block/diskstats: more accurate approximation of io_ticks for slow disks

commit 2b8bd423614c595540eaadcfbc702afe8e155e50 upstream.

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:

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   82,50    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>
From: "Banerjee, Debabrata" <dbanerje@akamai.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/Documentation/admin-guide/iostats.rst b/Documentation/admin-guide/iostats.rst
index 5d63b18bd6d1f626cfefcceb76727df2dcb5f38d..60c45c916f7d053c93e23e9488bf1eb92c337d61 100644 (file)
--- a/Documentation/admin-guide/iostats.rst
+++ b/Documentation/admin-guide/iostats.rst
@@ -99,7 +99,7 @@ Field 10 -- # of milliseconds spent doing I/Os
 
     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 unsigned long variable they are
 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
 -------------------
 

diff --git a/block/bio.c b/block/bio.c
index f07739300dfe3994d7fe5e711f42a84428fea612..24704bc2ad6f1c9bbe8c0b65d518eb8ebc1ce232 100644 (file)
--- a/block/bio.c
+++ b/block/bio.c
@@ -1754,14 +1754,14 @@ 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) {
@@ -1777,7 +1777,7 @@ void generic_start_io_acct(struct request_queue *q, int op,
 
        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));
@@ -1795,7 +1795,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op,
 
        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));

diff --git a/block/blk-core.c b/block/blk-core.c
index ca6b677356864367748a0488a35baa397d008aab..81aafb601df06d649636f0d5275fca80c028db6a 100644 (file)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1334,7 +1334,7 @@ void blk_account_io_done(struct request *req, u64 now)
                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));
@@ -1376,7 +1376,7 @@ void blk_account_io_start(struct request *rq, bool new_io)
                rq->part = part;
        }
 
-       update_io_ticks(part, jiffies);
+       update_io_ticks(part, jiffies, false);
 
        part_stat_unlock();
 }

diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 62a2ec9f17df80e1978834e0558e3f682ccfc9fc..c1bf9956256f6ee0d6676b707b634735ff60206b 100644 (file)
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -419,7 +419,7 @@ static inline void free_part_info(struct hd_struct *part)
        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,