linux/fs/xfs/xfs_mount.h
Dave Chinner ab23a77687 xfs: per-cpu deferred inode inactivation queues
Move inode inactivation to background work contexts so that it no
longer runs in the context that releases the final reference to an
inode. This will allow process work that ends up blocking on
inactivation to continue doing work while the filesytem processes
the inactivation in the background.

A typical demonstration of this is unlinking an inode with lots of
extents. The extents are removed during inactivation, so this blocks
the process that unlinked the inode from the directory structure. By
moving the inactivation to the background process, the userspace
applicaiton can keep working (e.g. unlinking the next inode in the
directory) while the inactivation work on the previous inode is
done by a different CPU.

The implementation of the queue is relatively simple. We use a
per-cpu lockless linked list (llist) to queue inodes for
inactivation without requiring serialisation mechanisms, and a work
item to allow the queue to be processed by a CPU bound worker
thread. We also keep a count of the queue depth so that we can
trigger work after a number of deferred inactivations have been
queued.

The use of a bound workqueue with a single work depth allows the
workqueue to run one work item per CPU. We queue the work item on
the CPU we are currently running on, and so this essentially gives
us affine per-cpu worker threads for the per-cpu queues. THis
maintains the effective CPU affinity that occurs within XFS at the
AG level due to all objects in a directory being local to an AG.
Hence inactivation work tends to run on the same CPU that last
accessed all the objects that inactivation accesses and this
maintains hot CPU caches for unlink workloads.

A depth of 32 inodes was chosen to match the number of inodes in an
inode cluster buffer. This hopefully allows sequential
allocation/unlink behaviours to defering inactivation of all the
inodes in a single cluster buffer at a time, further helping
maintain hot CPU and buffer cache accesses while running
inactivations.

A hard per-cpu queue throttle of 256 inode has been set to avoid
runaway queuing when inodes that take a long to time inactivate are
being processed. For example, when unlinking inodes with large
numbers of extents that can take a lot of processing to free.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
[djwong: tweak comments and tracepoints, convert opflags to state bits]
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2021-08-06 11:05:39 -07:00

373 lines
13 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_MOUNT_H__
#define __XFS_MOUNT_H__
struct xlog;
struct xfs_inode;
struct xfs_mru_cache;
struct xfs_ail;
struct xfs_quotainfo;
struct xfs_da_geometry;
struct xfs_perag;
/* dynamic preallocation free space thresholds, 5% down to 1% */
enum {
XFS_LOWSP_1_PCNT = 0,
XFS_LOWSP_2_PCNT,
XFS_LOWSP_3_PCNT,
XFS_LOWSP_4_PCNT,
XFS_LOWSP_5_PCNT,
XFS_LOWSP_MAX,
};
/*
* Error Configuration
*
* Error classes define the subsystem the configuration belongs to.
* Error numbers define the errors that are configurable.
*/
enum {
XFS_ERR_METADATA,
XFS_ERR_CLASS_MAX,
};
enum {
XFS_ERR_DEFAULT,
XFS_ERR_EIO,
XFS_ERR_ENOSPC,
XFS_ERR_ENODEV,
XFS_ERR_ERRNO_MAX,
};
#define XFS_ERR_RETRY_FOREVER -1
/*
* Although retry_timeout is in jiffies which is normally an unsigned long,
* we limit the retry timeout to 86400 seconds, or one day. So even a
* signed 32-bit long is sufficient for a HZ value up to 24855. Making it
* signed lets us store the special "-1" value, meaning retry forever.
*/
struct xfs_error_cfg {
struct xfs_kobj kobj;
int max_retries;
long retry_timeout; /* in jiffies, -1 = infinite */
};
/*
* Per-cpu deferred inode inactivation GC lists.
*/
struct xfs_inodegc {
struct llist_head list;
struct work_struct work;
/* approximate count of inodes in the list */
unsigned int items;
};
/*
* The struct xfsmount layout is optimised to separate read-mostly variables
* from variables that are frequently modified. We put the read-mostly variables
* first, then place all the other variables at the end.
*
* Typically, read-mostly variables are those that are set at mount time and
* never changed again, or only change rarely as a result of things like sysfs
* knobs being tweaked.
