* [PATCH V3 1/3] block: add io_extra_stats node
2021-02-02 3:10 [PATCH V3 0/3] block: add two statistic tables Guoqing Jiang
@ 2021-02-02 3:10 ` Guoqing Jiang
2021-02-02 3:10 ` [PATCH V3 2/3] block: add a statistic table for io latency Guoqing Jiang
` (2 subsequent siblings)
3 siblings, 0 replies; 6+ messages in thread
From: Guoqing Jiang @ 2021-02-02 3:10 UTC (permalink / raw)
To: axboe; +Cc: linux-block, danil.kipnis, jinpu.wang, Guoqing Jiang
We will track the size and latency of each io, which could make people
suffer from the additional overhead if they don't need the statistics.
So introduce a specific sysfs node to enable/disable the tracking.
Reviewed-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
---
Documentation/ABI/testing/sysfs-block | 9 +++++++++
Documentation/block/queue-sysfs.rst | 5 +++++
block/blk-sysfs.c | 3 +++
include/linux/blkdev.h | 2 ++
4 files changed, 19 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index e34cdeeeb9d4..503314efec13 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -316,3 +316,12 @@ Description:
does not complete in this time then the block driver timeout
handler is invoked. That timeout handler can decide to retry
the request, to fail it or to start a device recovery strategy.
+
+What: /sys/block/<disk>/queue/io_extra_stats
+Date: January 2021
+Contact: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
+Description:
+ Indicates if people want to know the extra statistics (I/O
+ size and I/O latency) from /sys/block/<disk>/io_latency
+ and /sys/block/<disk>/io_size. The value is 0 by default,
+ set if the extra statistics are needed.
diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index 2638d3446b79..28ffce653eb1 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -99,6 +99,11 @@ iostats (RW)
This file is used to control (on/off) the iostats accounting of the
disk.
+io_extra_stats (RW)
+-------------------
+This file is used to control (on/off) the additional accounting of the
+io size and io latency of disk.
+
logical_block_size (RO)
-----------------------
This is the logical block size of the device, in bytes.
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index b513f1683af0..ed31938e89fe 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -287,6 +287,7 @@ queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
+QUEUE_SYSFS_BIT_FNS(io_extra_stats, IO_EXTRA_STAT, 0);
QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
#undef QUEUE_SYSFS_BIT_FNS
@@ -613,6 +614,7 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
QUEUE_RW_ENTRY(queue_nonrot, "rotational");
QUEUE_RW_ENTRY(queue_iostats, "iostats");
+QUEUE_RW_ENTRY(queue_io_extra_stats, "io_extra_stats");
QUEUE_RW_ENTRY(queue_random, "add_random");
QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");
@@ -647,6 +649,7 @@ static struct attribute *queue_attrs[] = {
&queue_nomerges_entry.attr,
&queue_rq_affinity_entry.attr,
&queue_iostats_entry.attr,
+ &queue_io_extra_stats_entry.attr,
&queue_stable_writes_entry.attr,
&queue_random_entry.attr,
&queue_poll_entry.attr,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0dea268bd61b..62881db2004f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -621,6 +621,7 @@ struct request_queue {
#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */
#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */
#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */
+#define QUEUE_FLAG_IO_EXTRA_STAT 30 /* extra IO accounting for size and latency */
#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_SAME_COMP) | \
@@ -641,6 +642,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
#define blk_queue_stable_writes(q) \
test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
+#define blk_queue_io_extra_stat(q) test_bit(QUEUE_FLAG_IO_EXTRA_STAT, &(q)->queue_flags)
#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
#define blk_queue_zone_resetall(q) \
--
2.17.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH V3 2/3] block: add a statistic table for io latency
2021-02-02 3:10 [PATCH V3 0/3] block: add two statistic tables Guoqing Jiang
2021-02-02 3:10 ` [PATCH V3 1/3] block: add io_extra_stats node Guoqing Jiang
@ 2021-02-02 3:10 ` Guoqing Jiang
2021-02-02 3:10 ` [PATCH V3 3/3] block: add a statistic table for io sector Guoqing Jiang
2021-02-02 10:48 ` [PATCH V3 0/3] block: add two statistic tables Johannes Thumshirn
3 siblings, 0 replies; 6+ messages in thread
From: Guoqing Jiang @ 2021-02-02 3:10 UTC (permalink / raw)
To: axboe; +Cc: linux-block, danil.kipnis, jinpu.wang, Guoqing Jiang
Usually, we get the status of block device by cat stat file, but we can
only know the total time with that file. And we would like to know more
accurate statistic, such as each latency range, which helps people to
diagnose if there is issue about the hardware.
