Allow reusing any busy extent for metadata allocations, and reusing busy
userdata extents for userdata allocations. Most of the complexity is
propagating the userdata information from the XFS_BMAPI_METADATA flag
to xfs_bunmapi into the low-level extent freeing routines. After that
we can just track what type of busy extent we have and treat it accordingly.
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Index: xfs/fs/xfs/xfs_alloc.c
===================================================================
--- xfs.orig/fs/xfs/xfs_alloc.c 2011-03-21 14:49:14.000000000 +0100
+++ xfs/fs/xfs/xfs_alloc.c 2011-03-21 14:51:31.746155282 +0100
@@ -1396,7 +1396,8 @@ xfs_alloc_ag_vextent_small(
if (error)
goto error0;
if (fbno != NULLAGBLOCK) {
- xfs_alloc_busy_reuse(args->tp, args->agno, fbno, 1);
+ xfs_alloc_busy_reuse(args->tp, args->agno, fbno, 1,
+ args->userdata);
if (args->userdata) {
xfs_buf_t *bp;
@@ -2431,7 +2432,8 @@ int /* error */
xfs_free_extent(
xfs_trans_t *tp, /* transaction pointer */
xfs_fsblock_t bno, /* starting block number of extent */
- xfs_extlen_t len) /* length of extent */
+ xfs_extlen_t len,
+ bool userdata)/* length of extent */
{
xfs_alloc_arg_t args;
int error;
@@ -2444,6 +2446,7 @@ xfs_free_extent(
ASSERT(args.agno < args.mp->m_sb.sb_agcount);
args.agbno = XFS_FSB_TO_AGBNO(args.mp, bno);
args.pag = xfs_perag_get(args.mp, args.agno);
+ args.userdata = userdata;
if ((error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING)))
goto error0;
#ifdef DEBUG
@@ -2453,7 +2456,7 @@ xfs_free_extent(
#endif
error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len,
0);
if (error)
- xfs_alloc_busy_insert(tp, args.agno, args.agbno, len);
+ xfs_alloc_busy_insert(tp, args.agno, args.agbno, len, userdata);
error0:
xfs_perag_put(args.pag);
return error;
@@ -2464,7 +2467,8 @@ xfs_alloc_busy_insert(
struct xfs_trans *tp,
xfs_agnumber_t agno,
xfs_agblock_t bno,
- xfs_extlen_t len)
+ xfs_extlen_t len,
+ bool userdata)
{
struct xfs_busy_extent *new;
struct xfs_busy_extent *busyp;
@@ -2487,6 +2491,7 @@ xfs_alloc_busy_insert(
new->agno = agno;
new->bno = bno;
new->length = len;
+ new->flags = userdata ? XFS_ALLOC_BUSY_USERDATA : 0;
INIT_LIST_HEAD(&new->list);
/* trace before insert to be able to see failed inserts */
@@ -2688,7 +2693,8 @@ xfs_alloc_busy_reuse(
struct xfs_trans *tp,
xfs_agnumber_t agno,
xfs_agblock_t fbno,
- xfs_extlen_t flen)
+ xfs_extlen_t flen,
+ bool userdata)
{
struct xfs_perag *pag;
struct rb_node *rbp;
@@ -2717,7 +2723,7 @@ restart:
overlap = xfs_alloc_busy_try_reuse(pag, busyp,
fbno, fbno + flen);
- if (overlap) {
+ if (overlap == -1 || (overlap && userdata)) {
spin_unlock(&pag->pagb_lock);
xfs_log_force(tp->t_mountp, XFS_LOG_SYNC);
goto restart;
@@ -2754,6 +2760,7 @@ xfs_alloc_busy_trim(
ASSERT(flen > 0);
+restart:
spin_lock(&args->pag->pagb_lock);
rbp = args->pag->pagb_tree.rb_node;
while (rbp && flen >= args->minlen) {
@@ -2771,6 +2778,31 @@ xfs_alloc_busy_trim(
continue;
}
+ if (!args->userdata ||
+ (busyp->flags & XFS_ALLOC_BUSY_USERDATA)) {
+ int overlap;
+
+ overlap = xfs_alloc_busy_try_reuse(args->pag, busyp,
+ fbno, fbno + flen);
+ if (unlikely(overlap == -1)) {
+ spin_unlock(&args->pag->pagb_lock);
+ xfs_log_force(args->mp, XFS_LOG_SYNC);
+ goto restart;
+ }
+
+ /*
+ * No more busy extents to search.
+ */
+ if (bbno <= fbno && bend >= fend)
+ goto out;
+
+ if (fbno < bbno)
+ rbp = rbp->rb_left;
+ else
+ rbp = rbp->rb_right;
+ continue;
+ }
+
if (bbno <= fbno) {
/* start overlap */
@@ -2898,8 +2930,8 @@ xfs_alloc_busy_trim(
flen = fend - fbno;
}
+out:
spin_unlock(&args->pag->pagb_lock);
-
*rbno = fbno;
*rlen = flen;
return;
Index: xfs/fs/xfs/xfs_alloc.h
===================================================================
--- xfs.orig/fs/xfs/xfs_alloc.h 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_alloc.h 2011-03-21 14:49:21.933973842 +0100
@@ -137,7 +137,7 @@ xfs_alloc_longest_free_extent(struct xfs
#ifdef __KERNEL__
void
xfs_alloc_busy_insert(struct xfs_trans *tp, xfs_agnumber_t agno,
- xfs_agblock_t bno, xfs_extlen_t len);
+ xfs_agblock_t bno, xfs_extlen_t len, bool userdata);
void
xfs_alloc_busy_clear(struct xfs_mount *mp, struct xfs_busy_extent *busyp);
@@ -148,7 +148,7 @@ xfs_alloc_busy_search(struct xfs_mount *
void
xfs_alloc_busy_reuse(struct xfs_trans *tp, xfs_agnumber_t agno,
- xfs_agblock_t fbno, xfs_extlen_t flen);
+ xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata);
#endif /* __KERNEL__ */
/*
@@ -224,7 +224,8 @@ int /* error */
xfs_free_extent(
struct xfs_trans *tp, /* transaction pointer */
xfs_fsblock_t bno, /* starting block number of extent */
- xfs_extlen_t len); /* length of extent */
+ xfs_extlen_t len,
+ bool userdata);/* length of extent */
int /* error */
xfs_alloc_lookup_le(
Index: xfs/fs/xfs/xfs_alloc_btree.c
===================================================================
--- xfs.orig/fs/xfs/xfs_alloc_btree.c 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_alloc_btree.c 2011-03-21 14:49:21.937977488 +0100
@@ -95,7 +95,7 @@ xfs_allocbt_alloc_block(
return 0;
}
- xfs_alloc_busy_reuse(cur->bc_tp, cur->bc_private.a.agno, bno, 1);
+ xfs_alloc_busy_reuse(cur->bc_tp, cur->bc_private.a.agno, bno, 1, false);
xfs_trans_agbtree_delta(cur->bc_tp, 1);
new->s = cpu_to_be32(bno);
@@ -120,18 +120,8 @@ xfs_allocbt_free_block(
if (error)
return error;
- /*
- * Since blocks move to the free list without the coordination used in
- * xfs_bmap_finish, we can't allow block to be available for
- * reallocation and non-transaction writing (user data) until we know
- * that the transaction that moved it to the free list is permanently
- * on disk. We track the blocks by declaring these blocks as "busy";
- * the busy list is maintained on a per-ag basis and each transaction
- * records which entries should be removed when the iclog commits to
- * disk. If a busy block is allocated, the iclog is pushed up to the
- * LSN that freed the block.
