ocfs2: revert iput deferring code in ocfs2_drop_dentry_lock
The following patches are reverted in this patch because these patches
caused performance regression in the remote unlink() calls.
ea455f8ab683 - ocfs2: Push out dropping of dentry lock to ocfs2_wq
f7b1aa69be13 - ocfs2: Fix deadlock on umount
5fd131893793 - ocfs2: Don't oops in ocfs2_kill_sb on a failed mount
Previous patches in this series removed the possible deadlocks from
downconvert thread so the above patches shouldn't be needed anymore.
The regression is caused because these patches delay the iput() in case
of dentry unlocks. This also delays the unlocking of the open lockres.
The open lockresource is required to test if the inode can be wiped from
disk or not. When the deleting node does not get the open lock, it
marks it as orphan (even though it is not in use by another
node/process) and causes a journal checkpoint. This delays operations
following the inode eviction. This also moves the inode to the orphaned
inode which further causes more I/O and a lot of unneccessary orphans.
The following script can be used to generate the load causing issues:
declare -a create
declare -a remove
declare -a iterations=(1 2 4 8 16 32 64 128 256 512 1024 2048 4096 8192 16384)
unique="`mktemp -u XXXXX`"
script="/tmp/idontknow-${unique}.sh"
cat <<EOF > "${script}"
for n in {1..8}; do mkdir -p test/dir\${n}
eval touch test/dir\${n}/foo{1.."\$1"}
done
EOF
chmod 700 "${script}"
function fcreate ()
{
exec 2>&1 /usr/bin/time --format=%E "${script}" "$1"
}
function fremove ()
{
exec 2>&1 /usr/bin/time --format=%E ssh node2 "cd `pwd`; rm -Rf test*"
}
function fcp ()
{
exec 2>&1 /usr/bin/time --format=%E ssh node3 "cd `pwd`; cp -R test test.new"
}
echo -------------------------------------------------
echo "| # files | create #s | copy #s | remove #s |"
echo -------------------------------------------------
for ((x=0; x < ${#iterations[*]} ; x++)) do
create[$x]="`fcreate ${iterations[$x]}`"
copy[$x]="`fcp ${iterations[$x]}`"
remove[$x]="`fremove`"
printf "| %8d | %9s | %9s | %9s |\n" ${iterations[$x]} ${create[$x]} ${copy[$x]} ${remove[$x]}
done
rm "${script}"
echo "------------------------"
Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index b800a1f..888a145 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1241,30 +1241,11 @@
return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super);
}
-static void ocfs2_kill_sb(struct super_block *sb)
-{
- struct ocfs2_super *osb = OCFS2_SB(sb);
-
- /* Failed mount? */
- if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED)
- goto out;
-
- /* Prevent further queueing of inode drop events */
- spin_lock(&dentry_list_lock);
- ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
- spin_unlock(&dentry_list_lock);
- /* Wait for work to finish and/or remove it */
- cancel_work_sync(&osb->dentry_lock_work);
-out:
- kill_block_super(sb);
-}
-
static struct file_system_type ocfs2_fs_type = {
.owner = THIS_MODULE,
.name = "ocfs2",
.mount = ocfs2_mount,
- .kill_sb = ocfs2_kill_sb,
-
+ .kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
.next = NULL
};
@@ -1930,12 +1911,6 @@
debugfs_remove(osb->osb_ctxt);
- /*
- * Flush inode dropping work queue so that deletes are
- * performed while the filesystem is still working
- */
- ocfs2_drop_all_dl_inodes(osb);
-
/* Orphan scan should be stopped as early as possible */
ocfs2_orphan_scan_stop(osb);
@@ -2278,9 +2253,6 @@
INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
journal->j_state = OCFS2_JOURNAL_FREE;
- INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes);
- osb->dentry_lock_list = NULL;
-
INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
init_llist_head(&osb->dquot_drop_list);