From 19025df645ce865608ad5d0a1e92d5db24aea473 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@techsingularity.net>
Date: Fri, 5 Nov 2021 13:42:42 -0700
Subject: [PATCH] mm/vmscan: centralise timeout values for reclaim_throttle
References: bsc#1190208 (MM functional and performance backports)
Patch-mainline: v5.16-rc1
Git-commit: c3f4a9a2b082c5392fbff17c6d8551154add5fdb
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>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
mm/compaction.c | 2 +-
mm/internal.h | 3 +--
mm/page-writeback.c | 2 +-
mm/vmscan.c | 50 +++++++++++++++++++++++++++++++++++++-------------
4 files changed, 40 insertions(+), 17 deletions(-)
diff --git a/mm/compaction.c b/mm/compaction.c
index 62ad4c075477..fa9e46ae4f19 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -828,7 +828,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
if (cc->mode == MIGRATE_ASYNC)
return -EAGAIN;
- reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10);
+ reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED);
if (fatal_signal_pending(current))
return -EINTR;
diff --git a/mm/internal.h b/mm/internal.h
index 789090d6f77c..be57661ca139 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -129,8 +129,7 @@ extern unsigned long highest_memmap_pfn;
*/
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);
-extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason,
- long timeout);
+extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);
/*
* in mm/rmap.c:
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index df63b556abe4..bf503cd46c33 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2376,7 +2376,7 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
* guess as any.
*/
reclaim_throttle(NODE_DATA(numa_node_id()),
- VMSCAN_THROTTLE_WRITEBACK, HZ/50);
+ VMSCAN_THROTTLE_WRITEBACK);
}
/*
* Usually few pages are written by now from those we've just submitted
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 410a2a72be80..d55318dc9052 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -960,12 +960,10 @@ 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);
/*
@@ -977,17 +975,43 @@ 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),
@@ -2198,7 +2222,7 @@ 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))
@@ -3107,7 +3131,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
* until some pages complete writeback.
*/
if (sc->nr.immediate)
- reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10);
+ reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK);
}
/*
@@ -3131,7 +3155,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
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))
@@ -3203,7 +3227,7 @@ 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);
}
/*