[PATCH v3 0/6] Add support for I/O priority hints

[PATCH v3 0/6] Add support for I/O priority hints

[Damien Le Moal]

Linux kernel 6.5 adds support for I/O priority hints, which can be
used (for now) to specify command duration limits for block devices
supporting this feature.

This patch series extends fio I/O priority options and adds new options
to allow users to specify I/O priority hints.

Changes from v2:
 - Added patch 2 to generically define the cmdprio_xxx options. This
   dwisimplifies tidies up patch 5.
 - Added Niklas review tag to patch 1

Changes from v1:
 - Added patch 1
 - Addressed Niklas comments

Damien Le Moal (6):
  os-linux: Cleanup IO priority class and value macros
  cmdprio: Introduce generic option definitions
  os-linux: add initial support for IO priority hints
  options: add priohint option
  cmdprio: Add support for per I/O priority hint
  stats: Add hint information to per priority level stats

 HOWTO.rst          |  37 ++++++++++++++--
 backend.c          |   9 ++--
 cconv.c            |   2 +
 engines/cmdprio.c  |   9 ++--
 engines/cmdprio.h  | 106 +++++++++++++++++++++++++++++++++++++++++++++
 engines/io_uring.c |  86 ++----------------------------------
 engines/libaio.c   |  82 +----------------------------------
 fio.1              |  33 ++++++++++++--
 options.c          |  31 +++++++++++--
 os/os-dragonfly.h  |   4 +-
 os/os-linux.h      |  27 ++++++++----
 os/os.h            |   7 ++-
 server.h           |   2 +-
 stat.c             |  10 +++--
 thread_options.h   |   3 +-
 15 files changed, 251 insertions(+), 197 deletions(-)

-- 
2.41.0

[PATCH v3 1/6] os-linux: Cleanup IO priority class and value macros

[Damien Le Moal]

In os/os-linux.h, define the ioprio() macro using the already defined
IOPRIO_MAX_PRIO macro instead of hard coding the maximum priority value
again. Also move the definitions of the ioprio_class() and ioprio()
macros before the ioprio_value() function and use ioprio_class() inside
ioprio_value_is_class_rt() instead of re-coding the iopriority class
extraction again in that function.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
---
 os/os-linux.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/os/os-linux.h b/os/os-linux.h
index 2f9f7e79..72727ac3 100644
--- a/os/os-linux.h
+++ b/os/os-linux.h
@@ -131,6 +131,9 @@ enum {
 #define IOPRIO_MIN_PRIO_CLASS	0
 #define IOPRIO_MAX_PRIO_CLASS	3
 
+#define ioprio_class(ioprio)	((ioprio) >> IOPRIO_CLASS_SHIFT)
+#define ioprio(ioprio)		((ioprio) & IOPRIO_MAX_PRIO)
+
 static inline int ioprio_value(int ioprio_class, int ioprio)
 {
 	/*
@@ -144,7 +147,7 @@ static inline int ioprio_value(int ioprio_class, int ioprio)
 
 static inline bool ioprio_value_is_class_rt(unsigned int priority)
 {
-	return (priority >> IOPRIO_CLASS_SHIFT) == IOPRIO_CLASS_RT;
+	return ioprio_class(priority) == IOPRIO_CLASS_RT;
 }
 
 static inline int ioprio_set(int which, int who, int ioprio_class, int ioprio)
@@ -153,9 +156,6 @@ static inline int ioprio_set(int which, int who, int ioprio_class, int ioprio)
 		       ioprio_value(ioprio_class, ioprio));
 }
 
-#define ioprio_class(ioprio)	((ioprio) >> IOPRIO_CLASS_SHIFT)
-#define ioprio(ioprio)		((ioprio) & 7)
-
 #ifndef CONFIG_HAVE_GETTID
 static inline int gettid(void)
 {
-- 
2.41.0

[PATCH v3 2/6] cmdprio: Introduce generic option definitions

[Damien Le Moal]

The definition of the per-I/O priority options for the io_uring and
libaio I/O engines are almost identical, differing only by the option
group and option data structure used.

Introduce the CMDPRIO_OPTIONS macro in engines/cmdprio.h to generically
define these options in the io_uring and libaio engines to simplify the
code.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
---
 engines/cmdprio.h  | 84 ++++++++++++++++++++++++++++++++++++++++++++++
 engines/io_uring.c | 82 +-------------------------------------------
 engines/libaio.c   | 82 +-------------------------------------------
 3 files changed, 86 insertions(+), 162 deletions(-)

diff --git a/engines/cmdprio.h b/engines/cmdprio.h
index 755da8d0..2c9d87bc 100644
--- a/engines/cmdprio.h
+++ b/engines/cmdprio.h
@@ -7,6 +7,7 @@
 #define FIO_CMDPRIO_H
 
 #include "../fio.h"
+#include "../optgroup.h"
 
 /* read and writes only, no trim */
 #define CMDPRIO_RWDIR_CNT 2
@@ -42,6 +43,89 @@ struct cmdprio_options {
 	char *bssplit_str;
 };
 
