xfs: replace dop_low with transaction flag

The dop_low field enables the low free space allocation mode when a
previous allocation has detected difficulty allocating blocks. It
has historically been part of the xfs_defer_ops structure, which
means if enabled, it remains enabled across a set of transactions
until the deferred operations have completed and the dfops is reset.

Now that the dfops is embedded in the transaction, we can save a bit
more space by using a transaction flag rather than a standalone
boolean. Drop the ->dop_low field and replace it with a transaction
flag that is set at the same points, carried across rolling
transactions and cleared on completion of deferred operations. This
essentially emulates the behavior of ->dop_low and so should not
change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
This commit is contained in:
Brian Foster 2018-08-01 07:20:31 -07:00 committed by Darrick J. Wong
parent ce356d6477
commit 1214f1cf66
8 changed files with 36 additions and 30 deletions

View File

@ -700,7 +700,7 @@ xfs_bmap_extents_to_btree(
if (tp->t_firstblock == NULLFSBLOCK) {
args.type = XFS_ALLOCTYPE_START_BNO;
args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
} else if (tp->t_dfops->dop_low) {
} else if (tp->t_flags & XFS_TRANS_LOWMODE) {
args.type = XFS_ALLOCTYPE_START_BNO;
args.fsbno = tp->t_firstblock;
} else {
@ -3449,7 +3449,7 @@ xfs_bmap_btalloc(
error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
if (error)
return error;
} else if (ap->tp->t_dfops->dop_low) {
} else if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
if (xfs_inode_is_filestream(ap->ip))
args.type = XFS_ALLOCTYPE_FIRST_AG;
else
@ -3484,7 +3484,7 @@ xfs_bmap_btalloc(
* is >= the stripe unit and the allocation offset is
* at the end of file.
*/
if (!ap->tp->t_dfops->dop_low && ap->aeof) {
if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) {
if (!ap->offset) {
args.alignment = stripe_align;
atype = args.type;
@ -3576,7 +3576,7 @@ xfs_bmap_btalloc(
args.total = ap->minlen;
if ((error = xfs_alloc_vextent(&args)))
return error;
ap->tp->t_dfops->dop_low = true;
ap->tp->t_flags |= XFS_TRANS_LOWMODE;
}
if (args.fsbno != NULLFSBLOCK) {
/*

View File

@ -226,7 +226,7 @@ xfs_bmbt_alloc_block(
* block allocation here and corrupt the filesystem.
*/
args.minleft = args.tp->t_blk_res;
} else if (cur->bc_tp->t_dfops->dop_low) {
} else if (cur->bc_tp->t_flags & XFS_TRANS_LOWMODE) {
args.type = XFS_ALLOCTYPE_START_BNO;
} else {
args.type = XFS_ALLOCTYPE_NEAR_BNO;
@ -253,7 +253,7 @@ xfs_bmbt_alloc_block(
error = xfs_alloc_vextent(&args);
if (error)
goto error0;
cur->bc_tp->t_dfops->dop_low = true;
cur->bc_tp->t_flags |= XFS_TRANS_LOWMODE;
}
if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
*stat = 0;

View File

@ -330,9 +330,14 @@ xfs_defer_reset(
ASSERT(!xfs_defer_has_unfinished_work(dop));
dop->dop_low = false;
memset(dop->dop_inodes, 0, sizeof(dop->dop_inodes));
memset(dop->dop_bufs, 0, sizeof(dop->dop_bufs));
/*
* Low mode state transfers across transaction rolls to mirror dfops
* lifetime. Clear it now that dfops is reset.
*/
tp->t_flags &= ~XFS_TRANS_LOWMODE;
}
/*
@ -590,7 +595,14 @@ xfs_defer_move(
memcpy(dst->dop_inodes, src->dop_inodes, sizeof(dst->dop_inodes));
memcpy(dst->dop_bufs, src->dop_bufs, sizeof(dst->dop_bufs));
dst->dop_low = src->dop_low;
/*
* Low free space mode was historically controlled by a dfops field.
* This meant that low mode state potentially carried across multiple
* transaction rolls. Transfer low mode on a dfops move to preserve
* that behavior.
*/
dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE);
xfs_defer_reset(stp);
}

