leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
fe2429b096
linux/fs/xfs/xfs_buf.h
Christoph Hellwig 43ff2122e6 xfs: on-stack delayed write buffer lists 
Queue delwri buffers on a local on-stack list instead of a per-buftarg one,
and write back the buffers per-process instead of by waking up xfsbufd.

This is now easily doable given that we have very few places left that write
delwri buffers:

 - log recovery:
	Only done at mount time, and already forcing out the buffers
	synchronously using xfs_flush_buftarg

 - quotacheck:
	Same story.

 - dquot reclaim:
	Writes out dirty dquots on the LRU under memory pressure.  We might
	want to look into doing more of this via xfsaild, but it's already
	more optimal than the synchronous inode reclaim that writes each
	buffer synchronously.

 - xfsaild:
	This is the main beneficiary of the change.  By keeping a local list
	of buffers to write we reduce latency of writing out buffers, and
	more importably we can remove all the delwri list promotions which
	were hitting the buffer cache hard under sustained metadata loads.

The implementation is very straight forward - xfs_buf_delwri_queue now gets
a new list_head pointer that it adds the delwri buffers to, and all callers
need to eventually submit the list using xfs_buf_delwi_submit or
xfs_buf_delwi_submit_nowait.  Buffers that already are on a delwri list are
skipped in xfs_buf_delwri_queue, assuming they already are on another delwri
list.  The biggest change to pass down the buffer list was done to the AIL
pushing. Now that we operate on buffers the trylock, push and pushbuf log
item methods are merged into a single push routine, which tries to lock the
item, and if possible add the buffer that needs writeback to the buffer list.
This leads to much simpler code than the previous split but requires the
individual IOP_PUSH instances to unlock and reacquire the AIL around calls
to blocking routines.

Given that xfsailds now also handle writing out buffers, the conditions for
log forcing and the sleep times needed some small changes.  The most
important one is that we consider an AIL busy as long we still have buffers
to push, and the other one is that we do increment the pushed LSN for
buffers that are under flushing at this moment, but still count them towards
the stuck items for restart purposes.  Without this we could hammer on stuck
items without ever forcing the log and not make progress under heavy random
delete workloads on fast flash storage devices.

[ Dave Chinner:
	- rebase on previous patches.
	- improved comments for XBF_DELWRI_Q handling
	- fix XBF_ASYNC handling in queue submission (test 106 failure)
	- rename delwri submit function buffer list parameters for clarity
	- xfs_efd_item_push() should return XFS_ITEM_PINNED ]

