Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.33 as permitted sender) client-ip=23.128.96.33;
From:   Xiaobing Li <xiaobing.li@samsung.com>
To:     axboe@kernel.dk, asml.silence@gmail.com
Cc:     linux-kernel@vger.kernel.org, io-uring@vger.kernel.org,
        kun.dou@samsung.com, peiwei.li@samsung.com, joshi.k@samsung.com,
        kundan.kumar@samsung.com, wenwen.chen@samsung.com,
        ruyi.zhang@samsung.com, cliang01.li@samsung.com,
        xue01.he@samsung.com, Xiaobing Li <xiaobing.li@samsung.com>
Subject: [PATCH v4] io_uring: Statistics of the true utilization of sq
 threads.
Date:   Wed, 13 Dec 2023 11:25:13 +0800
Message-Id: <20231213032513.12591-1-xiaobing.li@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 105P
DLP-Filter: Pass
References: <CGME20231213033309epcas5p4a312be32080125bfe62bf5353abadd74@epcas5p4.samsung.com>
Precedence: bulk

v4:
1.Since the sq thread has a while(1) structure, during this process,
  there may be a lot of time that is not processing IO but does not
exceed the timeout period, therefore, the sqpoll thread will keep
running and will keep occupying the CPU. Obviously, the CPU is wasted at
this time;Our goal is to count the part of the time that the sqpoll
thread actually processes IO, so as to reflect the part of the CPU it
uses to process IO, which can be used to help improve the actual
utilization of the CPU in the future.

2."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 output "SqBusy" represents the percentage of time utilization that
the sq thread actually uses to process IO.

Signed-off-by: Xiaobing Li <xiaobing.li@samsung.com>

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
SqBusy: 97%
---
 io_uring/fdinfo.c | 4 ++++
 io_uring/sqpoll.c | 8 ++++++++
 io_uring/sqpoll.h | 2 ++
 3 files changed, 14 insertions(+)

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 976e9500f651..b0f9d296c5aa 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -64,6 +64,7 @@ __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;
+	int sq_busy = 0;
 	bool has_lock;
 	unsigned int i;
 
@@ -147,10 +148,13 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
 
 		sq_pid = sq->task_pid;
 		sq_cpu = sq->sq_cpu;
+		if (sq->total_time != 0)
+			sq_busy = (int)(sq->work_time * 100 / sq->total_time);
 	}
 
 	seq_printf(m, "SqThread:\t%d\n", sq_pid);
 	seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu);
+	seq_printf(m, "SqBusy:\t%d%%\n", sq_busy);
 	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;
 };
-- 
2.34.1