View File

@ -25,17 +25,6 @@ struct xfs_defer_pending {
/*
* Header for deferred operation list.
*
* dop_low is used by the allocator to activate the lowspace algorithm -
* when free space is running low the extent allocator may choose to
* allocate an extent from an AG without leaving sufficient space for
* a btree split when inserting the new extent. In this case the allocator
* will enable the lowspace algorithm which is supposed to allow further
* allocations (such as btree splits and newroots) to allocate from
* sequential AGs. In order to avoid locking AGs out of order the lowspace
* algorithm will start searching for free space from AG 0. If the correct
* transaction reservations have been made then this algorithm will eventually
* find all the space it needs.
*/
enum xfs_defer_ops_type {
XFS_DEFER_OPS_TYPE_BMAP,

View File

@ -64,6 +64,18 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
#define XFS_TRANS_RESERVE 0x20 /* OK to use reserved data blocks */
#define XFS_TRANS_NO_WRITECOUNT 0x40 /* do not elevate SB writecount */
#define XFS_TRANS_NOFS 0x80 /* pass KM_NOFS to kmem_alloc */
/*
* LOWMODE is used by the allocator to activate the lowspace algorithm - when
* free space is running low the extent allocator may choose to allocate an
* extent from an AG without leaving sufficient space for a btree split when
* inserting the new extent. In this case the allocator will enable the
* lowspace algorithm which is supposed to allow further allocations (such as
* btree splits and newroots) to allocate from sequential AGs. In order to
* avoid locking AGs out of order the lowspace algorithm will start searching
* for free space from AG 0. If the correct transaction reservations have been
* made then this algorithm will eventually find all the space it needs.
*/
#define XFS_TRANS_LOWMODE 0x100 /* allocate in low space mode */
/*
* Field values for xfs_trans_mod_sb.

View File

@ -20,6 +20,7 @@
#include "xfs_trace.h"
#include "xfs_ag_resv.h"
#include "xfs_trans.h"
#include "xfs_shared.h"
struct xfs_fstrm_item {
struct xfs_mru_cache_elem mru;
@ -378,7 +379,7 @@ xfs_filestream_new_ag(
if (xfs_alloc_is_userdata(ap->datatype))
flags |= XFS_PICK_USERDATA;
if (ap->tp->t_dfops->dop_low)
if (ap->tp->t_flags & XFS_TRANS_LOWMODE)
flags |= XFS_PICK_LOWSPACE;
err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);

View File

@ -2223,19 +2223,16 @@ DECLARE_EVENT_CLASS(xfs_defer_class,
__field(dev_t, dev)
__field(void *, dop)
__field(char, committed)
__field(char, low)
__field(unsigned long, caller_ip)
),
TP_fast_assign(
__entry->dev = mp ? mp->m_super->s_dev : 0;
__entry->dop = dop;
__entry->low = dop->dop_low;
__entry->caller_ip = caller_ip;
),
TP_printk("dev %d:%d ops %p low %d, caller %pS",
TP_printk("dev %d:%d ops %p caller %pS",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->dop,
__entry->low,
(char *)__entry->caller_ip)
)
#define DEFINE_DEFER_EVENT(name) \
@ -2251,19 +2248,16 @@ DECLARE_EVENT_CLASS(xfs_defer_error_class,
__field(dev_t, dev)
__field(void *, dop)
__field(char, committed)
__field(char, low)
__field(int, error)
),
TP_fast_assign(
__entry->dev = mp ? mp->m_super->s_dev : 0;
__entry->dop = dop;
__entry->low = dop->dop_low;
__entry->error = error;
),
TP_printk("dev %d:%d ops %p low %d err %d",
TP_printk("dev %d:%d ops %p err %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->dop,
__entry->low,
__entry->error)
)
#define DEFINE_DEFER_ERROR_EVENT(name) \

View File

@ -101,8 +101,6 @@ struct xfs_defer_ops {
/* relog these with each roll */
struct xfs_inode *dop_inodes[XFS_DEFER_OPS_NR_INODES];
struct xfs_buf *dop_bufs[XFS_DEFER_OPS_NR_BUFS];
bool dop_low; /* alloc in low mode */
};
/*