delayacct: track delays from thrashing cache pages

Delay accounting already measures the time a task spends in direct reclaim
and waiting for swapin, but in low memory situations tasks spend can spend
a significant amount of their time waiting on thrashing page cache.  This
isn't tracked right now.

To know the full impact of memory contention on an individual task,
measure the delay when waiting for a recently evicted active cache page to
read back into memory.

Also update tools/accounting/getdelays.c:

     [hannes@computer accounting]$ sudo ./getdelays -d -p 1
     print delayacct stats ON
     PID     1

     CPU             count     real total  virtual total    delay total  delay average
                     50318      745000000      847346785      400533713          0.008ms
     IO              count    delay total  delay average
                       435      122601218              0ms
     SWAP            count    delay total  delay average
                         0              0              0ms
     RECLAIM         count    delay total  delay average
                         0              0              0ms
     THRASHING       count    delay total  delay average
                        19       12621439              0ms

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Johannes Weiner <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Tested-by: Daniel Drake <[email protected]>
Tested-by: Suren Baghdasaryan <[email protected]>
Cc: Christopher Lameter <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Enderborg <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Vinayak Menon <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/delayacct.h

@@ -57,7 +57,12 @@ struct task_delay_info {
 
 	u64 freepages_start;
 	u64 freepages_delay;	/* wait for memory reclaim */
+
+	u64 thrashing_start;
+	u64 thrashing_delay;	/* wait for thrashing page */
+
 	u32 freepages_count;	/* total count of memory reclaim */
+	u32 thrashing_count;	/* total count of thrash waits */
 };
 #endif
 
@@ -76,6 +81,8 @@ 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);
+extern void __delayacct_thrashing_start(void);
+extern void __delayacct_thrashing_end(void);
 
 static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
 {
@@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void)
 		__delayacct_freepages_end();
 }
 
+static inline void delayacct_thrashing_start(void)
+{
+	if (current->delays)
+		__delayacct_thrashing_start();
+}
+
+static inline void delayacct_thrashing_end(void)
+{
+	if (current->delays)
+		__delayacct_thrashing_end();
+}
+
 #else
 static inline void delayacct_set_flag(int flag)
 {}
@@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void)
 {}
 static inline void delayacct_freepages_end(void)
 {}
+static inline void delayacct_thrashing_start(void)
+{}
+static inline void delayacct_thrashing_end(void)
+{}
 
 #endif /* CONFIG_TASK_DELAY_ACCT */
 

include/uapi/linux/taskstats.h

@@ -34,7 +34,7 @@
  */
 
 
-#define TASKSTATS_VERSION	8
+#define TASKSTATS_VERSION	9
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
@@ -164,6 +164,10 @@ struct taskstats {
 	/* Delay waiting for memory reclaim */
 	__u64	freepages_count;
 	__u64	freepages_delay_total;
+
+	/* Delay waiting for thrashing page */
+	__u64	thrashing_count;
+	__u64	thrashing_delay_total;
 };
 
 

kernel/delayacct.c

@@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
 	tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
 	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;
 	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;
 	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
@@ -169,3 +172,15 @@ void __delayacct_freepages_end(void)
 		&current->delays->freepages_count);
 }
 
+void __delayacct_thrashing_start(void)
+{
+	current->delays->thrashing_start = ktime_get_ns();
+}
+
+void __delayacct_thrashing_end(void)
+{
+	delayacct_end(&current->delays->lock,
+		      &current->delays->thrashing_start,
+		      &current->delays->thrashing_delay,
+		      &current->delays->thrashing_count);
+}

mm/filemap.c

@@ -36,6 +36,7 @@
 #include <linux/cleancache.h>
 #include <linux/shmem_fs.h>
 #include <linux/rmap.h>
+#include <linux/delayacct.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -1073,8 +1074,15 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 {
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
+	bool thrashing = false;
 	int ret = 0;
 
+	if (bit_nr == PG_locked && !PageSwapBacked(page) &&
+	    !PageUptodate(page) && PageWorkingset(page)) {
+		delayacct_thrashing_start();
+		thrashing = true;
+	}
+
 	init_wait(wait);
 	wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
 	wait->func = wake_page_function;
@@ -1113,6 +1121,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
 
 	finish_wait(q, wait);
 
+	if (thrashing)
+		delayacct_thrashing_end();
+
 	/*
 	 * A signal could leave PageWaiters set. Clearing it here if
 	 * !waitqueue_active would be possible (by open-coding finish_wait),

tools/accounting/getdelays.c

@@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t)
 	       "SWAP  %15s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n"
 	       "RECLAIM  %12s%15s%15s\n"
+	       "      %15llu%15llu%15llums\n"
+	       "THRASHING%12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n",
 	       "count", "real total", "virtual total",
 	       "delay total", "delay average",
@@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t)
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->freepages_count,
 	       (unsigned long long)t->freepages_delay_total,
-	       average_ms(t->freepages_delay_total, t->freepages_count));
+	       average_ms(t->freepages_delay_total, t->freepages_count),
+	       "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));
 }
 
 static void task_context_switch_counts(struct taskstats *t)