- */
- xfs_alloc_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1);
+ xfs_alloc_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno,
+ 1, false);
xfs_trans_agbtree_delta(cur->bc_tp, -1);
return 0;
}
Index: xfs/fs/xfs/xfs_ag.h
===================================================================
--- xfs.orig/fs/xfs/xfs_ag.h 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_ag.h 2011-03-21 14:49:21.941981228 +0100
@@ -187,6 +187,8 @@ struct xfs_busy_extent {
xfs_agnumber_t agno;
xfs_agblock_t bno;
xfs_extlen_t length;
+ unsigned int flags;
+#define XFS_ALLOC_BUSY_USERDATA 0x01 /* freed data extents */
};
/*
Index: xfs/fs/xfs/xfs_bmap.c
===================================================================
--- xfs.orig/fs/xfs/xfs_bmap.c 2011-03-21 14:48:04.238474593 +0100
+++ xfs/fs/xfs/xfs_bmap.c 2011-03-21 14:49:21.949973870 +0100
@@ -180,22 +180,6 @@ xfs_bmap_btree_to_extents(
int whichfork); /* data or attr fork */
/*
- * Called by xfs_bmapi to update file extent records and the btree
- * after removing space (or undoing a delayed allocation).
- */
-STATIC int /* error */
-xfs_bmap_del_extent(
- xfs_inode_t *ip, /* incore inode pointer */
- xfs_trans_t *tp, /* current trans pointer */
- xfs_extnum_t idx, /* extent number to update/insert */
- xfs_bmap_free_t *flist, /* list of extents to be freed */
- xfs_btree_cur_t *cur, /* if null, not a btree */
- xfs_bmbt_irec_t *new, /* new data to add to file extents */
- int *logflagsp,/* inode logging flags */
- int whichfork, /* data or attr fork */
- int rsvd); /* OK to allocate reserved blocks */
-
-/*
* Remove the entry "free" from the free item list. Prev points to the
* previous entry, unless "free" is the head of the list.
*/
@@ -2811,7 +2795,7 @@ xfs_bmap_btree_to_extents(
cblock = XFS_BUF_TO_BLOCK(cbp);
if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
return error;
- xfs_bmap_add_free(cbno, 1, cur->bc_private.b.flist, mp);
+ xfs_bmap_add_free(mp, cur->bc_private.b.flist, cbno, 1, 0);
ip->i_d.di_nblocks--;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
xfs_trans_binval(tp, cbp);
@@ -2838,8 +2822,7 @@ xfs_bmap_del_extent(
xfs_btree_cur_t *cur, /* if null, not a btree */
xfs_bmbt_irec_t *del, /* data to remove from extents */
int *logflagsp, /* inode logging flags */
- int whichfork, /* data or attr fork */
- int rsvd) /* OK to allocate reserved blocks */
+ int flags) /* XFS_BMAPI_* flags */
{
xfs_filblks_t da_new; /* new delay-alloc indirect blocks */
xfs_filblks_t da_old; /* old delay-alloc indirect blocks */
@@ -2849,7 +2832,6 @@ xfs_bmap_del_extent(
int do_fx; /* free extent at end of routine */
xfs_bmbt_rec_host_t *ep; /* current extent entry pointer */
int error; /* error return value */
- int flags; /* inode logging flags */
xfs_bmbt_irec_t got; /* current extent entry */
xfs_fileoff_t got_endoff; /* first offset past got */
int i; /* temp state */
@@ -2861,12 +2843,17 @@ xfs_bmap_del_extent(
uint qfield; /* quota field to update */
xfs_filblks_t temp; /* for indirect length calculations */
xfs_filblks_t temp2; /* for indirect length calculations */
- int state = 0;
+ int state, whichfork;
XFS_STATS_INC(xs_del_exlist);
- if (whichfork == XFS_ATTR_FORK)
- state |= BMAP_ATTRFORK;
+ if (flags & XFS_BMAPI_ATTRFORK) {
+ whichfork = XFS_ATTR_FORK;
+ state = BMAP_ATTRFORK;
+ } else {
+ whichfork = XFS_DATA_FORK;
+ state = 0;
+ }
mp = ip->i_mount;
ifp = XFS_IFORK_PTR(ip, whichfork);
@@ -3121,9 +3108,13 @@ xfs_bmap_del_extent(
/*
* If we need to, add to list of extents to delete.
