Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Khalid Aziz <khalid.aziz@oracle.com>
To:     akpm@linux-foundation.org, vbabka@suse.cz,
        mgorman@techsingularity.net, mhocko@suse.com,
        dan.j.williams@intel.com
Cc:     Khalid Aziz <khalid.aziz@oracle.com>, osalvador@suse.de,
        richard.weiyang@gmail.com, hannes@cmpxchg.org,
        arunks@codeaurora.org, rppt@linux.vnet.ibm.com, jgg@ziepe.ca,
        amir73il@gmail.com, alexander.h.duyck@linux.intel.com,
        linux-mm@kvack.org, linux-kernel-mentees@lists.linuxfoundation.org,
        linux-kernel@vger.kernel.org,
        Bharath Vedartham <linux.bhar@gmail.com>,
        Vandana BN <bnvandana@gmail.com>
Subject: [RFC PATCH 2/2] mm/vmscan: Add fragmentation and page starvation prediction to kswapd
Date:   Mon, 12 Aug 2019 19:40:12 -0600
Message-Id: <20190813014012.30232-3-khalid.aziz@oracle.com>
In-Reply-To: <20190813014012.30232-1-khalid.aziz@oracle.com>
References: <20190813014012.30232-1-khalid.aziz@oracle.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This patch adds proactive memory reclamation to kswapd using the
free page exhaustion/fragmentation prediction based upon memory
consumption trend. It uses the least squares fit algorithm introduced
earlier for this prediction. A new function node_trend_analysis()
iterates through all zones and updates trend data in the lookback
window for least square fit algorithm. At the same time it flags any
zones that have potential for exhaustion/fragmentation by setting
ZONE_POTENTIAL_FRAG flag.

prepare_kswapd_sleep() calls node_trend_analysis() to check if the
node has potential exhaustion/fragmentation. If so, kswapd will
continue reclamataion. balance_pgdat has been modified to take
potential fragmentation into account when deciding when to wake
kcompactd up. Any zones that have potential severe fragmentation get
watermark boosted to reclaim and compact free pages proactively.

Signed-off-by: Khalid Aziz <khalid.aziz@oracle.com>
Signed-off-by: Bharath Vedartham <linux.bhar@gmail.com>
Tested-by: Vandana BN <bnvandana@gmail.com>
---
 include/linux/mmzone.h |  38 ++++++++++++++
 mm/page_alloc.c        |  27 ----------
 mm/vmscan.c            | 116 ++++++++++++++++++++++++++++++++++++++---
 3 files changed, 148 insertions(+), 33 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9a0e5cab7171..a523476b5ce1 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -587,6 +587,12 @@ struct zone {
 
 	bool			contiguous;
 
+	/*
+	 * Structures to use for memory consumption prediction for
+	 * each order
+	 */
+	struct lsq_struct	mem_prediction[MAX_ORDER];
+
 	ZONE_PADDING(_pad3_)
 	/* Zone statistics */
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
@@ -611,6 +617,9 @@ enum zone_flags {
 	ZONE_BOOSTED_WATERMARK,		/* zone recently boosted watermarks.
 					 * Cleared when kswapd is woken.
 					 */
+	ZONE_POTENTIAL_FRAG,		/* zone detected with a potential
+					 * external fragmentation event.
+					 */
 };
 
 extern int mem_predict(struct frag_info *frag_vec, struct zone *zone);
@@ -1130,6 +1139,35 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 #define for_each_zone_zonelist(zone, z, zlist, highidx) \
 	for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL)
 
+extern int watermark_boost_factor;
+
+static inline void boost_watermark(struct zone *zone)
+{
+	unsigned long max_boost;
+
+	if (!watermark_boost_factor)
+		return;
+
+	max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
+			watermark_boost_factor, 10000);
+
+	/*
+	 * high watermark may be uninitialised if fragmentation occurs
+	 * very early in boot so do not boost. We do not fall
+	 * through and boost by pageblock_nr_pages as failing
+	 * allocations that early means that reclaim is not going
+	 * to help and it may even be impossible to reclaim the
+	 * boosted watermark resulting in a hang.
+	 */
+	if (!max_boost)
+		return;
+
+	max_boost = max(pageblock_nr_pages, max_boost);
+
+	zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
+		max_boost);
+}
+
 #ifdef CONFIG_SPARSEMEM
 #include <asm/sparsemem.h>
 #endif
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 272c6de1bf4e..1b4e6ba16f1c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2351,33 +2351,6 @@ static bool can_steal_fallback(unsigned int order, int start_mt)
 	return false;
 }
 
-static inline void boost_watermark(struct zone *zone)
-{
-	unsigned long max_boost;
-
-	if (!watermark_boost_factor)
-		return;
-
-	max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
-			watermark_boost_factor, 10000);
-
-	/*
-	 * high watermark may be uninitialised if fragmentation occurs
-	 * very early in boot so do not boost. We do not fall
-	 * through and boost by pageblock_nr_pages as failing
-	 * allocations that early means that reclaim is not going
-	 * to help and it may even be impossible to reclaim the
-	 * boosted watermark resulting in a hang.
-	 */
-	if (!max_boost)
-		return;
-
-	max_boost = max(pageblock_nr_pages, max_boost);
-
-	zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
-		max_boost);
-}
-
 /*
  * This function implements actual steal behaviour. If order is large enough,
  * we can steal whole pageblock. If not, we first move freepages in this
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 44df66a98f2a..b9cf6658c83d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -51,6 +51,7 @@
 #include <linux/printk.h>
 #include <linux/dax.h>
 #include <linux/psi.h>
+#include <linux/jiffies.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -3397,14 +3398,82 @@ static void clear_pgdat_congested(pg_data_t *pgdat)
 	clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
 }
 
