[RFC,V3,2/4] block: add a statistic table for io sector

Commit Message

Guoqing Jiang Aug. 13, 2020, 8:11 a.m. UTC

From: Guoqing Jiang <[e-mail]>

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
([e-mail]).

Signed-off-by: Guoqing Jiang <[e-mail]>
---
 Documentation/ABI/testing/sysfs-block |  9 +++++++
 block/Kconfig                         |  3 ++-
 block/blk-core.c                      | 18 +++++++++++++
 block/genhd.c                         | 37 +++++++++++++++++++++++++++
 include/linux/part_stat.h             |  3 ++-
 5 files changed, 68 insertions(+), 2 deletions(-)

--
2.17.1

Patch

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 1bae82238a79..d00d940e4e1b 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -32,6 +32,15 @@  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:		August 2020
+Contact:	Guoqing Jiang <[e-mail]>
+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 <[e-mail]>
diff --git a/block/Kconfig b/block/Kconfig
index 360f63111e2d..c9b9f99152d8 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -180,7 +180,8 @@  config BLK_ADDITIONAL_DISKSTAT
 	bool "Block layer additional diskstat"
 	default n
 	help
-	Enabling this option adds io latency statistics for each block device.
+	Enabling this option adds io latency and io size statistics for each
+	block device.

 	If unsure, say N.

diff --git a/block/blk-core.c b/block/blk-core.c
index fa339e0cc38a..1a8e508516c9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1438,6 +1438,22 @@  static void blk_additional_latency(struct hd_struct *part, const int sgrp,
 #endif
 }

+static void blk_additional_sector(struct hd_struct *part, const int sgrp,
+				  unsigned int sectors)
+{
+#ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT
+	unsigned int idx;
+
+	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]);
+#endif
+}
+
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (req->part && blk_do_io_stat(req)) {
@@ -1446,6 +1462,7 @@  static void blk_account_io_completion(struct request *req, unsigned int bytes)

 		part_stat_lock();
 		part = req->part;
+		blk_additional_sector(part, sgrp, bytes >> SECTOR_SHIFT);
 		part_stat_add(part, sectors[sgrp], bytes >> 9);
 		part_stat_unlock();
 	}
@@ -1499,6 +1516,7 @@  unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 	update_io_ticks(part, now, false);
 	part_stat_inc(part, ios[sgrp]);
 	part_stat_add(part, sectors[sgrp], sectors);
+	blk_additional_sector(part, sgrp, 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 21a3dae6a024..38517b86a968 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1454,6 +1454,42 @@  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 hd_struct *p = dev_to_part(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(p, 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);
 #endif

 static struct attribute *disk_attrs[] = {
@@ -1477,6 +1513,7 @@  static struct attribute *disk_attrs[] = {
 #endif
 #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT
 	&dev_attr_io_latency.attr,
+	&dev_attr_io_size.attr,
 #endif
 	NULL
 };
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index fe3def8c69d7..f23c367ea646 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -11,10 +11,11 @@  struct disk_stats {
 	unsigned long merges[NR_STAT_GROUPS];
 #ifdef CONFIG_BLK_ADDITIONAL_DISKSTAT
 /*
- * 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];
 #endif
 	unsigned long io_ticks;
 	local_t in_flight[2];