This change is based on our internal patch from Florian-Ewald Mueller
(florian-ewald.mueller@cloud.ionos.com).
Reviewed-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
---
Documentation/ABI/testing/sysfs-block | 8 ++++++
block/blk-core.c | 24 +++++++++++++++++
block/genhd.c | 37 +++++++++++++++++++++++++++
include/linux/part_stat.h | 5 ++++
4 files changed, 74 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 503314efec13..c4db84c507dd 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -27,6 +27,14 @@ Description:
For more details refer Documentation/admin-guide/iostats.rst
+What: /sys/block/<disk>/io_latency
+Date: January 2021
+Contact: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
+Description:
+ The /sys/block/<disk>/io_latency files displays the I/O
+ latency of disk <disk>. With it, it is convenient to know
+ the statistics of I/O latency for each type (read, write,
+ discard and flush) which have happened to the disk.
What: /sys/block/<disk>/<part>/stat
Date: February 2008
diff --git a/block/blk-core.c b/block/blk-core.c
index 5e752840b41a..1adc9f17e8b7 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1264,6 +1264,26 @@ static void update_io_ticks(struct block_device *part, unsigned long now,
}
}
+static void blk_additional_latency(struct block_device *part, const int sgrp,
+ struct request_queue *q,
+ unsigned long duration)
+{
+ unsigned int idx;
+
+ if (!blk_queue_io_extra_stat(q))
+ return;
+
+ duration /= NSEC_PER_MSEC;
+ duration /= HZ_TO_MSEC_NUM;
+ if (likely(duration > 0)) {
+ idx = ilog2(duration);
+ if (idx > ADD_STAT_NUM - 1)
+ idx = ADD_STAT_NUM - 1;
+ } else
+ idx = 0;
+ part_stat_inc(part, latency_table[idx][sgrp]);
+}
+
static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (req->part && blk_do_io_stat(req)) {
@@ -1288,6 +1308,8 @@ void blk_account_io_done(struct request *req, u64 now)
part_stat_lock();
update_io_ticks(req->part, jiffies, true);
+ blk_additional_latency(req->part, sgrp, req->q,
+ now - req->start_time_ns);
part_stat_inc(req->part, ios[sgrp]);
part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
part_stat_unlock();
@@ -1354,6 +1376,8 @@ static void __part_end_io_acct(struct block_device *part, unsigned int op,
part_stat_lock();
update_io_ticks(part, now, true);
+ blk_additional_latency(part, sgrp, part->bd_disk->queue,
+ jiffies_to_nsecs(duration));
part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
part_stat_local_dec(part, in_flight[op_is_write(op)]);
part_stat_unlock();
diff --git a/block/genhd.c b/block/genhd.c
index 304f8dcc9a9b..09cb177421e0 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1146,6 +1146,42 @@ static struct device_attribute dev_attr_fail_timeout =
__ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
#endif
+static ssize_t io_latency_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct block_device *bdev = dev_to_bdev(dev);
+ size_t count = 0;
+ int i, sgrp;
+
+ for (i = 0; i < ADD_STAT_NUM; i++) {
+ unsigned int from, to;
+
+ if (i == ADD_STAT_NUM - 1) {
+ count += scnprintf(buf + count, PAGE_SIZE - count, " >= %5d ms: ",
+ (2 << (i - 2)) * HZ_TO_MSEC_NUM);
+ } else {
+ if (i < 2) {
+ from = i;
+ to = i + 1;
+ } else {
+ from = 2 << (i - 2);
+ to = 2 << (i - 1);
+ }
+ count += scnprintf(buf + count, PAGE_SIZE - count, "[%5d - %-5d) ms: ",
+ from * HZ_TO_MSEC_NUM, to * HZ_TO_MSEC_NUM);
+ }
+
+ for (sgrp = 0; sgrp < NR_STAT_GROUPS; sgrp++)
+ count += scnprintf(buf + count, PAGE_SIZE - count, "%lu ",
+ part_stat_read(bdev, latency_table[i][sgrp]));
+ count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
+ }
+
+ return count;
+}
+
+static struct device_attribute dev_attr_io_latency =
+ __ATTR(io_latency, 0444, io_latency_show, NULL);
+
static struct attribute *disk_attrs[] = {
&dev_attr_range.attr,
&dev_attr_ext_range.attr,
@@ -1165,6 +1201,7 @@ static struct attribute *disk_attrs[] = {
#ifdef CONFIG_FAIL_IO_TIMEOUT
&dev_attr_fail_timeout.attr,
#endif
+ &dev_attr_io_latency.attr,
NULL
};
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index d2558121d48c..e2bde5160de4 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -9,6 +9,11 @@ struct disk_stats {
unsigned long sectors[NR_STAT_GROUPS];
unsigned long ios[NR_STAT_GROUPS];
unsigned long merges[NR_STAT_GROUPS];
+ /*
+ * We measure latency (ms) for 1, 2, ..., 1024 and >=1024.
