delayacct: add delay max to record delay peak

Introduce the use cases of delay max, which can help quickly detect
potential abnormal delays in the system and record the types and specific
details of delay spikes.

Problem
========
Delay accounting can track the average delay of processes to show
system workload. However, when a process experiences a significant
delay, maybe a delay spike, which adversely affects performance,
getdelays can only display the average system delay over a period
of time. Yet, average delay is unhelpful for diagnosing delay peak.
It is not even possible to determine which type of delay has spiked,
as this information might be masked by the average delay.

Solution
=========
the 'delay max' can display delay peak since the system's startup,
which can record potential abnormal delays over time, including
the type of delay and the maximum delay. This is helpful for
quickly identifying crash caused by delay.

Use case
=========
bash# ./getdelays -d -p 244
print delayacct stats ON
PID     244

CPU             count     real total  virtual total    delay total  delay average      delay max
                   68      192000000      213676651         705643          0.010ms     0.306381ms
IO              count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
SWAP            count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
RECLAIM         count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
THRASHING       count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
COMPACT         count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
WPCOPY          count    delay total  delay average      delay max
                  235       15648284          0.067ms     0.263842ms
IRQ             count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms

[wang.yaxin@zte.com.cn: update docs and fix some spelling errors]
  Link: https://lkml.kernel.org/r/20241213192700771XKZ8H30OtHSeziGqRVMs0@zte.com.cn
Link: https://lkml.kernel.org/r/20241203164848805CS62CQPQWG9GLdQj2_BxS@zte.com.cn
Co-developed-by: Wang Yong <wang.yong12@zte.com.cn>
Signed-off-by: Wang Yong <wang.yong12@zte.com.cn>
Co-developed-by: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: xu xin <xu.xin16@zte.com.cn>
Co-developed-by: Wang Yaxin <wang.yaxin@zte.com.cn>
Signed-off-by: Wang Yaxin <wang.yaxin@zte.com.cn>
Signed-off-by: Kun Jiang <jiang.kun2@zte.com.cn>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Fan Yu <fan.yu9@zte.com.cn>
Cc: Peilin He <he.peilin@zte.com.cn>
Cc: tuqiang <tu.qiang35@zte.com.cn>
Cc: Yang Yang <yang.yang29@zte.com.cn>
Cc: ye xingchen <ye.xingchen@zte.com.cn>
Cc: Yunkai Zhang <zhang.yunkai@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 19 insertions, 0 deletions

diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6639f48dac36..56fbfa2c2ac5 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -29,25 +29,32 @@ struct task_delay_info {
 	 * XXX_delay contains the accumulated delay time in nanoseconds.
 	 */
 	u64 blkio_start;
+	u64 blkio_delay_max;
 	u64 blkio_delay;	/* wait for sync block io completion */
 	u64 swapin_start;
+	u64 swapin_delay_max;
 	u64 swapin_delay;	/* wait for swapin */
 	u32 blkio_count;	/* total count of the number of sync block */
 				/* io operations performed */
 	u32 swapin_count;	/* total count of swapin */
 
 	u64 freepages_start;
+	u64 freepages_delay_max;
 	u64 freepages_delay;	/* wait for memory reclaim */
 
 	u64 thrashing_start;
+	u64 thrashing_delay_max;
 	u64 thrashing_delay;	/* wait for thrashing page */
 
 	u64 compact_start;
+	u64 compact_delay_max;
 	u64 compact_delay;	/* wait for memory compact */
 
 	u64 wpcopy_start;
+	u64 wpcopy_delay_max;
 	u64 wpcopy_delay;	/* wait for write-protect copy */
 
+	u64 irq_delay_max;
 	u64 irq_delay;	/* wait for IRQ/SOFTIRQ */
 
 	u32 freepages_count;	/* total count of memory reclaim */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 64934e0830af..a0ae3923b41d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -398,6 +398,9 @@ struct sched_info {
 	/* Time spent waiting on a runqueue: */
 	unsigned long long		run_delay;
 
+	/* Max time spent waiting on a runqueue: */
+	unsigned long long		max_run_delay;
+
 	/* Timestamps: */
 
 	/* When did we last run on a CPU? */
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
index b50b2eb257a0..e0d1c6fc9f3b 100644
--- a/include/uapi/linux/taskstats.h
+++ b/include/uapi/linux/taskstats.h
@@ -72,6 +72,7 @@ struct taskstats {
 	 */
 	__u64	cpu_count __attribute__((aligned(8)));
 	__u64	cpu_delay_total;
+	__u64	cpu_delay_max;
 
 	/* Following four fields atomically updated using task->delays->lock */
 
@@ -80,10 +81,12 @@ struct taskstats {
 	 */
 	__u64	blkio_count;
 	__u64	blkio_delay_total;
+	__u64	blkio_delay_max;
 
 	/* Delay waiting for page fault I/O (swap in only) */
 	__u64	swapin_count;
 	__u64	swapin_delay_total;
+	__u64	swapin_delay_max;
 
 	/* cpu "wall-clock" running time
 	 * On some architectures, value will adjust for cpu time stolen
@@ -166,10 +169,12 @@ struct taskstats {
 	/* Delay waiting for memory reclaim */
 	__u64	freepages_count;
 	__u64	freepages_delay_total;
+	__u64	freepages_delay_max;
 
 	/* Delay waiting for thrashing page */
 	__u64	thrashing_count;
 	__u64	thrashing_delay_total;
+	__u64	thrashing_delay_max;
 
 	/* v10: 64-bit btime to avoid overflow */
 	__u64	ac_btime64;		/* 64-bit begin time */
@@ -177,6 +182,7 @@ struct taskstats {
 	/* v11: Delay waiting for memory compact */
 	__u64	compact_count;
 	__u64	compact_delay_total;
+	__u64	compact_delay_max;
 
 	/* v12 begin */
 	__u32   ac_tgid;	/* thread group ID */
@@ -198,10 +204,13 @@ struct taskstats {
 	/* v13: Delay waiting for write-protect copy */
 	__u64    wpcopy_count;
 	__u64    wpcopy_delay_total;
+	__u64    wpcopy_delay_max;
 
 	/* v14: Delay waiting for IRQ/SOFTIRQ */
 	__u64    irq_count;
 	__u64    irq_delay_total;
+	__u64    irq_delay_max;
+	/* v15: add Delay max */
 };