+#ifdef FIO_HAVE_IOPRIO_CLASS
+#define CMDPRIO_OPTIONS(opt_struct, opt_group)					\
+	{									\
+		.name	= "cmdprio_percentage",					\
+		.lname	= "high priority percentage",				\
+		.type	= FIO_OPT_INT,						\
+		.off1	= offsetof(opt_struct,					\
+				   cmdprio_options.percentage[DDIR_READ]),	\
+		.off2	= offsetof(opt_struct,					\
+				   cmdprio_options.percentage[DDIR_WRITE]),	\
+		.minval	= 0,							\
+		.maxval	= 100,							\
+		.help	= "Send high priority I/O this percentage of the time",	\
+		.category = FIO_OPT_C_ENGINE,					\
+		.group	= opt_group,						\
+	},									\
+	{									\
+		.name	= "cmdprio_class",					\
+		.lname	= "Asynchronous I/O priority class",			\
+		.type	= FIO_OPT_INT,						\
+		.off1	= offsetof(opt_struct,					\
+				   cmdprio_options.class[DDIR_READ]),		\
+		.off2	= offsetof(opt_struct,					\
+				   cmdprio_options.class[DDIR_WRITE]),		\
+		.help	= "Set asynchronous IO priority class",			\
+		.minval	= IOPRIO_MIN_PRIO_CLASS + 1,				\
+		.maxval	= IOPRIO_MAX_PRIO_CLASS,				\
+		.interval = 1,							\
+		.category = FIO_OPT_C_ENGINE,					\
+		.group	= opt_group,						\
+	},									\
+	{									\
+		.name	= "cmdprio",						\
+		.lname	= "Asynchronous I/O priority level",			\
+		.type	= FIO_OPT_INT,						\
+		.off1	= offsetof(opt_struct,					\
+				   cmdprio_options.level[DDIR_READ]),		\
+		.off2	= offsetof(opt_struct,					\
+				   cmdprio_options.level[DDIR_WRITE]),		\
+		.help	= "Set asynchronous IO priority level",			\
+		.minval	= IOPRIO_MIN_PRIO,					\
+		.maxval	= IOPRIO_MAX_PRIO,					\
+		.interval = 1,							\
+		.category = FIO_OPT_C_ENGINE,					\
+		.group	= opt_group,						\
+	},									\
+	{									\
+		.name   = "cmdprio_bssplit",					\
+		.lname  = "Priority percentage block size split",		\
+		.type   = FIO_OPT_STR_STORE,					\
+		.off1   = offsetof(opt_struct, cmdprio_options.bssplit_str),	\
+		.help   = "Set priority percentages for different block sizes",	\
+		.category = FIO_OPT_C_ENGINE,					\
+		.group	= opt_group,						\
+	}
+#else
+#define CMDPRIO_OPTIONS(opt_struct, opt_group)					\
+	{									\
+		.name	= "cmdprio_percentage",					\
+		.lname	= "high priority percentage",				\
+		.type	= FIO_OPT_UNSUPPORTED,					\
+		.help	= "Platform does not support I/O priority classes",	\
+	},									\
+	{									\
+		.name	= "cmdprio_class",					\
+		.lname	= "Asynchronous I/O priority class",			\
+		.type	= FIO_OPT_UNSUPPORTED,					\
+		.help	= "Platform does not support I/O priority classes",	\
+	},									\
+	{									\
+		.name	= "cmdprio",						\
+		.lname	= "Asynchronous I/O priority level",			\
+		.type	= FIO_OPT_UNSUPPORTED,					\
+		.help	= "Platform does not support I/O priority classes",	\
+	},									\
+	{									\
+		.name   = "cmdprio_bssplit",					\
+		.lname  = "Priority percentage block size split",		\
+		.type	= FIO_OPT_UNSUPPORTED,					\
+		.help	= "Platform does not support I/O priority classes",	\
+	}
+#endif
+
 struct cmdprio {
 	struct cmdprio_options *options;
 	struct cmdprio_prio perc_entry[CMDPRIO_RWDIR_CNT];
diff --git a/engines/io_uring.c b/engines/io_uring.c
index f30a3c00..5613c4c6 100644
--- a/engines/io_uring.c
+++ b/engines/io_uring.c
@@ -127,87 +127,6 @@ static struct fio_option options[] = {
 		.category = FIO_OPT_C_ENGINE,
 		.group	= FIO_OPT_G_IOURING,
 	},
-#ifdef FIO_HAVE_IOPRIO_CLASS
-	{
-		.name	= "cmdprio_percentage",
-		.lname	= "high priority percentage",
-		.type	= FIO_OPT_INT,
-		.off1	= offsetof(struct ioring_options,
-				   cmdprio_options.percentage[DDIR_READ]),
-		.off2	= offsetof(struct ioring_options,
-				   cmdprio_options.percentage[DDIR_WRITE]),
-		.minval	= 0,
-		.maxval	= 100,
-		.help	= "Send high priority I/O this percentage of the time",
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_IOURING,
-	},
-	{
-		.name	= "cmdprio_class",
-		.lname	= "Asynchronous I/O priority class",
-		.type	= FIO_OPT_INT,
-		.off1	= offsetof(struct ioring_options,
-				   cmdprio_options.class[DDIR_READ]),
-		.off2	= offsetof(struct ioring_options,
-				   cmdprio_options.class[DDIR_WRITE]),
-		.help	= "Set asynchronous IO priority class",
-		.minval	= IOPRIO_MIN_PRIO_CLASS + 1,
-		.maxval	= IOPRIO_MAX_PRIO_CLASS,
-		.interval = 1,
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_IOURING,
-	},
-	{
-		.name	= "cmdprio",
-		.lname	= "Asynchronous I/O priority level",
-		.type	= FIO_OPT_INT,
-		.off1	= offsetof(struct ioring_options,
-				   cmdprio_options.level[DDIR_READ]),
-		.off2	= offsetof(struct ioring_options,
-				   cmdprio_options.level[DDIR_WRITE]),
-		.help	= "Set asynchronous IO priority level",
-		.minval	= IOPRIO_MIN_PRIO,
-		.maxval	= IOPRIO_MAX_PRIO,
-		.interval = 1,
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_IOURING,
-	},
-	{
-		.name   = "cmdprio_bssplit",
-		.lname  = "Priority percentage block size split",
-		.type   = FIO_OPT_STR_STORE,
-		.off1   = offsetof(struct ioring_options,
-				   cmdprio_options.bssplit_str),
-		.help   = "Set priority percentages for different block sizes",
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_IOURING,
-	},
-#else
-	{
-		.name	= "cmdprio_percentage",
-		.lname	= "high priority percentage",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-	{
-		.name	= "cmdprio_class",
-		.lname	= "Asynchronous I/O priority class",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-	{
-		.name	= "cmdprio",
-		.lname	= "Asynchronous I/O priority level",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-	{
-		.name   = "cmdprio_bssplit",
-		.lname  = "Priority percentage block size split",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-#endif
 	{
 		.name	= "fixedbufs",
 		.lname	= "Fixed (pre-mapped) IO buffers",
@@ -297,6 +216,7 @@ static struct fio_option options[] = {
 		.category = FIO_OPT_C_ENGINE,
 		.group	= FIO_OPT_G_IOURING,
 	},
+	CMDPRIO_OPTIONS(struct ioring_options, FIO_OPT_G_IOURING),
 	{
 		.name	= NULL,
 	},
diff --git a/engines/libaio.c b/engines/libaio.c
index 6a0745aa..aaccc7ce 100644
--- a/engines/libaio.c
+++ b/engines/libaio.c
@@ -72,87 +72,6 @@ static struct fio_option options[] = {
 		.category = FIO_OPT_C_ENGINE,
 		.group	= FIO_OPT_G_LIBAIO,
 	},
-#ifdef FIO_HAVE_IOPRIO_CLASS
-	{
-		.name	= "cmdprio_percentage",
-		.lname	= "high priority percentage",
-		.type	= FIO_OPT_INT,
-		.off1	= offsetof(struct libaio_options,
-				   cmdprio_options.percentage[DDIR_READ]),
-		.off2	= offsetof(struct libaio_options,
-				   cmdprio_options.percentage[DDIR_WRITE]),
-		.minval	= 0,
-		.maxval	= 100,
-		.help	= "Send high priority I/O this percentage of the time",
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_LIBAIO,
-	},
-	{
-		.name	= "cmdprio_class",
-		.lname	= "Asynchronous I/O priority class",
-		.type	= FIO_OPT_INT,
-		.off1	= offsetof(struct libaio_options,
-				   cmdprio_options.class[DDIR_READ]),
-		.off2	= offsetof(struct libaio_options,
-				   cmdprio_options.class[DDIR_WRITE]),
-		.help	= "Set asynchronous IO priority class",
-		.minval	= IOPRIO_MIN_PRIO_CLASS + 1,
-		.maxval	= IOPRIO_MAX_PRIO_CLASS,
-		.interval = 1,
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_LIBAIO,
-	},
-	{
-		.name	= "cmdprio",
-		.lname	= "Asynchronous I/O priority level",
-		.type	= FIO_OPT_INT,
-		.off1	= offsetof(struct libaio_options,
-				   cmdprio_options.level[DDIR_READ]),
-		.off2	= offsetof(struct libaio_options,
-				   cmdprio_options.level[DDIR_WRITE]),
-		.help	= "Set asynchronous IO priority level",
-		.minval	= IOPRIO_MIN_PRIO,
-		.maxval	= IOPRIO_MAX_PRIO,
-		.interval = 1,
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_LIBAIO,
-	},
-	{
-		.name   = "cmdprio_bssplit",
-		.lname  = "Priority percentage block size split",
-		.type   = FIO_OPT_STR_STORE,
-		.off1   = offsetof(struct libaio_options,
-				   cmdprio_options.bssplit_str),
-		.help   = "Set priority percentages for different block sizes",
-		.category = FIO_OPT_C_ENGINE,
-		.group	= FIO_OPT_G_LIBAIO,
-	},
-#else
-	{
-		.name	= "cmdprio_percentage",
-		.lname	= "high priority percentage",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-	{
-		.name	= "cmdprio_class",
-		.lname	= "Asynchronous I/O priority class",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-	{
-		.name	= "cmdprio",
-		.lname	= "Asynchronous I/O priority level",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-	{
-		.name   = "cmdprio_bssplit",
-		.lname  = "Priority percentage block size split",
-		.type	= FIO_OPT_UNSUPPORTED,
-		.help	= "Your platform does not support I/O priority classes",
-	},
-#endif
 	{
 		.name	= "nowait",
 		.lname	= "RWF_NOWAIT",
@@ -162,6 +81,7 @@ static struct fio_option options[] = {
 		.category = FIO_OPT_C_ENGINE,
 		.group	= FIO_OPT_G_LIBAIO,
 	},
+	CMDPRIO_OPTIONS(struct libaio_options, FIO_OPT_G_LIBAIO),
 	{
 		.name	= NULL,
 	},
-- 
2.41.0

[PATCH v3 3/6] os-linux: add initial support for IO priority hints

[Damien Le Moal]

Add initial support for Linux to allow specifying a hint for any
priority value. With this change, a priority value becomes the
combination of a priority class, a priority level and a hint.
The generic os.h ioprio manipulation macros, as well as the
os-dragonfly.h ioprio manipulation macros are modified to ignore this
hint.

For all other OSes that do not support priority classes, priotity hints
are ignored and always equal to 0.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
---
 backend.c         |  5 +++--
 engines/cmdprio.c |  4 ++--
 options.c         |  2 +-
 os/os-dragonfly.h |  4 ++--
 os/os-linux.h     | 19 +++++++++++++++----
 os/os.h           |  7 +++++--
 6 files changed, 28 insertions(+), 13 deletions(-)

diff --git a/backend.c b/backend.c
index b06a11a5..268b7825 100644
--- a/backend.c
+++ b/backend.c
@@ -1800,12 +1800,13 @@ static void *thread_main(void *data)
 	/* ioprio_set() has to be done before td_io_init() */
 	if (fio_option_is_set(o, ioprio) ||
 	    fio_option_is_set(o, ioprio_class)) {
-		ret = ioprio_set(IOPRIO_WHO_PROCESS, 0, o->ioprio_class, o->ioprio);
+		ret = ioprio_set(IOPRIO_WHO_PROCESS, 0, o->ioprio_class,
+				 o->ioprio, 0);
 		if (ret == -1) {
 			td_verror(td, errno, "ioprio_set");
 			goto err;
 		}
-		td->ioprio = ioprio_value(o->ioprio_class, o->ioprio);
+		td->ioprio = ioprio_value(o->ioprio_class, o->ioprio, 0);
 		td->ts.ioprio = td->ioprio;
 	}
 
diff --git a/engines/cmdprio.c b/engines/cmdprio.c
index 979a81b6..e6ff1fc2 100644
--- a/engines/cmdprio.c
+++ b/engines/cmdprio.c
@@ -342,7 +342,7 @@ static int fio_cmdprio_gen_perc(struct thread_data *td, struct cmdprio *cmdprio)
 		prio = &cmdprio->perc_entry[ddir];
 		prio->perc = options->percentage[ddir];
 		prio->prio = ioprio_value(options->class[ddir],
-					  options->level[ddir]);
+					  options->level[ddir], 0);
 		assign_clat_prio_index(prio, &values[ddir]);
 
 		ret = init_ts_clat_prio(ts, ddir, &values[ddir]);
@@ -400,7 +400,7 @@ static int fio_cmdprio_parse_and_gen_bssplit(struct thread_data *td,
 			goto err;
 
 		implicit_cmdprio = ioprio_value(options->class[ddir],
-						options->level[ddir]);
+						options->level[ddir], 0);
 
