[PATCHv2 0/9] libnvme: add support for retrieving additional NVMe stat

[PATCHv2 0/9] libnvme: add support for retrieving additional NVMe stat

[Nilay Shroff]

Hi,

Certain NVMe attributes and statistics can change dynamically at runtime.
However, the current libnvme implementation caches attribute values while
scanning and building the topology. Subsequent libnvme API calls return
these cached values.

While this approach works well for one-shot nvme-cli commands, it is not
suitable for use cases that require upto date information. In particular,
real-time monitoring tools such as nvme-top require access to the latest
(non-cached) values of such attributes.

To address this, this patchset introduces support for retrieving
non-cached values for selected attributes whose values may change
dynamically. The first three patches disable auto-generated accessors
for ana_state, numa_nodes, and iopolicy using "!accessors:none", and
provide custom implementations that always return the latest values.

In addition, libnvme lacks support for retrieving gendisk statistics, which
provide useful insight into disk activity (e.g., number of I/Os processed,
time spent servicing I/O, and in-flight I/O counts). This patchset adds
support for retrieving gendisk I/O statistics for both per-path and namespace
gendisks.

Finally, this series adds support for retrieving diagnostic counters at 
different levels, including per-path, namespace, nshead, and controller.
These counters should improve visibility into NVMe native multipath behavior.

All of the above statistics and counters can be leveraged by tools such as
nvme-top to provide real-time monitoring and analysis.

As usual, feedback and suggestions are welcome!

Changes from v1:
  - Avoid exposing internal state of libnvme to its users
    while exporting the nvme stat; add a switch while updating
    nvme stat which determines whether getters shall return the
    nvme diffstat or absolute stat (Daniel Wagner)
  - If libnvme API fails then return appropriate error code
    instead of -1 (Daniel Wagner)
Link to v1: https://lore.kernel.org/all/20260321152823.3197870-1-nilay@linux.ibm.com/

Nilay Shroff (9):
  libnvme: annotate nvme_path::ana_state with !accessors:none
  libnvme: annotate nvme_path::numa_nodes with !accessors:none
  libnvme: annotate nvme_subsystem::iopolicy with !accessors:none
  libnvme: add support for retrieving per-path gendisk I/O statistics
  libnvme: add support for retrieving namespace gendisk I/O statistics
  libnvme: add support for per-path diagnostic counters
  libnvme: add support for namespace diagnostic counters
  libnvme: add support for nshead diagnostic counters
  libnvme: add support for ctrl diagnostic counters

 libnvme/src/accessors.ld     |   6 -
 libnvme/src/libnvme.ld       |  36 +++
 libnvme/src/nvme/accessors.c |  39 ---
 libnvme/src/nvme/accessors.h |  47 ---
 libnvme/src/nvme/private.h   |  51 +++-
 libnvme/src/nvme/tree.c      | 563 +++++++++++++++++++++++++++++++++++
 libnvme/src/nvme/tree.h      | 297 ++++++++++++++++++
 7 files changed, 944 insertions(+), 95 deletions(-)

-- 
2.53.0

[PATCHv2 1/9] libnvme: annotate nvme_path::ana_state with !accessors:none

[Nilay Shroff]

The default accessor generation creates getters that return cached
attribute values. However, for nvme_path::ana_state, a real-time
(non-cached) value is required.

This is particularly useful for tools such as nvme-top, which rely on
up-to-date information for displaying a real-time dashboard.

Annotate nvme_path::ana_state with "!accessors:none" to disable the
auto-generated accessor, and provide a custom implementation of
nvme_path_get_ana_state() that returns the current value.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/accessors.ld     |  2 --
 libnvme/src/libnvme.ld       |  1 +
 libnvme/src/nvme/accessors.c | 13 -------------
 libnvme/src/nvme/accessors.h | 15 ---------------
 libnvme/src/nvme/private.h   |  2 +-
 libnvme/src/nvme/tree.c      | 15 +++++++++++++++
 libnvme/src/nvme/tree.h      |  8 ++++++++
 7 files changed, 25 insertions(+), 31 deletions(-)

