summaryrefslogtreecommitdiff
path: root/fs/ext4/balloc.c
diff options
context:
space:
mode:
authorAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>2008-10-09 18:56:23 +0400
committerTheodore Ts'o <tytso@mit.edu>2008-10-09 18:56:23 +0400
commita30d542a0035b886ffaafd0057ced0a2b28c3a4f (patch)
tree9e677eaf4eb1611701828554b27a1b0b0ae523fd /fs/ext4/balloc.c
parentc4a0c46ec92c194c873232b88debce4e1a448483 (diff)
downloadlinux-a30d542a0035b886ffaafd0057ced0a2b28c3a4f.tar.xz
ext4: Make sure all the block allocation paths reserve blocks
With delayed allocation we need to make sure block are reserved before we attempt to allocate them. Otherwise we get block allocation failure (ENOSPC) during writepages which cannot be handled. This would mean silent data loss (We do a printk stating data will be lost). This patch updates the DIO and fallocate code path to do block reservation before block allocation. This is needed to make sure parallel DIO and fallocate request doesn't take block out of delayed reserve space. When free blocks count go below a threshold we switch to a slow patch which looks at other CPU's accumulated percpu counter values. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs/ext4/balloc.c')
-rw-r--r--fs/ext4/balloc.c58
1 files changed, 42 insertions, 16 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 58005c01abb8..1707850301d6 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -1602,6 +1602,32 @@ out:
return ret;
}
+int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
+ ext4_fsblk_t nblocks)
+{
+ s64 free_blocks;
+ ext4_fsblk_t root_blocks = 0;
+ struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+
+ free_blocks = percpu_counter_read(fbc);
+
+ if (!capable(CAP_SYS_RESOURCE) &&
+ sbi->s_resuid != current->fsuid &&
+ (sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
+ root_blocks = ext4_r_blocks_count(sbi->s_es);
+
+ if (free_blocks - (nblocks + root_blocks) < EXT4_FREEBLOCKS_WATERMARK)
+ free_blocks = percpu_counter_sum(&sbi->s_freeblocks_counter);
+
+ if (free_blocks < (root_blocks + nblocks))
+ /* we don't have free space */
+ return -ENOSPC;
+
+ /* reduce fs free blocks counter */
+ percpu_counter_sub(fbc, nblocks);
+ return 0;
+}
+
/**
* ext4_has_free_blocks()
* @sbi: in-core super block structure.
@@ -1623,18 +1649,17 @@ ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
sbi->s_resuid != current->fsuid &&
(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
root_blocks = ext4_r_blocks_count(sbi->s_es);
-#ifdef CONFIG_SMP
- if (free_blocks - root_blocks < FBC_BATCH)
- free_blocks =
- percpu_counter_sum(&sbi->s_freeblocks_counter);
-#endif
+
+ if (free_blocks - (nblocks + root_blocks) < EXT4_FREEBLOCKS_WATERMARK)
+ free_blocks = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
+
if (free_blocks <= root_blocks)
/* we don't have free space */
return 0;
if (free_blocks - root_blocks < nblocks)
return free_blocks - root_blocks;
return nblocks;
- }
+}
/**
@@ -1713,14 +1738,11 @@ ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
/*
* With delalloc we already reserved the blocks
*/
- *count = ext4_has_free_blocks(sbi, *count);
- }
- if (*count == 0) {
- *errp = -ENOSPC;
- return 0; /*return with ENOSPC error */
+ if (ext4_claim_free_blocks(sbi, *count)) {
+ *errp = -ENOSPC;
+ return 0; /*return with ENOSPC error */
+ }
}
- num = *count;
-
/*
* Check quota for allocation of this block.
*/
@@ -1915,9 +1937,13 @@ allocated:
le16_add_cpu(&gdp->bg_free_blocks_count, -num);
gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
spin_unlock(sb_bgl_lock(sbi, group_no));
- if (!EXT4_I(inode)->i_delalloc_reserved_flag)
- percpu_counter_sub(&sbi->s_freeblocks_counter, num);
-
+ if (!EXT4_I(inode)->i_delalloc_reserved_flag && (*count != num)) {
+ /*
+ * we allocated less blocks than we
+ * claimed. Add the difference back.
+ */
+ percpu_counter_add(&sbi->s_freeblocks_counter, *count - num);
+ }
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, group_no);
spin_lock(sb_bgl_lock(sbi, flex_group));