 		ret = fio_cmdprio_generate_bsprio_desc(&cmdprio->bsprio_desc[ddir],
 						       &parse_res[ddir],
diff --git a/options.c b/options.c
index 0f739317..143d3583 100644
--- a/options.c
+++ b/options.c
@@ -344,7 +344,7 @@ static int parse_cmdprio_bssplit_entry(struct thread_options *o,
 	case 4: /* bs/perc/class/level case */
 		class = min(class, (unsigned int) IOPRIO_MAX_PRIO_CLASS);
 		level = min(level, (unsigned int) IOPRIO_MAX_PRIO);
-		entry->prio = ioprio_value(class, level);
+		entry->prio = ioprio_value(class, level, 0);
 		break;
 	default:
 		log_err("fio: invalid cmdprio_bssplit format\n");
diff --git a/os/os-dragonfly.h b/os/os-dragonfly.h
index bde39101..4ce72539 100644
--- a/os/os-dragonfly.h
+++ b/os/os-dragonfly.h
@@ -171,8 +171,8 @@ static inline int fio_getaffinity(int pid, os_cpu_mask_t *mask)
  * ioprio_set() with 4 arguments, so define fio's ioprio_set() as a macro.
  * Note that there is no idea of class within ioprio_set(2) unlike Linux.
  */
-#define ioprio_value(ioprio_class, ioprio)	(ioprio)
-#define ioprio_set(which, who, ioprio_class, ioprio)	\
+#define ioprio_value(ioprio_class, ioprio, ioprio_hint)	(ioprio)
+#define ioprio_set(which, who, ioprio_class, ioprio, ioprio_hint)	\
 	ioprio_set(which, who, ioprio)
 
 #define ioprio(ioprio)		(ioprio)
diff --git a/os/os-linux.h b/os/os-linux.h
index 72727ac3..c5cd6515 100644
--- a/os/os-linux.h
+++ b/os/os-linux.h
@@ -125,16 +125,24 @@ enum {
 #define IOPRIO_BITS		16
 #define IOPRIO_CLASS_SHIFT	13
 
+#define IOPRIO_HINT_BITS	10
+#define IOPRIO_HINT_SHIFT	3
+
 #define IOPRIO_MIN_PRIO		0	/* highest priority */
 #define IOPRIO_MAX_PRIO		7	/* lowest priority */
 
 #define IOPRIO_MIN_PRIO_CLASS	0
 #define IOPRIO_MAX_PRIO_CLASS	3
 
+#define IOPRIO_MIN_PRIO_HINT	0
+#define IOPRIO_MAX_PRIO_HINT	((1 << IOPRIO_HINT_BITS) - 1)
+
 #define ioprio_class(ioprio)	((ioprio) >> IOPRIO_CLASS_SHIFT)
 #define ioprio(ioprio)		((ioprio) & IOPRIO_MAX_PRIO)
+#define ioprio_hint(ioprio)	\
+	(((ioprio) >> IOPRIO_HINT_SHIFT) & IOPRIO_MAX_PRIO_HINT)
 
-static inline int ioprio_value(int ioprio_class, int ioprio)
+static inline int ioprio_value(int ioprio_class, int ioprio, int ioprio_hint)
 {
 	/*
 	 * If no class is set, assume BE
@@ -142,7 +150,9 @@ static inline int ioprio_value(int ioprio_class, int ioprio)
         if (!ioprio_class)
                 ioprio_class = IOPRIO_CLASS_BE;
 
-	return (ioprio_class << IOPRIO_CLASS_SHIFT) | ioprio;
+	return (ioprio_class << IOPRIO_CLASS_SHIFT) |
+		(ioprio_hint << IOPRIO_HINT_SHIFT) |
+		ioprio;
 }
 
 static inline bool ioprio_value_is_class_rt(unsigned int priority)
@@ -150,10 +160,11 @@ static inline bool ioprio_value_is_class_rt(unsigned int priority)
 	return ioprio_class(priority) == IOPRIO_CLASS_RT;
 }
 
-static inline int ioprio_set(int which, int who, int ioprio_class, int ioprio)
+static inline int ioprio_set(int which, int who, int ioprio_class, int ioprio,
+			     int ioprio_hint)
 {
 	return syscall(__NR_ioprio_set, which, who,
-		       ioprio_value(ioprio_class, ioprio));
+		       ioprio_value(ioprio_class, ioprio, ioprio_hint));
 }
 
 #ifndef CONFIG_HAVE_GETTID
diff --git a/os/os.h b/os/os.h
index 036fc233..0f182324 100644
--- a/os/os.h
+++ b/os/os.h
@@ -120,11 +120,14 @@ extern int fio_cpus_split(os_cpu_mask_t *mask, unsigned int cpu);
 #define ioprio_value_is_class_rt(prio)	(false)
 #define IOPRIO_MIN_PRIO_CLASS		0
 #define IOPRIO_MAX_PRIO_CLASS		0
+#define ioprio_hint(prio)		0
+#define IOPRIO_MIN_PRIO_HINT		0
+#define IOPRIO_MAX_PRIO_HINT		0
 #endif
 #ifndef FIO_HAVE_IOPRIO
-#define ioprio_value(prioclass, prio)	(0)
+#define ioprio_value(prioclass, prio, priohint)	(0)
 #define ioprio(ioprio)			0
-#define ioprio_set(which, who, prioclass, prio)	(0)
+#define ioprio_set(which, who, prioclass, prio, priohint) (0)
 #define IOPRIO_MIN_PRIO			0
 #define IOPRIO_MAX_PRIO			0
 #endif
-- 
2.41.0

[PATCH v3 4/6] options: add priohint option

[Damien Le Moal]

Introduce the new option priohint to allow users to specify an I/O
priority hint applying to all IOs issued by a job. This increases fio
server version (FIO_SERVER_VER) to 101.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
---
 HOWTO.rst        |  9 +++++++++
 backend.c        |  8 +++++---
 cconv.c          |  2 ++
 fio.1            |  8 ++++++++
 options.c        | 18 ++++++++++++++++++
 server.h         |  2 +-
 thread_options.h |  3 ++-
 7 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/HOWTO.rst b/HOWTO.rst
index 7fe70fbd..d1a476e4 100644
--- a/HOWTO.rst
+++ b/HOWTO.rst
@@ -3436,6 +3436,15 @@ Threads, processes and job synchronization
 	priority setting, see I/O engine specific :option:`cmdprio_percentage`
 	and :option:`cmdprio_class` options.
 
+.. option:: priohint=int
+
+	Set the I/O priority hint. This is only applicable to platforms that
+	support I/O priority classes and to devices with features controlled
+	through priority hints, e.g. block devices supporting command duration
+	limits, or CDL. CDL is a way to indicate the desired maximum latency
+	of I/Os so that the device can optimize its internal command scheduling
+	according to the latency limits indicated by the user.
+
 .. option:: cpus_allowed=str
 
 	Controls the same options as :option:`cpumask`, but accepts a textual
diff --git a/backend.c b/backend.c
index 268b7825..624d7c6f 100644
--- a/backend.c
+++ b/backend.c
@@ -1799,14 +1799,16 @@ static void *thread_main(void *data)
 
 	/* ioprio_set() has to be done before td_io_init() */
 	if (fio_option_is_set(o, ioprio) ||
-	    fio_option_is_set(o, ioprio_class)) {
+	    fio_option_is_set(o, ioprio_class) ||
+	    fio_option_is_set(o, ioprio_hint)) {
 		ret = ioprio_set(IOPRIO_WHO_PROCESS, 0, o->ioprio_class,
-				 o->ioprio, 0);
+				 o->ioprio, o->ioprio_hint);
 		if (ret == -1) {
 			td_verror(td, errno, "ioprio_set");
 			goto err;
 		}
-		td->ioprio = ioprio_value(o->ioprio_class, o->ioprio, 0);
+		td->ioprio = ioprio_value(o->ioprio_class, o->ioprio,
+					  o->ioprio_hint);
 		td->ts.ioprio = td->ioprio;
 	}
 
