aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4/ialloc.c
diff options
context:
space:
mode:
authorLukas Czerner <lczerner@redhat.com>2010-10-27 21:30:05 -0400
committerTheodore Ts'o <tytso@mit.edu>2010-10-27 21:30:05 -0400
commitbfff68738f1cb5c93dab1114634cea02aae9e7ba (patch)
treeb6cdf3f26e86464c7088cab62d837eb32f559fb9 /fs/ext4/ialloc.c
parente6fa0be699449d28a20e815bfe9ce26725ec4962 (diff)
ext4: add support for lazy inode table initialization
When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs/ext4/ialloc.c')
-rw-r--r--fs/ext4/ialloc.c120
1 files changed, 120 insertions, 0 deletions
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 45853e0d1f2..e428f23215c 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -107,6 +107,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
desc = ext4_get_group_desc(sb, block_group, NULL);
if (!desc)
return NULL;
+
bitmap_blk = ext4_inode_bitmap(sb, desc);
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
@@ -123,6 +124,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
unlock_buffer(bh);
return bh;
}
+
ext4_lock_group(sb, block_group);
if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
ext4_init_inode_bitmap(sb, bh, block_group, desc);
@@ -133,6 +135,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
return bh;
}
ext4_unlock_group(sb, block_group);
+
if (buffer_uptodate(bh)) {
/*
* if not uninit if bh is uptodate,
@@ -712,8 +715,17 @@ static int ext4_claim_inode(struct super_block *sb,
{
int free = 0, retval = 0, count;
struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_info *grp = ext4_get_group_info(sb, group);
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+ /*
+ * We have to be sure that new inode allocation does not race with
+ * inode table initialization, because otherwise we may end up
+ * allocating and writing new inode right before sb_issue_zeroout
+ * takes place and overwriting our new inode with zeroes. So we
+ * take alloc_sem to prevent it.
+ */
+ down_read(&grp->alloc_sem);
ext4_lock_group(sb, group);
if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
/* not a free inode */
@@ -724,6 +736,7 @@ static int ext4_claim_inode(struct super_block *sb,
if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
ino > EXT4_INODES_PER_GROUP(sb)) {
ext4_unlock_group(sb, group);
+ up_read(&grp->alloc_sem);
ext4_error(sb, "reserved inode or inode > inodes count - "
"block_group = %u, inode=%lu", group,
ino + group * EXT4_INODES_PER_GROUP(sb));
@@ -772,6 +785,7 @@ static int ext4_claim_inode(struct super_block *sb,
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
err_ret:
ext4_unlock_group(sb, group);
+ up_read(&grp->alloc_sem);
return retval;
}
@@ -1205,3 +1219,109 @@ unsigned long ext4_count_dirs(struct super_block * sb)
}
return count;
}
+
+/*
+ * Zeroes not yet zeroed inode table - just write zeroes through the whole
+ * inode table. Must be called without any spinlock held. The only place
+ * where it is called from on active part of filesystem is ext4lazyinit
+ * thread, so we do not need any special locks, however we have to prevent
+ * inode allocation from the current group, so we take alloc_sem lock, to
+ * block ext4_claim_inode until we are finished.
+ */
+extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+ int barrier)
+{
+ struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_desc *gdp = NULL;
+ struct buffer_head *group_desc_bh;
+ handle_t *handle;
+ ext4_fsblk_t blk;
+ int num, ret = 0, used_blks = 0;
+ unsigned long flags = BLKDEV_IFL_WAIT;
+
+ /* This should not happen, but just to be sure check this */
+ if (sb->s_flags & MS_RDONLY) {
+ ret = 1;
+ goto out;
+ }
+
+ gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+ if (!gdp)
+ goto out;
+
+ /*
+ * We do not need to lock this, because we are the only one
+ * handling this flag.
+ */
+ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
+ goto out;
+
+ handle = ext4_journal_start_sb(sb, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+
+ down_write(&grp->alloc_sem);
+ /*
+ * If inode bitmap was already initialized there may be some
+ * used inodes so we need to skip blocks with used inodes in
+ * inode table.
+ */
+ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
+ used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp)),
+ sbi->s_inodes_per_block);
+
+ blk = ext4_inode_table(sb, gdp) + used_blks;
+ num = sbi->s_itb_per_group - used_blks;
+
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+ ret = ext4_journal_get_write_access(handle,
+ group_desc_bh);
+ if (ret)
+ goto err_out;
+
+ if (unlikely(num > EXT4_INODES_PER_GROUP(sb))) {
+ ext4_error(sb, "Something is wrong with group %u\n"
+ "Used itable blocks: %d"
+ "Itable blocks per group: %lu\n",
+ group, used_blks, sbi->s_itb_per_group);
+ ret = 1;
+ goto err_out;
+ }
+
+ /*
+ * Skip zeroout if the inode table is full. But we set the ZEROED
+ * flag anyway, because obviously, when it is full it does not need
+ * further zeroing.
+ */
+ if (unlikely(num == 0))
+ goto skip_zeroout;
+
+ ext4_debug("going to zero out inode table in group %d\n",
+ group);
+ if (barrier)
+ flags |= BLKDEV_IFL_BARRIER;
+ ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS, flags);
+ if (ret < 0)
+ goto err_out;
+
+skip_zeroout:
+ ext4_lock_group(sb, group);
+ gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+ gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+ ext4_unlock_group(sb, group);
+
+ BUFFER_TRACE(group_desc_bh,
+ "call ext4_handle_dirty_metadata");
+ ret = ext4_handle_dirty_metadata(handle, NULL,
+ group_desc_bh);
+
+err_out:
+ up_write(&grp->alloc_sem);
+ ext4_journal_stop(handle);
+out:
+ return ret;
+}