diff --git a/libnvme/src/accessors.ld b/libnvme/src/accessors.ld
index 3cd26f8f7..9e5653b92 100644
--- a/libnvme/src/accessors.ld
+++ b/libnvme/src/accessors.ld
@@ -14,8 +14,6 @@ LIBNVME_ACCESSORS_3 {
 		nvme_path_set_name;
 		nvme_path_get_sysfs_dir;
 		nvme_path_set_sysfs_dir;
-		nvme_path_get_ana_state;
-		nvme_path_set_ana_state;
 		nvme_path_get_numa_nodes;
 		nvme_path_set_numa_nodes;
 		nvme_path_get_grpid;
diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index 2a34886af..38625cbf4 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -142,6 +142,7 @@ LIBNVME_3 {
 		nvme_path_get_ctrl;
 		nvme_path_get_ns;
 		nvme_path_get_queue_depth;
+		nvme_path_get_ana_state;
 		nvme_random_uuid;
 		nvme_read_config;
 		nvme_read_hostid;
diff --git a/libnvme/src/nvme/accessors.c b/libnvme/src/nvme/accessors.c
index d3c507d7e..8b095ed4d 100644
--- a/libnvme/src/nvme/accessors.c
+++ b/libnvme/src/nvme/accessors.c
@@ -52,19 +52,6 @@ __public const char *nvme_path_get_sysfs_dir(const struct nvme_path *p)
 	return p->sysfs_dir;
 }
 
-__public void nvme_path_set_ana_state(
-		struct nvme_path *p,
-		const char *ana_state)
-{
-	free(p->ana_state);
-	p->ana_state = ana_state ? strdup(ana_state) : NULL;
-}
-
-__public const char *nvme_path_get_ana_state(const struct nvme_path *p)
-{
-	return p->ana_state;
-}
-
 __public void nvme_path_set_numa_nodes(
 		struct nvme_path *p,
 		const char *numa_nodes)
diff --git a/libnvme/src/nvme/accessors.h b/libnvme/src/nvme/accessors.h
index 5c594dd12..3ede23cbc 100644
--- a/libnvme/src/nvme/accessors.h
+++ b/libnvme/src/nvme/accessors.h
@@ -68,21 +68,6 @@ void nvme_path_set_sysfs_dir(struct nvme_path *p, const char *sysfs_dir);
  */
 const char *nvme_path_get_sysfs_dir(const struct nvme_path *p);
 
-/**
- * nvme_path_set_ana_state() - Set ana_state.
- * @p: The &struct nvme_path instance to update.
- * @ana_state: New string; a copy is stored. Pass NULL to clear.
- */
-void nvme_path_set_ana_state(struct nvme_path *p, const char *ana_state);
-
-/**
- * nvme_path_get_ana_state() - Get ana_state.
- * @p: The &struct nvme_path instance to query.
- *
- * Return: The value of the ana_state field, or NULL if not set.
- */
-const char *nvme_path_get_ana_state(const struct nvme_path *p);
-
 /**
  * nvme_path_set_numa_nodes() - Set numa_nodes.
  * @p: The &struct nvme_path instance to update.
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index c3651fb95..7631c4084 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -137,8 +137,8 @@ struct nvme_path { /*!generate-accessors*/
 
 	char *name;
 	char *sysfs_dir;
-	char *ana_state;
 	char *numa_nodes;
+	char *ana_state; //!accessors:none
 	int grpid;
 	int queue_depth; //!accessors:none
 };
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index 377f6e8ea..f087d7b03 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -806,6 +806,21 @@ __public int nvme_path_get_queue_depth(nvme_path_t p)
 	return p->queue_depth;
 }
 