diff --git a/cconv.c b/cconv.c
index 1bfa770f..ce6acbe6 100644
--- a/cconv.c
+++ b/cconv.c
@@ -281,6 +281,7 @@ int convert_thread_options_to_cpu(struct thread_options *o,
 	o->nice = le32_to_cpu(top->nice);
 	o->ioprio = le32_to_cpu(top->ioprio);
 	o->ioprio_class = le32_to_cpu(top->ioprio_class);
+	o->ioprio_hint = le32_to_cpu(top->ioprio_hint);
 	o->file_service_type = le32_to_cpu(top->file_service_type);
 	o->group_reporting = le32_to_cpu(top->group_reporting);
 	o->stats = le32_to_cpu(top->stats);
@@ -496,6 +497,7 @@ void convert_thread_options_to_net(struct thread_options_pack *top,
 	top->nice = cpu_to_le32(o->nice);
 	top->ioprio = cpu_to_le32(o->ioprio);
 	top->ioprio_class = cpu_to_le32(o->ioprio_class);
+	top->ioprio_hint = cpu_to_le32(o->ioprio_hint);
 	top->file_service_type = cpu_to_le32(o->file_service_type);
 	top->group_reporting = cpu_to_le32(o->group_reporting);
 	top->stats = cpu_to_le32(o->stats);
diff --git a/fio.1 b/fio.1
index 20acd081..e2a36327 100644
--- a/fio.1
+++ b/fio.1
@@ -3144,6 +3144,14 @@ Set the I/O priority class. See man \fBionice\fR\|(1). For per-command
 priority setting, see the I/O engine specific `cmdprio_percentage` and
 `cmdprio_class` options.
 .TP
+.BI priohint \fR=\fPint
+Set the I/O priority hint. This is only applicable to platforms that support
+I/O priority classes and to devices with features controlled through priority
+hints, e.g. block devices supporting command duration limits, or CDL. CDL is a
+way to indicate the desired maximum latency of I/Os so that the device can
+optimize its internal command scheduling according to the latency limits
+indicated by the user.
+.TP
 .BI cpus_allowed \fR=\fPstr
 Controls the same options as \fBcpumask\fR, but accepts a textual
 specification of the permitted CPUs instead and CPUs are indexed from 0. So
diff --git a/options.c b/options.c
index 143d3583..56672960 100644
--- a/options.c
+++ b/options.c
@@ -3806,6 +3806,18 @@ struct fio_option fio_options[FIO_MAX_OPTS] = {
 		.category = FIO_OPT_C_GENERAL,
 		.group	= FIO_OPT_G_CRED,
 	},
+	{
+		.name	= "priohint",
+		.lname	= "I/O nice priority hint",
+		.type	= FIO_OPT_INT,
+		.off1	= offsetof(struct thread_options, ioprio_hint),
+		.help	= "Set job IO priority hint",
+		.minval	= IOPRIO_MIN_PRIO_HINT,
+		.maxval	= IOPRIO_MAX_PRIO_HINT,
+		.interval = 1,
+		.category = FIO_OPT_C_GENERAL,
+		.group	= FIO_OPT_G_CRED,
+	},
 #else
 	{
 		.name	= "prioclass",
@@ -3813,6 +3825,12 @@ struct fio_option fio_options[FIO_MAX_OPTS] = {
 		.type	= FIO_OPT_UNSUPPORTED,
 		.help	= "Your platform does not support IO priority classes",
 	},
+	{
+		.name	= "priohint",
+		.lname	= "I/O nice priority hint",
+		.type	= FIO_OPT_UNSUPPORTED,
+		.help	= "Your platform does not support IO priority hints",
+	},
 #endif
 	{
 		.name	= "thinktime",
diff --git a/server.h b/server.h
index 601d3340..ad706118 100644
--- a/server.h
+++ b/server.h
@@ -51,7 +51,7 @@ struct fio_net_cmd_reply {
 };
 
 enum {
-	FIO_SERVER_VER			= 100,
+	FIO_SERVER_VER			= 101,
 
 	FIO_SERVER_MAX_FRAGMENT_PDU	= 1024,
 	FIO_SERVER_MAX_CMD_MB		= 2048,
diff --git a/thread_options.h b/thread_options.h
index 1715b36c..38a9993d 100644
--- a/thread_options.h
+++ b/thread_options.h
@@ -248,6 +248,7 @@ struct thread_options {
 	unsigned int nice;
 	unsigned int ioprio;
 	unsigned int ioprio_class;
+	unsigned int ioprio_hint;
 	unsigned int file_service_type;
 	unsigned int group_reporting;
 	unsigned int stats;
@@ -568,6 +569,7 @@ struct thread_options_pack {
 	uint32_t nice;
 	uint32_t ioprio;
 	uint32_t ioprio_class;
+	uint32_t ioprio_hint;
 	uint32_t file_service_type;
 	uint32_t group_reporting;
 	uint32_t stats;
@@ -601,7 +603,6 @@ struct thread_options_pack {
 	uint32_t lat_percentiles;
 	uint32_t slat_percentiles;
 	uint32_t percentile_precision;
-	uint32_t pad5;
 	fio_fp64_t percentile_list[FIO_IO_U_LIST_MAX_LEN];
 
 	uint8_t read_iolog_file[FIO_TOP_STR_MAX];
-- 
2.41.0

[PATCH v3 5/6] cmdprio: Add support for per I/O priority hint

[Damien Le Moal]

Introduce the new option cmdprio_hint to allow specifying I/O priority
hints per IO with the io_uring and libaio IO engines. A third acceptable
format for the cmdprio_bssplit option is also introduced to allow
specifying an I/O hint in addition to a priority class and level.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
---
 HOWTO.rst          | 28 ++++++++++++++++++++++++----
 engines/cmdprio.c  |  9 ++++++---
 engines/cmdprio.h  | 22 ++++++++++++++++++++++
 engines/io_uring.c |  4 ++--
 fio.1              | 27 +++++++++++++++++++++++----
 options.c          | 13 ++++++++++---
 6 files changed, 87 insertions(+), 16 deletions(-)

diff --git a/HOWTO.rst b/HOWTO.rst
index d1a476e4..ac8314f3 100644
--- a/HOWTO.rst
+++ b/HOWTO.rst
@@ -2287,6 +2287,16 @@ with the caveat that when used on the command line, they must come after the
 	reads and writes. See :manpage:`ionice(1)`. See also the
 	:option:`prioclass` option.
 
+.. option:: cmdprio_hint=int[,int] : [io_uring] [libaio]
+
+	Set the I/O priority hint to use for I/Os that must be issued with
+	a priority when :option:`cmdprio_percentage` or
+	:option:`cmdprio_bssplit` is set. If not specified when
+	:option:`cmdprio_percentage` or :option:`cmdprio_bssplit` is set,
+	this defaults to 0 (no hint). A single value applies to reads and
+	writes. Comma-separated values may be specified for reads and writes.
+	See also the :option:`priohint` option.
+
 .. option:: cmdprio=int[,int] : [io_uring] [libaio]
 
 	Set the I/O priority value to use for I/Os that must be issued with
@@ -2313,9 +2323,9 @@ with the caveat that when used on the command line, they must come after the
 
 		cmdprio_bssplit=blocksize/percentage:blocksize/percentage
 
-	In this case, each entry will use the priority class and priority
-	level defined by the options :option:`cmdprio_class` and
-	:option:`cmdprio` respectively.
+	In this case, each entry will use the priority class, priority hint
+	and priority level defined by the options :option:`cmdprio_class`,
+        :option:`cmdprio` and :option:`cmdprio_hint` respectively.
 
 	The second accepted format for this option is:
 
@@ -2326,7 +2336,14 @@ with the caveat that when used on the command line, they must come after the
 	accepted format does not restrict all entries to have the same priority
 	class and priority level.
 
-	For both formats, only the read and write data directions are supported,
+	The third accepted format for this option is:
+
+		cmdprio_bssplit=blocksize/percentage/class/level/hint:...
+
+	This is an extension of the second accepted format that allows to also
+	specify a priority hint.
+
+	For all formats, only the read and write data directions are supported,
 	values for trim IOs are ignored. This option is mutually exclusive with
 	the :option:`cmdprio_percentage` option.
 
@@ -3445,6 +3462,9 @@ Threads, processes and job synchronization
 	of I/Os so that the device can optimize its internal command scheduling
 	according to the latency limits indicated by the user.
 
+	For per-I/O priority hint setting, see the I/O engine specific
+	:option:`cmdprio_hint` option.
+
 .. option:: cpus_allowed=str
 
 	Controls the same options as :option:`cpumask`, but accepts a textual
diff --git a/engines/cmdprio.c b/engines/cmdprio.c
index e6ff1fc2..153e3691 100644
--- a/engines/cmdprio.c
+++ b/engines/cmdprio.c
@@ -267,7 +267,8 @@ static int fio_cmdprio_percentage(struct cmdprio *cmdprio, struct io_u *io_u,
  * to be set. If the random percentage value is within the user specified
  * percentage of I/Os that should use a cmdprio priority value (rather than
  * the default priority), then this function updates the io_u with an ioprio
- * value as defined by the cmdprio/cmdprio_class or cmdprio_bssplit options.
+ * value as defined by the cmdprio/cmdprio_hint/cmdprio_class or
+ * cmdprio_bssplit options.
  *
  * Return true if the io_u ioprio was changed and false otherwise.
  */
@@ -342,7 +343,8 @@ static int fio_cmdprio_gen_perc(struct thread_data *td, struct cmdprio *cmdprio)
 		prio = &cmdprio->perc_entry[ddir];
 		prio->perc = options->percentage[ddir];
 		prio->prio = ioprio_value(options->class[ddir],
-					  options->level[ddir], 0);
+					  options->level[ddir],
+					  options->hint[ddir]);
 		assign_clat_prio_index(prio, &values[ddir]);
 
 		ret = init_ts_clat_prio(ts, ddir, &values[ddir]);
@@ -400,7 +402,8 @@ static int fio_cmdprio_parse_and_gen_bssplit(struct thread_data *td,
 			goto err;
 
 		implicit_cmdprio = ioprio_value(options->class[ddir],
-						options->level[ddir], 0);
+						options->level[ddir],
+						options->hint[ddir]);
 
 		ret = fio_cmdprio_generate_bsprio_desc(&cmdprio->bsprio_desc[ddir],
 						       &parse_res[ddir],
diff --git a/engines/cmdprio.h b/engines/cmdprio.h
index 2c9d87bc..81e6c390 100644
--- a/engines/cmdprio.h
+++ b/engines/cmdprio.h
@@ -40,6 +40,7 @@ struct cmdprio_options {
 	unsigned int percentage[CMDPRIO_RWDIR_CNT];
 	unsigned int class[CMDPRIO_RWDIR_CNT];
 	unsigned int level[CMDPRIO_RWDIR_CNT];
+	unsigned int hint[CMDPRIO_RWDIR_CNT];
 	char *bssplit_str;
 };
 