*/
- if (do_fx)
- xfs_bmap_add_free(del->br_startblock, del->br_blockcount, flist,
- mp);
+ if (do_fx) {
+ xfs_bmap_add_free(mp, flist, del->br_startblock,
+ del->br_blockcount,
+ (flags & XFS_BMAPI_METADATA) ? 0 :
+ XFS_BFI_USERDATA);
+ }
+
/*
* Adjust inode # blocks in the file.
*/
@@ -3142,7 +3133,9 @@ xfs_bmap_del_extent(
ASSERT(da_old >= da_new);
if (da_old > da_new) {
xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS,
- (int64_t)(da_old - da_new), rsvd);
+ (int64_t)(da_old - da_new),
+ !!(flags & XFS_BMAPI_RSVBLOCKS));
+
}
done:
*logflagsp = flags;
@@ -3723,10 +3716,11 @@ error0:
/* ARGSUSED */
void
xfs_bmap_add_free(
+ struct xfs_mount *mp, /* mount point structure */
+ struct xfs_bmap_free *flist, /* list of extents */
xfs_fsblock_t bno, /* fs block number of extent */
xfs_filblks_t len, /* length of extent */
- xfs_bmap_free_t *flist, /* list of extents */
- xfs_mount_t *mp) /* mount point structure */
+ unsigned int flags)
{
xfs_bmap_free_item_t *cur; /* current (next) element */
xfs_bmap_free_item_t *new; /* new element */
@@ -3750,6 +3744,7 @@ xfs_bmap_add_free(
new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
new->xbfi_startblock = bno;
new->xbfi_blockcount = (xfs_extlen_t)len;
+ new->xbfi_flags = XFS_BFI_USERDATA;
for (prev = NULL, cur = flist->xbf_first;
cur != NULL;
prev = cur, cur = cur->xbfi_next) {
@@ -3883,8 +3878,11 @@ xfs_bmap_finish(
efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count);
for (free = flist->xbf_first; free != NULL; free = next) {
next = free->xbfi_next;
- if ((error = xfs_free_extent(ntp, free->xbfi_startblock,
- free->xbfi_blockcount))) {
+
+ error = xfs_free_extent(ntp, free->xbfi_startblock,
+ free->xbfi_blockcount,
+ !!(free->xbfi_flags & XFS_BFI_USERDATA));
+ if (error) {
/*
* The bmap free list will be cleaned up at a
* higher level. The EFI will be canceled when
@@ -5278,7 +5276,7 @@ xfs_bunmapi(
goto error0;
}
error = xfs_bmap_del_extent(ip, tp, lastx, flist, cur, &del,
- &tmp_logflags, whichfork, rsvd);
+ &tmp_logflags, flags);
logflags |= tmp_logflags;
if (error)
goto error0;
Index: xfs/fs/xfs/xfs_bmap.h
===================================================================
--- xfs.orig/fs/xfs/xfs_bmap.h 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_bmap.h 2011-03-21 14:49:21.953974825 +0100
@@ -35,6 +35,8 @@ typedef struct xfs_bmap_free_item
{
xfs_fsblock_t xbfi_startblock;/* starting fs block number */
xfs_extlen_t xbfi_blockcount;/* number of blocks in extent */
+ unsigned int xbfi_flags;
+#define XFS_BFI_USERDATA 0x01 /* userdata extent */
struct xfs_bmap_free_item *xbfi_next; /* link to next entry */
} xfs_bmap_free_item_t;
@@ -188,10 +190,11 @@ xfs_bmap_add_attrfork(
*/
void
xfs_bmap_add_free(
+ struct xfs_mount *mp, /* mount point structure */
+ struct xfs_bmap_free *flist, /* list of extents */
xfs_fsblock_t bno, /* fs block number of extent */
xfs_filblks_t len, /* length of extent */
- xfs_bmap_free_t *flist, /* list of extents */
