aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
authorEric Sandeen2009-12-23 07:58:12 -0500
committerTheodore Ts'o2009-12-23 07:58:12 -0500
commitc8afb44682fcef6273e8b8eb19fab13ddd05b386 (patch)
tree44c170427e54b611d7f02a31bbd5733cc9cf1dd0 /fs/ext4
parent17bd55d037a02b04d9119511cfd1a4b985d20f63 (diff)
ext4: flush delalloc blocks when space is low
Creating many small files in rapid succession on a small filesystem can lead to spurious ENOSPC; on a 104MB filesystem: for i in `seq 1 22500`; do echo -n > $SCRATCH_MNT/$i echo XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX > $SCRATCH_MNT/$i done leads to ENOSPC even though after a sync, 40% of the fs is free again. This is because we reserve worst-case metadata for delalloc writes, and when data is allocated that worst-case reservation is not usually needed. When freespace is low, kicking off an async writeback will start converting that worst-case space usage into something more realistic, almost always freeing up space to continue. This resolves the testcase for me, and survives all 4 generic ENOSPC tests in xfstests. We'll still need a hard synchronous sync to squeeze out the last bit, but this fixes things up to a large degree. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/inode.c11
1 files changed, 9 insertions, 2 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ab807963a614..282621f18c10 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2993,11 +2993,18 @@ static int ext4_nonda_switch(struct super_block *sb)
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
/*
- * free block count is less that 150% of dirty blocks
- * or free blocks is less that watermark
+ * free block count is less than 150% of dirty blocks
+ * or free blocks is less than watermark
*/
return 1;
}
+ /*
+ * Even if we don't switch but are nearing capacity,
+ * start pushing delalloc when 1/2 of free blocks are dirty.
+ */
+ if (free_blocks < 2 * dirty_blocks)
+ writeback_inodes_sb_if_idle(sb);
+
return 0;
}