@@ -74,6 +75,21 @@ struct cmdprio_options {
 		.category = FIO_OPT_C_ENGINE,					\
 		.group	= opt_group,						\
 	},									\
+	{									\
+		.name	= "cmdprio_hint",					\
+		.lname	= "Asynchronous I/O priority hint",			\
+		.type	= FIO_OPT_INT,						\
+		.off1	= offsetof(opt_struct,					\
+				   cmdprio_options.hint[DDIR_READ]),		\
+		.off2	= offsetof(opt_struct,					\
+				   cmdprio_options.hint[DDIR_WRITE]),		\
+		.help	= "Set asynchronous IO priority hint",			\
+		.minval	= IOPRIO_MIN_PRIO_HINT,					\
+		.maxval	= IOPRIO_MAX_PRIO_HINT,					\
+		.interval = 1,							\
+		.category = FIO_OPT_C_ENGINE,					\
+		.group	= opt_group,						\
+	},									\
 	{									\
 		.name	= "cmdprio",						\
 		.lname	= "Asynchronous I/O priority level",			\
@@ -112,6 +128,12 @@ struct cmdprio_options {
 		.type	= FIO_OPT_UNSUPPORTED,					\
 		.help	= "Platform does not support I/O priority classes",	\
 	},									\
+	{									\
+		.name	= "cmdprio_hint",					\
+		.lname	= "Asynchronous I/O priority hint",			\
+		.type	= FIO_OPT_UNSUPPORTED,					\
+		.help	= "Platform does not support I/O priority classes",	\
+	},									\
 	{									\
 		.name	= "cmdprio",						\
 		.lname	= "Asynchronous I/O priority level",			\
diff --git a/engines/io_uring.c b/engines/io_uring.c
index 5613c4c6..e1abf688 100644
--- a/engines/io_uring.c
+++ b/engines/io_uring.c
@@ -285,8 +285,8 @@ static int fio_ioring_prep(struct thread_data *td, struct io_u *io_u)
 		/*
 		 * Since io_uring can have a submission context (sqthread_poll)
 		 * that is different from the process context, we cannot rely on
-		 * the IO priority set by ioprio_set() (option prio/prioclass)
-		 * to be inherited.
+		 * the IO priority set by ioprio_set() (options prio, prioclass,
+		 * and priohint) to be inherited.
 		 * td->ioprio will have the value of the "default prio", so set
 		 * this unconditionally. This value might get overridden by
 		 * fio_ioring_cmdprio_prep() if the option cmdprio_percentage or
diff --git a/fio.1 b/fio.1
index e2a36327..f62617e7 100644
--- a/fio.1
+++ b/fio.1
@@ -2084,6 +2084,14 @@ is set, this defaults to the highest priority class. A single value applies
 to reads and writes. Comma-separated values may be specified for reads and
 writes. See man \fBionice\fR\|(1). See also the \fBprioclass\fR option.
 .TP
+.BI (io_uring,libaio)cmdprio_hint \fR=\fPint[,int]
+Set the I/O priority hint to use for I/Os that must be issued with a
+priority when \fBcmdprio_percentage\fR or \fBcmdprio_bssplit\fR is set.
+If not specified when \fBcmdprio_percentage\fR or \fBcmdprio_bssplit\fR
+is set, this defaults to 0 (no hint). A single value applies to reads and
+writes. Comma-separated values may be specified for reads and writes.
+See also the \fBpriohint\fR option.
+.TP
 .BI (io_uring,libaio)cmdprio \fR=\fPint[,int]
 Set the I/O priority value to use for I/Os that must be issued with a
 priority when \fBcmdprio_percentage\fR or \fBcmdprio_bssplit\fR is set.
@@ -2109,8 +2117,9 @@ The first accepted format for this option is the same as the format of the
 cmdprio_bssplit=blocksize/percentage:blocksize/percentage
 .RE
 .P
-In this case, each entry will use the priority class and priority level defined
-by the options \fBcmdprio_class\fR and \fBcmdprio\fR respectively.
+In this case, each entry will use the priority class, priority hint and
+priority level defined by the options \fBcmdprio_class\fR, \fBcmdprio\fR
+and \fBcmdprio_hint\fR respectively.
 .P
 The second accepted format for this option is:
 .RS
@@ -2123,7 +2132,16 @@ entry. In comparison with the first accepted format, the second accepted format
 does not restrict all entries to have the same priority class and priority
 level.
 .P
-For both formats, only the read and write data directions are supported, values
+The third accepted format for this option is:
+.RS
+.P
+cmdprio_bssplit=blocksize/percentage/class/level/hint:...
+.RE
+.P
+This is an extension of the second accepted format that allows to also
+specify a priority hint.
+.P
+For all formats, only the read and write data directions are supported, values
 for trim IOs are ignored. This option is mutually exclusive with the
 \fBcmdprio_percentage\fR option.
 .RE
@@ -3150,7 +3168,8 @@ I/O priority classes and to devices with features controlled through priority
 hints, e.g. block devices supporting command duration limits, or CDL. CDL is a
 way to indicate the desired maximum latency of I/Os so that the device can
 optimize its internal command scheduling according to the latency limits
-indicated by the user.
+indicated by the user. For per-I/O priority hint setting, see the I/O engine
+specific \fBcmdprio_hint\fB option.
 .TP
 .BI cpus_allowed \fR=\fPstr
 Controls the same options as \fBcpumask\fR, but accepts a textual
diff --git a/options.c b/options.c
index 56672960..48aa0d7b 100644
--- a/options.c
+++ b/options.c
@@ -313,15 +313,17 @@ static int parse_cmdprio_bssplit_entry(struct thread_options *o,
 	int matches = 0;
 	char *bs_str = NULL;
 	long long bs_val;
-	unsigned int perc = 0, class, level;
+	unsigned int perc = 0, class, level, hint;
 
 	/*
 	 * valid entry formats:
 	 * bs/ - %s/ - set perc to 0, prio to -1.
 	 * bs/perc - %s/%u - set prio to -1.
 	 * bs/perc/class/level - %s/%u/%u/%u
+	 * bs/perc/class/level/hint - %s/%u/%u/%u/%u
 	 */
-	matches = sscanf(str, "%m[^/]/%u/%u/%u", &bs_str, &perc, &class, &level);
+	matches = sscanf(str, "%m[^/]/%u/%u/%u/%u",
+			 &bs_str, &perc, &class, &level, &hint);
 	if (matches < 1) {
 		log_err("fio: invalid cmdprio_bssplit format\n");
 		return 1;
@@ -342,9 +344,14 @@ static int parse_cmdprio_bssplit_entry(struct thread_options *o,
 	case 2: /* bs/perc case */
 		break;
 	case 4: /* bs/perc/class/level case */
+	case 5: /* bs/perc/class/level/hint case */
 		class = min(class, (unsigned int) IOPRIO_MAX_PRIO_CLASS);
 		level = min(level, (unsigned int) IOPRIO_MAX_PRIO);
-		entry->prio = ioprio_value(class, level, 0);
+		if (matches == 5)
+			hint = min(hint, (unsigned int) IOPRIO_MAX_PRIO_HINT);
+		else
+			hint = 0;
+		entry->prio = ioprio_value(class, level, hint);
 		break;
 	default:
 		log_err("fio: invalid cmdprio_bssplit format\n");
-- 
2.41.0

[PATCH v3 6/6] stats: Add hint information to per priority level stats

[Damien Le Moal]

Modify the json and standard per-priority output stats to display the
hint value together with the priority class and level.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
---
 stat.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/stat.c b/stat.c
index 7fad73d1..7b791628 100644
--- a/stat.c
+++ b/stat.c
@@ -597,10 +597,11 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts,
 				continue;
 
 			snprintf(buf, sizeof(buf),
-				 "%s prio %u/%u",
+				 "%s prio %u/%u/%u",
 				 clat_type,
 				 ioprio_class(ts->clat_prio[ddir][i].ioprio),
-				 ioprio(ts->clat_prio[ddir][i].ioprio));
+				 ioprio(ts->clat_prio[ddir][i].ioprio),
+				 ioprio_hint(ts->clat_prio[ddir][i].ioprio));
 			display_lat(buf, min, max, mean, dev, out);
 		}
 	}
@@ -640,10 +641,11 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts,
 					continue;
 
 				snprintf(prio_name, sizeof(prio_name),
-					 "%s prio %u/%u (%.2f%% of IOs)",
+					 "%s prio %u/%u/%u (%.2f%% of IOs)",
 					 clat_type,
 					 ioprio_class(ts->clat_prio[ddir][i].ioprio),
 					 ioprio(ts->clat_prio[ddir][i].ioprio),
+					 ioprio_hint(ts->clat_prio[ddir][i].ioprio),
 					 100. * (double) prio_samples / (double) samples);
 				show_clat_percentiles(ts->clat_prio[ddir][i].io_u_plat,
 						prio_samples, ts->percentile_list,
@@ -1533,6 +1535,8 @@ static void add_ddir_status_json(struct thread_stat *ts,
 				ioprio_class(ts->clat_prio[ddir][i].ioprio));
 			json_object_add_value_int(obj, "prio",
 				ioprio(ts->clat_prio[ddir][i].ioprio));
+			json_object_add_value_int(obj, "priohint",
+				ioprio_hint(ts->clat_prio[ddir][i].ioprio));
 
 			tmp_object = add_ddir_lat_json(ts,
 					ts->clat_percentiles | ts->lat_percentiles,
-- 
2.41.0