+ */
+#define ADD_STAT_NUM 12
+ unsigned long latency_table[ADD_STAT_NUM][NR_STAT_GROUPS];
unsigned long io_ticks;
local_t in_flight[2];
};
--
2.17.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH V3 3/3] block: add a statistic table for io sector
2021-02-02 3:10 [PATCH V3 0/3] block: add two statistic tables Guoqing Jiang
2021-02-02 3:10 ` [PATCH V3 1/3] block: add io_extra_stats node Guoqing Jiang
2021-02-02 3:10 ` [PATCH V3 2/3] block: add a statistic table for io latency Guoqing Jiang
@ 2021-02-02 3:10 ` Guoqing Jiang
2021-02-02 10:48 ` [PATCH V3 0/3] block: add two statistic tables Johannes Thumshirn
3 siblings, 0 replies; 6+ messages in thread
From: Guoqing Jiang @ 2021-02-02 3:10 UTC (permalink / raw)
To: axboe; +Cc: linux-block, danil.kipnis, jinpu.wang, Guoqing Jiang
With the sector table, so we can know the distribution of different IO
size from upper layer, which means we could have the opportunity to tune
the performance based on the mostly issued IOs.
This change is based on our internal patch from Florian-Ewald Mueller
(florian-ewald.mueller@cloud.ionos.com).
Reviewed-by: Jack Wang <jinpu.wang@cloud.ionos.com>
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
---
Documentation/ABI/testing/sysfs-block | 9 +++++++
block/blk-core.c | 19 ++++++++++++++
block/genhd.c | 37 +++++++++++++++++++++++++++
include/linux/part_stat.h | 3 ++-
4 files changed, 67 insertions(+), 1 deletion(-)
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index c4db84c507dd..e1611c62a3e1 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -36,6 +36,15 @@ Description:
the statistics of I/O latency for each type (read, write,
discard and flush) which have happened to the disk.
+What: /sys/block/<disk>/io_size
+Date: January 2021
+Contact: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
+Description:
+ The /sys/block/<disk>/io_size files displays the I/O
+ size of disk <disk>. With it, it is convenient to know
+ the statistics of I/O size for each type (read, write,
+ discard and flush) which have happened to the disk.