+/*
+ * Update  trend data and perform trend analysis for a zone to foresee
+ * a low memory or severe fragmentation event
+ */
+static int zone_trend_analysis(struct zone *zone)
+{
+	struct frag_info frag_vec[MAX_ORDER];
+	int order, result;
+	unsigned long total_free_pages;
+	unsigned long curr_free_pages;
+
+	total_free_pages = frag_vec[0].free_pages = 0;
+	for (order = 0; order < MAX_ORDER; order++) {
+		curr_free_pages = zone->free_area[order].nr_free << order;
+		total_free_pages += curr_free_pages;
+
+		if (order < MAX_ORDER - 1) {
+			frag_vec[order + 1].free_pages =
+				frag_vec[order].free_pages + curr_free_pages;
+			frag_vec[order + 1].time =
+				jiffies64_to_msecs(get_jiffies_64()
+				- INITIAL_JIFFIES);
+		}
+	}
+	frag_vec[0].free_pages = total_free_pages;
+	frag_vec[0].time = frag_vec[MAX_ORDER - 1].time;
+
+	result = mem_predict(frag_vec, zone);
+
+	return result;
+}
+
+/*
+ * Perform trend analysis for memory usage for each zone in the node to
+ * detect potential upcoming low memory or fragmented memory conditions
+ */
+static int node_trend_analysis(pg_data_t *pgdat, int classzone_idx)
+{
+	struct zone *zone = NULL;
+	int i, retval = 0;
+
+	for (i = 0; i <= classzone_idx; i++) {
+		int zoneval;
+
+		zone = pgdat->node_zones + i;
+
+		if (!managed_zone(zone))
+			continue;
+
+		/*
+		 * Check if trend analysis shows potential fragmentation
+		 * in near future
+		 */
+		zoneval = zone_trend_analysis(zone);
+		if (zoneval & MEMPREDICT_COMPACT)
+			set_bit(ZONE_POTENTIAL_FRAG, &zone->flags);
+		if (zoneval & MEMPREDICT_RECLAIM)
+			boost_watermark(zone);
+		retval |= zoneval;
+	}
+
+	return retval;
+}
+
 /*
  * Prepare kswapd for sleeping. This verifies that there are no processes
  * waiting in throttle_direct_reclaim() and that watermarks have been met.
+ * It also checks if this node could have a potential external fragmentation
+ * event which could lead to direct reclaim/compaction stalls.
  *
  * Returns true if kswapd is ready to sleep
  */
 static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 {
+	int retval;
+
 	/*
 	 * The throttled processes are normally woken up in balance_pgdat() as
 	 * soon as allow_direct_reclaim() is true. But there is a potential
@@ -3425,6 +3494,21 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
 		return true;
 
+	/*
+	 * Check whether this node could have a potential memory
+	 * exhaustion in near future. If trend analysis shows such
+	 * an event occurring, don't allow kswapd to sleep so
+	 * reclamation starts now to prevent memory exhaustion. If
+	 * trend analysis shows no impending memory exhaustion but
+	 * shows impending severe fragmentation, return true to
+	 * wake up kcompactd.
+	 */
+	retval = node_trend_analysis(pgdat, classzone_idx);
+	if (retval & MEMPREDICT_RECLAIM)
+		return false;
+	if (retval & MEMPREDICT_COMPACT)
+		return true;
+
 	if (pgdat_balanced(pgdat, order, classzone_idx)) {
 		clear_pgdat_congested(pgdat);
 		return true;
@@ -3498,6 +3582,8 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 	unsigned long nr_boost_reclaim;
 	unsigned long zone_boosts[MAX_NR_ZONES] = { 0, };
 	bool boosted;
+	bool potential_frag = 0;
+	bool need_compact;
 	struct zone *zone;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
@@ -3524,9 +3610,27 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 
 		nr_boost_reclaim += zone->watermark_boost;
 		zone_boosts[i] = zone->watermark_boost;
+
+		/*
+		 * Check if any of the zones could have a potential
+		 * fragmentation event.
+		 */
+		if (test_bit(ZONE_POTENTIAL_FRAG, &zone->flags)) {
+			potential_frag = 1;
+			clear_bit(ZONE_POTENTIAL_FRAG, &zone->flags);
+		}
 	}
 	boosted = nr_boost_reclaim;
 
+	/*
+	 * If kswapd is woken up because of watermark boosting or forced
+	 * to run another balance_pgdat run because it detected an
+	 * external fragmentation event, run compaction after
+	 * reclaiming some pages. need_compact is true if such compaction
+	 * is required.
+	 */
+	need_compact = boosted || potential_frag;
+
 restart:
 	sc.priority = DEF_PRIORITY;
 	do {
@@ -3645,7 +3749,6 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		 */
 		nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
 		nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed);
-
 		/*
 		 * If reclaim made no progress for a boost, stop reclaim as
 		 * IO cannot be queued and it could be an infinite loop in
@@ -3676,13 +3779,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 			zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]);
 			spin_unlock_irqrestore(&zone->lock, flags);
 		}
+	}
 
-		/*
-		 * As there is now likely space, wakeup kcompact to defragment
-		 * pageblocks.
-		 */
+	/*
+	 * As there is now likely space, wakeup kcompactd to defragment
+	 * pageblocks.
+	 */
+	if (need_compact)
 		wakeup_kcompactd(pgdat, pageblock_order, classzone_idx);
-	}
 
 	snapshot_refaults(NULL, pgdat);
 	__fs_reclaim_release();
-- 
2.20.1