*/
typedef struct xfs_mount {
struct xfs_sb m_sb; /* copy of fs superblock */
struct super_block *m_super;
struct xfs_ail *m_ail; /* fs active log item list */
struct xfs_buf *m_sb_bp; /* buffer for superblock */
char *m_rtname; /* realtime device name */
char *m_logname; /* external log device name */
struct xfs_da_geometry *m_dir_geo; /* directory block geometry */
struct xfs_da_geometry *m_attr_geo; /* attribute block geometry */
struct xlog *m_log; /* log specific stuff */
struct xfs_inode *m_rbmip; /* pointer to bitmap inode */
struct xfs_inode *m_rsumip; /* pointer to summary inode */
struct xfs_inode *m_rootip; /* pointer to root directory */
struct xfs_quotainfo *m_quotainfo; /* disk quota information */
xfs_buftarg_t *m_ddev_targp; /* saves taking the address */
xfs_buftarg_t *m_logdev_targp;/* ptr to log device */
xfs_buftarg_t *m_rtdev_targp; /* ptr to rt device */
struct list_head m_mount_list; /* global mount list */
void __percpu *m_inodegc; /* percpu inodegc structures */
/*
* Optional cache of rt summary level per bitmap block with the
* invariant that m_rsum_cache[bbno] <= the minimum i for which
* rsum[i][bbno] != 0. Reads and writes are serialized by the rsumip
* inode lock.
*/
uint8_t *m_rsum_cache;
struct xfs_mru_cache *m_filestream; /* per-mount filestream data */
struct workqueue_struct *m_buf_workqueue;
struct workqueue_struct *m_unwritten_workqueue;
struct workqueue_struct *m_cil_workqueue;
struct workqueue_struct *m_reclaim_workqueue;
struct workqueue_struct *m_sync_workqueue;
struct workqueue_struct *m_blockgc_wq;
struct workqueue_struct *m_inodegc_wq;
int m_bsize; /* fs logical block size */
uint8_t m_blkbit_log; /* blocklog + NBBY */
uint8_t m_blkbb_log; /* blocklog - BBSHIFT */
uint8_t m_agno_log; /* log #ag's */
uint8_t m_sectbb_log; /* sectlog - BBSHIFT */
uint m_blockmask; /* sb_blocksize-1 */
uint m_blockwsize; /* sb_blocksize in words */
uint m_blockwmask; /* blockwsize-1 */
uint m_alloc_mxr[2]; /* max alloc btree records */
uint m_alloc_mnr[2]; /* min alloc btree records */
uint m_bmap_dmxr[2]; /* max bmap btree records */
uint m_bmap_dmnr[2]; /* min bmap btree records */
uint m_rmap_mxr[2]; /* max rmap btree records */
uint m_rmap_mnr[2]; /* min rmap btree records */
uint m_refc_mxr[2]; /* max refc btree records */
uint m_refc_mnr[2]; /* min refc btree records */
uint m_ag_maxlevels; /* XFS_AG_MAXLEVELS */
uint m_bm_maxlevels[2]; /* XFS_BM_MAXLEVELS */
uint m_rmap_maxlevels; /* max rmap btree levels */
uint m_refc_maxlevels; /* max refcount btree level */
xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */
uint m_alloc_set_aside; /* space we can't use */
uint m_ag_max_usable; /* max space per AG */
int m_dalign; /* stripe unit */
int m_swidth; /* stripe width */
xfs_agnumber_t m_maxagi; /* highest inode alloc group */
uint m_allocsize_log;/* min write size log bytes */
uint m_allocsize_blocks; /* min write size blocks */
int m_logbufs; /* number of log buffers */
int m_logbsize; /* size of each log buffer */
uint m_rsumlevels; /* rt summary levels */
uint m_rsumsize; /* size of rt summary, bytes */
int m_fixedfsid[2]; /* unchanged for life of FS */
uint m_qflags; /* quota status flags */
uint64_t m_flags; /* global mount flags */
int64_t m_low_space[XFS_LOWSP_MAX];
struct xfs_ino_geometry m_ino_geo; /* inode geometry */
struct xfs_trans_resv m_resv; /* precomputed res values */
/* low free space thresholds */
unsigned long m_opstate; /* dynamic state flags */
bool m_always_cow;
bool m_fail_unmount;
bool m_finobt_nores; /* no per-AG finobt resv. */
bool m_update_sb; /* sb needs update in mount */
/*
* Bitsets of per-fs metadata that have been checked and/or are sick.
* Callers must hold m_sb_lock to access these two fields.
