mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-08-05 16:54:27 +00:00
6bdcf26ade
Replace the current linear list and the indirection array for the in-core extent list with a b+tree to avoid the need for larger memory allocations for the indirection array when lots of extents are present. The current extent list implementations leads to heavy pressure on the memory allocator when modifying files with a high extent count, and can lead to high latencies because of that. The replacement is a b+tree with a few quirks. The leaf nodes directly store the extent record in two u64 values. The encoding is a little bit different from the existing in-core extent records so that the start offset and length which are required for lookups can be retreived with simple mask operations. The inner nodes store a 64-bit key containing the start offset in the first half of the node, and the pointers to the next lower level in the second half. In either case we walk the node from the beginninig to the end and do a linear search, as that is more efficient for the low number of cache lines touched during a search (2 for the inner nodes, 4 for the leaf nodes) than a binary search. We store termination markers (zero length for the leaf nodes, an otherwise impossible high bit for the inner nodes) to terminate the key list / records instead of storing a count to use the available cache lines as efficiently as possible. One quirk of the algorithm is that while we normally split a node half and half like usual btree implementations we just spill over entries added at the very end of the list to a new node on its own. This means we get a 100% fill grade for the common cases of bulk insertion when reading an inode into memory, and when only sequentially appending to a file. The downside is a slightly higher chance of splits on the first random insertions. Both insert and removal manually recurse into the lower levels, but the bulk deletion of the whole tree is still implemented as a recursive function call, although one limited by the overall depth and with very little stack usage in every iteration. For the first few extents we dynamically grow the list from a single extent to the next powers of two until we have a first full leaf block and that building the actual tree. The code started out based on the generic lib/btree.c code from Joern Engel based on earlier work from Peter Zijlstra, but has since been rewritten beyond recognition. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
189 lines
6 KiB
C
189 lines
6 KiB
C
/*
|
|
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
|
|
* All Rights Reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it would be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write the Free Software Foundation,
|
|
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
#ifndef __XFS_INODE_FORK_H__
|
|
#define __XFS_INODE_FORK_H__
|
|
|
|
struct xfs_inode_log_item;
|
|
struct xfs_dinode;
|
|
|
|
/*
|
|
* File incore extent information, present for each of data & attr forks.
|
|
*/
|
|
typedef struct xfs_ifork {
|
|
int if_bytes; /* bytes in if_u1 */
|
|
int if_real_bytes; /* bytes allocated in if_u1 */
|
|
struct xfs_btree_block *if_broot; /* file's incore btree root */
|
|
short if_broot_bytes; /* bytes allocated for root */
|
|
unsigned char if_flags; /* per-fork flags */
|
|
int if_height; /* height of the extent tree */
|
|
union {
|
|
void *if_root; /* extent tree root */
|
|
char *if_data; /* inline file data */
|
|
} if_u1;
|
|
} xfs_ifork_t;
|
|
|
|
/*
|
|
* Per-fork incore inode flags.
|
|
*/
|
|
#define XFS_IFINLINE 0x01 /* Inline data is read in */
|
|
#define XFS_IFEXTENTS 0x02 /* All extent pointers are read in */
|
|
#define XFS_IFBROOT 0x04 /* i_broot points to the bmap b-tree root */
|
|
|
|
/*
|
|
* Fork handling.
|
|
*/
|
|
|
|
#define XFS_IFORK_Q(ip) ((ip)->i_d.di_forkoff != 0)
|
|
#define XFS_IFORK_BOFF(ip) ((int)((ip)->i_d.di_forkoff << 3))
|
|
|
|
#define XFS_IFORK_PTR(ip,w) \
|
|
((w) == XFS_DATA_FORK ? \
|
|
&(ip)->i_df : \
|
|
((w) == XFS_ATTR_FORK ? \
|
|
(ip)->i_afp : \
|
|
(ip)->i_cowfp))
|
|
#define XFS_IFORK_DSIZE(ip) \
|
|
(XFS_IFORK_Q(ip) ? \
|
|
XFS_IFORK_BOFF(ip) : \
|
|
XFS_LITINO((ip)->i_mount, (ip)->i_d.di_version))
|
|
#define XFS_IFORK_ASIZE(ip) \
|
|
(XFS_IFORK_Q(ip) ? \
|
|
XFS_LITINO((ip)->i_mount, (ip)->i_d.di_version) - \
|
|
XFS_IFORK_BOFF(ip) : \
|
|
0)
|
|
#define XFS_IFORK_SIZE(ip,w) \
|
|
((w) == XFS_DATA_FORK ? \
|
|
XFS_IFORK_DSIZE(ip) : \
|
|
((w) == XFS_ATTR_FORK ? \
|
|
XFS_IFORK_ASIZE(ip) : \
|
|
0))
|
|
#define XFS_IFORK_FORMAT(ip,w) \
|
|
((w) == XFS_DATA_FORK ? \
|
|
(ip)->i_d.di_format : \
|
|
((w) == XFS_ATTR_FORK ? \
|
|
(ip)->i_d.di_aformat : \
|
|
(ip)->i_cformat))
|
|
#define XFS_IFORK_FMT_SET(ip,w,n) \
|
|
((w) == XFS_DATA_FORK ? \
|
|
((ip)->i_d.di_format = (n)) : \
|
|
((w) == XFS_ATTR_FORK ? \
|
|
((ip)->i_d.di_aformat = (n)) : \
|
|
((ip)->i_cformat = (n))))
|
|
#define XFS_IFORK_NEXTENTS(ip,w) \
|
|
((w) == XFS_DATA_FORK ? \
|
|
(ip)->i_d.di_nextents : \
|
|
((w) == XFS_ATTR_FORK ? \
|
|
(ip)->i_d.di_anextents : \
|
|
(ip)->i_cnextents))
|
|
#define XFS_IFORK_NEXT_SET(ip,w,n) \
|
|
((w) == XFS_DATA_FORK ? \
|
|
((ip)->i_d.di_nextents = (n)) : \
|
|
((w) == XFS_ATTR_FORK ? \
|
|
((ip)->i_d.di_anextents = (n)) : \
|
|
((ip)->i_cnextents = (n))))
|
|
#define XFS_IFORK_MAXEXT(ip, w) \
|
|
(XFS_IFORK_SIZE(ip, w) / sizeof(xfs_bmbt_rec_t))
|
|
|
|
struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
|
|
|
|
int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
|
|
void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
|
|
struct xfs_inode_log_item *, int);
|
|
void xfs_idestroy_fork(struct xfs_inode *, int);
|
|
void xfs_idata_realloc(struct xfs_inode *, int, int);
|
|
void xfs_iroot_realloc(struct xfs_inode *, int, int);
|
|
int xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int);
|
|
int xfs_iextents_copy(struct xfs_inode *, struct xfs_bmbt_rec *,
|
|
int);
|
|
void xfs_init_local_fork(struct xfs_inode *, int, const void *, int);
|
|
|
|
xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp);
|
|
void xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur,
|
|
xfs_extnum_t, struct xfs_bmbt_irec *, int);
|
|
void xfs_iext_remove(struct xfs_inode *, struct xfs_iext_cursor *,
|
|
int, int);
|
|
void xfs_iext_destroy(struct xfs_ifork *);
|
|
|
|
bool xfs_iext_lookup_extent(struct xfs_inode *ip,
|
|
struct xfs_ifork *ifp, xfs_fileoff_t bno,
|
|
struct xfs_iext_cursor *cur,
|
|
struct xfs_bmbt_irec *gotp);
|
|
bool xfs_iext_lookup_extent_before(struct xfs_inode *ip,
|
|
struct xfs_ifork *ifp, xfs_fileoff_t *end,
|
|
struct xfs_iext_cursor *cur,
|
|
struct xfs_bmbt_irec *gotp);
|
|
bool xfs_iext_get_extent(struct xfs_ifork *ifp,
|
|
struct xfs_iext_cursor *cur,
|
|
struct xfs_bmbt_irec *gotp);
|
|
void xfs_iext_update_extent(struct xfs_inode *ip, int state,
|
|
struct xfs_iext_cursor *cur,
|
|
struct xfs_bmbt_irec *gotp);
|
|
|
|
void xfs_iext_first(struct xfs_ifork *, struct xfs_iext_cursor *);
|
|
void xfs_iext_last(struct xfs_ifork *, struct xfs_iext_cursor *);
|
|
void xfs_iext_next(struct xfs_ifork *, struct xfs_iext_cursor *);
|
|
void xfs_iext_prev(struct xfs_ifork *, struct xfs_iext_cursor *);
|
|
|
|
static inline bool xfs_iext_next_extent(struct xfs_ifork *ifp,
|
|
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp)
|
|
{
|
|
xfs_iext_next(ifp, cur);
|
|
return xfs_iext_get_extent(ifp, cur, gotp);
|
|
}
|
|
|
|
static inline bool xfs_iext_prev_extent(struct xfs_ifork *ifp,
|
|
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp)
|
|
{
|
|
xfs_iext_prev(ifp, cur);
|
|
return xfs_iext_get_extent(ifp, cur, gotp);
|
|
}
|
|
|
|
/*
|
|
* Return the extent after cur in gotp without updating the cursor.
|
|
*/
|
|
static inline bool xfs_iext_peek_next_extent(struct xfs_ifork *ifp,
|
|
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp)
|
|
{
|
|
struct xfs_iext_cursor ncur = *cur;
|
|
|
|
xfs_iext_next(ifp, &ncur);
|
|
return xfs_iext_get_extent(ifp, &ncur, gotp);
|
|
}
|
|
|
|
/*
|
|
* Return the extent before cur in gotp without updating the cursor.
|
|
*/
|
|
static inline bool xfs_iext_peek_prev_extent(struct xfs_ifork *ifp,
|
|
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *gotp)
|
|
{
|
|
struct xfs_iext_cursor ncur = *cur;
|
|
|
|
xfs_iext_prev(ifp, &ncur);
|
|
return xfs_iext_get_extent(ifp, &ncur, gotp);
|
|
}
|
|
|
|
#define for_each_xfs_iext(ifp, ext, got) \
|
|
for (xfs_iext_first((ifp), (ext)); \
|
|
xfs_iext_get_extent((ifp), (ext), (got)); \
|
|
xfs_iext_next((ifp), (ext)))
|
|
|
|
extern struct kmem_zone *xfs_ifork_zone;
|
|
|
|
extern void xfs_ifork_init_cow(struct xfs_inode *ip);
|
|
|
|
#endif /* __XFS_INODE_FORK_H__ */
|