per-task-delay-accounting: add memory reclaim delay

Sometimes, application responses become bad under heavy memory load.
Applications take a bit time to reclaim memory. The statistics, how long
memory reclaim takes, will be useful to measure memory usage.

This patch adds accounting memory reclaim to per-task-delay-accounting for
accounting the time of do_try_to_free_pages().

<i.e>

- When System is under low memory load,
memory reclaim may not occur.

$ free
total used free shared buffers cached
Mem: 8197800 1577300 6620500 0 4808 1516724
-/+ buffers/cache: 55768 8142032
Swap: 16386292 0 16386292

$ vmstat 1
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0
0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0
0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0

Measure the time of tar command.

$ ls -s test.dat
1501472 test.dat

$ time tar cvf test.tar test.dat
real 0m13.388s
user 0m0.116s
sys 0m5.304s

$ ./delayget -d -p <pid>
CPU count real total virtual total delay total
428 5528345500 5477116080 62749891
IO count delay total
338 8078977189
SWAP count delay total
0 0
RECLAIM count delay total
0 0

- When system is under heavy memory load
memory reclaim may occur.

$ vmstat 1
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0
0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0
0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0

In this case, one process uses more 8G memory
by execution of malloc() and memset().

$ time tar cvf test.tar test.dat
real 1m38.563s <- increased by 85 sec
user 0m0.140s
sys 0m7.060s

$ ./delayget -d -p <pid>
CPU count real total virtual total delay total
9021 7140446250 7315277975 923201824
IO count delay total
8965 90466349669
SWAP count delay total
3 21036367
RECLAIM count delay total
740 61011951153

In the later case, the value of RECLAIM is increasing.
So, taskstats can show how much memory reclaim influences TAT.

Signed-off-by: Keika Kobayashi <[e-mail]>
Acked-by: Balbir Singh <[e-mail]>
Acked-by: KOSAKI Motohiro <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/delayacct.h

···
 extern void __delayacct_blkio_end(void);
 extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
 extern __u64 __delayacct_blkio_ticks(struct task_struct *);
+extern void __delayacct_freepages_start(void);
+extern void __delayacct_freepages_end(void);
 
 static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
 {
···
 	return 0;
 }
 
+static inline void delayacct_freepages_start(void)
+{
+	if (current->delays)
+		__delayacct_freepages_start();
+}
+
+static inline void delayacct_freepages_end(void)
+{
+	if (current->delays)
+		__delayacct_freepages_end();
+}
+
 #else
 static inline void delayacct_set_flag(int flag)
 {}
···
 { return 0; }
 static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
 { return 0; }
+static inline void delayacct_freepages_start(void)
+{}
+static inline void delayacct_freepages_end(void)
+{}
+
 #endif /* CONFIG_TASK_DELAY_ACCT */
 
 #endif

include/linux/sched.h

···
 				/* io operations performed */
 	u32 swapin_count;	/* total count of the number of swapin block */
 				/* io operations performed */
+
+	struct timespec freepages_start, freepages_end;
+	u64 freepages_delay;	/* wait for memory reclaim */
+	u32 freepages_count;	/* total count of memory reclaim */
 };
 #endif	/* CONFIG_TASK_DELAY_ACCT */
 

kernel/delayacct.c

···
 	return ret;
 }
 
+void __delayacct_freepages_start(void)
+{
+	delayacct_start(&current->delays->freepages_start);
+}
+
+void __delayacct_freepages_end(void)
+{
+	delayacct_end(&current->delays->freepages_start,
+			&current->delays->freepages_end,
+			&current->delays->freepages_delay,
+			&current->delays->freepages_count);
+}
+

mm/vmscan.c

···
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/memcontrol.h>
+#include <linux/delayacct.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
···
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
 
+	delayacct_freepages_start();
+
 	if (scan_global_lru(sc))
 		count_vm_event(ALLOCSTALL);
 	/*
···
 		}
 	} else
 		mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
+
+	delayacct_freepages_end();
 
 	return ret;
 }