block: Track DISCARD statistics and output them in stat and diskstat

Add tracking of REQ_OP_DISCARD ios to the partition statistics and
append them to the various stat files in /sys as well as
/proc/diskstats.  These are tracked with the same four stats as reads
and writes:

Number of discard ios completed.
Number of discard ios merged
Number of discard sectors completed
Milliseconds spent on discard requests

This is done via adding a new STAT_DISCARD define to genhd.h and then
using it to index that stat field for discard requests.

tj: Refreshed on top of v4.17 and other previous updates.

Signed-off-by: Michael Callahan <michaelcallahan@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Andy Newell <newella@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Michael Callahan 2018-07-18 04:47:40 -07:00 committed by Jens Axboe
parent ddcf35d397
commit bdca3c87fb
7 changed files with 68 additions and 18 deletions

View File

@ -5,6 +5,7 @@ Description:
The /proc/diskstats file displays the I/O statistics
of block devices. Each line contains the following 14
fields:
1 - major number
2 - minor mumber
3 - device name
@ -19,4 +20,13 @@ Description:
12 - I/Os currently in progress
13 - time spent doing I/Os (ms)
14 - weighted time spent doing I/Os (ms)
Kernel 4.18+ appends four more fields for discard
tracking putting the total at 18:
15 - discards completed successfully
16 - discards merged
17 - sectors discarded
18 - time spent discarding
For more details refer to Documentation/iostats.txt

View File

@ -31,28 +31,32 @@ write ticks milliseconds total wait time for write requests
in_flight requests number of I/Os currently in flight
io_ticks milliseconds total time this block device has been active
time_in_queue milliseconds total wait time for all requests
discard I/Os requests number of discard I/Os processed
discard merges requests number of discard I/Os merged with in-queue I/O
discard sectors sectors number of sectors discarded
discard ticks milliseconds total wait time for discard requests
read I/Os, write I/Os
=====================
read I/Os, write I/Os, discard I/0s
===================================
These values increment when an I/O request completes.
read merges, write merges
=========================
read merges, write merges, discard merges
=========================================
These values increment when an I/O request is merged with an
already-queued I/O request.
read sectors, write sectors
===========================
read sectors, write sectors, discard_sectors
============================================
These values count the number of sectors read from or written to this
block device. The "sectors" in question are the standard UNIX 512-byte
sectors, not any device- or filesystem-specific block size. The
counters are incremented when the I/O completes.
These values count the number of sectors read from, written to, or
discarded from this block device. The "sectors" in question are the
standard UNIX 512-byte sectors, not any device- or filesystem-specific
block size. The counters are incremented when the I/O completes.
read ticks, write ticks
=======================
read ticks, write ticks, discard ticks
======================================
These values count the number of milliseconds that I/O requests have
waited on this block device. If there are multiple I/O requests waiting,

View File

@ -31,6 +31,9 @@ Here are examples of these different formats::
3 0 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
3 1 hda1 35486 38030 38030 38030
4.18+ diskstats:
3 0 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160 0 0 0 0
On 2.4 you might execute ``grep 'hda ' /proc/partitions``. On 2.6+, you have
a choice of ``cat /sys/block/hda/stat`` or ``grep 'hda ' /proc/diskstats``.
@ -101,6 +104,18 @@ Field 11 -- weighted # of milliseconds spent doing I/Os
last update of this field. This can provide an easy measure of both
I/O completion time and the backlog that may be accumulating.
Field 12 -- # of discards completed
This is the total number of discards completed successfully.
Field 13 -- # of discards merged
See the description of field 2
Field 14 -- # of sectors discarded
This is the total number of sectors discarded successfully.
Field 15 -- # of milliseconds spent discarding
This is the total number of milliseconds spent by all discards (as
measured from __make_request() to end_that_request_last()).
To avoid introducing performance bottlenecks, no locks are held while
modifying these counters. This implies that minor inaccuracies may be

View File

@ -1333,8 +1333,11 @@ static int diskstats_show(struct seq_file *seqf, void *v)
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 %lu %lu %lu %u %u %u %u\n",
seq_printf(seqf, "%4d %7d %s "
"%lu %lu %lu %u "
"%lu %lu %lu %u "
"%u %u %u "
"%lu %lu %lu %u\n",
MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
disk_name(gp, hd->partno, buf),
part_stat_read(hd, ios[STAT_READ]),
@ -1347,7 +1350,11 @@ static int diskstats_show(struct seq_file *seqf, void *v)
jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
inflight[0],
jiffies_to_msecs(part_stat_read(hd, io_ticks)),
jiffies_to_msecs(part_stat_read(hd, time_in_queue))
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]))
);
}
disk_part_iter_exit(&piter);

View File

@ -130,7 +130,8 @@ ssize_t part_stat_show(struct device *dev,
return sprintf(buf,
"%8lu %8lu %8llu %8u "
"%8lu %8lu %8llu %8u "
"%8u %8u %8u"
"%8u %8u %8u "
"%8lu %8lu %8llu %8u"
"\n",
part_stat_read(p, ios[STAT_READ]),
part_stat_read(p, merges[STAT_READ]),
@ -142,7 +143,11 @@ ssize_t part_stat_show(struct device *dev,
jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
inflight[0],
jiffies_to_msecs(part_stat_read(p, io_ticks)),
jiffies_to_msecs(part_stat_read(p, time_in_queue)));
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])));
}
ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,

View File

@ -360,6 +360,7 @@ enum req_flag_bits {
enum stat_group {
STAT_READ,
STAT_WRITE,
STAT_DISCARD,
NR_STAT_GROUPS
};
@ -401,8 +402,15 @@ static inline bool op_is_sync(unsigned int op)
(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
}
static inline bool op_is_discard(unsigned int op)
{
return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
}
static inline int op_stat_group(unsigned int op)
{
if (op_is_discard(op))
return STAT_DISCARD;
return op_is_write(op);
}

View File

@ -356,7 +356,8 @@ static inline void free_part_stats(struct hd_struct *part)
#define part_stat_read_accum(part, field) \
(part_stat_read(part, field[STAT_READ]) + \
part_stat_read(part, field[STAT_WRITE]))
part_stat_read(part, field[STAT_WRITE]) + \
part_stat_read(part, field[STAT_DISCARD]))
#define part_stat_add(cpu, part, field, addnd) do { \
__part_stat_add((cpu), (part), field, addnd); \