Re: [PATCH v3 2/6] cmdprio: Introduce generic option definitions

[Niklas Cassel]

On Fri, Jul 21, 2023 at 08:05:06PM +0900, Damien Le Moal wrote:
> The definition of the per-I/O priority options for the io_uring and
> libaio I/O engines are almost identical, differing only by the option
> group and option data structure used.
> 
> Introduce the CMDPRIO_OPTIONS macro in engines/cmdprio.h to generically
> define these options in the io_uring and libaio engines to simplify the
> code.
> 
> Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
> ---
>  engines/cmdprio.h  | 84 ++++++++++++++++++++++++++++++++++++++++++++++
>  engines/io_uring.c | 82 +-------------------------------------------
>  engines/libaio.c   | 82 +-------------------------------------------
>  3 files changed, 86 insertions(+), 162 deletions(-)
> 
> diff --git a/engines/cmdprio.h b/engines/cmdprio.h
> index 755da8d0..2c9d87bc 100644
> --- a/engines/cmdprio.h
> +++ b/engines/cmdprio.h
> @@ -7,6 +7,7 @@
>  #define FIO_CMDPRIO_H
>  
>  #include "../fio.h"
> +#include "../optgroup.h"
>  
>  /* read and writes only, no trim */
>  #define CMDPRIO_RWDIR_CNT 2
> @@ -42,6 +43,89 @@ struct cmdprio_options {
>  	char *bssplit_str;
>  };
>  
> +#ifdef FIO_HAVE_IOPRIO_CLASS
> +#define CMDPRIO_OPTIONS(opt_struct, opt_group)					\
> +	{									\
> +		.name	= "cmdprio_percentage",					\
> +		.lname	= "high priority percentage",				\
> +		.type	= FIO_OPT_INT,						\
> +		.off1	= offsetof(opt_struct,					\
> +				   cmdprio_options.percentage[DDIR_READ]),	\
> +		.off2	= offsetof(opt_struct,					\
> +				   cmdprio_options.percentage[DDIR_WRITE]),	\
> +		.minval	= 0,							\
> +		.maxval	= 100,							\
> +		.help	= "Send high priority I/O this percentage of the time",	\
> +		.category = FIO_OPT_C_ENGINE,					\
> +		.group	= opt_group,						\
> +	},									\
> +	{									\
> +		.name	= "cmdprio_class",					\
> +		.lname	= "Asynchronous I/O priority class",			\
> +		.type	= FIO_OPT_INT,						\
> +		.off1	= offsetof(opt_struct,					\
> +				   cmdprio_options.class[DDIR_READ]),		\
> +		.off2	= offsetof(opt_struct,					\
> +				   cmdprio_options.class[DDIR_WRITE]),		\
> +		.help	= "Set asynchronous IO priority class",			\
> +		.minval	= IOPRIO_MIN_PRIO_CLASS + 1,				\
> +		.maxval	= IOPRIO_MAX_PRIO_CLASS,				\
> +		.interval = 1,							\
> +		.category = FIO_OPT_C_ENGINE,					\
> +		.group	= opt_group,						\
> +	},									\
> +	{									\
> +		.name	= "cmdprio",						\
> +		.lname	= "Asynchronous I/O priority level",			\
> +		.type	= FIO_OPT_INT,						\
> +		.off1	= offsetof(opt_struct,					\
> +				   cmdprio_options.level[DDIR_READ]),		\
> +		.off2	= offsetof(opt_struct,					\
> +				   cmdprio_options.level[DDIR_WRITE]),		\
> +		.help	= "Set asynchronous IO priority level",			\
> +		.minval	= IOPRIO_MIN_PRIO,					\
> +		.maxval	= IOPRIO_MAX_PRIO,					\
> +		.interval = 1,							\
> +		.category = FIO_OPT_C_ENGINE,					\
> +		.group	= opt_group,						\
> +	},									\
> +	{									\
> +		.name   = "cmdprio_bssplit",					\
> +		.lname  = "Priority percentage block size split",		\
> +		.type   = FIO_OPT_STR_STORE,					\
> +		.off1   = offsetof(opt_struct, cmdprio_options.bssplit_str),	\
> +		.help   = "Set priority percentages for different block sizes",	\
> +		.category = FIO_OPT_C_ENGINE,					\
> +		.group	= opt_group,						\
> +	}
> +#else
> +#define CMDPRIO_OPTIONS(opt_struct, opt_group)					\
> +	{									\
> +		.name	= "cmdprio_percentage",					\
> +		.lname	= "high priority percentage",				\
> +		.type	= FIO_OPT_UNSUPPORTED,					\
> +		.help	= "Platform does not support I/O priority classes",	\
> +	},									\
> +	{									\
> +		.name	= "cmdprio_class",					\
> +		.lname	= "Asynchronous I/O priority class",			\
> +		.type	= FIO_OPT_UNSUPPORTED,					\
> +		.help	= "Platform does not support I/O priority classes",	\
> +	},									\
> +	{									\
> +		.name	= "cmdprio",						\
> +		.lname	= "Asynchronous I/O priority level",			\
> +		.type	= FIO_OPT_UNSUPPORTED,					\
> +		.help	= "Platform does not support I/O priority classes",	\
> +	},									\
> +	{									\
> +		.name   = "cmdprio_bssplit",					\
> +		.lname  = "Priority percentage block size split",		\
> +		.type	= FIO_OPT_UNSUPPORTED,					\
> +		.help	= "Platform does not support I/O priority classes",	\
> +	}
> +#endif
> +
>  struct cmdprio {
>  	struct cmdprio_options *options;
>  	struct cmdprio_prio perc_entry[CMDPRIO_RWDIR_CNT];
> diff --git a/engines/io_uring.c b/engines/io_uring.c
> index f30a3c00..5613c4c6 100644
> --- a/engines/io_uring.c
> +++ b/engines/io_uring.c
> @@ -127,87 +127,6 @@ static struct fio_option options[] = {
>  		.category = FIO_OPT_C_ENGINE,
>  		.group	= FIO_OPT_G_IOURING,
>  	},
> -#ifdef FIO_HAVE_IOPRIO_CLASS
> -	{
> -		.name	= "cmdprio_percentage",
> -		.lname	= "high priority percentage",
> -		.type	= FIO_OPT_INT,
> -		.off1	= offsetof(struct ioring_options,
> -				   cmdprio_options.percentage[DDIR_READ]),
> -		.off2	= offsetof(struct ioring_options,
> -				   cmdprio_options.percentage[DDIR_WRITE]),
> -		.minval	= 0,
> -		.maxval	= 100,
> -		.help	= "Send high priority I/O this percentage of the time",
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_IOURING,
> -	},
> -	{
> -		.name	= "cmdprio_class",
> -		.lname	= "Asynchronous I/O priority class",
> -		.type	= FIO_OPT_INT,
> -		.off1	= offsetof(struct ioring_options,
> -				   cmdprio_options.class[DDIR_READ]),
> -		.off2	= offsetof(struct ioring_options,
> -				   cmdprio_options.class[DDIR_WRITE]),
> -		.help	= "Set asynchronous IO priority class",
> -		.minval	= IOPRIO_MIN_PRIO_CLASS + 1,
> -		.maxval	= IOPRIO_MAX_PRIO_CLASS,
> -		.interval = 1,
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_IOURING,
> -	},
> -	{
> -		.name	= "cmdprio",
> -		.lname	= "Asynchronous I/O priority level",
> -		.type	= FIO_OPT_INT,
> -		.off1	= offsetof(struct ioring_options,
> -				   cmdprio_options.level[DDIR_READ]),
> -		.off2	= offsetof(struct ioring_options,
> -				   cmdprio_options.level[DDIR_WRITE]),
> -		.help	= "Set asynchronous IO priority level",
> -		.minval	= IOPRIO_MIN_PRIO,
> -		.maxval	= IOPRIO_MAX_PRIO,
> -		.interval = 1,
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_IOURING,
> -	},
> -	{
> -		.name   = "cmdprio_bssplit",
> -		.lname  = "Priority percentage block size split",
> -		.type   = FIO_OPT_STR_STORE,
> -		.off1   = offsetof(struct ioring_options,
> -				   cmdprio_options.bssplit_str),
> -		.help   = "Set priority percentages for different block sizes",
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_IOURING,
> -	},
> -#else
> -	{
> -		.name	= "cmdprio_percentage",
> -		.lname	= "high priority percentage",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -	{
> -		.name	= "cmdprio_class",
> -		.lname	= "Asynchronous I/O priority class",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -	{
> -		.name	= "cmdprio",
> -		.lname	= "Asynchronous I/O priority level",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -	{
> -		.name   = "cmdprio_bssplit",
> -		.lname  = "Priority percentage block size split",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -#endif
>  	{
>  		.name	= "fixedbufs",
>  		.lname	= "Fixed (pre-mapped) IO buffers",
> @@ -297,6 +216,7 @@ static struct fio_option options[] = {
>  		.category = FIO_OPT_C_ENGINE,
>  		.group	= FIO_OPT_G_IOURING,
>  	},
> +	CMDPRIO_OPTIONS(struct ioring_options, FIO_OPT_G_IOURING),
>  	{
>  		.name	= NULL,
>  	},
> diff --git a/engines/libaio.c b/engines/libaio.c
> index 6a0745aa..aaccc7ce 100644
> --- a/engines/libaio.c
> +++ b/engines/libaio.c
> @@ -72,87 +72,6 @@ static struct fio_option options[] = {
>  		.category = FIO_OPT_C_ENGINE,
>  		.group	= FIO_OPT_G_LIBAIO,
>  	},
> -#ifdef FIO_HAVE_IOPRIO_CLASS
> -	{
> -		.name	= "cmdprio_percentage",
> -		.lname	= "high priority percentage",
> -		.type	= FIO_OPT_INT,
> -		.off1	= offsetof(struct libaio_options,
> -				   cmdprio_options.percentage[DDIR_READ]),
> -		.off2	= offsetof(struct libaio_options,
> -				   cmdprio_options.percentage[DDIR_WRITE]),
> -		.minval	= 0,
> -		.maxval	= 100,
> -		.help	= "Send high priority I/O this percentage of the time",
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_LIBAIO,
> -	},
> -	{
> -		.name	= "cmdprio_class",
> -		.lname	= "Asynchronous I/O priority class",
> -		.type	= FIO_OPT_INT,
> -		.off1	= offsetof(struct libaio_options,
> -				   cmdprio_options.class[DDIR_READ]),
> -		.off2	= offsetof(struct libaio_options,
> -				   cmdprio_options.class[DDIR_WRITE]),
> -		.help	= "Set asynchronous IO priority class",
> -		.minval	= IOPRIO_MIN_PRIO_CLASS + 1,
> -		.maxval	= IOPRIO_MAX_PRIO_CLASS,
> -		.interval = 1,
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_LIBAIO,
> -	},
> -	{
> -		.name	= "cmdprio",
> -		.lname	= "Asynchronous I/O priority level",
> -		.type	= FIO_OPT_INT,
> -		.off1	= offsetof(struct libaio_options,
> -				   cmdprio_options.level[DDIR_READ]),
> -		.off2	= offsetof(struct libaio_options,
> -				   cmdprio_options.level[DDIR_WRITE]),
> -		.help	= "Set asynchronous IO priority level",
> -		.minval	= IOPRIO_MIN_PRIO,
> -		.maxval	= IOPRIO_MAX_PRIO,
> -		.interval = 1,
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_LIBAIO,
> -	},
> -	{
> -		.name   = "cmdprio_bssplit",
> -		.lname  = "Priority percentage block size split",
> -		.type   = FIO_OPT_STR_STORE,
> -		.off1   = offsetof(struct libaio_options,
> -				   cmdprio_options.bssplit_str),
> -		.help   = "Set priority percentages for different block sizes",
> -		.category = FIO_OPT_C_ENGINE,
> -		.group	= FIO_OPT_G_LIBAIO,
> -	},
> -#else
> -	{
> -		.name	= "cmdprio_percentage",
> -		.lname	= "high priority percentage",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -	{
> -		.name	= "cmdprio_class",
> -		.lname	= "Asynchronous I/O priority class",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -	{
> -		.name	= "cmdprio",
> -		.lname	= "Asynchronous I/O priority level",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -	{
> -		.name   = "cmdprio_bssplit",
> -		.lname  = "Priority percentage block size split",
> -		.type	= FIO_OPT_UNSUPPORTED,
> -		.help	= "Your platform does not support I/O priority classes",
> -	},
> -#endif
>  	{
>  		.name	= "nowait",
>  		.lname	= "RWF_NOWAIT",
> @@ -162,6 +81,7 @@ static struct fio_option options[] = {
>  		.category = FIO_OPT_C_ENGINE,
>  		.group	= FIO_OPT_G_LIBAIO,
>  	},
> +	CMDPRIO_OPTIONS(struct libaio_options, FIO_OPT_G_LIBAIO),
>  	{
>  		.name	= NULL,
>  	},
> -- 
> 2.41.0
> 