+__public char *nvme_path_get_ana_state(nvme_path_t p)
+{
+	_cleanup_free_ char *ana_state = NULL;
+
+	ana_state = nvme_get_path_attr(p, "ana_state");
+	if (ana_state) {
+		if (!p->ana_state || strcmp(ana_state, p->ana_state)) {
+			free(p->ana_state);
+			p->ana_state = strdup(ana_state);
+		}
+	}
+
+	return p->ana_state;
+}
+
 void nvme_free_path(struct nvme_path *p)
 {
 	list_del_init(&p->entry);
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index 07b75677c..ec0f4f2e6 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -679,6 +679,14 @@ int nvme_ns_identify_descs(nvme_ns_t n, struct nvme_ns_id_desc *descs);
  */
 int nvme_path_get_queue_depth(nvme_path_t p);
 
+/**
+ * nvme_path_get_ana_state() - ANA state of an nvme_path_t object
+ * @p: &nvme_path_t object
+ *
+ * Return: ANA state of @p
+ */
+char *nvme_path_get_ana_state(nvme_path_t p);
+
 /**
  * nvme_path_get_ctrl() - Parent controller of an nvme_path_t object
  * @p:	&nvme_path_t object
-- 
2.53.0

[PATCHv2 2/9] libnvme: annotate nvme_path::numa_nodes with !accessors:none

[Nilay Shroff]

The default accessor generation creates getters that return cached
attribute values. However, for nvme_path::numa_nodes, a real-time
(non-cached) value is required.

This is particularly useful for tools such as nvme-top, which rely on
up-to-date information for displaying a real-time dashboard.

Annotate nvme_path::numa_nodes with "!accessors:none" to disable the
auto-generated accessor, and provide a custom implementation of
nvme_path_get_numa_nodes() that returns the current value.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/accessors.ld     |  2 --
 libnvme/src/libnvme.ld       |  1 +
 libnvme/src/nvme/accessors.c | 13 -------------
 libnvme/src/nvme/accessors.h | 15 ---------------
 libnvme/src/nvme/private.h   |  2 +-
 libnvme/src/nvme/tree.c      | 15 +++++++++++++++
 libnvme/src/nvme/tree.h      |  8 ++++++++
 7 files changed, 25 insertions(+), 31 deletions(-)

diff --git a/libnvme/src/accessors.ld b/libnvme/src/accessors.ld
index 9e5653b92..433767191 100644
--- a/libnvme/src/accessors.ld
+++ b/libnvme/src/accessors.ld
@@ -14,8 +14,6 @@ LIBNVME_ACCESSORS_3 {
 		nvme_path_set_name;
 		nvme_path_get_sysfs_dir;
 		nvme_path_set_sysfs_dir;
-		nvme_path_get_numa_nodes;
-		nvme_path_set_numa_nodes;
 		nvme_path_get_grpid;
 		nvme_path_set_grpid;
 		nvme_ns_get_nsid;
diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index 38625cbf4..f2972f455 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -143,6 +143,7 @@ LIBNVME_3 {
 		nvme_path_get_ns;
 		nvme_path_get_queue_depth;
 		nvme_path_get_ana_state;
+		nvme_path_get_numa_nodes;
 		nvme_random_uuid;
 		nvme_read_config;
 		nvme_read_hostid;
diff --git a/libnvme/src/nvme/accessors.c b/libnvme/src/nvme/accessors.c
index 8b095ed4d..a98f26234 100644
--- a/libnvme/src/nvme/accessors.c
+++ b/libnvme/src/nvme/accessors.c
@@ -52,19 +52,6 @@ __public const char *nvme_path_get_sysfs_dir(const struct nvme_path *p)
 	return p->sysfs_dir;
 }
 
-__public void nvme_path_set_numa_nodes(
-		struct nvme_path *p,
-		const char *numa_nodes)
-{
-	free(p->numa_nodes);
-	p->numa_nodes = numa_nodes ? strdup(numa_nodes) : NULL;
-}
-
-__public const char *nvme_path_get_numa_nodes(const struct nvme_path *p)
-{
-	return p->numa_nodes;
-}
-
 __public void nvme_path_set_grpid(struct nvme_path *p, int grpid)
 {
 	p->grpid = grpid;
diff --git a/libnvme/src/nvme/accessors.h b/libnvme/src/nvme/accessors.h
index 3ede23cbc..f9323ad11 100644
--- a/libnvme/src/nvme/accessors.h
+++ b/libnvme/src/nvme/accessors.h
@@ -68,21 +68,6 @@ void nvme_path_set_sysfs_dir(struct nvme_path *p, const char *sysfs_dir);
  */
 const char *nvme_path_get_sysfs_dir(const struct nvme_path *p);
 
