[PATCH v2] block: Add ioprio to block_rq tracepoint

From: Dongliang Cui
Date: Mon Apr 22 2024 - 01:47:12 EST


Sometimes we need to track the processing order of requests with
ioprio set. So the ioprio of request can be useful information.

Example:

block_rq_insert: 8,0 WS 4096 () 16573296 + 8 rt,4 [highpool[1]]
block_rq_issue: 8,0 WS 4096 () 16573296 + 8 rt,4 [kworker/7:0H]
block_rq_complete: 8,0 WS () 16573296 + 8 rt,4 [0]

Signed-off-by: Dongliang Cui <dongliang.cui@xxxxxxxxxx>

Changes history
Changes in v2:
Update the printing method of ioprio_class.
---
include/trace/events/block.h | 36 ++++++++++++++++++++++++++----------
include/uapi/linux/ioprio.h | 7 +++++++
2 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 0e128ad51460..8aa0116077ee 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -9,6 +9,7 @@
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/tracepoint.h>
+#include <uapi/linux/ioprio.h>

#define RWBS_LEN 8

@@ -82,6 +83,8 @@ TRACE_EVENT(block_rq_requeue,
__field( dev_t, dev )
__field( sector_t, sector )
__field( unsigned int, nr_sector )
+ __field( unsigned int, ioprio_class )
+ __field( unsigned int, ioprio_value )
__array( char, rwbs, RWBS_LEN )
__dynamic_array( char, cmd, 1 )
),
@@ -90,16 +93,19 @@ TRACE_EVENT(block_rq_requeue,
__entry->dev = rq->q->disk ? disk_devt(rq->q->disk) : 0;
__entry->sector = blk_rq_trace_sector(rq);
__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
+ __entry->ioprio_class = rq->ioprio >> IOPRIO_CLASS_SHIFT & 0x3;
+ __entry->ioprio_value = rq->ioprio & 0xff;

blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
__get_str(cmd)[0] = '\0';
),

- TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+ TP_printk("%d,%d %s (%s) %llu + %u %s,%u [%d]",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->rwbs, __get_str(cmd),
- (unsigned long long)__entry->sector,
- __entry->nr_sector, 0)
+ (unsigned long long)__entry->sector, __entry->nr_sector,
+ __print_symbolic(__entry->ioprio_class, IOPRIO_CLASS_STRINGS),
+ __entry->ioprio_value, 0)
);

DECLARE_EVENT_CLASS(block_rq_completion,
@@ -113,6 +119,8 @@ DECLARE_EVENT_CLASS(block_rq_completion,
__field( sector_t, sector )
__field( unsigned int, nr_sector )
__field( int , error )
+ __field( unsigned int, ioprio_class )
+ __field( unsigned int, ioprio_value )
__array( char, rwbs, RWBS_LEN )
__dynamic_array( char, cmd, 1 )
),
@@ -122,16 +130,19 @@ DECLARE_EVENT_CLASS(block_rq_completion,
__entry->sector = blk_rq_pos(rq);
__entry->nr_sector = nr_bytes >> 9;
__entry->error = blk_status_to_errno(error);
+ __entry->ioprio_class = rq->ioprio >> IOPRIO_CLASS_SHIFT & 0x3;
+ __entry->ioprio_value = rq->ioprio & 0xff;

blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
__get_str(cmd)[0] = '\0';
),

- TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+ TP_printk("%d,%d %s (%s) %llu + %u %s,%u [%d]",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->rwbs, __get_str(cmd),
- (unsigned long long)__entry->sector,
- __entry->nr_sector, __entry->error)
+ (unsigned long long)__entry->sector, __entry->nr_sector,
+ __print_symbolic(__entry->ioprio_class, IOPRIO_CLASS_STRINGS),
+ __entry->ioprio_value, __entry->error)
);

/**
@@ -180,8 +191,10 @@ DECLARE_EVENT_CLASS(block_rq,
__field( sector_t, sector )
__field( unsigned int, nr_sector )
__field( unsigned int, bytes )
+ __field( unsigned int, ioprio_class )
+ __field( unsigned int, ioprio_value )
__array( char, rwbs, RWBS_LEN )
- __array( char, comm, TASK_COMM_LEN )
+ __array( char, comm, TASK_COMM_LEN )
__dynamic_array( char, cmd, 1 )
),

@@ -190,17 +203,20 @@ DECLARE_EVENT_CLASS(block_rq,
__entry->sector = blk_rq_trace_sector(rq);
__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
__entry->bytes = blk_rq_bytes(rq);
+ __entry->ioprio_class = rq->ioprio >> IOPRIO_CLASS_SHIFT & 0x3;
+ __entry->ioprio_value = rq->ioprio & 0xff;

blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
__get_str(cmd)[0] = '\0';
memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
),

- TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+ TP_printk("%d,%d %s %u (%s) %llu + %u %s,%u [%s]",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->rwbs, __entry->bytes, __get_str(cmd),
- (unsigned long long)__entry->sector,
- __entry->nr_sector, __entry->comm)
+ (unsigned long long)__entry->sector, __entry->nr_sector,
+ __print_symbolic(__entry->ioprio_class, IOPRIO_CLASS_STRINGS),
+ __entry->ioprio_value, __entry->comm)
);

/**
diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h
index bee2bdb0eedb..9a43ad3a65ab 100644
--- a/include/uapi/linux/ioprio.h
+++ b/include/uapi/linux/ioprio.h
@@ -35,6 +35,13 @@ enum {
IOPRIO_CLASS_INVALID = 7,
};

+#define IOPRIO_CLASS_STRINGS \
+ { IOPRIO_CLASS_NONE, "none" }, \
+ { IOPRIO_CLASS_RT, "rt" }, \
+ { IOPRIO_CLASS_BE, "be" }, \
+ { IOPRIO_CLASS_IDLE, "idle" }, \
+ { IOPRIO_CLASS_INVALID, "invalid" }
+
/*
* The RT and BE priority classes both support up to 8 priority levels that
* can be specified using the lower 3-bits of the priority data.
--
2.25.1