Nice cleanup!

Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>

Re: [PATCH v3 5/6] cmdprio: Add support for per I/O priority hint

[Niklas Cassel]

On Fri, Jul 21, 2023 at 08:05:09PM +0900, Damien Le Moal wrote:
> Introduce the new option cmdprio_hint to allow specifying I/O priority
> hints per IO with the io_uring and libaio IO engines. A third acceptable
> format for the cmdprio_bssplit option is also introduced to allow
> specifying an I/O hint in addition to a priority class and level.
> 
> Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
> ---
>  HOWTO.rst          | 28 ++++++++++++++++++++++++----
>  engines/cmdprio.c  |  9 ++++++---
>  engines/cmdprio.h  | 22 ++++++++++++++++++++++
>  engines/io_uring.c |  4 ++--
>  fio.1              | 27 +++++++++++++++++++++++----
>  options.c          | 13 ++++++++++---
>  6 files changed, 87 insertions(+), 16 deletions(-)
> 
> diff --git a/HOWTO.rst b/HOWTO.rst
> index d1a476e4..ac8314f3 100644
> --- a/HOWTO.rst
> +++ b/HOWTO.rst
> @@ -2287,6 +2287,16 @@ with the caveat that when used on the command line, they must come after the
>  	reads and writes. See :manpage:`ionice(1)`. See also the
>  	:option:`prioclass` option.
>  
> +.. option:: cmdprio_hint=int[,int] : [io_uring] [libaio]
> +
> +	Set the I/O priority hint to use for I/Os that must be issued with
> +	a priority when :option:`cmdprio_percentage` or
> +	:option:`cmdprio_bssplit` is set. If not specified when
> +	:option:`cmdprio_percentage` or :option:`cmdprio_bssplit` is set,
> +	this defaults to 0 (no hint). A single value applies to reads and
> +	writes. Comma-separated values may be specified for reads and writes.
> +	See also the :option:`priohint` option.
> +
>  .. option:: cmdprio=int[,int] : [io_uring] [libaio]
>  
>  	Set the I/O priority value to use for I/Os that must be issued with
> @@ -2313,9 +2323,9 @@ with the caveat that when used on the command line, they must come after the
>  
>  		cmdprio_bssplit=blocksize/percentage:blocksize/percentage
>  
> -	In this case, each entry will use the priority class and priority
> -	level defined by the options :option:`cmdprio_class` and
> -	:option:`cmdprio` respectively.
> +	In this case, each entry will use the priority class, priority hint
> +	and priority level defined by the options :option:`cmdprio_class`,
> +        :option:`cmdprio` and :option:`cmdprio_hint` respectively.
>  
>  	The second accepted format for this option is:
>  
> @@ -2326,7 +2336,14 @@ with the caveat that when used on the command line, they must come after the
>  	accepted format does not restrict all entries to have the same priority
>  	class and priority level.
>  
> -	For both formats, only the read and write data directions are supported,
> +	The third accepted format for this option is:
> +
> +		cmdprio_bssplit=blocksize/percentage/class/level/hint:...
> +
> +	This is an extension of the second accepted format that allows to also
> +	specify a priority hint.
> +
> +	For all formats, only the read and write data directions are supported,
>  	values for trim IOs are ignored. This option is mutually exclusive with
>  	the :option:`cmdprio_percentage` option.
>  
> @@ -3445,6 +3462,9 @@ Threads, processes and job synchronization
>  	of I/Os so that the device can optimize its internal command scheduling
>  	according to the latency limits indicated by the user.
>  
> +	For per-I/O priority hint setting, see the I/O engine specific
> +	:option:`cmdprio_hint` option.
> +
>  .. option:: cpus_allowed=str
>  
>  	Controls the same options as :option:`cpumask`, but accepts a textual
> diff --git a/engines/cmdprio.c b/engines/cmdprio.c
> index e6ff1fc2..153e3691 100644
> --- a/engines/cmdprio.c
> +++ b/engines/cmdprio.c
> @@ -267,7 +267,8 @@ static int fio_cmdprio_percentage(struct cmdprio *cmdprio, struct io_u *io_u,
>   * to be set. If the random percentage value is within the user specified
>   * percentage of I/Os that should use a cmdprio priority value (rather than
>   * the default priority), then this function updates the io_u with an ioprio
> - * value as defined by the cmdprio/cmdprio_class or cmdprio_bssplit options.
> + * value as defined by the cmdprio/cmdprio_hint/cmdprio_class or
> + * cmdprio_bssplit options.
>   *
>   * Return true if the io_u ioprio was changed and false otherwise.
>   */
> @@ -342,7 +343,8 @@ static int fio_cmdprio_gen_perc(struct thread_data *td, struct cmdprio *cmdprio)
>  		prio = &cmdprio->perc_entry[ddir];
>  		prio->perc = options->percentage[ddir];
>  		prio->prio = ioprio_value(options->class[ddir],
> -					  options->level[ddir], 0);
> +					  options->level[ddir],
> +					  options->hint[ddir]);
>  		assign_clat_prio_index(prio, &values[ddir]);
>  
>  		ret = init_ts_clat_prio(ts, ddir, &values[ddir]);
> @@ -400,7 +402,8 @@ static int fio_cmdprio_parse_and_gen_bssplit(struct thread_data *td,
>  			goto err;
>  
>  		implicit_cmdprio = ioprio_value(options->class[ddir],
> -						options->level[ddir], 0);
> +						options->level[ddir],
> +						options->hint[ddir]);
>  
>  		ret = fio_cmdprio_generate_bsprio_desc(&cmdprio->bsprio_desc[ddir],
>  						       &parse_res[ddir],
> diff --git a/engines/cmdprio.h b/engines/cmdprio.h
> index 2c9d87bc..81e6c390 100644
> --- a/engines/cmdprio.h
> +++ b/engines/cmdprio.h
> @@ -40,6 +40,7 @@ struct cmdprio_options {
>  	unsigned int percentage[CMDPRIO_RWDIR_CNT];
>  	unsigned int class[CMDPRIO_RWDIR_CNT];
>  	unsigned int level[CMDPRIO_RWDIR_CNT];
> +	unsigned int hint[CMDPRIO_RWDIR_CNT];
>  	char *bssplit_str;
>  };
>  
> @@ -74,6 +75,21 @@ struct cmdprio_options {
>  		.category = FIO_OPT_C_ENGINE,					\
>  		.group	= opt_group,						\
>  	},									\
> +	{									\
> +		.name	= "cmdprio_hint",					\
> +		.lname	= "Asynchronous I/O priority hint",			\
> +		.type	= FIO_OPT_INT,						\
> +		.off1	= offsetof(opt_struct,					\
> +				   cmdprio_options.hint[DDIR_READ]),		\
> +		.off2	= offsetof(opt_struct,					\
> +				   cmdprio_options.hint[DDIR_WRITE]),		\
> +		.help	= "Set asynchronous IO priority hint",			\
> +		.minval	= IOPRIO_MIN_PRIO_HINT,					\
> +		.maxval	= IOPRIO_MAX_PRIO_HINT,					\
> +		.interval = 1,							\
> +		.category = FIO_OPT_C_ENGINE,					\
> +		.group	= opt_group,						\
> +	},									\
>  	{									\
>  		.name	= "cmdprio",						\
>  		.lname	= "Asynchronous I/O priority level",			\
> @@ -112,6 +128,12 @@ struct cmdprio_options {
>  		.type	= FIO_OPT_UNSUPPORTED,					\
>  		.help	= "Platform does not support I/O priority classes",	\
>  	},									\
> +	{									\
> +		.name	= "cmdprio_hint",					\
> +		.lname	= "Asynchronous I/O priority hint",			\
