提交 9c6dea45 编写于 作者: M Mikulas Patocka 提交者: Yang Yingliang

block: delete part_round_stats and switch to less precise counting

mainline inclusion
from mainline-5.0-rc1
commit 5b18b5a737600fd20ba2045f320d5926ebbf341a
category: bugfix
bugzilla: 31388
CVE: NA
---------------------------

We want to convert to per-cpu in_flight counters.

The function part_round_stats needs the in_flight counter every jiffy, it
would be too costly to sum all the percpu variables every jiffy, so it
must be deleted. part_round_stats is used to calculate two counters -
time_in_queue and io_ticks.

time_in_queue can be calculated without part_round_stats, by adding the
duration of the I/O when the I/O ends (the value is almost as exact as the
previously calculated value, except that time for in-progress I/Os is not
counted).

io_ticks can be approximated by increasing the value when I/O is started
or ended and the jiffies value has changed. If the I/Os take less than a
jiffy, the value is as exact as the previously calculated value. If the
I/Os take more than a jiffy, io_ticks can drift behind the previously
calculated value.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Conflict:
	block/bio.c
	block/blk-core.c
	block/blk-merge.c
	block/genhd.c
	include/linux/genhd.h
Signed-off-by: NYufen Yu <yuyufen@huawei.com>
Reviewed-by: NHou Tao <houtao1@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>
上级 0d2a9b34
......@@ -1668,13 +1668,28 @@ void bio_check_pages_dirty(struct bio *bio)
}
EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
void update_io_ticks(int cpu, struct hd_struct *part, unsigned long now)
{
unsigned long stamp;
again:
stamp = READ_ONCE(part->stamp);
if (unlikely(stamp != now)) {
if (likely(cmpxchg(&part->stamp, stamp, now) == stamp))
__part_stat_add(cpu, part, io_ticks, 1);
}
if (part->partno) {
part = &part_to_disk(part)->part0;
goto again;
}
}
void generic_start_io_acct(struct request_queue *q, int op,
unsigned long sectors, struct hd_struct *part)
{
const int sgrp = op_stat_group(op);
int cpu = part_stat_lock();
part_round_stats(q, cpu, part);
update_io_ticks(cpu, part, jiffies);
part_stat_inc(cpu, part, ios[sgrp]);
part_stat_add(cpu, part, sectors[sgrp], sectors);
part_inc_in_flight(q, part, op_is_write(op));
......@@ -1686,12 +1701,14 @@ EXPORT_SYMBOL(generic_start_io_acct);
void generic_end_io_acct(struct request_queue *q, int req_op,
struct hd_struct *part, unsigned long start_time)
{
unsigned long duration = jiffies - start_time;
unsigned long now = jiffies;
unsigned long duration = now - start_time;
const int sgrp = op_stat_group(req_op);
int cpu = part_stat_lock();
update_io_ticks(cpu, part, now);
part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration));
part_round_stats(q, cpu, part);
part_stat_add(cpu, part, time_in_queue, duration);
part_dec_in_flight(q, part, op_is_write(req_op));
part_stat_unlock();
......
......@@ -2740,9 +2740,10 @@ void blk_account_io_done(struct request *req, u64 now)
cpu = part_stat_lock();
part = req->part;
update_io_ticks(cpu, part, jiffies);
part_stat_inc(cpu, part, ios[sgrp]);
part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns);
part_round_stats(req->q, cpu, part);
part_stat_add(cpu, part, time_in_queue, nsecs_to_jiffies64(now - req->start_time_ns));
part_dec_in_flight(req->q, part, rq_data_dir(req));
hd_struct_put(part);
......@@ -2790,11 +2791,12 @@ void blk_account_io_start(struct request *rq, bool new_io)
part_stat_inc(cpu, part, merges[rw]);
} else {
part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
part_round_stats(rq->q, cpu, part);
part_inc_in_flight(rq->q, part, rw);
rq->part = part;
}
update_io_ticks(cpu, part, jiffies);
part_stat_unlock();
}
......
......@@ -656,7 +656,6 @@ static void blk_account_io_merge(struct request *req)
cpu = part_stat_lock();
part = req->part;
part_round_stats(req->q, cpu, part);
part_dec_in_flight(req->q, part, rq_data_dir(req));
hd_struct_put(part);
......
......@@ -1342,7 +1342,6 @@ static int diskstats_show(struct seq_file *seqf, void *v)
struct hd_struct *hd;
char buf[BDEVNAME_SIZE];
unsigned int inflight[2];
int cpu;
/*
if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
......@@ -1354,9 +1353,6 @@ static int diskstats_show(struct seq_file *seqf, void *v)
disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
while ((hd = disk_part_iter_next(&piter))) {
cpu = part_stat_lock();
part_round_stats(gp->queue, cpu, hd);
part_stat_unlock();
part_in_flight(gp->queue, hd, inflight);
seq_printf(seqf, "%4d %7d %s "
"%lu %lu %lu %u "
......
......@@ -121,11 +121,7 @@ ssize_t part_stat_show(struct device *dev,
struct hd_struct *p = dev_to_part(dev);
struct request_queue *q = part_to_disk(p)->queue;
unsigned int inflight[2];
int cpu;
cpu = part_stat_lock();
part_round_stats(q, cpu, p);
part_stat_unlock();
part_in_flight(q, p, inflight);
return sprintf(buf,
"%8lu %8lu %8llu %8u "
......
......@@ -422,6 +422,7 @@ static inline void free_part_info(struct hd_struct *part)
/* block/blk-core.c */
extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part);
void update_io_ticks(int cpu, struct hd_struct *part, unsigned long now);
/* block/genhd.c */
extern void device_add_disk(struct device *parent, struct gendisk *disk);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册