mm/vmscan: centralise timeout values for reclaim_throttle

Neil Brown raised concerns about callers of reclaim_throttle specifying
a timeout value.  The original timeout values to congestion_wait() were
probably pulled out of thin air or copy&pasted from somewhere else.
This patch centralises the timeout values and selects a timeout based on
the reason for reclaim throttling.  These figures are also pulled out of
the same thin air but better values may be derived

Running a workload that is throttling for inappropriate periods and
tracing mm_vmscan_throttled can be used to pick a more appropriate
value.  Excessive throttling would pick a lower timeout where as
excessive CPU usage in reclaim context would select a larger timeout.
Ideally a large value would always be used and the wakeups would occur
before a timeout but that requires careful testing.

Link: https://lkml.kernel.org/r/20211022144651.19914-7-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: "Darrick J . Wong" <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: NeilBrown <neilb@suse.de>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 37 insertions, 13 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7d3fe5938e3b..599e5616b123 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1006,12 +1006,10 @@ static void handle_write_error(struct address_space *mapping,
 	unlock_page(page);
 }
 
-void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
-							long timeout)
+void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
 {
 	wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason];
-	long ret;
-	bool acct_writeback = (reason == VMSCAN_THROTTLE_WRITEBACK);
+	long timeout, ret;
 	DEFINE_WAIT(wait);
 
 	/*
@@ -1023,17 +1021,43 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
 	    current->flags & (PF_IO_WORKER|PF_KTHREAD))
 		return;
 
-	if (acct_writeback &&
-	    atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
-		WRITE_ONCE(pgdat->nr_reclaim_start,
-			node_page_state(pgdat, NR_THROTTLED_WRITTEN));
+	/*
+	 * These figures are pulled out of thin air.
+	 * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many
+	 * parallel reclaimers which is a short-lived event so the timeout is
+	 * short. Failing to make progress or waiting on writeback are
+	 * potentially long-lived events so use a longer timeout. This is shaky
+	 * logic as a failure to make progress could be due to anything from
+	 * writeback to a slow device to excessive references pages at the tail
+	 * of the inactive LRU.
+	 */
+	switch(reason) {
+	case VMSCAN_THROTTLE_WRITEBACK:
+		timeout = HZ/10;
+
+		if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) {
+			WRITE_ONCE(pgdat->nr_reclaim_start,
+				node_page_state(pgdat, NR_THROTTLED_WRITTEN));
+		}
+
+		break;
+	case VMSCAN_THROTTLE_NOPROGRESS:
+		timeout = HZ/10;
+		break;
+	case VMSCAN_THROTTLE_ISOLATED:
+		timeout = HZ/50;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		timeout = HZ;
+		break;
 	}
 
 	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
 	ret = schedule_timeout(timeout);
 	finish_wait(wqh, &wait);
 
-	if (acct_writeback)
+	if (reason == VMSCAN_THROTTLE_WRITEBACK)
 		atomic_dec(&pgdat->nr_writeback_throttled);
 
 	trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout),
@@ -2318,7 +2342,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 		/* wait a bit for the reclaimer. */
 		stalled = true;
-		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10);
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);
 
 		/* We are about to die and free our memory. Return now. */
 		if (fatal_signal_pending(current))
@@ -3250,7 +3274,7 @@ again:
 		 * until some pages complete writeback.
 		 */
 		if (sc->nr.immediate)
-			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10);
+			reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
 	}
 
 	/*
@@ -3274,7 +3298,7 @@ again:
 	if (!current_is_kswapd() && current_may_throttle() &&
 	    !sc->hibernation_mode &&
 	    test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
-		reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10);
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
 
 	if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
 				    sc))
@@ -3346,7 +3370,7 @@ static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc)
 
 	/* Throttle if making no progress at high prioities. */
 	if (sc->priority < DEF_PRIORITY - 2)
-		reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS, HZ/10);
+		reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS);
 }
 
 /*