@@ -119,6 +119,21 @@ all zones are compacted such that free m
blocks where possible. This can be important for example in the allocation of
huge pages although processes will also directly compact memory as required.
+compaction_proactiveness
+========================
+
+This tunable takes a value in the range [0, 100] with a default value of
+20. This tunable determines how aggressively compaction is done in the
+background. Setting it to 0 disables proactive compaction.
+
+Note that compaction has a non-trivial system-wide impact as pages
+belonging to different processes are moved around, which could also lead
+to latency spikes in unsuspecting applications. The kernel employs
+various heuristics to avoid wasting CPU cycles if it detects that
+proactive compaction is not being effective.
+
+Be careful when setting it to extreme values like 100, as that may
+cause excessive background compaction activity.
compact_unevictable_allowed
===========================
@@ -85,11 +85,13 @@ static inline unsigned long compact_gap(
#ifdef CONFIG_COMPACTION
extern int sysctl_compact_memory;
+extern int sysctl_compaction_proactiveness;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos);
extern int sysctl_extfrag_threshold;
extern int sysctl_compact_unevictable_allowed;
+extern int extfrag_for_order(struct zone *zone, unsigned int order);
extern int fragmentation_index(struct zone *zone, unsigned int order);
extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
unsigned int order, unsigned int alloc_flags,
@@ -2852,6 +2852,15 @@ static struct ctl_table vm_table[] = {
.proc_handler = sysctl_compaction_handler,
},
{
+ .procname = "compaction_proactiveness",
+ .data = &sysctl_compaction_proactiveness,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &one_hundred,
+ },
+ {
.procname = "extfrag_threshold",
.data = &sysctl_extfrag_threshold,
.maxlen = sizeof(int),
@@ -50,6 +50,24 @@ static inline void count_compact_events(
#define pageblock_start_pfn(pfn) block_start_pfn(pfn, pageblock_order)
#define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order)
+/*
+ * Fragmentation score check interval for proactive compaction purposes.
+ */
+static const int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500;
+
+/*
+ * Page order with-respect-to which proactive compaction
+ * calculates external fragmentation, which is used as
+ * the "fragmentation score" of a node/zone.
+ */
+#if defined CONFIG_TRANSPARENT_HUGEPAGE
+#define COMPACTION_HPAGE_ORDER HPAGE_PMD_ORDER
+#elif defined HUGETLB_PAGE_ORDER
+#define COMPACTION_HPAGE_ORDER HUGETLB_PAGE_ORDER
+#else
+#define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT)
+#endif
+
static unsigned long release_freepages(struct list_head *freelist)
{
struct page *page, *next;
@@ -1857,6 +1875,76 @@ static inline bool is_via_compact_memory
return order == -1;
}
+static bool kswapd_is_running(pg_data_t *pgdat)
+{
+ return pgdat->kswapd && (pgdat->kswapd->state == TASK_RUNNING);
+}
+
+/*
+ * A zone's fragmentation score is the external fragmentation wrt to the
+ * COMPACTION_HPAGE_ORDER scaled by the zone's size. It returns a value
+ * in the range [0, 100].
+ *
+ * The scaling factor ensures that proactive compaction focuses on larger
+ * zones like ZONE_NORMAL, rather than smaller, specialized zones like
+ * ZONE_DMA32. For smaller zones, the score value remains close to zero,
+ * and thus never exceeds the high threshold for proactive compaction.
+ */
+static int fragmentation_score_zone(struct zone *zone)
+{
+ unsigned long score;
+
+ score = zone->present_pages *
+ extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+ return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
+}
+
+/*
+ * The per-node proactive (background) compaction process is started by its
+ * corresponding kcompactd thread when the node's fragmentation score
+ * exceeds the high threshold. The compaction process remains active till
+ * the node's score falls below the low threshold, or one of the back-off
+ * conditions is met.
+ */
+static int fragmentation_score_node(pg_data_t *pgdat)
+{
+ unsigned long score = 0;
+ int zoneid;
+
+ for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+ struct zone *zone;
+
+ zone = &pgdat->node_zones[zoneid];
+ score += fragmentation_score_zone(zone);
+ }
+
+ return score;
+}
+
+static int fragmentation_score_wmark(pg_data_t *pgdat, bool low)
+{
+ int wmark_low;
+
+ /*
+ * Cap the low watermak to avoid excessive compaction
+ * activity in case a user sets the proactivess tunable
+ * close to 100 (maximum).
