xfs: dynamic speculative EOF preallocation

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, the size of 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

Because it is hard to take back specualtive preallocation, cases
where there are large slow growing log files on a nearly full
filesystem may cause premature ENOSPC. Hence as the filesystem nears
full, the maximum dynamic prealloc size іs reduced according to this
table (based on 4k block size):

freespace       max prealloc size
  >5%             full extent (8GB)
  4-5%             2GB (8GB >> 2)
  3-4%             1GB (8GB >> 3)
  2-3%           512MB (8GB >> 4)
  1-2%           256MB (8GB >> 5)
  <1%            128MB (8GB >> 6)

This should reduce the amount of space held in speculative
preallocation for such cases.

The allocsize mount option turns off the dynamic behaviour and fixes
the prealloc size to whatever the mount option specifies. i.e. the
behaviour is unchanged.

Signed-off-by: Dave Chinner <dchinner@redhat.com>

1 files changed, 14 insertions, 0 deletions

diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 5861b4980740..a62e8971539d 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);