*/
uint8_t m_fs_checked;
uint8_t m_fs_sick;
/*
* Bitsets of rt metadata that have been checked and/or are sick.
* Callers must hold m_sb_lock to access this field.
*/
uint8_t m_rt_checked;
uint8_t m_rt_sick;
/*
* End of read-mostly variables. Frequently written variables and locks
* should be placed below this comment from now on. The first variable
* here is marked as cacheline aligned so they it is separated from
* the read-mostly variables.
*/
spinlock_t ____cacheline_aligned m_sb_lock; /* sb counter lock */
struct percpu_counter m_icount; /* allocated inodes counter */
struct percpu_counter m_ifree; /* free inodes counter */
struct percpu_counter m_fdblocks; /* free block counter */
/*
* Count of data device blocks reserved for delayed allocations,
* including indlen blocks. Does not include allocated CoW staging
* extents or anything related to the rt device.
*/
struct percpu_counter m_delalloc_blks;
/*
* Global count of allocation btree blocks in use across all AGs. Only
* used when perag reservation is enabled. Helps prevent block
* reservation from attempting to reserve allocation btree blocks.
*/
atomic64_t m_allocbt_blks;
struct radix_tree_root m_perag_tree; /* per-ag accounting info */
spinlock_t m_perag_lock; /* lock for m_perag_tree */
uint64_t m_resblks; /* total reserved blocks */
uint64_t m_resblks_avail;/* available reserved blocks */
uint64_t m_resblks_save; /* reserved blks @ remount,ro */
struct delayed_work m_reclaim_work; /* background inode reclaim */
struct xfs_kobj m_kobj;
struct xfs_kobj m_error_kobj;
struct xfs_kobj m_error_meta_kobj;
struct xfs_error_cfg m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX];
struct xstats m_stats; /* per-fs stats */
xfs_agnumber_t m_agfrotor; /* last ag where space found */
xfs_agnumber_t m_agirotor; /* last ag dir inode alloced */
spinlock_t m_agirotor_lock;/* .. and lock protecting it */
/*
* Workqueue item so that we can coalesce multiple inode flush attempts
* into a single flush.
*/
struct work_struct m_flush_inodes_work;
/*
* Generation of the filesysyem layout. This is incremented by each
* growfs, and used by the pNFS server to ensure the client updates
* its view of the block device once it gets a layout that might
* reference the newly added blocks. Does not need to be persistent
* as long as we only allow file system size increments, but if we
* ever support shrinks it would have to be persisted in addition
* to various other kinds of pain inflicted on the pNFS server.
*/
uint32_t m_generation;
struct mutex m_growlock; /* growfs mutex */
#ifdef DEBUG
/*
* Frequency with which errors are injected. Replaces xfs_etest; the
* value stored in here is the inverse of the frequency with which the
* error triggers. 1 = always, 2 = half the time, etc.
*/
unsigned int *m_errortag;
struct xfs_kobj m_errortag_kobj;
#endif
} xfs_mount_t;
#define M_IGEO(mp) (&(mp)->m_ino_geo)
/*
* Flags for m_flags.
*/
#define XFS_MOUNT_WSYNC (1ULL << 0) /* for nfs - all metadata ops
must be synchronous except
for space allocations */
#define XFS_MOUNT_UNMOUNTING (1ULL << 1) /* filesystem is unmounting */
#define XFS_MOUNT_WAS_CLEAN (1ULL << 3)
#define XFS_MOUNT_FS_SHUTDOWN (1ULL << 4) /* atomic stop of all filesystem
operations, typically for
disk errors in metadata */
#define XFS_MOUNT_DISCARD (1ULL << 5) /* discard unused blocks */
#define XFS_MOUNT_NOALIGN (1ULL << 7) /* turn off stripe alignment
allocations */
#define XFS_MOUNT_ATTR2 (1ULL << 8) /* allow use of attr2 format */
#define XFS_MOUNT_GRPID (1ULL << 9) /* group-ID assigned from directory */
#define XFS_MOUNT_NORECOVERY (1ULL << 10) /* no recovery - dirty fs */
#define XFS_MOUNT_ALLOCSIZE (1ULL << 12) /* specified allocation size */
#define XFS_MOUNT_SMALL_INUMS (1ULL << 14) /* user wants 32bit inodes */
#define XFS_MOUNT_32BITINODES (1ULL << 15) /* inode32 allocator active */
#define XFS_MOUNT_NOUUID (1ULL << 16) /* ignore uuid during mount */
#define XFS_MOUNT_IKEEP (1ULL << 18) /* keep empty inode clusters*/
#define XFS_MOUNT_SWALLOC (1ULL << 19) /* turn on stripe width
* allocation */
#define XFS_MOUNT_RDONLY (1ULL << 20) /* read-only fs */
#define XFS_MOUNT_DIRSYNC (1ULL << 21) /* synchronous directory ops */
#define XFS_MOUNT_LARGEIO (1ULL << 22) /* report large preferred
* I/O size in stat() */
#define XFS_MOUNT_FILESTREAMS (1ULL << 24) /* enable the filestreams
allocator */
#define XFS_MOUNT_NOATTR2 (1ULL << 25) /* disable use of attr2 format */
#define XFS_MOUNT_DAX_ALWAYS (1ULL << 26)
#define XFS_MOUNT_DAX_NEVER (1ULL << 27)
/*
* If set, inactivation worker threads will be scheduled to process queued
* inodegc work. If not, queued inodes remain in memory waiting to be
* processed.