-/**
- * nvme_path_set_numa_nodes() - Set numa_nodes.
- * @p: The &struct nvme_path instance to update.
- * @numa_nodes: New string; a copy is stored. Pass NULL to clear.
- */
-void nvme_path_set_numa_nodes(struct nvme_path *p, const char *numa_nodes);
-
-/**
- * nvme_path_get_numa_nodes() - Get numa_nodes.
- * @p: The &struct nvme_path instance to query.
- *
- * Return: The value of the numa_nodes field, or NULL if not set.
- */
-const char *nvme_path_get_numa_nodes(const struct nvme_path *p);
-
 /**
  * nvme_path_set_grpid() - Set grpid.
  * @p: The &struct nvme_path instance to update.
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index 7631c4084..e115c4310 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -137,8 +137,8 @@ struct nvme_path { /*!generate-accessors*/
 
 	char *name;
 	char *sysfs_dir;
-	char *numa_nodes;
 	char *ana_state; //!accessors:none
+	char *numa_nodes; //!accessors:none
 	int grpid;
 	int queue_depth; //!accessors:none
 };
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index f087d7b03..93982dfd2 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -821,6 +821,21 @@ __public char *nvme_path_get_ana_state(nvme_path_t p)
 	return p->ana_state;
 }
 
+__public char *nvme_path_get_numa_nodes(nvme_path_t p)
+{
+	_cleanup_free_ char *numa_nodes = NULL;
+
+	numa_nodes = nvme_get_path_attr(p, "numa_nodes");
+	if (numa_nodes) {
+		if (!p->numa_nodes || strcmp(numa_nodes, p->numa_nodes)) {
+			free(p->numa_nodes);
+			p->numa_nodes = strdup(numa_nodes);
+		}
+	}
+
+	return p->numa_nodes;
+}
+
 void nvme_free_path(struct nvme_path *p)
 {
 	list_del_init(&p->entry);
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index ec0f4f2e6..1240f3023 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -687,6 +687,14 @@ int nvme_path_get_queue_depth(nvme_path_t p);
  */
 char *nvme_path_get_ana_state(nvme_path_t p);
 
+/**
+ * nvme_path_get_numa_nodes() - Numa nodes of an nvme_path_t object
+ * @p: &nvme_path_t object
+ *
+ * Return: Numa nodes of @p
+ */
+char *nvme_path_get_numa_nodes(nvme_path_t p);
+
 /**
  * nvme_path_get_ctrl() - Parent controller of an nvme_path_t object
  * @p:	&nvme_path_t object
-- 
2.53.0

[PATCHv2 3/9] libnvme: annotate nvme_subsystem::iopolicy with !accessors:none

[Nilay Shroff]

The default accessor generation creates getters that return cached
attribute values. However, for nvme_subsystem::iopolicy, a real-time
(non-cached) value is required.

This is particularly useful for tools such as nvme-top, which rely on
up-to-date information for displaying a real-time dashboard.

Annotate nvme_subsystem::iopolicy with "!accessors:none" to disable the
auto-generated accessor, and provide a custom implementation of
nvme_subsystem_get_iopolicy() that returns the current value.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/accessors.ld     |  2 --
 libnvme/src/libnvme.ld       |  1 +
 libnvme/src/nvme/accessors.c | 13 -------------
 libnvme/src/nvme/accessors.h | 17 -----------------
 libnvme/src/nvme/private.h   |  2 +-
 libnvme/src/nvme/tree.c      | 15 +++++++++++++++
 libnvme/src/nvme/tree.h      |  8 ++++++++
 7 files changed, 25 insertions(+), 33 deletions(-)

