Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: SeongJae Park <sjpark@amazon.com>
To: <akpm@linux-foundation.org>
Cc: SeongJae Park <sjpark@amazon.de>, <Jonathan.Cameron@Huawei.com>,
	<aarcange@redhat.com>, <acme@kernel.org>,
	<alexander.shishkin@linux.intel.com>, <amit@kernel.org>,
	<benh@kernel.crashing.org>, <brendan.d.gregg@gmail.com>,
	<brendanhiggins@google.com>, <cai@lca.pw>,
	<colin.king@canonical.com>, <corbet@lwn.net>, <david@redhat.com>,
	<dwmw@amazon.com>, <foersleo@amazon.de>, <irogers@google.com>,
	<jolsa@redhat.com>, <kirill@shutemov.name>,
	<mark.rutland@arm.com>, <mgorman@suse.de>, <minchan@kernel.org>,
	<mingo@redhat.com>, <namhyung@kernel.org>, <peterz@infradead.org>,
	<rdunlap@infradead.org>, <riel@surriel.com>,
	<rientjes@google.com>, <rostedt@goodmis.org>, <rppt@kernel.org>,
	<sblbir@amazon.com>, <shakeelb@google.com>, <shuah@kernel.org>,
	<sj38.park@gmail.com>, <snu@amazon.de>, <vbabka@suse.cz>,
	<vdavydov.dev@gmail.com>, <yang.shi@linux.alibaba.com>,
	<ying.huang@intel.com>, <linux-damon@amazon.com>,
	<linux-mm@kvack.org>, <linux-doc@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>
Subject: [PATCH v18 04/14] mm/damon: Adaptively adjust regions
Date: Mon, 13 Jul 2020 10:41:34 +0200
Message-ID: <20200713084144.4430-5-sjpark@amazon.com> (raw)
In-Reply-To: <20200713084144.4430-1-sjpark@amazon.com>

From: SeongJae Park <sjpark@amazon.de>

Even somehow the initial monitoring target regions are well constructed
to fulfill the assumption (pages in same region have similar access
frequencies), the data access pattern can be dynamically changed.  This
will result in low monitoring quality.  To keep the assumption as much
as possible, DAMON adaptively merges and splits each region based on
their access frequency.

For each ``aggregation interval``, it compares the access frequencies of
adjacent regions and merges those if the frequency difference is small.
Then, after it reports and clears the aggregated access frequency of
each region, it splits each region into two or three regions if the
total number of regions will not exceed the user-specified maximum
number of regions after the split.

In this way, DAMON provides its best-effort quality and minimal overhead
while keeping the upper-bound overhead that users set.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
Reviewed-by: Leonard Foerster <foersleo@amazon.de>
---
 include/linux/damon.h |  11 ++-
 mm/damon.c            | 191 ++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 189 insertions(+), 13 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 7adc7b6b3507..97ddc74e207f 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -61,7 +61,8 @@ struct damon_task {
  *
  * @sample_interval:		The time between access samplings.
  * @aggr_interval:		The time between monitor results aggregations.
- * @nr_regions:			The number of monitoring regions.
+ * @min_nr_regions:		The minimum number of monitoring regions.
+ * @max_nr_regions:		The maximum number of monitoring regions.
  *
  * For each @sample_interval, DAMON checks whether each region is accessed or
  * not.  It aggregates and keeps the access information (number of accesses to
@@ -114,7 +115,8 @@ struct damon_task {
 struct damon_ctx {
 	unsigned long sample_interval;
 	unsigned long aggr_interval;
-	unsigned long nr_regions;
+	unsigned long min_nr_regions;
+	unsigned long max_nr_regions;
 
 	struct timespec64 last_aggregation;
 
@@ -133,8 +135,9 @@ struct damon_ctx {
 };
 
 int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids);
-int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
-		unsigned long aggr_int, unsigned long min_nr_reg);
+int damon_set_attrs(struct damon_ctx *ctx,
+		unsigned long sample_int, unsigned long aggr_int,
+		unsigned long min_nr_reg, unsigned long max_nr_reg);
 int damon_start(struct damon_ctx *ctx);
 int damon_stop(struct damon_ctx *ctx);
 
diff --git a/mm/damon.c b/mm/damon.c
index 29d82c2d65be..02bc7542a76f 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -176,6 +176,26 @@ static unsigned int nr_damon_regions(struct damon_task *t)
 	return nr_regions;
 }
 
+/* Returns the size upper limit for each monitoring region */
+static unsigned long damon_region_sz_limit(struct damon_ctx *ctx)
+{
+	struct damon_task *t;
+	struct damon_region *r;
+	unsigned long sz = 0;
+
+	damon_for_each_task(t, ctx) {
+		damon_for_each_region(r, t)
+			sz += r->ar.end - r->ar.start;
+	}
+
+	if (ctx->min_nr_regions)
+		sz /= ctx->min_nr_regions;
+	if (sz < MIN_REGION)
+		sz = MIN_REGION;
+
+	return sz;
+}
+
 /*
  * Functions for DAMON core logics and features
  */
@@ -226,6 +246,145 @@ static void kdamond_reset_aggregated(struct damon_ctx *c)
 	}
 }
 
+#define sz_damon_region(r) (r->ar.end - r->ar.start)
+
+/*
+ * Merge two adjacent regions into one region
+ */
+static void damon_merge_two_regions(struct damon_region *l,
+				struct damon_region *r)
+{
+	l->nr_accesses = (l->nr_accesses * sz_damon_region(l) +
+			r->nr_accesses * sz_damon_region(r)) /
+			(sz_damon_region(l) + sz_damon_region(r));
+	l->ar.end = r->ar.end;
+	damon_destroy_region(r);
+}
+
+#define diff_of(a, b) (a > b ? a - b : b - a)
+
+/*
+ * Merge adjacent regions having similar access frequencies
+ *
+ * t		task affected by merge operation
+ * thres	'->nr_accesses' diff threshold for the merge
+ * sz_limit	size upper limit of each region
+ */
+static void damon_merge_regions_of(struct damon_task *t, unsigned int thres,
+				   unsigned long sz_limit)
+{
+	struct damon_region *r, *prev = NULL, *next;
+
+	damon_for_each_region_safe(r, next, t) {
+		if (prev && prev->ar.end == r->ar.start &&
+		    diff_of(prev->nr_accesses, r->nr_accesses) <= thres &&
+		    sz_damon_region(prev) + sz_damon_region(r) <= sz_limit)
+			damon_merge_two_regions(prev, r);
+		else
+			prev = r;
+	}
+}
+
+/*
+ * Merge adjacent regions having similar access frequencies
+ *
+ * threshold	'->nr_accesses' diff threshold for the merge
+ * sz_limit	size upper limit of each region
+ *
+ * This function merges monitoring target regions which are adjacent and their
+ * access frequencies are similar.  This is for minimizing the monitoring
+ * overhead under the dynamically changeable access pattern.  If a merge was
+ * unnecessarily made, later 'kdamond_split_regions()' will revert it.
+ */
+static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold,
+				  unsigned long sz_limit)
+{
+	struct damon_task *t;
+
+	damon_for_each_task(t, c)
+		damon_merge_regions_of(t, threshold, sz_limit);
+}
+
+/*
+ * Split a region in two
+ *
+ * r		the region to be split
+ * sz_r		size of the first sub-region that will be made
+ */
+static void damon_split_region_at(struct damon_ctx *ctx,
+				  struct damon_region *r, unsigned long sz_r)
+{
+	struct damon_region *new;
+
+	new = damon_new_region(r->ar.start + sz_r, r->ar.end);
+	r->ar.end = new->ar.start;
+
+	damon_insert_region(new, r, damon_next_region(r));
+}
+
+/* Split every region in the given task into 'nr_subs' regions */
+static void damon_split_regions_of(struct damon_ctx *ctx,
+				     struct damon_task *t, int nr_subs)
+{
+	struct damon_region *r, *next;
+	unsigned long sz_region, sz_sub = 0;
+	int i;
+
+	damon_for_each_region_safe(r, next, t) {
+		sz_region = r->ar.end - r->ar.start;
+
+		for (i = 0; i < nr_subs - 1 &&
+				sz_region > 2 * MIN_REGION; i++) {
+			/*
+			 * Randomly select size of left sub-region to be at
+			 * least 10 percent and at most 90% of original region
+			 */
+			sz_sub = ALIGN_DOWN(damon_rand(1, 10) *
+					sz_region / 10, MIN_REGION);
+			/* Do not allow blank region */
+			if (sz_sub == 0 || sz_sub >= sz_region)
+				continue;
+
+			damon_split_region_at(ctx, r, sz_sub);
+			sz_region = sz_sub;
+		}
+	}
+}
+
+/*
+ * Split every target region into randomly-sized small regions
+ *
+ * This function splits every target region into random-sized small regions if
+ * current total number of the regions is equal or smaller than half of the
+ * user-specified maximum number of regions.  This is for maximizing the
+ * monitoring accuracy under the dynamically changeable access patterns.  If a
+ * split was unnecessarily made, later 'kdamond_merge_regions()' will revert
+ * it.
+ */
+static void kdamond_split_regions(struct damon_ctx *ctx)
+{
+	struct damon_task *t;
+	unsigned int nr_regions = 0;
+	static unsigned int last_nr_regions;
+	int nr_subregions = 2;
+
+	damon_for_each_task(t, ctx)
+		nr_regions += nr_damon_regions(t);
+
+	if (nr_regions > ctx->max_nr_regions / 2)
+		return;
+
+	/* Maybe the middle of the region has different access frequency */
+	if (last_nr_regions == nr_regions &&
+			nr_regions < ctx->max_nr_regions / 3)
+		nr_subregions = 3;
+
+	damon_for_each_task(t, ctx)
+		damon_split_regions_of(ctx, t, nr_subregions);
+
+	last_nr_regions = nr_regions;
+}
+
 /*
  * Check whether current monitoring should be stopped
  *
@@ -269,10 +428,14 @@ static int kdamond_fn(void *data)
 	struct damon_ctx *ctx = (struct damon_ctx *)data;
 	struct damon_task *t;
 	struct damon_region *r, *next;
+	unsigned int max_nr_accesses = 0;
+	unsigned long sz_limit = 0;
 
 	pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
 	if (ctx->init_target_regions)
 		ctx->init_target_regions(ctx);
+	sz_limit = damon_region_sz_limit(ctx);
+
 	while (!kdamond_need_stop(ctx)) {
 		if (ctx->prepare_access_checks)
 			ctx->prepare_access_checks(ctx);
@@ -282,14 +445,16 @@ static int kdamond_fn(void *data)
 		usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
 
 		if (ctx->check_accesses)
-			ctx->check_accesses(ctx);
+			max_nr_accesses = ctx->check_accesses(ctx);
 
 		if (kdamond_aggregate_interval_passed(ctx)) {
 			if (ctx->aggregate_cb)
 				ctx->aggregate_cb(ctx);
+			kdamond_merge_regions(ctx, max_nr_accesses / 10,
+					sz_limit);
 			kdamond_reset_aggregated(ctx);
+			kdamond_split_regions(ctx);
 		}
-
 	}
 	damon_for_each_task(t, ctx) {
 		damon_for_each_region_safe(r, next, t)
@@ -400,25 +565,33 @@ int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids)
  * @ctx:		monitoring context
  * @sample_int:		time interval between samplings
  * @aggr_int:		time interval between aggregations
- * @nr_reg:		number of regions
+ * @min_nr_reg:		minimal number of regions
+ * @max_nr_reg:		maximum number of regions
  *
  * This function should not be called while the kdamond is running.
  * Every time interval is in micro-seconds.
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
-		unsigned long aggr_int, unsigned long nr_reg)
+int damon_set_attrs(struct damon_ctx *ctx,
+		    unsigned long sample_int, unsigned long aggr_int,
+		    unsigned long min_nr_reg, unsigned long max_nr_reg)
 {
-	if (nr_reg < 3) {
-		pr_err("nr_regions (%lu) must be at least 3\n",
-				nr_reg);
+	if (min_nr_reg < 3) {
+		pr_err("min_nr_regions (%lu) must be at least 3\n",
+				min_nr_reg);
+		return -EINVAL;
+	}
+	if (min_nr_reg > max_nr_reg) {
+		pr_err("invalid nr_regions.  min (%lu) > max (%lu)\n",
+				min_nr_reg, max_nr_reg);
 		return -EINVAL;
 	}
 
 	ctx->sample_interval = sample_int;
 	ctx->aggr_interval = aggr_int;
-	ctx->nr_regions = nr_reg;
+	ctx->min_nr_regions = min_nr_reg;
+	ctx->max_nr_regions = max_nr_reg;
 
 	return 0;
 }
-- 
2.17.1



  parent reply index

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-13  8:41 [PATCH v18 00/14] Introduce Data Access MONitor (DAMON) SeongJae Park
2020-07-13  8:41 ` [PATCH v18 01/14] mm/page_ext: Export lookup_page_ext() to GPL modules SeongJae Park
2020-07-13 12:08   ` Mike Rapoport
2020-07-13 12:21     ` SeongJae Park
2020-07-13 17:19       ` Mike Rapoport
2020-07-13 17:38         ` SeongJae Park
2020-07-17  9:59           ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 02/14] mm: Introduce Data Access MONitor (DAMON) SeongJae Park
2020-07-18  2:47   ` Shakeel Butt
2020-07-18 13:31     ` SeongJae Park
2020-07-29 15:31       ` Shakeel Butt
2020-07-29 17:29         ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 03/14] mm/damon: Implement region based sampling SeongJae Park
2020-07-13  8:41 ` SeongJae Park [this message]
2020-07-13  8:41 ` [PATCH v18 05/14] mm/damon: Track dynamic monitoring target regions update SeongJae Park
2020-07-13  8:41 ` [PATCH v18 06/14] mm/damon: Implement callbacks for the virtual memory address spaces SeongJae Park
2020-07-17  0:46   ` Shakeel Butt
2020-07-17  6:53     ` SeongJae Park
2020-07-17 15:17       ` Shakeel Butt
2020-07-17 16:24         ` SeongJae Park
2020-07-18  2:23           ` Shakeel Butt
2020-07-18  2:51             ` SeongJae Park
2020-07-27  7:34   ` Greg Thelen
2020-07-27  9:02     ` SeongJae Park
2020-07-28 17:42       ` Shakeel Butt
2020-07-29  6:20         ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 07/14] mm/damon: Implement access pattern recording SeongJae Park
2020-07-13  8:41 ` [PATCH v18 08/14] mm/damon: Add a tracepoint SeongJae Park
2020-07-13  8:41 ` [PATCH v18 09/14] mm/damon: Implement a debugfs interface SeongJae Park
2020-07-22 10:36   ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 10/14] tools: Introduce a minimal user-space tool for DAMON SeongJae Park
2020-07-13  8:41 ` [PATCH v18 11/14] Documentation: Add documents " SeongJae Park
2020-07-27  7:19   ` Greg Thelen
2020-07-27  7:38     ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 12/14] mm/damon: Add kunit tests SeongJae Park
2020-07-13  8:41 ` [PATCH v18 13/14] mm/damon: Add user space selftests SeongJae Park
2020-07-13  8:41 ` [PATCH v18 14/14] MAINTAINERS: Update for DAMON SeongJae Park

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200713084144.4430-5-sjpark@amazon.com \
    --to=sjpark@amazon.com \
    --cc=Jonathan.Cameron@Huawei.com \
    --cc=aarcange@redhat.com \
    --cc=acme@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=amit@kernel.org \
    --cc=benh@kernel.crashing.org \
    --cc=brendan.d.gregg@gmail.com \
    --cc=brendanhiggins@google.com \
    --cc=cai@lca.pw \
    --cc=colin.king@canonical.com \
    --cc=corbet@lwn.net \
    --cc=david@redhat.com \
    --cc=dwmw@amazon.com \
    --cc=foersleo@amazon.de \
    --cc=irogers@google.com \
    --cc=jolsa@redhat.com \
    --cc=kirill@shutemov.name \
    --cc=linux-damon@amazon.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mark.rutland@arm.com \
    --cc=mgorman@suse.de \
    --cc=minchan@kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rdunlap@infradead.org \
    --cc=riel@surriel.com \
    --cc=rientjes@google.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=sblbir@amazon.com \
    --cc=shakeelb@google.com \
    --cc=shuah@kernel.org \
    --cc=sj38.park@gmail.com \
    --cc=sjpark@amazon.de \
    --cc=snu@amazon.de \
    --cc=vbabka@suse.cz \
    --cc=vdavydov.dev@gmail.com \
    --cc=yang.shi@linux.alibaba.com \
    --cc=ying.huang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git