From 2b8bd423614c595540eaadcfbc702afe8e155e50 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Wed, 25 Mar 2020 16:07:04 +0300
Subject: [PATCH] block/diskstats: more accurate approximation of io_ticks for
 slow disks
Git-commit: 2b8bd423614c595540eaadcfbc702afe8e155e50
Patch-mainline: v5.7-rc1
References: bsc#1168761

Currently io_ticks is approximated by adding one at each start and end of
requests if jiffies counter has changed. This works perfectly for requests
shorter than a jiffy or if one of requests starts/ends at each jiffy.

If disk executes just one request at a time and they are longer than two
jiffies then only first and last jiffies will be accounted.

Fix is simple: at the end of request add up into io_ticks jiffies passed
since last update rather than just one jiffy.

Example: common HDD executes random read 4k requests around 12ms.

fio --name=test --filename=/dev/sdb --rw=randread --direct=1 --runtime=30 &
iostat -x 10 sdb

Note changes of iostat's "%util" 8,43% -> 99,99% before/after patch:

Before: 

Device: rrqm/s   wrqm/s     r/s     w/s    rkB/s    wkB/s avgrq-sz avgqu-sz   await r_await w_await  svctm  %util
sdb               0,00     0,00   82,60    0,00   330,40     0,00     8,00     0,96   12,09   12,09    0,00   1,02   8,43

After: 

sdb               0,00     0,00   82,50    0,00   330,00     0,00     8,00     1,00   12,10   12,10    0,00  12,12  99,99

Now io_ticks does not loose time between start and end of requests, but
for queue-depth > 1 some I/O time between adjacent starts might be lost.

For load estimation "%util" is not as useful as average queue length,
but it clearly shows how often disk queue is completely empty.

Fixes: 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting")
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Jan Kara <jack@suse.cz>

---
 Documentation/admin-guide/iostats.rst |    5 ++++-
 block/bio.c                           |    8 ++++----
 block/blk-core.c                      |    4 ++--
 include/linux/genhd.h                 |    2 +-
 4 files changed, 11 insertions(+), 8 deletions(-)

--- a/Documentation/admin-guide/iostats.rst
+++ b/Documentation/admin-guide/iostats.rst
@@ -99,7 +99,7 @@ Field 10 -- # of milliseconds spent doin
 
     Since 5.0 this field counts jiffies when at least one request was
     started or completed. If request runs more than 2 jiffies then some
-    I/O time will not be accounted unless there are other requests.
+    I/O time might be not accounted in case of concurrent requests.
 
 Field 11 -- weighted # of milliseconds spent doing I/Os
     This field is incremented at each I/O start, I/O completion, I/O
@@ -133,6 +133,9 @@ are summed (possibly overflowing the uns
 summed to) and the result given to the user.  There is no convenient
 user interface for accessing the per-CPU counters themselves.
 
+Since 4.19 request times are measured with nanoseconds precision and
+truncated to milliseconds before showing in this interface.
+
 Disks vs Partitions
 -------------------
 
--- a/block/bio.c
+++ b/block/bio.c
@@ -1700,14 +1700,14 @@ defer:
 	schedule_work(&bio_dirty_work);
 }
 
-void update_io_ticks(struct hd_struct *part, unsigned long now)
+void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
 {
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->stamp);
 	if (unlikely(stamp != now)) {
 		if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) {
-			__part_stat_add(part, io_ticks, 1);
+			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 		}
 	}
 	if (part->partno) {
@@ -1723,7 +1723,7 @@ void generic_start_io_acct(struct reques
 
 	part_stat_lock();
 
-	update_io_ticks(part, jiffies);
+	update_io_ticks(part, jiffies, false);
 	part_stat_inc(part, ios[sgrp]);
 	part_stat_add(part, sectors[sgrp], sectors);
 	part_inc_in_flight(q, part, op_is_write(op));
@@ -1741,7 +1741,7 @@ void generic_end_io_acct(struct request_
 
 	part_stat_lock();
 
-	update_io_ticks(part, now);
+	update_io_ticks(part, now, true);
 	part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
 	part_stat_add(part, time_in_queue, duration);
 	part_dec_in_flight(q, part, op_is_write(req_op));
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1333,7 +1333,7 @@ void blk_account_io_done(struct request
 		part_stat_lock();
 		part = req->part;
 
-		update_io_ticks(part, jiffies);
+		update_io_ticks(part, jiffies, true);
 		part_stat_inc(part, ios[sgrp]);
 		part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
 		part_stat_add(part, time_in_queue, nsecs_to_jiffies64(now - req->start_time_ns));
@@ -1375,7 +1375,7 @@ void blk_account_io_start(struct request
 		rq->part = part;
 	}
 
-	update_io_ticks(part, jiffies);
+	update_io_ticks(part, jiffies, false);
 
 	part_stat_unlock();
 }
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -419,7 +419,7 @@ static inline void free_part_info(struct
 	kfree(part->info);
 }
 
-void update_io_ticks(struct hd_struct *part, unsigned long now);
+void update_io_ticks(struct hd_struct *part, unsigned long now, bool end);
 
 /* block/genhd.c */
 extern void device_add_disk(struct device *parent, struct gendisk *disk,