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
2012-05-14 16:20:31 -05:00

280 lines
9.7 KiB
C
Raw Blame History

/*
* Copyright (c) 2000-2005 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_BUF_H__
#define __XFS_BUF_H__
#include <linux/list.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/uio.h>
/*
* Base types
*/
#define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL))
#define xfs_buf_ctob(pp) ((pp) * PAGE_CACHE_SIZE)
#define xfs_buf_btoc(dd) (((dd) + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT)
#define xfs_buf_btoct(dd) ((dd) >> PAGE_CACHE_SHIFT)
#define xfs_buf_poff(aa) ((aa) & ~PAGE_CACHE_MASK)
typedef enum {
XBRW_READ = 1, /* transfer into target memory */
XBRW_WRITE = 2, /* transfer from target memory */
XBRW_ZERO = 3, /* Zero target memory */
} xfs_buf_rw_t;
#define XBF_READ (1 << 0) /* buffer intended for reading from device */
#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */
#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */
#define XBF_MAPPED (1 << 3) /* buffer mapped (b_addr valid) */
#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */
#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */
#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */
/* I/O hints for the BIO layer */
#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */
#define XBF_FUA (1 << 11)/* force cache write through mode */
#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */
/* flags used only as arguments to access routines */
#define XBF_LOCK (1 << 15)/* lock requested */
#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */
#define XBF_DONT_BLOCK (1 << 17)/* do not block in current thread */
/* flags used only internally */
#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */
#define _XBF_KMEM (1 << 21)/* backed by heap memory */
#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */
typedef unsigned int xfs_buf_flags_t;
#define XFS_BUF_FLAGS \
{ XBF_READ, "READ" }, \
{ XBF_WRITE, "WRITE" }, \
{ XBF_READ_AHEAD, "READ_AHEAD" }, \
{ XBF_MAPPED, "MAPPED" }, \
{ XBF_ASYNC, "ASYNC" }, \
{ XBF_DONE, "DONE" }, \
{ XBF_STALE, "STALE" }, \
{ XBF_SYNCIO, "SYNCIO" }, \
{ XBF_FUA, "FUA" }, \
{ XBF_FLUSH, "FLUSH" }, \
{ XBF_LOCK, "LOCK" }, /* should never be set */\
{ XBF_TRYLOCK, "TRYLOCK" }, /* ditto */\
{ XBF_DONT_BLOCK, "DONT_BLOCK" }, /* ditto */\
{ _XBF_PAGES, "PAGES" }, \
{ _XBF_KMEM, "KMEM" }, \
{ _XBF_DELWRI_Q, "DELWRI_Q" }
typedef struct xfs_buftarg {
dev_t bt_dev;
struct block_device *bt_bdev;
struct backing_dev_info *bt_bdi;
struct xfs_mount *bt_mount;
unsigned int bt_bsize;
unsigned int bt_sshift;
size_t bt_smask;
/* LRU control structures */
struct shrinker bt_shrinker;
struct list_head bt_lru;
spinlock_t bt_lru_lock;
unsigned int bt_lru_nr;
} xfs_buftarg_t;
struct xfs_buf;
typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
#define XB_PAGES 2
typedef struct xfs_buf {
/*
* first cacheline holds all the fields needed for an uncontended cache
* hit to be fully processed. The semaphore straddles the cacheline
* boundary, but the counter and lock sits on the first cacheline,
* which is the only bit that is touched if we hit the semaphore
* fast-path on locking.
*/
struct rb_node b_rbnode; /* rbtree node */
xfs_off_t b_file_offset; /* offset in file */
size_t b_buffer_length;/* size of buffer in bytes */
atomic_t b_hold; /* reference count */
atomic_t b_lru_ref; /* lru reclaim ref count */
xfs_buf_flags_t b_flags; /* status flags */
struct semaphore b_sema; /* semaphore for lockables */
struct list_head b_lru; /* lru list */
wait_queue_head_t b_waiters; /* unpin waiters */
struct list_head b_list;
struct xfs_perag *b_pag; /* contains rbtree root */
xfs_buftarg_t *b_target; /* buffer target (device) */
xfs_daddr_t b_bn; /* block number for I/O */
size_t b_count_desired;/* desired transfer size */
void *b_addr; /* virtual address of buffer */
struct work_struct b_iodone_work;
xfs_buf_iodone_t b_iodone; /* I/O completion function */
struct completion b_iowait; /* queue for I/O waiters */
void *b_fspriv;
struct xfs_trans *b_transp;
struct page **b_pages; /* array of page pointers */
struct page *b_page_array[XB_PAGES]; /* inline pages */
atomic_t b_pin_count; /* pin count */
atomic_t b_io_remaining; /* #outstanding I/O requests */
unsigned int b_page_count; /* size of page array */
unsigned int b_offset; /* page offset in first page */
unsigned short b_error; /* error code on I/O */
#ifdef XFS_BUF_LOCK_TRACKING