> +		.type	= FIO_OPT_UNSUPPORTED,					\
> +		.help	= "Platform does not support I/O priority classes",	\
> +	},									\
>  	{									\
>  		.name	= "cmdprio",						\
>  		.lname	= "Asynchronous I/O priority level",			\
> diff --git a/engines/io_uring.c b/engines/io_uring.c
> index 5613c4c6..e1abf688 100644
> --- a/engines/io_uring.c
> +++ b/engines/io_uring.c
> @@ -285,8 +285,8 @@ static int fio_ioring_prep(struct thread_data *td, struct io_u *io_u)
>  		/*
>  		 * Since io_uring can have a submission context (sqthread_poll)
>  		 * that is different from the process context, we cannot rely on
> -		 * the IO priority set by ioprio_set() (option prio/prioclass)
> -		 * to be inherited.
> +		 * the IO priority set by ioprio_set() (options prio, prioclass,
> +		 * and priohint) to be inherited.
>  		 * td->ioprio will have the value of the "default prio", so set
>  		 * this unconditionally. This value might get overridden by
>  		 * fio_ioring_cmdprio_prep() if the option cmdprio_percentage or
> diff --git a/fio.1 b/fio.1
> index e2a36327..f62617e7 100644
> --- a/fio.1
> +++ b/fio.1
> @@ -2084,6 +2084,14 @@ is set, this defaults to the highest priority class. A single value applies
>  to reads and writes. Comma-separated values may be specified for reads and
>  writes. See man \fBionice\fR\|(1). See also the \fBprioclass\fR option.
>  .TP
> +.BI (io_uring,libaio)cmdprio_hint \fR=\fPint[,int]
> +Set the I/O priority hint to use for I/Os that must be issued with a
> +priority when \fBcmdprio_percentage\fR or \fBcmdprio_bssplit\fR is set.
> +If not specified when \fBcmdprio_percentage\fR or \fBcmdprio_bssplit\fR
> +is set, this defaults to 0 (no hint). A single value applies to reads and
> +writes. Comma-separated values may be specified for reads and writes.
> +See also the \fBpriohint\fR option.
> +.TP
>  .BI (io_uring,libaio)cmdprio \fR=\fPint[,int]
>  Set the I/O priority value to use for I/Os that must be issued with a
>  priority when \fBcmdprio_percentage\fR or \fBcmdprio_bssplit\fR is set.
> @@ -2109,8 +2117,9 @@ The first accepted format for this option is the same as the format of the
>  cmdprio_bssplit=blocksize/percentage:blocksize/percentage
>  .RE
>  .P
> -In this case, each entry will use the priority class and priority level defined
> -by the options \fBcmdprio_class\fR and \fBcmdprio\fR respectively.
> +In this case, each entry will use the priority class, priority hint and
> +priority level defined by the options \fBcmdprio_class\fR, \fBcmdprio\fR
> +and \fBcmdprio_hint\fR respectively.
>  .P
>  The second accepted format for this option is:
>  .RS
> @@ -2123,7 +2132,16 @@ entry. In comparison with the first accepted format, the second accepted format
>  does not restrict all entries to have the same priority class and priority
>  level.
>  .P
> -For both formats, only the read and write data directions are supported, values
> +The third accepted format for this option is:
> +.RS
> +.P
> +cmdprio_bssplit=blocksize/percentage/class/level/hint:...
> +.RE
> +.P
> +This is an extension of the second accepted format that allows to also
> +specify a priority hint.
> +.P
> +For all formats, only the read and write data directions are supported, values
>  for trim IOs are ignored. This option is mutually exclusive with the
>  \fBcmdprio_percentage\fR option.
>  .RE
> @@ -3150,7 +3168,8 @@ I/O priority classes and to devices with features controlled through priority
>  hints, e.g. block devices supporting command duration limits, or CDL. CDL is a
>  way to indicate the desired maximum latency of I/Os so that the device can
>  optimize its internal command scheduling according to the latency limits
> -indicated by the user.
> +indicated by the user. For per-I/O priority hint setting, see the I/O engine
> +specific \fBcmdprio_hint\fB option.
>  .TP
>  .BI cpus_allowed \fR=\fPstr
>  Controls the same options as \fBcpumask\fR, but accepts a textual
> diff --git a/options.c b/options.c
> index 56672960..48aa0d7b 100644
> --- a/options.c
> +++ b/options.c
> @@ -313,15 +313,17 @@ static int parse_cmdprio_bssplit_entry(struct thread_options *o,
>  	int matches = 0;
>  	char *bs_str = NULL;
>  	long long bs_val;
> -	unsigned int perc = 0, class, level;
> +	unsigned int perc = 0, class, level, hint;
>  
>  	/*
>  	 * valid entry formats:
>  	 * bs/ - %s/ - set perc to 0, prio to -1.
>  	 * bs/perc - %s/%u - set prio to -1.
>  	 * bs/perc/class/level - %s/%u/%u/%u
> +	 * bs/perc/class/level/hint - %s/%u/%u/%u/%u
>  	 */
> -	matches = sscanf(str, "%m[^/]/%u/%u/%u", &bs_str, &perc, &class, &level);
> +	matches = sscanf(str, "%m[^/]/%u/%u/%u/%u",
> +			 &bs_str, &perc, &class, &level, &hint);
>  	if (matches < 1) {
>  		log_err("fio: invalid cmdprio_bssplit format\n");
>  		return 1;
> @@ -342,9 +344,14 @@ static int parse_cmdprio_bssplit_entry(struct thread_options *o,
>  	case 2: /* bs/perc case */
>  		break;
>  	case 4: /* bs/perc/class/level case */
> +	case 5: /* bs/perc/class/level/hint case */
>  		class = min(class, (unsigned int) IOPRIO_MAX_PRIO_CLASS);
>  		level = min(level, (unsigned int) IOPRIO_MAX_PRIO);
> -		entry->prio = ioprio_value(class, level, 0);
> +		if (matches == 5)
> +			hint = min(hint, (unsigned int) IOPRIO_MAX_PRIO_HINT);
> +		else
> +			hint = 0;
> +		entry->prio = ioprio_value(class, level, hint);
>  		break;
>  	default:
>  		log_err("fio: invalid cmdprio_bssplit format\n");
> -- 
> 2.41.0
> 

Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>

Re: [PATCH v3 0/6] Add support for I/O priority hints

[Jens Axboe]

On Fri, 21 Jul 2023 20:05:04 +0900, Damien Le Moal wrote:
> Linux kernel 6.5 adds support for I/O priority hints, which can be
> used (for now) to specify command duration limits for block devices
> supporting this feature.
> 
> This patch series extends fio I/O priority options and adds new options
> to allow users to specify I/O priority hints.
> 
> [...]

Applied, thanks!

[1/6] os-linux: Cleanup IO priority class and value macros
      commit: d4d503a557d4a664ff3fd7a811966df038d06634
[2/6] cmdprio: Introduce generic option definitions
      commit: 2838f77aa80605c13cd18ce5e941005a42cec4a4
[3/6] os-linux: add initial support for IO priority hints
      commit: b3048c1b564fc793ee11004a17b2a4de5a82be27
[4/6] options: add priohint option
      commit: 860462dad312ef121766f5d17b1df7b05d1f47ee
[5/6] cmdprio: Add support for per I/O priority hint
      commit: 79012fece0a0ecb02ad6a3322913980efdb1d726
[6/6] stats: Add hint information to per priority level stats
      commit: 219a868280716e4e221b57269ee3b8a39ea9c29b

Best regards,
-- 
Jens Axboe