ext4: reduce contention on s_orphan_lock

Shuffle code around in ext4_orphan_add() and ext4_orphan_del() so that
we avoid taking global s_orphan_lock in some cases and hold it for
shorter time in other cases.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
This commit is contained in:
Jan Kara 2014-05-26 11:56:53 -04:00 committed by Theodore Ts'o
parent cd2c080c33
commit d745a8c20c
1 changed files with 65 additions and 44 deletions

View File

@ -2540,13 +2540,17 @@ static int empty_dir(struct inode *inode)
return 1;
}
/* ext4_orphan_add() links an unlinked or truncated inode into a list of
/*
* ext4_orphan_add() links an unlinked or truncated inode into a list of
* such inodes, starting at the superblock, in case we crash before the
* file is closed/deleted, or in case the inode truncate spans multiple
* transactions and the last transaction is not recovered after a crash.
*
* At filesystem recovery time, we walk this list deleting unlinked
* inodes and truncating linked inodes in ext4_orphan_cleanup().
*
* Orphan list manipulation functions must be called under i_mutex unless
* we are just creating the inode or deleting it.
*/
int ext4_orphan_add(handle_t *handle, struct inode *inode)
{
@ -2554,13 +2558,19 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_iloc iloc;
int err = 0, rc;
bool dirty = false;
if (!sbi->s_journal)
return 0;
mutex_lock(&sbi->s_orphan_lock);
WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
!mutex_is_locked(&inode->i_mutex));
/*
* Exit early if inode already is on orphan list. This is a big speedup
* since we don't have to contend on the global s_orphan_lock.
*/
if (!list_empty(&EXT4_I(inode)->i_orphan))
goto out_unlock;
return 0;
/*
* Orphan handling is only valid for files with data blocks
@ -2574,44 +2584,47 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto out_unlock;
goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out_unlock;
goto out;
mutex_lock(&sbi->s_orphan_lock);
/*
* Due to previous errors inode may be already a part of on-disk
* orphan list. If so skip on-disk list modification.
*/
if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
(le32_to_cpu(sbi->s_es->s_inodes_count)))
goto mem_insert;
/* Insert this inode at the head of the on-disk orphan list... */
NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
err = ext4_handle_dirty_super(handle, sb);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
/* Only add to the head of the in-memory list if all the
* previous operations succeeded. If the orphan_add is going to
* fail (possibly taking the journal offline), we can't risk
* leaving the inode on the orphan list: stray orphan-list
* entries can cause panics at unmount time.
*
* This is safe: on error we're going to ignore the orphan list
* anyway on the next recovery. */
mem_insert:
if (!err)
list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) >
(le32_to_cpu(sbi->s_es->s_inodes_count))) {
/* Insert this inode at the head of the on-disk orphan list */
NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
dirty = true;
}
list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
mutex_unlock(&sbi->s_orphan_lock);
if (dirty) {
err = ext4_handle_dirty_super(handle, sb);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
if (err) {
/*
* We have to remove inode from in-memory list if
* addition to on disk orphan list failed. Stray orphan
* list entries can cause panics at unmount time.
*/
mutex_lock(&sbi->s_orphan_lock);
list_del(&EXT4_I(inode)->i_orphan);
mutex_unlock(&sbi->s_orphan_lock);
}
}
jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
jbd_debug(4, "orphan inode %lu will point to %d\n",
inode->i_ino, NEXT_ORPHAN(inode));
out_unlock:
mutex_unlock(&sbi->s_orphan_lock);
out:
ext4_std_error(sb, err);
return err;
}
@ -2632,35 +2645,43 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS))
return 0;
mutex_lock(&sbi->s_orphan_lock);
WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
!mutex_is_locked(&inode->i_mutex));
/* Do this quick check before taking global s_orphan_lock. */
if (list_empty(&ei->i_orphan))
goto out;
return 0;
ino_next = NEXT_ORPHAN(inode);
prev = ei->i_orphan.prev;
if (handle) {
/* Grab inode buffer early before taking global s_orphan_lock */
err = ext4_reserve_inode_write(handle, inode, &iloc);
}
mutex_lock(&sbi->s_orphan_lock);
jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
prev = ei->i_orphan.prev;
list_del_init(&ei->i_orphan);
/* If we're on an error path, we may not have a valid
* transaction handle with which to update the orphan list on
* disk, but we still need to remove the inode from the linked
* list in memory. */
if (!handle)
goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
if (!handle || err) {
mutex_unlock(&sbi->s_orphan_lock);
goto out_err;
}
ino_next = NEXT_ORPHAN(inode);
if (prev == &sbi->s_orphan) {
jbd_debug(4, "superblock will point to %u\n", ino_next);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
if (err) {
mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
}
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
mutex_unlock(&sbi->s_orphan_lock);
err = ext4_handle_dirty_super(handle, inode->i_sb);
} else {
struct ext4_iloc iloc2;
@ -2670,20 +2691,20 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
jbd_debug(4, "orphan inode %lu will point to %u\n",
i_prev->i_ino, ino_next);
err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
if (err)
if (err) {
mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
}
NEXT_ORPHAN(i_prev) = ino_next;
err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
mutex_unlock(&sbi->s_orphan_lock);
}
if (err)
goto out_brelse;
NEXT_ORPHAN(inode) = 0;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
out_err:
ext4_std_error(inode->i_sb, err);
out:
mutex_unlock(&sbi->s_orphan_lock);
return err;
out_brelse: