summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorSeongJae Park <sjpark@amazon.de>2021-09-08 05:56:36 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-08 21:50:24 +0300
commitb9a6ac4e4ede4172d165c133398b93e3233b0ba7 (patch)
treeea95534379ce9674af9e0e8791a9c74fa827ba66 /mm
parentf23b8eee1871a6db5c37f90831147de5426c40b7 (diff)
downloadlinux-b9a6ac4e4ede4172d165c133398b93e3233b0ba7.tar.xz
mm/damon: adaptively adjust regions
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. Link: https://lkml.kernel.org/r/20210716081449.22187-4-sj38.park@gmail.com Signed-off-by: SeongJae Park <sjpark@amazon.de> Reviewed-by: Leonard Foerster <foersleo@amazon.de> Reviewed-by: Fernand Sieber <sieberf@amazon.com> Acked-by: Shakeel Butt <shakeelb@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Amit Shah <amit@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Brendan Higgins <brendanhiggins@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: David Woodhouse <dwmw@amazon.com> Cc: Fan Du <fan.du@intel.com> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Greg Thelen <gthelen@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Marco Elver <elver@google.com> Cc: Markus Boehme <markubo@amazon.de> Cc: Maximilian Heyne <mheyne@amazon.de> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/damon/core.c224
1 files changed, 215 insertions, 9 deletions
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 947486a150ce..28a2c78914fa 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -10,8 +10,12 @@
#include <linux/damon.h>
#include <linux/delay.h>
#include <linux/kthread.h>
+#include <linux/random.h>
#include <linux/slab.h>
+/* Get a random number in [l, r) */
+#define damon_rand(l, r) (l + prandom_u32_max(r - l))
+
static DEFINE_MUTEX(damon_lock);
static int nr_running_ctxs;
@@ -40,19 +44,23 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end)
* Add a region between two other regions
*/
inline void damon_insert_region(struct damon_region *r,
- struct damon_region *prev, struct damon_region *next)
+ struct damon_region *prev, struct damon_region *next,
+ struct damon_target *t)
{
__list_add(&r->list, &prev->list, &next->list);
+ t->nr_regions++;
}
void damon_add_region(struct damon_region *r, struct damon_target *t)
{
list_add_tail(&r->list, &t->regions_list);
+ t->nr_regions++;
}
-static void damon_del_region(struct damon_region *r)
+static void damon_del_region(struct damon_region *r, struct damon_target *t)
{
list_del(&r->list);
+ t->nr_regions--;
}
static void damon_free_region(struct damon_region *r)
@@ -60,9 +68,9 @@ static void damon_free_region(struct damon_region *r)
kfree(r);
}
-void damon_destroy_region(struct damon_region *r)
+void damon_destroy_region(struct damon_region *r, struct damon_target *t)
{
- damon_del_region(r);
+ damon_del_region(r, t);
damon_free_region(r);
}
@@ -80,6 +88,7 @@ struct damon_target *damon_new_target(unsigned long id)
return NULL;
t->id = id;
+ t->nr_regions = 0;
INIT_LIST_HEAD(&t->regions_list);
return t;
@@ -87,7 +96,7 @@ struct damon_target *damon_new_target(unsigned long id)
void damon_add_target(struct damon_ctx *ctx, struct damon_target *t)
{
- list_add_tail(&t->list, &ctx->region_targets);
+ list_add_tail(&t->list, &ctx->adaptive_targets);
}
static void damon_del_target(struct damon_target *t)
@@ -110,6 +119,11 @@ void damon_destroy_target(struct damon_target *t)
damon_free_target(t);
}
+unsigned int damon_nr_regions(struct damon_target *t)
+{
+ return t->nr_regions;
+}
+
struct damon_ctx *damon_new_ctx(void)
{
struct damon_ctx *ctx;
@@ -127,7 +141,10 @@ struct damon_ctx *damon_new_ctx(void)
mutex_init(&ctx->kdamond_lock);
- INIT_LIST_HEAD(&ctx->region_targets);
+ ctx->min_nr_regions = 10;
+ ctx->max_nr_regions = 1000;
+
+ INIT_LIST_HEAD(&ctx->adaptive_targets);
return ctx;
}
@@ -157,6 +174,8 @@ void damon_destroy_ctx(struct damon_ctx *ctx)
* @sample_int: time interval between samplings
* @aggr_int: time interval between aggregations
* @primitive_upd_int: time interval between monitoring primitive updates
+ * @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.
@@ -164,15 +183,49 @@ void damon_destroy_ctx(struct damon_ctx *ctx)
* 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 primitive_upd_int)
+ unsigned long aggr_int, unsigned long primitive_upd_int,
+ unsigned long min_nr_reg, unsigned long max_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->primitive_update_interval = primitive_upd_int;
+ ctx->min_nr_regions = min_nr_reg;
+ ctx->max_nr_regions = max_nr_reg;
return 0;
}
+/* Returns the size upper limit for each monitoring region */
+static unsigned long damon_region_sz_limit(struct damon_ctx *ctx)
+{
+ struct damon_target *t;
+ struct damon_region *r;
+ unsigned long sz = 0;
+
+ damon_for_each_target(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 < DAMON_MIN_REGION)
+ sz = DAMON_MIN_REGION;
+
+ return sz;
+}
+
static bool damon_kdamond_running(struct damon_ctx *ctx)
{
bool running;
@@ -339,6 +392,150 @@ 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_target *t,
+ struct damon_region *l, struct damon_region *r)
+{
+ unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r);
+
+ l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
+ (sz_l + sz_r);
+ l->ar.end = r->ar.end;
+ damon_destroy_region(r, t);
+}
+
+#define diff_of(a, b) (a > b ? a - b : b - a)
+
+/*
+ * Merge adjacent regions having similar access frequencies
+ *
+ * t target affected by this 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_target *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(t, 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_target *t;
+
+ damon_for_each_target(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_target *t, struct damon_region *r,
+ unsigned long sz_r)
+{
+ struct damon_region *new;
+
+ new = damon_new_region(r->ar.start + sz_r, r->ar.end);
+ if (!new)
+ return;
+
+ r->ar.end = new->ar.start;
+
+ damon_insert_region(new, r, damon_next_region(r), t);
+}
+
+/* Split every region in the given target into 'nr_subs' regions */
+static void damon_split_regions_of(struct damon_ctx *ctx,
+ struct damon_target *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 * DAMON_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, DAMON_MIN_REGION);
+ /* Do not allow blank region */
+ if (sz_sub == 0 || sz_sub >= sz_region)
+ continue;
+
+ damon_split_region_at(ctx, t, 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_target *t;
+ unsigned int nr_regions = 0;
+ static unsigned int last_nr_regions;
+ int nr_subregions = 2;
+
+ damon_for_each_target(t, ctx)
+ nr_regions += damon_nr_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_target(t, ctx)
+ damon_split_regions_of(ctx, t, nr_subregions);
+
+ last_nr_regions = nr_regions;
+}
+
/*
* Check whether it is time to check and apply the target monitoring regions
*
@@ -395,6 +592,8 @@ static int kdamond_fn(void *data)
struct damon_ctx *ctx = (struct damon_ctx *)data;
struct damon_target *t;
struct damon_region *r, *next;
+ unsigned int max_nr_accesses = 0;
+ unsigned long sz_limit = 0;
mutex_lock(&ctx->kdamond_lock);
pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
@@ -405,6 +604,8 @@ static int kdamond_fn(void *data)
if (ctx->callback.before_start && ctx->callback.before_start(ctx))
set_kdamond_stop(ctx);
+ sz_limit = damon_region_sz_limit(ctx);
+
while (!kdamond_need_stop(ctx)) {
if (ctx->primitive.prepare_access_checks)
ctx->primitive.prepare_access_checks(ctx);
@@ -415,13 +616,17 @@ static int kdamond_fn(void *data)
usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
if (ctx->primitive.check_accesses)
- ctx->primitive.check_accesses(ctx);
+ max_nr_accesses = ctx->primitive.check_accesses(ctx);
if (kdamond_aggregate_interval_passed(ctx)) {
+ kdamond_merge_regions(ctx,
+ max_nr_accesses / 10,
+ sz_limit);
if (ctx->callback.after_aggregation &&
ctx->callback.after_aggregation(ctx))
set_kdamond_stop(ctx);
kdamond_reset_aggregated(ctx);
+ kdamond_split_regions(ctx);
if (ctx->primitive.reset_aggregated)
ctx->primitive.reset_aggregated(ctx);
}
@@ -429,11 +634,12 @@ static int kdamond_fn(void *data)
if (kdamond_need_update_primitive(ctx)) {
if (ctx->primitive.update)
ctx->primitive.update(ctx);
+ sz_limit = damon_region_sz_limit(ctx);
}
}
damon_for_each_target(t, ctx) {
damon_for_each_region_safe(r, next, t)
- damon_destroy_region(r);
+ damon_destroy_region(r, t);
}
if (ctx->callback.before_terminate &&