linux-stable/fs/xfs/xfs_dquot.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

164 lines
5 KiB
C

/*
* 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_DQUOT_H__
#define __XFS_DQUOT_H__
/*
* Dquots are structures that hold quota information about a user or a group,
* much like inodes are for files. In fact, dquots share many characteristics
* with inodes. However, dquots can also be a centralized resource, relative
* to a collection of inodes. In this respect, dquots share some characteristics
* of the superblock.
* XFS dquots exploit both those in its algorithms. They make every attempt
* to not be a bottleneck when quotas are on and have minimal impact, if any,
* when quotas are off.
*/
struct xfs_mount;
struct xfs_trans;
/*
* The incore dquot structure
*/
typedef struct xfs_dquot {
uint dq_flags; /* various flags (XFS_DQ_*) */
struct list_head q_lru; /* global free list of dquots */
struct xfs_mount*q_mount; /* filesystem this relates to */
struct xfs_trans*q_transp; /* trans this belongs to currently */
uint q_nrefs; /* # active refs from inodes */
xfs_daddr_t q_blkno; /* blkno of dquot buffer */
int q_bufoffset; /* off of dq in buffer (# dquots) */
xfs_fileoff_t q_fileoffset; /* offset in quotas file */
struct xfs_dquot*q_gdquot; /* group dquot, hint only */
xfs_disk_dquot_t q_core; /* actual usage & quotas */
xfs_dq_logitem_t q_logitem; /* dquot log item */
xfs_qcnt_t q_res_bcount; /* total regular nblks used+reserved */
xfs_qcnt_t q_res_icount; /* total inos allocd+reserved */
xfs_qcnt_t q_res_rtbcount;/* total realtime blks used+reserved */
struct mutex q_qlock; /* quota lock */
struct completion q_flush; /* flush completion queue */
atomic_t q_pincount; /* dquot pin count */
wait_queue_head_t q_pinwait; /* dquot pinning wait queue */
} xfs_dquot_t;
/*
* Lock hierarchy for q_qlock:
* XFS_QLOCK_NORMAL is the implicit default,
* XFS_QLOCK_NESTED is the dquot with the higher id in xfs_dqlock2
*/
enum {
XFS_QLOCK_NORMAL = 0,
XFS_QLOCK_NESTED,
};
/*
* Manage the q_flush completion queue embedded in the dquot. This completion
* queue synchronizes processes attempting to flush the in-core dquot back to
* disk.
*/
static inline void xfs_dqflock(xfs_dquot_t *dqp)
{
wait_for_completion(&dqp->q_flush);
}
static inline int xfs_dqflock_nowait(xfs_dquot_t *dqp)
{
return try_wait_for_completion(&dqp->q_flush);
}
static inline void xfs_dqfunlock(xfs_dquot_t *dqp)
{
complete(&dqp->q_flush);
}
static inline int xfs_dqlock_nowait(struct xfs_dquot *dqp)
{
return mutex_trylock(&dqp->q_qlock);
}
static inline void xfs_dqlock(struct xfs_dquot *dqp)
{
mutex_lock(&dqp->q_qlock);
}
static inline void xfs_dqunlock(struct xfs_dquot *dqp)
{
mutex_unlock(&dqp->q_qlock);
}
static inline int xfs_this_quota_on(struct xfs_mount *mp, int type)
{
switch (type & XFS_DQ_ALLTYPES) {
case XFS_DQ_USER:
return XFS_IS_UQUOTA_ON(mp);
case XFS_DQ_GROUP:
case XFS_DQ_PROJ:
return XFS_IS_OQUOTA_ON(mp);
default:
return 0;
}
}
static inline xfs_dquot_t *xfs_inode_dquot(struct xfs_inode *ip, int type)
{
switch (type & XFS_DQ_ALLTYPES) {
case XFS_DQ_USER:
return ip->i_udquot;
case XFS_DQ_GROUP:
case XFS_DQ_PROJ:
return ip->i_gdquot;
default:
return NULL;
}
}
#define XFS_DQ_IS_LOCKED(dqp) (mutex_is_locked(&((dqp)->q_qlock)))
#define XFS_DQ_IS_DIRTY(dqp) ((dqp)->dq_flags & XFS_DQ_DIRTY)
#define XFS_QM_ISUDQ(dqp) ((dqp)->dq_flags & XFS_DQ_USER)
#define XFS_QM_ISPDQ(dqp) ((dqp)->dq_flags & XFS_DQ_PROJ)
#define XFS_QM_ISGDQ(dqp) ((dqp)->dq_flags & XFS_DQ_GROUP)
#define XFS_DQ_TO_QINF(dqp) ((dqp)->q_mount->m_quotainfo)
#define XFS_DQ_TO_QIP(dqp) (XFS_QM_ISUDQ(dqp) ? \
XFS_DQ_TO_QINF(dqp)->qi_uquotaip : \
XFS_DQ_TO_QINF(dqp)->qi_gquotaip)
extern int xfs_qm_dqread(struct xfs_mount *, xfs_dqid_t, uint,
uint, struct xfs_dquot **);
extern void xfs_qm_dqdestroy(xfs_dquot_t *);
extern int xfs_qm_dqflush(struct xfs_dquot *, struct xfs_buf **);
extern void xfs_qm_dqunpin_wait(xfs_dquot_t *);
extern void xfs_qm_adjust_dqtimers(xfs_mount_t *,
xfs_disk_dquot_t *);
extern void xfs_qm_adjust_dqlimits(xfs_mount_t *,
xfs_disk_dquot_t *);
extern int xfs_qm_dqget(xfs_mount_t *, xfs_inode_t *,
xfs_dqid_t, uint, uint, xfs_dquot_t **);
extern void xfs_qm_dqput(xfs_dquot_t *);
extern void xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *);
static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
{
xfs_dqlock(dqp);
dqp->q_nrefs++;
xfs_dqunlock(dqp);
return dqp;
}
#endif /* __XFS_DQUOT_H__ */