xfs: increase the default parallelism levels of pwork clients

Increase the parallelism level for pwork clients to the workqueue
defaults so that we can take advantage of computers with a lot of CPUs
and a lot of hardware.  On fast systems this will speed up quotacheck by
a large factor, and the following posteof/cowblocks cleanup series will
use the functionality presented in this patch to run garbage collection
as quickly as possible.

We do this by switching the pwork workqueue to unbounded, since the
current user (quotacheck) runs lengthy scans for each work item and we
don't care about dispatching the work on a warm cpu cache or anything
like that.  Also set WQ_SYSFS so that we can monitor where the wq is
running.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>

3 files changed, 7 insertions, 27 deletions

diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index eae3aff9bc97..c4a340f1f1e1 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -618,15 +618,12 @@ xfs_iwalk_threaded(
 {
 	struct xfs_pwork_ctl	pctl;
 	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, startino);
-	unsigned int		nr_threads;
 	int			error;
 
 	ASSERT(agno < mp->m_sb.sb_agcount);
 	ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL));
 
-	nr_threads = xfs_pwork_guess_datadev_parallelism(mp);
-	error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk",
-			nr_threads);
+	error = xfs_pwork_init(mp, &pctl, xfs_iwalk_ag_work, "xfs_iwalk");
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c
index b03333f1c84a..c283b801cc5d 100644
--- a/fs/xfs/xfs_pwork.c
+++ b/fs/xfs/xfs_pwork.c
@@ -61,16 +61,18 @@ xfs_pwork_init(
 	struct xfs_mount	*mp,
 	struct xfs_pwork_ctl	*pctl,
 	xfs_pwork_work_fn	work_fn,
-	const char		*tag,
-	unsigned int		nr_threads)
+	const char		*tag)
 {
+	unsigned int		nr_threads = 0;
+
 #ifdef DEBUG
 	if (xfs_globals.pwork_threads >= 0)
 		nr_threads = xfs_globals.pwork_threads;
 #endif
 	trace_xfs_pwork_init(mp, nr_threads, current->pid);
 
-	pctl->wq = alloc_workqueue("%s-%d", WQ_FREEZABLE, nr_threads, tag,
+	pctl->wq = alloc_workqueue("%s-%d",
+			WQ_UNBOUND | WQ_SYSFS | WQ_FREEZABLE, nr_threads, tag,
 			current->pid);
 	if (!pctl->wq)
 		return -ENOMEM;
@@ -117,20 +119,3 @@ xfs_pwork_poll(
 				atomic_read(&pctl->nr_work) == 0, HZ) == 0)
 		touch_softlockup_watchdog();
 }
-
-/*
- * Return the amount of parallelism that the data device can handle, or 0 for
- * no limit.
- */
-unsigned int
-xfs_pwork_guess_datadev_parallelism(
-	struct xfs_mount	*mp)
-{
-	struct xfs_buftarg	*btp = mp->m_ddev_targp;
-
-	/*
-	 * For now we'll go with the most conservative setting possible,
-	 * which is two threads for an SSD and 1 thread everywhere else.
-	 */
-	return blk_queue_nonrot(btp->bt_bdev->bd_disk->queue) ? 2 : 1;
-}
diff --git a/fs/xfs/xfs_pwork.h b/fs/xfs/xfs_pwork.h
index 8133124cf3bb..c0ef81fc85dd 100644
--- a/fs/xfs/xfs_pwork.h
+++ b/fs/xfs/xfs_pwork.h
@@ -51,11 +51,9 @@ xfs_pwork_want_abort(
 }
 
 int xfs_pwork_init(struct xfs_mount *mp, struct xfs_pwork_ctl *pctl,
-		xfs_pwork_work_fn work_fn, const char *tag,
-		unsigned int nr_threads);
+		xfs_pwork_work_fn work_fn, const char *tag);
 void xfs_pwork_queue(struct xfs_pwork_ctl *pctl, struct xfs_pwork *pwork);
 int xfs_pwork_destroy(struct xfs_pwork_ctl *pctl);
 void xfs_pwork_poll(struct xfs_pwork_ctl *pctl);
-unsigned int xfs_pwork_guess_datadev_parallelism(struct xfs_mount *mp);
 
 #endif /* __XFS_PWORK_H__ */