diff --git a/libnvme/src/accessors.ld b/libnvme/src/accessors.ld
index 433767191..56348a7e5 100644
--- a/libnvme/src/accessors.ld
+++ b/libnvme/src/accessors.ld
@@ -77,8 +77,6 @@ LIBNVME_ACCESSORS_3 {
 		nvme_subsystem_get_subsystype;
 		nvme_subsystem_get_application;
 		nvme_subsystem_set_application;
-		nvme_subsystem_get_iopolicy;
-		nvme_subsystem_set_iopolicy;
 		nvme_host_get_hostnqn;
 		nvme_host_get_hostid;
 		nvme_host_get_dhchap_host_key;
diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index f2972f455..1ff451d3d 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -180,6 +180,7 @@ LIBNVME_3 {
 		nvme_subsystem_first_ctrl;
 		nvme_subsystem_first_ns;
 		nvme_subsystem_get_host;
+		nvme_subsystem_get_iopolicy;
 		nvme_subsystem_lookup_namespace;
 		nvme_subsystem_next_ctrl;
 		nvme_subsystem_next_ns;
diff --git a/libnvme/src/nvme/accessors.c b/libnvme/src/nvme/accessors.c
index a98f26234..55fd11320 100644
--- a/libnvme/src/nvme/accessors.c
+++ b/libnvme/src/nvme/accessors.c
@@ -404,19 +404,6 @@ __public const char *nvme_subsystem_get_application(
 	return p->application;
 }
 
-__public void nvme_subsystem_set_iopolicy(
-		struct nvme_subsystem *p,
-		const char *iopolicy)
-{
-	free(p->iopolicy);
-	p->iopolicy = iopolicy ? strdup(iopolicy) : NULL;
-}
-
-__public const char *nvme_subsystem_get_iopolicy(const struct nvme_subsystem *p)
-{
-	return p->iopolicy;
-}
-
 /****************************************************************************
  * Accessors for: struct nvme_host
  ****************************************************************************/
diff --git a/libnvme/src/nvme/accessors.h b/libnvme/src/nvme/accessors.h
index f9323ad11..9ea96a634 100644
--- a/libnvme/src/nvme/accessors.h
+++ b/libnvme/src/nvme/accessors.h
@@ -575,23 +575,6 @@ void nvme_subsystem_set_application(
  */
 const char *nvme_subsystem_get_application(const struct nvme_subsystem *p);
 
-/**
- * nvme_subsystem_set_iopolicy() - Set iopolicy.
- * @p: The &struct nvme_subsystem instance to update.
- * @iopolicy: New string; a copy is stored. Pass NULL to clear.
- */
-void nvme_subsystem_set_iopolicy(
-		struct nvme_subsystem *p,
-		const char *iopolicy);
-
-/**
- * nvme_subsystem_get_iopolicy() - Get iopolicy.
- * @p: The &struct nvme_subsystem instance to query.
- *
- * Return: The value of the iopolicy field, or NULL if not set.
- */
-const char *nvme_subsystem_get_iopolicy(const struct nvme_subsystem *p);
-
 /****************************************************************************
  * Accessors for: struct nvme_host
  ****************************************************************************/
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index e115c4310..0b8dec81e 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -230,7 +230,7 @@ struct nvme_subsystem { /*!generate-accessors*/
 	char *firmware; /*!accessors:readonly*/
 	char *subsystype; /*!accessors:readonly*/
 	char *application;
-	char *iopolicy;
+	char *iopolicy; //!accessors:none
 };
 
 struct nvme_host { /*!generate-accessors*/
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index 93982dfd2..ac3779dca 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -445,6 +445,21 @@ __public nvme_host_t nvme_subsystem_get_host(nvme_subsystem_t s)
 	return s->h;
 }
 
