes yes no
> lm_notify: yes no no
> lm_grant: no no no
> lm_break: yes no no
> lm_change yes no no
>
> - ->lm_compare_owner is generally called with *an* inode->i_lock
> -held. It may not be the i_lock of the inode for either file_lock being
> -compared! This is the case with deadlock detection, since the code has
> -to chase down the owners of locks that may be entirely unrelated to the
> -one on which the lock is being acquired. For deadlock detection however,
> -the file_lock_lock is also held. The locks primarily ensure that neither
> -file_lock disappear out from under you while doing the comparison.
> + ->lm_compare_owner and ->lm_owner_key are generally called with
> +*an* inode->i_lock held. It may not be the i_lock of the inode
> +associated with either file_lock argument! This is the case with deadlock
> +detection, since the code has to chase down the owners of locks that may
> +be entirely unrelated to the one on which the lock is being acquired.
> +For deadlock detection however, the file_lock_lock is also held. The
> +fact that these locks are held ensures that the file_locks do not
> +disappear out from under you while doing the comparison or generating an
> +owner key.
>
> --------------------------- buffer_head -----------------------------------
> prototypes:
> diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
> index e703318..ce2cdab 100644
> --- a/fs/lockd/svclock.c
> +++ b/fs/lockd/svclock.c
> @@ -744,8 +744,20 @@ static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2)
> return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid;
> }
>
> +/*
> + * Since NLM uses two "keys" for tracking locks, we need to hash them down
> + * to one for the blocked_hash. Here, we're just xor'ing the host address
> + * with the pid in order to create a key value for picking a hash bucket.
> + */
> +static unsigned long
> +nlmsvc_owner_key(struct file_lock *fl)
> +{
> + return (unsigned long)fl->fl_owner ^ (unsigned long)fl->fl_pid;
> +}
> +
> const struct lock_manager_operations nlmsvc_lock_operations = {
> .lm_compare_owner = nlmsvc_same_owner,
> + .lm_owner_key = nlmsvc_owner_key,
> .lm_notify = nlmsvc_notify_blocked,
> .lm_grant = nlmsvc_grant_deferred,
> };
> diff --git a/fs/locks.c b/fs/locks.c
> index 76fb7af..11e7784 100644
> --- a/fs/locks.c
> +++ b/fs/locks.c
> @@ -481,11 +481,19 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
> return fl1->fl_owner == fl2->fl_owner;
> }
>
> +static unsigned long
> +posix_owner_key(struct file_lock *fl)
> +{
> + if (fl->fl_lmops && fl->fl_lmops->lm_owner_key)
> + return fl->fl_lmops->lm_owner_key(fl);
> + return (unsigned long)fl->fl_owner;
> +}
> +
> /* Remove a blocker or lock from one of the global lists */
> static inline void
> locks_insert_global_blocked(struct file_lock *waiter)
> {
> - hash_add(blocked_hash, &waiter->fl_link, (unsigned long)waiter->fl_owner);
> + hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter));
> }
>
> static inline void
> @@ -739,7 +747,7 @@ static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl)
> {
> struct file_lock *fl;
>
> - hash_for_each_possible(blocked_hash, fl, fl_link, (unsigned long)block_fl->fl_owner) {
> + hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) {
> if (posix_same_owner(fl, block_fl))
> return fl->fl_next;
> }
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 3b340f7..232a345 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -908,6 +908,7 @@ struct file_lock_operations {
>
> struct lock_manager_operations {
> int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
> + unsigned long (*lm_owner_key)(struct file_lock *);
> void (*lm_notify)(struct file_lock *); /* unblock callback */
> int (*lm_grant)(struct file_lock *, struct file_lock *, int);
> void (*lm_break)(struct file_lock *);
> --
> 1.7.1
>
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
