[PATCH v6] io_uring: Statistics of the true utilization of sq threads.

[Xiaobing Li <xiaobing.li@xxxxxxxxxxx>]

Count the running time and actual IO processing time of the sqpoll
thread, and output the statistical data to fdinfo.

Variable description:
"work_time" in the code represents the sum of the jiffies of the sq
thread actually processing IO, that is, how many milliseconds it
actually takes to process IO. "total_time" represents the total time
that the sq thread has elapsed from the beginning of the loop to the
current time point, that is, how many milliseconds it has spent in
total.

The test results are as follows:
Every 0.5s: cat /proc/23112/fdinfo/6 | grep Sq
SqMask: 0x3
SqHead: 1168417
SqTail: 1168418
CachedSqHead:   1168418
SqThread:       23112
SqThreadCpu:    55
SqWorkTime:     12423
SqTotalTime:    12843

changes：
v6:
 - Replace the percentages in the fdinfo output with the actual running
time and the time actually processing IO

v5：
 - list the changes in each iteration.

v4：
 - Resubmit the patch based on removing sq->lock

v3：
 - output actual working time as a percentage of total time
 - detailed description of the meaning of each variable
 - added test results

v2：
 - output the total statistical time and work time to fdinfo

v1：
 - initial version
 - Statistics of total time and work time

Signed-off-by: Xiaobing Li <xiaobing.li@xxxxxxxxxxx>
---
 io_uring/fdinfo.c | 6 ++++++
 io_uring/sqpoll.c | 8 ++++++++
 io_uring/sqpoll.h | 2 ++
 3 files changed, 16 insertions(+)

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 976e9500f651..82d3d9471bac 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -64,6 +64,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 	unsigned int sq_shift = 0;
 	unsigned int sq_entries, cq_entries;
 	int sq_pid = -1, sq_cpu = -1;
+	unsigned long work_time = 0;
+	unsigned long total_time = 0;
 	bool has_lock;
 	unsigned int i;
 
@@ -147,10 +149,14 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 
 		sq_pid = sq->task_pid;
 		sq_cpu = sq->sq_cpu;
+		work_time = sq->work_time;
+		total_time = sq->total_time;
 	}
 
 	seq_printf(m, "SqThread:\t%d\n", sq_pid);
 	seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
+	seq_printf(m, "SqWorkTime:\t%lu\n", work_time);
+	seq_printf(m, "SqTotalTime:\t%lu\n", total_time);
 	seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
 	for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
 		struct file *f = io_file_from_index(&ctx->file_table, i);
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 65b5dbe3c850..9b74e344c52a 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -225,6 +225,7 @@ static int io_sq_thread(void *data)
 	struct io_ring_ctx *ctx;
 	unsigned long timeout = 0;
 	char buf[TASK_COMM_LEN];
+	unsigned long sq_start, sq_work_begin, sq_work_end;
 	DEFINE_WAIT(wait);
 
 	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
@@ -241,6 +242,7 @@ static int io_sq_thread(void *data)
 	}
 
 	mutex_lock(&sqd->lock);
+	sq_start = jiffies;
 	while (1) {
 		bool cap_entries, sqt_spin = false;
 
@@ -251,6 +253,7 @@ static int io_sq_thread(void *data)
 		}
 
 		cap_entries = !list_is_singular(&sqd->ctx_list);
+		sq_work_begin = jiffies;
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
 			int ret = __io_sq_thread(ctx, cap_entries);
 
@@ -260,6 +263,11 @@ static int io_sq_thread(void *data)
 		if (io_run_task_work())
 			sqt_spin = true;
 
+		sq_work_end = jiffies;
+		sqd->total_time = sq_work_end - sq_start;
+		if (sqt_spin == true)
+			sqd->work_time += sq_work_end - sq_work_begin;
+
 		if (sqt_spin || !time_after(jiffies, timeout)) {
 			if (sqt_spin)
 				timeout = jiffies + sqd->sq_thread_idle;
diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
index 8df37e8c9149..92b4b07220fa 100644
--- a/io_uring/sqpoll.h
+++ b/io_uring/sqpoll.h
@@ -16,6 +16,8 @@ struct io_sq_data {
 	pid_t			task_pid;
 	pid_t			task_tgid;
 
+	unsigned long		work_time;
+	unsigned long		total_time;
 	unsigned long		state;
 	struct completion	exited;
 };
-- 
2.43.0