f2ebb3a921
The current mainline has copies propagated to *all* nodes, then
tears down the copies we made for nodes that do not contain
counterparts of the desired mountpoint. That sets the right
propagation graph for the copies (at teardown time we move
the slaves of removed node to a surviving peer or directly
to master), but we end up paying a fairly steep price in
useless allocations. It's fairly easy to create a situation
where N calls of mount(2) create exactly N bindings, with
O(N^2) vfsmounts allocated and freed in process.
Fortunately, it is possible to avoid those allocations/freeings.
The trick is to create copies in the right order and find which
one would've eventually become a master with the current algorithm.
It turns out to be possible in O(nodes getting propagation) time
and with no extra allocations at all.
One part is that we need to make sure that eventual master will be
created before its slaves, so we need to walk the propagation
tree in a different order - by peer groups. And iterate through
the peers before dealing with the next group.
Another thing is finding the (earlier) copy that will be a master
of one we are about to create; to do that we are (temporary) marking
the masters of mountpoints we are attaching the copies to.
Either we are in a peer of the last mountpoint we'd dealt with,
or we have the following situation: we are attaching to mountpoint M,
the last copy S_0 had been attached to M_0 and there are sequences
S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i},
S_{i} mounted on M{i} and we need to create a slave of the first S_{k}
such that M is getting propagation from M_{k}. It means that the master
of M_{k} will be among the sequence of masters of M. On the
other hand, the nearest marked node in that sequence will either
be the master of M_{k} or the master of M_{k-1} (the latter -
in the case if M_{k-1} is a slave of something M gets propagation
from, but in a wrong peer group).
So we go through the sequence of masters of M until we find
a marked one (P). Let N be the one before it. Then we go through
the sequence of masters of S_0 until we find one (say, S) mounted
on a node D that has P as master and check if D is a peer of N.
If it is, S will be the master of new copy, if not - the master of S
will be.
That's it for the hard part; the rest is fairly simple. Iterator
is in next_group(), handling of one prospective mountpoint is
propagate_one().
It seems to survive all tests and gives a noticably better performance
than the current mainline for setups that are seriously using shared
subtrees.
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
88 lines
2.6 KiB
C
88 lines
2.6 KiB
C
/*
|
|
*
|
|
* Definitions for mount interface. This describes the in the kernel build
|
|
* linkedlist with mounted filesystems.
|
|
*
|
|
* Author: Marco van Wieringen <mvw@planets.elm.net>
|
|
*
|
|
*/
|
|
#ifndef _LINUX_MOUNT_H
|
|
#define _LINUX_MOUNT_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/list.h>
|
|
#include <linux/nodemask.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/seqlock.h>
|
|
#include <linux/atomic.h>
|
|
|
|
struct super_block;
|
|
struct vfsmount;
|
|
struct dentry;
|
|
struct mnt_namespace;
|
|
|
|
#define MNT_NOSUID 0x01
|
|
#define MNT_NODEV 0x02
|
|
#define MNT_NOEXEC 0x04
|
|
#define MNT_NOATIME 0x08
|
|
#define MNT_NODIRATIME 0x10
|
|
#define MNT_RELATIME 0x20
|
|
#define MNT_READONLY 0x40 /* does the user want this to be r/o? */
|
|
|
|
#define MNT_SHRINKABLE 0x100
|
|
#define MNT_WRITE_HOLD 0x200
|
|
|
|
#define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */
|
|
#define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */
|
|
/*
|
|
* MNT_SHARED_MASK is the set of flags that should be cleared when a
|
|
* mount becomes shared. Currently, this is only the flag that says a
|
|
* mount cannot be bind mounted, since this is how we create a mount
|
|
* that shares events with another mount. If you add a new MNT_*
|
|
* flag, consider how it interacts with shared mounts.
|
|
*/
|
|
#define MNT_SHARED_MASK (MNT_UNBINDABLE)
|
|
#define MNT_PROPAGATION_MASK (MNT_SHARED | MNT_UNBINDABLE)
|
|
|
|
#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
|
|
MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED)
|
|
|
|
#define MNT_INTERNAL 0x4000
|
|
|
|
#define MNT_LOCK_READONLY 0x400000
|
|
#define MNT_LOCKED 0x800000
|
|
#define MNT_DOOMED 0x1000000
|
|
#define MNT_SYNC_UMOUNT 0x2000000
|
|
#define MNT_MARKED 0x4000000
|
|
|
|
struct vfsmount {
|
|
struct dentry *mnt_root; /* root of the mounted tree */
|
|
struct super_block *mnt_sb; /* pointer to superblock */
|
|
int mnt_flags;
|
|
};
|
|
|
|
struct file; /* forward dec */
|
|
|
|
extern int mnt_want_write(struct vfsmount *mnt);
|
|
extern int mnt_want_write_file(struct file *file);
|
|
extern int mnt_clone_write(struct vfsmount *mnt);
|
|
extern void mnt_drop_write(struct vfsmount *mnt);
|
|
extern void mnt_drop_write_file(struct file *file);
|
|
extern void mntput(struct vfsmount *mnt);
|
|
extern struct vfsmount *mntget(struct vfsmount *mnt);
|
|
extern void mnt_pin(struct vfsmount *mnt);
|
|
extern void mnt_unpin(struct vfsmount *mnt);
|
|
extern int __mnt_is_readonly(struct vfsmount *mnt);
|
|
|
|
struct file_system_type;
|
|
extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
|
|
int flags, const char *name,
|
|
void *data);
|
|
|
|
extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
|
|
extern void mark_mounts_for_expiry(struct list_head *mounts);
|
|
|
|
extern dev_t name_to_dev_t(char *name);
|
|
|
|
#endif /* _LINUX_MOUNT_H */
|