*/
#define XFS_OPSTATE_INODEGC_ENABLED 0
#define __XFS_IS_OPSTATE(name, NAME) \
static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
{ \
return test_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \
} \
static inline bool xfs_clear_ ## name (struct xfs_mount *mp) \
{ \
return test_and_clear_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \
} \
static inline bool xfs_set_ ## name (struct xfs_mount *mp) \
{ \
return test_and_set_bit(XFS_OPSTATE_ ## NAME, &mp->m_opstate); \
}
__XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED)
#define XFS_OPSTATE_STRINGS \
{ (1UL << XFS_OPSTATE_INODEGC_ENABLED), "inodegc" }
/*
* Max and min values for mount-option defined I/O
* preallocation sizes.
*/
#define XFS_MAX_IO_LOG 30 /* 1G */
#define XFS_MIN_IO_LOG PAGE_SHIFT
#define XFS_LAST_UNMOUNT_WAS_CLEAN(mp) \
((mp)->m_flags & XFS_MOUNT_WAS_CLEAN)
#define XFS_FORCED_SHUTDOWN(mp) ((mp)->m_flags & XFS_MOUNT_FS_SHUTDOWN)
void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
int lnnum);
#define xfs_force_shutdown(m,f) \
xfs_do_force_shutdown(m, f, __FILE__, __LINE__)
#define SHUTDOWN_META_IO_ERROR 0x0001 /* write attempt to metadata failed */
#define SHUTDOWN_LOG_IO_ERROR 0x0002 /* write attempt to the log failed */
#define SHUTDOWN_FORCE_UMOUNT 0x0004 /* shutdown from a forced unmount */
#define SHUTDOWN_CORRUPT_INCORE 0x0008 /* corrupt in-memory data structures */
/*
* Flags for xfs_mountfs
*/
#define XFS_MFSI_QUIET 0x40 /* Be silent if mount errors found */
static inline xfs_agnumber_t
xfs_daddr_to_agno(struct xfs_mount *mp, xfs_daddr_t d)
{
xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d);
do_div(ld, mp->m_sb.sb_agblocks);
return (xfs_agnumber_t) ld;
}
static inline xfs_agblock_t
xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
{
xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d);
return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks);
}
int xfs_buf_hash_init(struct xfs_perag *pag);
void xfs_buf_hash_destroy(struct xfs_perag *pag);
extern void xfs_uuid_table_free(void);
extern uint64_t xfs_default_resblks(xfs_mount_t *mp);
extern int xfs_mountfs(xfs_mount_t *mp);
extern void xfs_unmountfs(xfs_mount_t *);
extern int xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta,
bool reserved);
extern int xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);
extern int xfs_readsb(xfs_mount_t *, int);
extern void xfs_freesb(xfs_mount_t *);
extern bool xfs_fs_writable(struct xfs_mount *mp, int level);
extern int xfs_sb_validate_fsb_count(struct xfs_sb *, uint64_t);
extern int xfs_dev_is_read_only(struct xfs_mount *, char *);
extern void xfs_set_low_space_thresholds(struct xfs_mount *);
int xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
xfs_off_t count_fsb);
struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
int error_class, int error);
void xfs_force_summary_recalc(struct xfs_mount *mp);
void xfs_mod_delalloc(struct xfs_mount *mp, int64_t delta);
#endif /* __XFS_MOUNT_H__ */