+__public char *nvme_subsystem_get_iopolicy(nvme_subsystem_t s)
+{
+	_cleanup_free_ char *iopolicy = NULL;
+
+	iopolicy = nvme_get_subsys_attr(s, "iopolicy");
+	if (iopolicy) {
+		if (!s->iopolicy || strcmp(iopolicy, s->iopolicy)) {
+			free(s->iopolicy);
+			s->iopolicy = strdup(iopolicy);
+		}
+	}
+
+	return s->iopolicy;
+}
+
 __public nvme_ns_t nvme_subsystem_first_ns(nvme_subsystem_t s)
 {
 	return list_top(&s->namespaces, struct nvme_ns, entry);
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index 1240f3023..39d715508 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -212,6 +212,14 @@ void nvme_free_subsystem(struct nvme_subsystem *s);
  */
 nvme_host_t nvme_subsystem_get_host(nvme_subsystem_t s);
 
+/**
+ * nvme_subsystem_get_iopolicy() - Get subsystem iopolicy name
+ * @s:	subsystem
+ *
+ * Return: The iopolicy configured in subsystem @s
+ */
+char *nvme_subsystem_get_iopolicy(nvme_subsystem_t s);
+
 /**
  * nvme_ctrl_first_ns() - Start namespace iterator
  * @c:	Controller instance
-- 
2.53.0

[PATCHv2 4/9] libnvme: add support for retrieving per-path gendisk I/O statistics

[Nilay Shroff]

Gendisk I/O statistics provide useful insight into disk activity,
including read/write/discard/flush operations, as well as information
about in-flight I/Os and I/O timing.

Parsing these statistics allows users to determine the number of I/Os
processed, time spent servicing I/O, number of sectors accessed, and
the count of in-flight requests.

Add support for retrieving per-path gendisk I/O statistics. Also add
support for computing deltas of these statistics between samples, such
as I/O ticks, number of sectors, and number of serviced I/Os.

These metrics can be used by tools such as nvme-top to display
real-time disk activity. Per-path metrics are particularly useful when
NVMe native multipath is enabled.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/libnvme.ld     |  12 ++
 libnvme/src/nvme/private.h |  29 ++++
 libnvme/src/nvme/tree.c    | 268 +++++++++++++++++++++++++++++++++++++
 libnvme/src/nvme/tree.h    |  93 +++++++++++++
 4 files changed, 402 insertions(+)

diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index 1ff451d3d..53b5f90e5 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -144,6 +144,18 @@ LIBNVME_3 {
 		nvme_path_get_queue_depth;
 		nvme_path_get_ana_state;
 		nvme_path_get_numa_nodes;
+		nvme_path_get_stat;
+		nvme_path_get_read_ios;
+		nvme_path_get_write_ios;
+		nvme_path_get_inflights;
+		nvme_path_get_stat_interval;
+		nvme_path_get_io_ticks;
+		nvme_path_get_read_ticks;
+		nvme_path_get_write_ticks;
+		nvme_path_get_read_sectors;
+		nvme_path_get_write_sectors;
+		nvme_path_reset_stat;
+		nvme_path_update_stat;
 		nvme_random_uuid;
 		nvme_read_config;
 		nvme_read_hostid;
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index 0b8dec81e..2e8e792b9 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -20,6 +20,7 @@
 
 #include <nvme/fabrics.h>
 #include <nvme/mi.h>
+#include <nvme/tree.h>
 
 const char *nvme_subsys_sysfs_dir(void);
 const char *nvme_ctrl_sysfs_dir(void);
@@ -128,10 +129,38 @@ struct nvme_transport_handle {
 	struct nvme_log *log;
 };
 
+enum stat_group {
+	READ = 0,
+	WRITE,
+	DISCARD,
+	FLUSH,
+
+	NR_STAT_GROUPS
+};
+
+struct nvme_stat {
+	struct {
+		unsigned long ios;
+		unsigned long merges;
+		unsigned long long sectors;
+		unsigned int ticks;	/* in milliseconds */
+	} group[NR_STAT_GROUPS];
+
+	unsigned int inflights;
+	unsigned int io_ticks;		/* in milliseconds */
+	unsigned int tot_ticks;		/* in milliseconds */
+
+	double ts_ms;			/* timestamp when the stat is updated */
+};
+
 struct nvme_path { /*!generate-accessors*/
 	struct list_node entry;
 	struct list_node nentry;
 
