FEX-Emu/linux
1
0
Fork 0
mirror of https://github.com/FEX-Emu/linux.git synced 2024-12-21 08:53:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
b1c5ebb213
linux/fs/xfs/xfs_trans.h
Dave Chinner b1c5ebb213 xfs: allocate log vector buffers outside CIL context lock 
One of the problems we currently have with delayed logging is that
under serious memory pressure we can deadlock memory reclaim. THis
occurs when memory reclaim (such as run by kswapd) is reclaiming XFS
inodes and issues a log force to unpin inodes that are dirty in the
CIL.

The CIL is pushed, but this will only occur once it gets the CIL
context lock to ensure that all committing transactions are complete
and no new transactions start being committed to the CIL while the
push switches to a new context.

The deadlock occurs when the CIL context lock is held by a
committing process that is doing memory allocation for log vector
buffers, and that allocation is then blocked on memory reclaim
making progress. Memory reclaim, however, is blocked waiting for
a log force to make progress, and so we effectively deadlock at this
point.

To solve this problem, we have to move the CIL log vector buffer
allocation outside of the context lock so that memory reclaim can
always make progress when it needs to force the log. The problem
with doing this is that a CIL push can take place while we are
determining if we need to allocate a new log vector buffer for
an item and hence the current log vector may go away without
warning. That means we canot rely on the existing log vector being
present when we finally grab the context lock and so we must have a
replacement buffer ready to go at all times.

To ensure this, introduce a "shadow log vector" buffer that is
always guaranteed to be present when we gain the CIL context lock
and format the item. This shadow buffer may or may not be used
during the formatting, but if the log item does not have an existing
log vector buffer or that buffer is too small for the new
modifications, we swap it for the new shadow buffer and format
the modifications into that new log vector buffer.

The result of this is that for any object we modify more than once
in a given CIL checkpoint, we double the memory required
to track dirty regions in the log. For single modifications then
we consume the shadow log vectorwe allocate on commit, and that gets
consumed by the checkpoint. However, if we make multiple
modifications, then the second transaction commit will allocate a
shadow log vector and hence we will end up with double the memory
usage as only one of the log vectors is consumed by the CIL
checkpoint. The remaining shadow vector will be freed when th elog
item is freed.

This can probably be optimised in future - access to the shadow log
vector is serialised by the object lock (as opposited to the active
log vector, which is controlled by the CIL context lock) and so we
can probably free shadow log vector from some objects when the log
item is marked clean on removal from the AIL.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-07-22 09:52:35 +10:00