+ */
+ wmark_low = max(100 - sysctl_compaction_proactiveness, 5);
+ return low ? wmark_low : min(wmark_low + 10, 100);
+}
+
+static bool should_proactive_compact_node(pg_data_t *pgdat)
+{
+ int wmark_high;
+
+ if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat))
+ return false;
+
+ wmark_high = fragmentation_score_wmark(pgdat, false);
+ return fragmentation_score_node(pgdat) > wmark_high;
+}
+
static enum compact_result __compact_finished(struct compact_control *cc)
{
unsigned int order;
@@ -1883,6 +1971,25 @@ static enum compact_result __compact_fin
return COMPACT_PARTIAL_SKIPPED;
}
+ if (cc->proactive_compaction) {
+ int score, wmark_low;
+ pg_data_t *pgdat;
+
+ pgdat = cc->zone->zone_pgdat;
+ if (kswapd_is_running(pgdat))
+ return COMPACT_PARTIAL_SKIPPED;
+
+ score = fragmentation_score_zone(cc->zone);
+ wmark_low = fragmentation_score_wmark(pgdat, true);
+
+ if (score > wmark_low)
+ ret = COMPACT_CONTINUE;
+ else
+ ret = COMPACT_SUCCESS;
+
+ goto out;
+ }
+
if (is_via_compact_memory(cc->order))
return COMPACT_CONTINUE;
@@ -1941,6 +2048,7 @@ static enum compact_result __compact_fin
}
}
+out:
if (cc->contended || fatal_signal_pending(current))
ret = COMPACT_CONTENDED;
@@ -2421,6 +2529,41 @@ enum compact_result try_to_compact_pages
return rc;
}
+/*
+ * Compact all zones within a node till each zone's fragmentation score
+ * reaches within proactive compaction thresholds (as determined by the
+ * proactiveness tunable).
+ *
+ * It is possible that the function returns before reaching score targets
+ * due to various back-off conditions, such as, contention on per-node or
+ * per-zone locks.
+ */
+static void proactive_compact_node(pg_data_t *pgdat)
+{
+ int zoneid;
+ struct zone *zone;
+ struct compact_control cc = {
+ .order = -1,
+ .mode = MIGRATE_SYNC_LIGHT,
+ .ignore_skip_hint = true,
+ .whole_zone = true,
+ .gfp_mask = GFP_KERNEL,
+ .proactive_compaction = true,
+ };
+
+ for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+ zone = &pgdat->node_zones[zoneid];
+ if (!populated_zone(zone))
+ continue;
+
+ cc.zone = zone;
+
+ compact_zone(&cc, NULL);
+
+ VM_BUG_ON(!list_empty(&cc.freepages));
+ VM_BUG_ON(!list_empty(&cc.migratepages));
+ }
+}
/* Compact all zones within a node */
static void compact_node(int nid)
@@ -2468,6 +2611,13 @@ static void compact_nodes(void)
int sysctl_compact_memory;
/*
+ * Tunable for proactive compaction. It determines how
+ * aggressively the kernel should compact memory in the
+ * background. It takes values in the range [0, 100].
+ */
+int __read_mostly sysctl_compaction_proactiveness = 20;
+
+/*
* This is the entry point for compacting all nodes via
* /proc/sys/vm/compact_memory
*/
@@ -2646,6 +2796,7 @@ static int kcompactd(void *p)
{
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
+ unsigned int proactive_defer = 0;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
@@ -2661,12 +2812,34 @@ static int kcompactd(void *p)
unsigned long pflags;
trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
- wait_event_freezable(pgdat->kcompactd_wait,
- kcompactd_work_requested(pgdat));
+ if (wait_event_freezable_timeout(pgdat->kcompactd_wait,
+ kcompactd_work_requested(pgdat),
+ msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) {
+
+ psi_memstall_enter(&pflags);
+ kcompactd_do_work(pgdat);
+ psi_memstall_leave(&pflags);
+ continue;
+ }
- psi_memstall_enter(&pflags);
- kcompactd_do_work(pgdat);
- psi_memstall_leave(&pflags);
+ /* kcompactd wait timeout */
+ if (should_proactive_compact_node(pgdat)) {
+ unsigned int prev_score, score;
+
+ if (proactive_defer) {
+ proactive_defer--;
+ continue;
+ }
+ prev_score = fragmentation_score_node(pgdat);
+ proactive_compact_node(pgdat);
+ score = fragmentation_score_node(pgdat);
+ /*
+ * Defer proactive compaction if the fragmentation
+ * score did not go down i.e. no progress made.
+ */
+ proactive_defer = score < prev_score ?
+ 0 : 1 << COMPACT_MAX_DEFER_SHIFT;
+ }
}
return 0;
@@ -239,6 +239,7 @@ struct compact_control {
bool no_set_skip_hint; /* Don't mark blocks for skipping */
bool ignore_block_suitable; /* Scan blocks considered unsuitable */
bool direct_compaction; /* False from kcompactd or /proc/... */
+ bool proactive_compaction; /* kcompactd proactive compaction */
bool whole_zone; /* Whole zone should/has been scanned */
bool contended; /* Signal lock or sched contention */
bool rescan; /* Rescanning the same pageblock */
@@ -1096,6 +1096,24 @@ static int __fragmentation_index(unsigne
return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total);
}
+/*
+ * Calculates external fragmentation within a zone wrt the given order.
+ * It is defined as the percentage of pages found in blocks of size
+ * less than 1 << order. It returns values in range [0, 100].
+ */
+int extfrag_for_order(struct zone *zone, unsigned int order)
+{
+ struct contig_page_info info;
+
+ fill_contig_page_info(zone, order, &info);
+ if (info.free_pages == 0)
+ return 0;
+
+ return div_u64((info.free_pages -
+ (info.free_blocks_suitable << order)) * 100,
+ info.free_pages);
+}
+
/* Same as __fragmentation index but allocs contig_page_info on stack */
int fragmentation_index(struct zone *zone, unsigned int order)
{