+	struct nvme_stat stat[2];	/* gendisk I/O stat */
+	unsigned int curr_idx;		/* current index into the stat[] */
+	bool diffstat;
+
 	struct nvme_ctrl *c;
 	struct nvme_ns *n;
 
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index ac3779dca..b5f8c219d 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -16,6 +16,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <time.h>
 
 #include <arpa/inet.h>
 #include <netdb.h>
@@ -851,6 +852,273 @@ __public char *nvme_path_get_numa_nodes(nvme_path_t p)
 	return p->numa_nodes;
 }
 
+static nvme_stat_t nvme_path_get_stat(nvme_path_t p, unsigned int idx)
+{
+	if (idx > 1)
+		return NULL;
+
+	return &p->stat[idx];
+}
+
+__public void nvme_path_reset_stat(nvme_path_t p)
+{
+	nvme_stat_t stat = &p->stat[0];
+
+	memset(stat, 0, 2 * sizeof(struct nvme_stat));
+}
+
+static int nvme_update_stat(const char *sysfs_stat_path, nvme_stat_t stat)
+{
+	int n;
+	struct timespec ts;
+	unsigned long rd_ios, rd_merges, wr_ios, wr_merges;
+	unsigned long dc_ios, dc_merges, fl_ios;
+	unsigned long long rd_sectors, wr_sectors, dc_sectors;
+	unsigned int rd_ticks, wr_ticks, dc_ticks, fl_ticks;
+	unsigned int io_ticks, tot_ticks, inflights;
+
+	memset(stat, 0, sizeof(struct nvme_stat));
+
+	n = sscanf(sysfs_stat_path,
+		"%lu %lu %llu %u %lu %lu %llu %u %u %u %u %lu %lu %llu %u %lu %u",
+		&rd_ios, &rd_merges, &rd_sectors, &rd_ticks,
+		&wr_ios, &wr_merges, &wr_sectors, &wr_ticks,
+		&inflights, &io_ticks, &tot_ticks,
+		&dc_ios, &dc_merges, &dc_sectors, &dc_ticks,
+		&fl_ios, &fl_ticks);
+
+	if (n < 17)
+		return -EINVAL;
+
+	/* update read stat */
+	stat->group[READ].ios = rd_ios;
+	stat->group[READ].merges = rd_merges;
+	stat->group[READ].sectors = rd_sectors;
+	stat->group[READ].ticks = rd_ticks;
+
+	/* update write stat */
+	stat->group[WRITE].ios = wr_ios;
+	stat->group[WRITE].merges = wr_merges;
+	stat->group[WRITE].sectors = wr_sectors;
+	stat->group[WRITE].ticks = wr_ticks;
+
+	/* update inflight counters and ticks */
+	stat->inflights = inflights;
+	stat->io_ticks = io_ticks;
+	stat->tot_ticks = tot_ticks;
+
+	/* update discard stat */
+	stat->group[DISCARD].ios = dc_ios;
+	stat->group[DISCARD].merges = dc_merges;
+	stat->group[DISCARD].sectors = dc_sectors;
+	stat->group[DISCARD].ticks = dc_ticks;
+
+	/* update flush stat */
+	stat->group[FLUSH].ios = fl_ios;
+	stat->group[FLUSH].ticks = fl_ticks;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	stat->ts_ms = ts.tv_sec * 1000 + (double)ts.tv_nsec / 1e6;
+
+	return 0;
+}
+
+__public int nvme_path_update_stat(nvme_path_t p, bool diffstat)
+{
+	_cleanup_free_ char *sysfs_stat_path = NULL;
+	nvme_stat_t stat;
+
+	p->diffstat = diffstat;
+	p->curr_idx ^= 1;
+	stat = nvme_path_get_stat(p, p->curr_idx);
+	if (!stat)
+		return -EINVAL;
+
+	sysfs_stat_path = nvme_get_path_attr(p, "stat");
+	if (!sysfs_stat_path)
+		return -EINVAL;
+
+	return nvme_update_stat(sysfs_stat_path, stat);
+}
+
+static int nvme_stat_get_inflights(nvme_stat_t stat)
+{
+	return stat->inflights;
+}
+
+__public unsigned int nvme_path_get_inflights(nvme_path_t p)
