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:
parent
cd2c080c33
commit
d745a8c20c
109
fs/ext4/namei.c
109
fs/ext4/namei.c
|
@ -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:
|
||||
|
|
Loading…
Reference in New Issue