240 lines
8.5 KiB
C
Raw Blame History

/*
* Copyright (c) 2000-2002,2005 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_TRANS_H__
#define __XFS_TRANS_H__
/* kernel only transaction subsystem defines */
struct xfs_buf;
struct xfs_buftarg;
struct xfs_efd_log_item;
struct xfs_efi_log_item;
struct xfs_inode;
struct xfs_item_ops;
struct xfs_log_iovec;
struct xfs_log_item_desc;
struct xfs_mount;
struct xfs_trans;
struct xfs_trans_res;
struct xfs_dquot_acct;
struct xfs_busy_extent;
typedef struct xfs_log_item {
struct list_head li_ail; /* AIL pointers */
xfs_lsn_t li_lsn; /* last on-disk lsn */
struct xfs_log_item_desc *li_desc; /* ptr to current desc*/
struct xfs_mount *li_mountp; /* ptr to fs mount */
struct xfs_ail *li_ailp; /* ptr to AIL */
uint li_type; /* item type */
uint li_flags; /* misc flags */
struct xfs_log_item *li_bio_list; /* buffer item list */
void (*li_cb)(struct xfs_buf *,
struct xfs_log_item *);
/* buffer item iodone */
/* callback func */
const struct xfs_item_ops *li_ops; /* function list */
/* delayed logging */
struct list_head li_cil; /* CIL pointers */
struct xfs_log_vec *li_lv; /* active log vector */
struct xfs_log_vec *li_lv_shadow; /* standby vector */
xfs_lsn_t li_seq; /* CIL commit seq */
} xfs_log_item_t;
#define XFS_LI_IN_AIL 0x1
#define XFS_LI_ABORTED 0x2
#define XFS_LI_FLAGS \
{ XFS_LI_IN_AIL, "IN_AIL" }, \
{ XFS_LI_ABORTED, "ABORTED" }
struct xfs_item_ops {
void (*iop_size)(xfs_log_item_t *, int *, int *);
void (*iop_format)(xfs_log_item_t *, struct xfs_log_vec *);
void (*iop_pin)(xfs_log_item_t *);
void (*iop_unpin)(xfs_log_item_t *, int remove);
uint (*iop_push)(struct xfs_log_item *, struct list_head *);
void (*iop_unlock)(xfs_log_item_t *);
xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
};
void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
int type, const struct xfs_item_ops *ops);
/*
* Return values for the iop_push() routines.
*/
#define XFS_ITEM_SUCCESS 0
#define XFS_ITEM_PINNED 1
#define XFS_ITEM_LOCKED 2
#define XFS_ITEM_FLUSHING 3
/*
* This is the structure maintained for every active transaction.
*/
typedef struct xfs_trans {
unsigned int t_magic; /* magic number */
unsigned int t_log_res; /* amt of log space resvd */
unsigned int t_log_count; /* count for perm log res */
unsigned int t_blk_res; /* # of blocks resvd */
unsigned int t_blk_res_used; /* # of resvd blocks used */
unsigned int t_rtx_res; /* # of rt extents resvd */
unsigned int t_rtx_res_used; /* # of resvd rt extents used */
struct xlog_ticket *t_ticket; /* log mgr ticket */
xfs_lsn_t t_lsn; /* log seq num of start of
* transaction. */
xfs_lsn_t t_commit_lsn; /* log seq num of end of
* transaction. */
struct xfs_mount *t_mountp; /* ptr to fs mount struct */
struct xfs_dquot_acct *t_dqinfo; /* acctg info for dquots */
unsigned int t_flags; /* misc flags */
int64_t t_icount_delta; /* superblock icount change */
int64_t t_ifree_delta; /* superblock ifree change */
int64_t t_fdblocks_delta; /* superblock fdblocks chg */
int64_t t_res_fdblocks_delta; /* on-disk only chg */
int64_t t_frextents_delta;/* superblock freextents chg*/
int64_t t_res_frextents_delta; /* on-disk only chg */
#if defined(DEBUG) || defined(XFS_WARN)
int64_t t_ag_freeblks_delta; /* debugging counter */
int64_t t_ag_flist_delta; /* debugging counter */
int64_t t_ag_btree_delta; /* debugging counter */
#endif
int64_t t_dblocks_delta;/* superblock dblocks change */
int64_t t_agcount_delta;/* superblock agcount change */
int64_t t_imaxpct_delta;/* superblock imaxpct change */
int64_t t_rextsize_delta;/* superblock rextsize chg */
int64_t t_rbmblocks_delta;/* superblock rbmblocks chg */
int64_t t_rblocks_delta;/* superblock rblocks change */
int64_t t_rextents_delta;/* superblocks rextents chg */
int64_t t_rextslog_delta;/* superblocks rextslog chg */
struct list_head t_items; /* log item descriptors */
struct list_head t_busy; /* list of busy extents */
unsigned long t_pflags; /* saved process flags state */
} xfs_trans_t;
/*
* XFS transaction mechanism exported interfaces that are
* actually macros.
*/
#define xfs_trans_set_sync(tp) ((tp)->t_flags |= XFS_TRANS_SYNC)
#if defined(DEBUG) || defined(XFS_WARN)
#define xfs_trans_agblocks_delta(tp, d) ((tp)->t_ag_freeblks_delta += (int64_t)d)
#define xfs_trans_agflist_delta(tp, d) ((tp)->t_ag_flist_delta += (int64_t)d)
#define xfs_trans_agbtree_delta(tp, d) ((tp)->t_ag_btree_delta += (int64_t)d)
#else
#define xfs_trans_agblocks_delta(tp, d)
#define xfs_trans_agflist_delta(tp, d)
#define xfs_trans_agbtree_delta(tp, d)
#endif
/*
* XFS transaction mechanism exported interfaces.
*/
int xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp,
uint blocks, uint rtextents, uint flags,
struct xfs_trans **tpp);
void xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
struct xfs_buf *xfs_trans_get_buf_map(struct xfs_trans *tp,
struct xfs_buftarg *target,
struct xfs_buf_map *map, int nmaps,
uint flags);
static inline struct xfs_buf *
xfs_trans_get_buf(
struct xfs_trans *tp,
struct xfs_buftarg *target,
xfs_daddr_t blkno,
int numblks,
uint flags)
{
DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
return xfs_trans_get_buf_map(tp, target, &map, 1, flags);
}
int xfs_trans_read_buf_map(struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_buftarg *target,
struct xfs_buf_map *map, int nmaps,
xfs_buf_flags_t flags,
struct xfs_buf **bpp,
const struct xfs_buf_ops *ops);
static inline int
xfs_trans_read_buf(
struct xfs_mount *mp,
struct xfs_trans *tp,
struct xfs_buftarg *target,
xfs_daddr_t blkno,
int numblks,
xfs_buf_flags_t flags,
struct xfs_buf **bpp,
const struct xfs_buf_ops *ops)
{
DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
return xfs_trans_read_buf_map(mp, tp, target, &map, 1,
flags, bpp, ops);
}
struct xfs_buf *xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int);
void xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_bjoin(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_bhold(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_binval(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint);
void xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int);
void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint);
void xfs_trans_log_buf(xfs_trans_t *, struct xfs_buf *, uint, uint);
void xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint);
struct xfs_efi_log_item *xfs_trans_get_efi(xfs_trans_t *, uint);
void xfs_trans_log_efi_extent(xfs_trans_t *,
struct xfs_efi_log_item *,
xfs_fsblock_t,
xfs_extlen_t);
struct xfs_efd_log_item *xfs_trans_get_efd(xfs_trans_t *,
struct xfs_efi_log_item *,
uint);
int xfs_trans_free_extent(struct xfs_trans *,
struct xfs_efd_log_item *, xfs_fsblock_t,
xfs_extlen_t);
int xfs_trans_commit(struct xfs_trans *);
int __xfs_trans_roll(struct xfs_trans **, struct xfs_inode *, int *);
int xfs_trans_roll(struct xfs_trans **, struct xfs_inode *);
void xfs_trans_cancel(xfs_trans_t *);
int xfs_trans_ail_init(struct xfs_mount *);
void xfs_trans_ail_destroy(struct xfs_mount *);
void xfs_trans_buf_set_type(struct xfs_trans *, struct xfs_buf *,
enum xfs_blft);
void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
struct xfs_buf *src_bp);
extern kmem_zone_t *xfs_trans_zone;
extern kmem_zone_t *xfs_log_item_desc_zone;
#endif /* __XFS_TRANS_H__ */
Reference in New Issue View Git Blame Copy Permalink