From: Dave Chinner <dchinner@xxxxxxxxxx>
Currently the size of the speculative preallocation during delayed
allocation is fixed by either the allocsize mount option of a
default size. We are seeing a lot of cases where we need to
recommend using the allocsize mount option to prevent fragmentation
when buffered writes land in the same AG.
Rather than using a fixed preallocation size by default (up to 64k),
make it dynamic by basing it on the current inode size. That way the
EOF preallocation will increase as the file size increases. Hence
for streaming writes we are much more likely to get large
preallocations exactly when we need it to reduce fragementation.
For default settings, ãe size and the initial extents is determined
by the number of parallel writers and the amount of memory in the
machine. For 4GB RAM and 4 concurrent 32GB file writes:
EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL
0: [0..1048575]: 1048672..2097247 0 (1048672..2097247) 1048576
1: [1048576..2097151]: 5242976..6291551 0 (5242976..6291551) 1048576
2: [2097152..4194303]: 12583008..14680159 0 (12583008..14680159) 2097152
3: [4194304..8388607]: 25165920..29360223 0 (25165920..29360223) 4194304
4: [8388608..16777215]: 58720352..67108959 0 (58720352..67108959) 8388608
5: [16777216..33554423]: 117440584..134217791 0 (117440584..134217791) 16777208
6: [33554424..50331511]: 184549056..201326143 0 (184549056..201326143) 16777088
7: [50331512..67108599]: 251657408..268434495 0 (251657408..268434495) 16777088
and for 16 concurrent 16GB file writes:
EXT: FILE-OFFSET BLOCK-RANGE AG AG-OFFSET TOTAL
0: [0..262143]: 2490472..2752615 0 (2490472..2752615) 262144
1: [262144..524287]: 6291560..6553703 0 (6291560..6553703) 262144
2: [524288..1048575]: 13631592..14155879 0 (13631592..14155879) 524288
3: [1048576..2097151]: 30408808..31457383 0 (30408808..31457383) 1048576
4: [2097152..4194303]: 52428904..54526055 0 (52428904..54526055) 2097152
5: [4194304..8388607]: 104857704..109052007 0 (104857704..109052007) 4194304
6: [8388608..16777215]: 209715304..218103911 0 (209715304..218103911) 8388608
7: [16777216..33554423]: 452984848..469762055 0 (452984848..469762055) 16777208
The allocsize mount option still controls the minimum preallocation size, so
the smallest extent size can stil be bound in situations where this behaviour
is not sufficient.
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
---
fs/xfs/xfs_iomap.c | 53 ++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 43 insertions(+), 10 deletions(-)
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 2057614..0227ac1 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -389,6 +389,9 @@ 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(
@@ -405,6 +408,7 @@ 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)
@@ -427,11 +431,16 @@ xfs_iomap_eof_want_preallocate(
if ((imap[n].br_startblock != HOLESTARTBLOCK) &&
(imap[n].br_startblock != DELAYSTARTBLOCK))
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;
}
@@ -469,6 +478,7 @@ 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,
ioflag, imap, XFS_WRITE_IMAPS, &prealloc);
if (error)
@@ -476,9 +486,23 @@ xfs_iomap_write_delay(
retry:
if (prealloc) {
+ xfs_fileoff_t alloc_blocks = 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.
+ */
+ if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
+ alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size);
+ alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
+ rounddown_pow_of_two(alloc_blocks));
+ }
+ if (alloc_blocks < mp->m_writeio_blocks)
+ alloc_blocks = mp->m_writeio_blocks;
+
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)));
}
@@ -496,22 +520,31 @@ 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;
--
1.7.2.3
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