int b_last_holder;
#endif
} xfs_buf_t;
/* Finding and Reading Buffers */
extern xfs_buf_t *_xfs_buf_find(xfs_buftarg_t *, xfs_off_t, size_t,
xfs_buf_flags_t, xfs_buf_t *);
#define xfs_incore(buftarg,blkno,len,lockit) \
_xfs_buf_find(buftarg, blkno ,len, lockit, NULL)
extern xfs_buf_t *xfs_buf_get(xfs_buftarg_t *, xfs_off_t, size_t,
xfs_buf_flags_t);
extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t,
xfs_buf_flags_t);
struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *, xfs_off_t, size_t,
xfs_buf_flags_t);
extern void xfs_buf_set_empty(struct xfs_buf *bp, size_t len);
extern xfs_buf_t *xfs_buf_get_uncached(struct xfs_buftarg *, size_t, int);
extern int xfs_buf_associate_memory(xfs_buf_t *, void *, size_t);
extern void xfs_buf_hold(xfs_buf_t *);
extern void xfs_buf_readahead(xfs_buftarg_t *, xfs_off_t, size_t);
struct xfs_buf *xfs_buf_read_uncached(struct xfs_mount *mp,
struct xfs_buftarg *target,
xfs_daddr_t daddr, size_t length, int flags);
/* Releasing Buffers */
extern void xfs_buf_free(xfs_buf_t *);
extern void xfs_buf_rele(xfs_buf_t *);
/* Locking and Unlocking Buffers */
extern int xfs_buf_trylock(xfs_buf_t *);
extern void xfs_buf_lock(xfs_buf_t *);
extern void xfs_buf_unlock(xfs_buf_t *);
#define xfs_buf_islocked(bp) \
((bp)->b_sema.count <= 0)
/* Buffer Read and Write Routines */
extern int xfs_bwrite(struct xfs_buf *bp);
extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
extern int xfs_bdstrat_cb(struct xfs_buf *);
extern void xfs_buf_ioend(xfs_buf_t *, int);
extern void xfs_buf_ioerror(xfs_buf_t *, int);
extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
extern int xfs_buf_iorequest(xfs_buf_t *);
extern int xfs_buf_iowait(xfs_buf_t *);
extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
xfs_buf_rw_t);
#define xfs_buf_zero(bp, off, len) \
xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
static inline int xfs_buf_geterror(xfs_buf_t *bp)
{
return bp ? bp->b_error : ENOMEM;
}
/* Buffer Utility Routines */
extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
/* Delayed Write Buffer Routines */
extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
extern int xfs_buf_delwri_submit(struct list_head *);
extern int xfs_buf_delwri_submit_nowait(struct list_head *);
/* Buffer Daemon Setup Routines */
extern int xfs_buf_init(void);
extern void xfs_buf_terminate(void);
#define XFS_BUF_ZEROFLAGS(bp) \
((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
void xfs_buf_stale(struct xfs_buf *bp);
#define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE)
#define XFS_BUF_ISSTALE(bp) ((bp)->b_flags & XBF_STALE)
#define XFS_BUF_DONE(bp) ((bp)->b_flags |= XBF_DONE)
#define XFS_BUF_UNDONE(bp) ((bp)->b_flags &= ~XBF_DONE)
#define XFS_BUF_ISDONE(bp) ((bp)->b_flags & XBF_DONE)
#define XFS_BUF_ASYNC(bp) ((bp)->b_flags |= XBF_ASYNC)
#define XFS_BUF_UNASYNC(bp) ((bp)->b_flags &= ~XBF_ASYNC)
#define XFS_BUF_ISASYNC(bp) ((bp)->b_flags & XBF_ASYNC)
#define XFS_BUF_READ(bp) ((bp)->b_flags |= XBF_READ)
#define XFS_BUF_UNREAD(bp) ((bp)->b_flags &= ~XBF_READ)
#define XFS_BUF_ISREAD(bp) ((bp)->b_flags & XBF_READ)
#define XFS_BUF_WRITE(bp) ((bp)->b_flags |= XBF_WRITE)
#define XFS_BUF_UNWRITE(bp) ((bp)->b_flags &= ~XBF_WRITE)
#define XFS_BUF_ISWRITE(bp) ((bp)->b_flags & XBF_WRITE)
#define XFS_BUF_ADDR(bp) ((bp)->b_bn)
#define XFS_BUF_SET_ADDR(bp, bno) ((bp)->b_bn = (xfs_daddr_t)(bno))
#define XFS_BUF_OFFSET(bp) ((bp)->b_file_offset)
#define XFS_BUF_SET_OFFSET(bp, off) ((bp)->b_file_offset = (off))
#define XFS_BUF_COUNT(bp) ((bp)->b_count_desired)
#define XFS_BUF_SET_COUNT(bp, cnt) ((bp)->b_count_desired = (cnt))
#define XFS_BUF_SIZE(bp) ((bp)->b_buffer_length)
#define XFS_BUF_SET_SIZE(bp, cnt) ((bp)->b_buffer_length = (cnt))
static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
{
atomic_set(&bp->b_lru_ref, lru_ref);
}
static inline int xfs_buf_ispinned(struct xfs_buf *bp)
{
return atomic_read(&bp->b_pin_count);
}
static inline void xfs_buf_relse(xfs_buf_t *bp)
{
xfs_buf_unlock(bp);
xfs_buf_rele(bp);
}
/*
* Handling of buftargs.
*/
extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
struct block_device *, int, const char *);
extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
extern void xfs_wait_buftarg(xfs_buftarg_t *);
extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev)
#define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev)
#endif /* __XFS_BUF_H__ */
Reference in New Issue View Git Blame Copy Permalink