+
What: /sys/block/<disk>/<part>/stat
Date: February 2008
Contact: Jerome Marchand <jmarchan@redhat.com>
diff --git a/block/blk-core.c b/block/blk-core.c
index 1adc9f17e8b7..a44684033382 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1284,12 +1284,30 @@ static void blk_additional_latency(struct block_device *part, const int sgrp,
part_stat_inc(part, latency_table[idx][sgrp]);
}
+static void blk_additional_sector(struct block_device *part, const int sgrp,
+ struct request_queue *q, unsigned int sectors)
+{
+ unsigned int idx;
+
+ if (!blk_queue_io_extra_stat(q))
+ return;
+
+ if (sectors == 1)
+ idx = 0;
+ else
+ idx = ilog2(sectors);
+
+ idx = (idx > (ADD_STAT_NUM - 1)) ? (ADD_STAT_NUM - 1) : idx;
+ part_stat_inc(part, size_table[idx][sgrp]);
+}
+
static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (req->part && blk_do_io_stat(req)) {
const int sgrp = op_stat_group(req_op(req));
part_stat_lock();
+ blk_additional_sector(req->part, sgrp, req->q, bytes >> SECTOR_SHIFT);
part_stat_add(req->part, sectors[sgrp], bytes >> 9);
part_stat_unlock();
}
@@ -1342,6 +1360,7 @@ static unsigned long __part_start_io_acct(struct block_device *part,
update_io_ticks(part, now, false);
part_stat_inc(part, ios[sgrp]);
part_stat_add(part, sectors[sgrp], sectors);
+ blk_additional_sector(part, sgrp, part->bd_disk->queue, sectors);
part_stat_local_inc(part, in_flight[op_is_write(op)]);
part_stat_unlock();
diff --git a/block/genhd.c b/block/genhd.c
index 09cb177421e0..f43574d9dc8c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1182,6 +1182,42 @@ static ssize_t io_latency_show(struct device *dev, struct device_attribute *attr
static struct device_attribute dev_attr_io_latency =
__ATTR(io_latency, 0444, io_latency_show, NULL);
+static ssize_t io_size_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct block_device *bdev = dev_to_bdev(dev);
+ size_t count = 0;
+ int i, sgrp;
+
+ for (i = 0; i < ADD_STAT_NUM; i++) {
+ unsigned int from, to;
+
+ if (i == ADD_STAT_NUM - 1) {
+ from = 2 << (i - 2);
+ count += scnprintf(buf + count, PAGE_SIZE - count,
+ " >=%5d KB: ", from);
+ } else {
+ if (i < 2) {
+ from = i;
+ to = i + 1;
+ } else {
+ from = 2 << (i - 2);
+ to = 2 << (i - 1);
+ }
+ count += scnprintf(buf + count, PAGE_SIZE - count,
+ "[%5d - %-5d) KB: ", from, to);
+ }
+ for (sgrp = 0; sgrp < NR_STAT_GROUPS; sgrp++)
+ count += scnprintf(buf + count, PAGE_SIZE - count, "%lu ",
+ part_stat_read(bdev, size_table[i][sgrp]));
+ count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
+ }
+
+ return count;
+}
+
+static struct device_attribute dev_attr_io_size =
+ __ATTR(io_size, 0444, io_size_show, NULL);
+
static struct attribute *disk_attrs[] = {
&dev_attr_range.attr,
&dev_attr_ext_range.attr,
@@ -1202,6 +1238,7 @@ static struct attribute *disk_attrs[] = {
&dev_attr_fail_timeout.attr,
#endif
&dev_attr_io_latency.attr,
+ &dev_attr_io_size.attr,
NULL
};
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index e2bde5160de4..221fb3a884b2 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -10,10 +10,11 @@ struct disk_stats {
unsigned long ios[NR_STAT_GROUPS];
unsigned long merges[NR_STAT_GROUPS];
/*
- * We measure latency (ms) for 1, 2, ..., 1024 and >=1024.
+ * We measure latency (ms) and size (KB) for 1, 2, ..., 1024 and >=1024.
*/
#define ADD_STAT_NUM 12
unsigned long latency_table[ADD_STAT_NUM][NR_STAT_GROUPS];
+ unsigned long size_table[ADD_STAT_NUM][NR_STAT_GROUPS];
unsigned long io_ticks;
local_t in_flight[2];
};
--
2.17.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* Re: [PATCH V3 0/3] block: add two statistic tables
2021-02-02 3:10 [PATCH V3 0/3] block: add two statistic tables Guoqing Jiang
` (2 preceding siblings ...)
2021-02-02 3:10 ` [PATCH V3 3/3] block: add a statistic table for io sector Guoqing Jiang
@ 2021-02-02 10:48 ` Johannes Thumshirn
2021-02-02 14:42 ` Guoqing Jiang
3 siblings, 1 reply; 6+ messages in thread
From: Johannes Thumshirn @ 2021-02-02 10:48 UTC (permalink / raw)
To: Guoqing Jiang, axboe; +Cc: linux-block, danil.kipnis, jinpu.wang
Not a huge fan of the function names, but I don't have a better idea either.
For the whole series,
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
^ permalink raw reply [flat|nested] 6+ messages in thread