xfs: increase the default parallelism levels of pwork clients

mainline-inclusion
from mainline-v5.11-rc4
commit f83d436a
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I4KIAO
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=f83d436aef5def77b318effc14809fdc57092588

-------------------------------------------------

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: NDarrick J. Wong <djwong@kernel.org>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NBrian Foster <bfoster@redhat.com>
Signed-off-by: NLihong Kou <koulihong@huawei.com>
Reviewed-by: NZhang Yi <yi.zhang@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

Documentation/admin-guide/xfs.rst

@@ -495,3 +495,41 @@ the class and error context. For example, the default values for
 "metadata/ENODEV" are "0" rather than "-1" so that this error handler defaults
 to "fail immediately" behaviour. This is done because ENODEV is a fatal,
 unrecoverable error no matter how many times the metadata IO is retried.
+
+Workqueue Concurrency
+=====================
+
+XFS uses kernel workqueues to parallelize metadata update processes.  This
+enables it to take advantage of storage hardware that can service many IO
+operations simultaneously.  This interface exposes internal implementation
+details of XFS, and as such is explicitly not part of any userspace API/ABI
+guarantee the kernel may give userspace.  These are undocumented features of
+the generic workqueue implementation XFS uses for concurrency, and they are
+provided here purely for diagnostic and tuning purposes and may change at any
+time in the future.
+
+The control knobs for a filesystem's workqueues are organized by task at hand
+and the short name of the data device.  They all can be found in:
+
+  /sys/bus/workqueue/devices/${task}!${device}
+
+================  ===========
+  Task            Description
+================  ===========
+  xfs_iwalk-$pid  Inode scans of the entire filesystem. Currently limited to
+                  mount time quotacheck.
+================  ===========
+
+For example, the knobs for the quotacheck workqueue for /dev/nvme0n1 would be
+found in /sys/bus/workqueue/devices/xfs_iwalk-1111!nvme0n1/.
+
+The interesting knobs for XFS workqueues are as follows:
+
+============     ===========
+  Knob           Description
+============     ===========
+  max_active     Maximum number of background threads that can be started to
+                 run the work.
+  cpumask        CPUs upon which the threads are allowed to run.
+  nice           Relative priority of scheduling the threads.  These are the
+                 same nice levels that can be applied to userspace processes.

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;
 

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;
-}

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__ */