- struct xfs_mount *mp); /* mount point structure */
+ unsigned int flags);
/*
* Routine to clean up the free list data structure when
Index: xfs/fs/xfs/xfs_bmap_btree.c
===================================================================
--- xfs.orig/fs/xfs/xfs_bmap_btree.c 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_bmap_btree.c 2011-03-21 14:49:21.957973331 +0100
@@ -598,7 +598,7 @@ xfs_bmbt_free_block(
struct xfs_trans *tp = cur->bc_tp;
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
- xfs_bmap_add_free(fsbno, 1, cur->bc_private.b.flist, mp);
+ xfs_bmap_add_free(mp, cur->bc_private.b.flist, fsbno, 1, 0);
ip->i_d.di_nblocks--;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
Index: xfs/fs/xfs/xfs_fsops.c
===================================================================
--- xfs.orig/fs/xfs/xfs_fsops.c 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_fsops.c 2011-03-21 14:49:21.961974307 +0100
@@ -344,7 +344,7 @@ xfs_growfs_data_private(
* Free the new space.
*/
error = xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, agno,
- be32_to_cpu(agf->agf_length) - new), new);
+ be32_to_cpu(agf->agf_length) - new), new, false);
if (error) {
goto error0;
}
Index: xfs/fs/xfs/xfs_ialloc.c
===================================================================
--- xfs.orig/fs/xfs/xfs_ialloc.c 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_ialloc.c 2011-03-21 14:49:21.965975280 +0100
@@ -1154,9 +1154,10 @@ xfs_difree(
goto error0;
}
- xfs_bmap_add_free(XFS_AGB_TO_FSB(mp,
- agno, XFS_INO_TO_AGBNO(mp,rec.ir_startino)),
- XFS_IALLOC_BLOCKS(mp), flist, mp);
+ xfs_bmap_add_free(mp, flist,
+ XFS_AGB_TO_FSB(mp, agno,
+ XFS_INO_TO_AGBNO(mp,rec.ir_startino)),
+ XFS_IALLOC_BLOCKS(mp), 0);
} else {
*delete = 0;
Index: xfs/fs/xfs/xfs_ialloc_btree.c
===================================================================
--- xfs.orig/fs/xfs/xfs_ialloc_btree.c 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_ialloc_btree.c 2011-03-21 14:49:21.973975583 +0100
@@ -117,7 +117,7 @@ xfs_inobt_free_block(
int error;
fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp));
- error = xfs_free_extent(cur->bc_tp, fsbno, 1);
+ error = xfs_free_extent(cur->bc_tp, fsbno, 1, false);
if (error)
return error;
Index: xfs/fs/xfs/xfs_log_recover.c
===================================================================
--- xfs.orig/fs/xfs/xfs_log_recover.c 2011-03-21 14:48:04.000000000 +0100
+++ xfs/fs/xfs/xfs_log_recover.c 2011-03-21 14:49:21.973975583 +0100
@@ -2907,8 +2907,9 @@ xlog_recover_process_efi(
efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents);
for (i = 0; i < efip->efi_format.efi_nextents; i++) {
- extp = &(efip->efi_format.efi_extents[i]);
- error = xfs_free_extent(tp, extp->ext_start, extp->ext_len);
+ extp = &efip->efi_format.efi_extents[i];
+ error = xfs_free_extent(tp, extp->ext_start, extp->ext_len,
+ false);
if (error)
goto abort_error;
xfs_trans_log_efd_extent(tp, efdp, extp->ext_start,
|