delayacct: track delays from memory compact

Delay accounting does not track the delay of memory compact.  When there
is not enough free memory, tasks can spend a amount of their time
waiting for compact.

To get the impact of tasks in direct memory compact, measure the delay
when allocating memory through memory compact.

Also update tools/accounting/getdelays.c:

    / # ./getdelays_next  -di -p 304
    print delayacct stats ON
    printing IO accounting
    PID     304

    CPU             count     real total  virtual total    delay total  delay average
                      277      780000000      849039485       18877296          0.068ms
    IO              count    delay total  delay average
                        0              0              0ms
    SWAP            count    delay total  delay average
                        0              0              0ms
    RECLAIM         count    delay total  delay average
                        5    11088812685           2217ms
    THRASHING       count    delay total  delay average
                        0              0              0ms
    COMPACT         count    delay total  delay average
                        3          72758              0ms
    watch: read=0, write=0, cancelled_write=0

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: wangyong <[email protected]>
Reviewed-by: Jiang Xuexin <[email protected]>
Reviewed-by: Zhang Wenya <[email protected]>
Reviewed-by: Yang Yang <[email protected]>
Reviewed-by: Balbir Singh <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/delayacct.h

@@ -42,8 +42,12 @@ struct task_delay_info {
 	u64 thrashing_start;
 	u64 thrashing_delay;	/* wait for thrashing page */
 
+	u64 compact_start;
+	u64 compact_delay;	/* wait for memory compact */
+
 	u32 freepages_count;	/* total count of memory reclaim */
 	u32 thrashing_count;	/* total count of thrash waits */
+	u32 compact_count;	/* total count of memory compact */
 };
 #endif
 
@@ -72,6 +76,8 @@ extern void __delayacct_thrashing_start(void);
 extern void __delayacct_thrashing_end(void);
 extern void __delayacct_swapin_start(void);
 extern void __delayacct_swapin_end(void);
+extern void __delayacct_compact_start(void);
+extern void __delayacct_compact_end(void);
 
 static inline void delayacct_tsk_init(struct task_struct *tsk)
 {
@@ -170,6 +176,24 @@ static inline void delayacct_swapin_end(void)
 		__delayacct_swapin_end();
 }
 
+static inline void delayacct_compact_start(void)
+{
+	if (!static_branch_unlikely(&delayacct_key))
+		return;
+
+	if (current->delays)
+		__delayacct_compact_start();
+}
+
+static inline void delayacct_compact_end(void)
+{
+	if (!static_branch_unlikely(&delayacct_key))
+		return;
+
+	if (current->delays)
+		__delayacct_compact_end();
+}
+
 #else
 static inline void delayacct_init(void)
 {}
@@ -200,6 +224,10 @@ static inline void delayacct_swapin_start(void)
 {}
 static inline void delayacct_swapin_end(void)
 {}
+static inline void delayacct_compact_start(void)
+{}
+static inline void delayacct_compact_end(void)
+{}
 
 #endif /* CONFIG_TASK_DELAY_ACCT */
 

include/uapi/linux/taskstats.h

@@ -34,7 +34,7 @@
  */
 
 
-#define TASKSTATS_VERSION	10
+#define TASKSTATS_VERSION	11
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
@@ -172,6 +172,10 @@ struct taskstats {
 
 	/* v10: 64-bit btime to avoid overflow */
 	__u64	ac_btime64;		/* 64-bit begin time */
+
+	/* Delay waiting for memory compact */
+	__u64	compact_count;
+	__u64	compact_delay_total;
 };
 
 

kernel/delayacct.c

@@ -155,10 +155,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
 	tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
 	d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
+	tmp = d->compact_delay_total + tsk->delays->compact_delay;
+	d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp;
 	d->blkio_count += tsk->delays->blkio_count;
 	d->swapin_count += tsk->delays->swapin_count;
 	d->freepages_count += tsk->delays->freepages_count;
 	d->thrashing_count += tsk->delays->thrashing_count;
+	d->compact_count += tsk->delays->compact_count;
 	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
@@ -213,3 +216,16 @@ void __delayacct_swapin_end(void)
 		      &current->delays->swapin_delay,
 		      &current->delays->swapin_count);
 }
+
+void __delayacct_compact_start(void)
+{
+	current->delays->compact_start = local_clock();
+}
+
+void __delayacct_compact_end(void)
+{
+	delayacct_end(&current->delays->lock,
+		      &current->delays->compact_start,
+		      &current->delays->compact_delay,
+		      &current->delays->compact_count);
+}

mm/page_alloc.c

@@ -72,6 +72,7 @@
 #include <linux/padata.h>
 #include <linux/khugepaged.h>
 #include <linux/buffer_head.h>
+#include <linux/delayacct.h>
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -4348,13 +4349,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 	psi_memstall_enter(&pflags);
+	delayacct_compact_start();
 	noreclaim_flag = memalloc_noreclaim_save();
 
 	*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
 								prio, &page);
 
 	memalloc_noreclaim_restore(noreclaim_flag);
 	psi_memstall_leave(&pflags);
+	delayacct_compact_end();
 
 	if (*compact_result == COMPACT_SKIPPED)
 		return NULL;

tools/accounting/getdelays.c

@@ -205,6 +205,8 @@ static void print_delayacct(struct taskstats *t)
 	       "RECLAIM  %12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n"
 	       "THRASHING%12s%15s%15s\n"
+	       "      %15llu%15llu%15llums\n"
+	       "COMPACT  %12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n",
 	       "count", "real total", "virtual total",
 	       "delay total", "delay average",
@@ -228,7 +230,11 @@ static void print_delayacct(struct taskstats *t)
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->thrashing_count,
 	       (unsigned long long)t->thrashing_delay_total,
-	       average_ms(t->thrashing_delay_total, t->thrashing_count));
+	       average_ms(t->thrashing_delay_total, t->thrashing_count),
+	       "count", "delay total", "delay average",
+	       (unsigned long long)t->compact_count,
+	       (unsigned long long)t->compact_delay_total,
+	       average_ms(t->compact_delay_total, t->compact_count));
 }
 
 static void task_context_switch_counts(struct taskstats *t)