aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--fs/xfs/xfs_fsops.c1
-rw-r--r--fs/xfs/xfs_iomap.c84
-rw-r--r--fs/xfs/xfs_mount.c21
-rw-r--r--fs/xfs/xfs_mount.h14
4 files changed, 110 insertions, 10 deletions
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a7c116e814a..f56d30e8040 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -374,6 +374,7 @@ xfs_growfs_data_private(
mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
} else
mp->m_maxicount = 0;
+ xfs_set_low_space_thresholds(mp);
/* update secondary superblocks. */
for (agno = 1; agno < nagcount; agno++) {
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 22b62a179e8..55582bd6665 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -267,6 +267,9 @@ error_out:
* If the caller is doing a write at the end of the file, then extend the
* allocation out to the file system's write iosize. We clean up any extra
* space left over when the file is closed in xfs_inactive().
+ *
+ * If we find we already have delalloc preallocation beyond EOF, don't do more
+ * preallocation as it it not needed.
*/
STATIC int
xfs_iomap_eof_want_preallocate(
@@ -282,6 +285,7 @@ xfs_iomap_eof_want_preallocate(
xfs_filblks_t count_fsb;
xfs_fsblock_t firstblock;
int n, error, imaps;
+ int found_delalloc = 0;
*prealloc = 0;
if ((offset + count) <= ip->i_size)
@@ -306,12 +310,60 @@ xfs_iomap_eof_want_preallocate(
return 0;
start_fsb += imap[n].br_blockcount;
count_fsb -= imap[n].br_blockcount;
+
+ if (imap[n].br_startblock == DELAYSTARTBLOCK)
+ found_delalloc = 1;
}
}
- *prealloc = 1;
+ if (!found_delalloc)
+ *prealloc = 1;
return 0;
}
+/*
+ * If we don't have a user specified preallocation size, dynamically increase
+ * the preallocation size as the size of the file grows. Cap the maximum size
+ * at a single extent or less if the filesystem is near full. The closer the
+ * filesystem is to full, the smaller the maximum prealocation.
+ */
+STATIC xfs_fsblock_t
+xfs_iomap_prealloc_size(
+ struct xfs_mount *mp,
+ struct xfs_inode *ip)
+{
+ xfs_fsblock_t alloc_blocks = 0;
+
+ if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
+ int shift = 0;
+ int64_t freesp;
+
+ alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size);
+ alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
+ rounddown_pow_of_two(alloc_blocks));
+
+ xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT);
+ freesp = mp->m_sb.sb_fdblocks;
+ if (freesp < mp->m_low_space[XFS_LOWSP_5_PCNT]) {
+ shift = 2;
+ if (freesp < mp->m_low_space[XFS_LOWSP_4_PCNT])
+ shift++;
+ if (freesp < mp->m_low_space[XFS_LOWSP_3_PCNT])
+ shift++;
+ if (freesp < mp->m_low_space[XFS_LOWSP_2_PCNT])
+ shift++;
+ if (freesp < mp->m_low_space[XFS_LOWSP_1_PCNT])
+ shift++;
+ }
+ if (shift)
+ alloc_blocks >>= shift;
+ }
+
+ if (alloc_blocks < mp->m_writeio_blocks)
+ alloc_blocks = mp->m_writeio_blocks;
+
+ return alloc_blocks;
+}
+
int
xfs_iomap_write_delay(
xfs_inode_t *ip,
@@ -344,6 +396,7 @@ xfs_iomap_write_delay(
extsz = xfs_get_extsz_hint(ip);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
+
error = xfs_iomap_eof_want_preallocate(mp, ip, offset, count,
imap, XFS_WRITE_IMAPS, &prealloc);
if (error)
@@ -351,9 +404,11 @@ xfs_iomap_write_delay(
retry:
if (prealloc) {
+ xfs_fsblock_t alloc_blocks = xfs_iomap_prealloc_size(mp, ip);
+
aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1));
ioalign = XFS_B_TO_FSBT(mp, aligned_offset);
- last_fsb = ioalign + mp->m_writeio_blocks;
+ last_fsb = ioalign + alloc_blocks;
} else {
last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count)));
}
@@ -371,22 +426,31 @@ retry:
XFS_BMAPI_DELAY | XFS_BMAPI_WRITE |
XFS_BMAPI_ENTIRE, &firstblock, 1, imap,
&nimaps, NULL);
- if (error && (error != ENOSPC))
+ switch (error) {
+ case 0:
+ case ENOSPC:
+ case EDQUOT:
+ break;
+ default:
return XFS_ERROR(error);
+ }
/*
- * If bmapi returned us nothing, and if we didn't get back EDQUOT,
- * then we must have run out of space - flush all other inodes with
- * delalloc blocks and retry without EOF preallocation.
+ * If bmapi returned us nothing, we got either ENOSPC or EDQUOT. For
+ * ENOSPC, * flush all other inodes with delalloc blocks to free up
+ * some of the excess reserved metadata space. For both cases, retry
+ * without EOF preallocation.
*/
if (nimaps == 0) {
trace_xfs_delalloc_enospc(ip, offset, count);
if (flushed)
- return XFS_ERROR(ENOSPC);
+ return XFS_ERROR(error ? error : ENOSPC);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_flush_inodes(ip);
- xfs_ilock(ip, XFS_ILOCK_EXCL);
+ if (error == ENOSPC) {
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_flush_inodes(ip);
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ }
flushed = 1;
error = 0;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 19e9dfa1c25..40579fdf0d0 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -975,6 +975,24 @@ xfs_set_rw_sizes(xfs_mount_t *mp)
}
/*
+ * precalculate the low space thresholds for dynamic speculative preallocation.
+ */
+void
+xfs_set_low_space_thresholds(
+ struct xfs_mount *mp)
+{
+ int i;
+
+ for (i = 0; i < XFS_LOWSP_MAX; i++) {
+ __uint64_t space = mp->m_sb.sb_dblocks;
+
+ do_div(space, 100);
+ mp->m_low_space[i] = space * (i + 1);
+ }
+}
+
+
+/*
* Set whether we're using inode alignment.
*/
STATIC void
@@ -1196,6 +1214,9 @@ xfs_mountfs(
*/
xfs_set_rw_sizes(mp);
+ /* set the low space thresholds for dynamic preallocation */
+ xfs_set_low_space_thresholds(mp);
+
/*
* Set the inode cluster size.
* This may still be overridden by the file system
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 5861b498074..a62e8971539 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -103,6 +103,16 @@ extern int xfs_icsb_modify_counters(struct xfs_mount *, xfs_sb_field_t,
xfs_mod_incore_sb(mp, field, delta, rsvd)
#endif
+/* 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,
+};
+
typedef struct xfs_mount {
struct super_block *m_super;
xfs_tid_t m_tid; /* next unused tid for fs */
@@ -202,6 +212,8 @@ typedef struct xfs_mount {
__int64_t m_update_flags; /* sb flags we need to update
on the next remount,rw */
struct shrinker m_inode_shrink; /* inode reclaim shrinker */
+ int64_t m_low_space[XFS_LOWSP_MAX];
+ /* low free space thresholds */
} xfs_mount_t;
/*
@@ -379,6 +391,8 @@ 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 *);
+
#endif /* __KERNEL__ */
extern void xfs_mod_sb(struct xfs_trans *, __int64_t);
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2024-12-01 09:14:42 +0000