From 2b8bd423614c595540eaadcfbc702afe8e155e50 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 25 Mar 2020 16:07:04 +0300 Subject: block/diskstats: more accurate approximation of io_ticks for slow disks 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 Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/bio.c | 8 ++++---- block/blk-core.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'block') diff --git a/block/bio.c b/block/bio.c index 209715765a7a..68f65ef2ceba 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1768,14 +1768,14 @@ 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) { @@ -1791,7 +1791,7 @@ 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)); @@ -1809,7 +1809,7 @@ 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 abfdcf81a228..4401b30a1751 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1337,7 +1337,7 @@ 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)); @@ -1379,7 +1379,7 @@ 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(); } -- cgit v1.2.3-59-g8ed1b