Commit b57e99b4 authored by Omar Sandoval's avatar Omar Sandoval Committed by Jens Axboe
Browse files

block: use nanosecond resolution for iostat 



Klaus Kusche reported that the I/O busy time in /proc/diskstats was not
updating properly on 4.18. This is because we started using ktime to
track elapsed time, and we convert nanoseconds to jiffies when we update
the partition counter. However, this gets rounded down, so any I/Os that
take less than a jiffy are not accounted for. Previously in this case,
the value of jiffies would sometimes increment while we were doing I/O,
so at least some I/Os were accounted for.

Let's convert the stats to use nanoseconds internally. We still report
milliseconds as before, now more accurately than ever. The value is
still truncated to 32 bits for backwards compatibility.

Fixes: 522a7775 ("block: consolidate struct request timestamp fields")
Cc: stable@vger.kernel.org
Reported-by: default avatarKlaus Kusche <klaus.kusche@computerix.info>
Signed-off-by: default avatarOmar Sandoval <osandov@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent d611aaf3

block/bio.c

+1 −1
Original line number Diff line number Diff line
@@ -1684,7 +1684,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op, 
	const int sgrp = op_stat_group(req_op);

	int cpu = part_stat_lock();



	part_stat_add(cpu, part, ticks[sgrp], duration);

	part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration));

	part_round_stats(q, cpu, part);

	part_dec_in_flight(q, part, op_is_write(req_op));

block/blk-core.c

+1 −3
Original line number Diff line number Diff line
@@ -2733,17 +2733,15 @@ void blk_account_io_done(struct request *req, u64 now) 
	 * containing request is enough.

	 */

	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {

		unsigned long duration;

		const int sgrp = op_stat_group(req_op(req));

		struct hd_struct *part;

		int cpu;



		duration = nsecs_to_jiffies(now - req->start_time_ns);

		cpu = part_stat_lock();

		part = req->part;



		part_stat_inc(cpu, part, ios[sgrp]);

		part_stat_add(cpu, part, ticks[sgrp], duration);

		part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns);

		part_round_stats(req->q, cpu, part);

		part_dec_in_flight(req->q, part, rq_data_dir(req));

block/genhd.c

+3 −3
Original line number Diff line number Diff line
@@ -1343,18 +1343,18 @@ static int diskstats_show(struct seq_file *seqf, void *v) 
			   part_stat_read(hd, ios[STAT_READ]),

			   part_stat_read(hd, merges[STAT_READ]),

			   part_stat_read(hd, sectors[STAT_READ]),

			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])),

			   (unsigned int)part_stat_read_msecs(hd, STAT_READ),

			   part_stat_read(hd, ios[STAT_WRITE]),

			   part_stat_read(hd, merges[STAT_WRITE]),

			   part_stat_read(hd, sectors[STAT_WRITE]),

			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),

			   (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),

			   inflight[0],

			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),

			   jiffies_to_msecs(part_stat_read(hd, time_in_queue)),

			   part_stat_read(hd, ios[STAT_DISCARD]),

			   part_stat_read(hd, merges[STAT_DISCARD]),

			   part_stat_read(hd, sectors[STAT_DISCARD]),

			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD]))

			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)

			);

	}

	disk_part_iter_exit(&piter);

block/partition-generic.c

+3 −3
Original line number Diff line number Diff line
@@ -136,18 +136,18 @@ ssize_t part_stat_show(struct device *dev, 
		part_stat_read(p, ios[STAT_READ]),

		part_stat_read(p, merges[STAT_READ]),

		(unsigned long long)part_stat_read(p, sectors[STAT_READ]),

		jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])),

		(unsigned int)part_stat_read_msecs(p, STAT_READ),

		part_stat_read(p, ios[STAT_WRITE]),

		part_stat_read(p, merges[STAT_WRITE]),

		(unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),

		jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),

		(unsigned int)part_stat_read_msecs(p, STAT_WRITE),

		inflight[0],

		jiffies_to_msecs(part_stat_read(p, io_ticks)),

		jiffies_to_msecs(part_stat_read(p, time_in_queue)),

		part_stat_read(p, ios[STAT_DISCARD]),

		part_stat_read(p, merges[STAT_DISCARD]),

		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),

		jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD])));

		(unsigned int)part_stat_read_msecs(p, STAT_DISCARD));

}



ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,

include/linux/genhd.h

+4 −1
Original line number Diff line number Diff line
@@ -83,10 +83,10 @@ struct partition { 
} __attribute__((packed));



struct disk_stats {

	u64 nsecs[NR_STAT_GROUPS];

	unsigned long sectors[NR_STAT_GROUPS];

	unsigned long ios[NR_STAT_GROUPS];

	unsigned long merges[NR_STAT_GROUPS];

	unsigned long ticks[NR_STAT_GROUPS];

	unsigned long io_ticks;

	unsigned long time_in_queue;

};
@@ -354,6 +354,9 @@ static inline void free_part_stats(struct hd_struct *part) 


#endif /* CONFIG_SMP */



#define part_stat_read_msecs(part, which)				\

	div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC)



#define part_stat_read_accum(part, field)				\

	(part_stat_read(part, field[STAT_READ]) +			\

	 part_stat_read(part, field[STAT_WRITE]) +			\

CRA Git | Maintained and supported by SUSTech CRA and CCSE