+{
+	nvme_stat_t curr;
+
+	curr = nvme_path_get_stat(p, p->curr_idx);
+	if (!curr)
+		return 0;
+
+	return nvme_stat_get_inflights(curr);
+}
+
+static int nvme_stat_get_io_ticks(nvme_stat_t curr, nvme_stat_t prev,
+		bool diffstat)
+{
+	unsigned int delta = 0;
+
+	if (!diffstat)
+		return curr->io_ticks;
+
+	if (curr->io_ticks > prev->io_ticks)
+		delta = curr->io_ticks - prev->io_ticks;
+
+	return delta;
+}
+
+__public unsigned int nvme_path_get_io_ticks(nvme_path_t p)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_path_get_stat(p, p->curr_idx);
+	prev = nvme_path_get_stat(p, !p->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_io_ticks(curr, prev, p->diffstat);
+}
+
+static unsigned int nvme_stat_get_ticks(nvme_stat_t curr,
+		nvme_stat_t prev, enum stat_group grp, bool diffstat)
+{
+	unsigned int delta = 0;
+
+	if (!diffstat)
+		return curr->group[grp].ticks;
+
+	if (curr->group[grp].ticks > prev->group[grp].ticks)
+		delta = curr->group[grp].ticks - prev->group[grp].ticks;
+
+	return delta;
+}
+
+static unsigned int __nvme_path_get_ticks(nvme_path_t p, enum stat_group grp)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_path_get_stat(p, p->curr_idx);
+	prev = nvme_path_get_stat(p, !p->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_ticks(curr, prev, grp, p->diffstat);
+}
+
+__public unsigned int nvme_path_get_read_ticks(nvme_path_t p)
+{
+	return __nvme_path_get_ticks(p, READ);
+}
+
+__public unsigned int nvme_path_get_write_ticks(nvme_path_t p)
+{
+	return __nvme_path_get_ticks(p, WRITE);
+}
+
+static double nvme_stat_get_interval(nvme_stat_t curr, nvme_stat_t prev)
+{
+	double delta = 0.0;
+
+	if (prev->ts_ms && curr->ts_ms > prev->ts_ms)
+		delta = curr->ts_ms - prev->ts_ms;
+
+	return delta;
+}
+
+__public double nvme_path_get_stat_interval(nvme_path_t p)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_path_get_stat(p, p->curr_idx);
+	prev = nvme_path_get_stat(p, !p->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_interval(curr, prev);
+}
+
+static unsigned long nvme_stat_get_ios(nvme_stat_t curr, nvme_stat_t prev,
+		enum stat_group grp, bool diffstat)
+{
+	unsigned long ios = 0;
+
+	if (!diffstat)
+		return curr->group[grp].ios;
+
+	if (curr->group[grp].ios > prev->group[grp].ios)
+		ios = curr->group[grp].ios - prev->group[grp].ios;
+
+	return ios;
+}
+
+static unsigned long __nvme_path_get_ios(nvme_path_t p, enum stat_group grp)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_path_get_stat(p, p->curr_idx);
+	prev = nvme_path_get_stat(p, !p->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_ios(curr, prev, grp, p->diffstat);
+}
+
+__public unsigned long nvme_path_get_read_ios(nvme_path_t p)
+{
+	return __nvme_path_get_ios(p, READ);
+}
+
+__public unsigned long nvme_path_get_write_ios(nvme_path_t p)
+{
+	return __nvme_path_get_ios(p, WRITE);
+}
+
+static unsigned long long nvme_stat_get_sectors(nvme_stat_t curr,
+		nvme_stat_t prev, enum stat_group grp, bool diffstat)
+{
+	unsigned long long sec = 0;
+
+	if (!diffstat)
+		return curr->group[grp].sectors;
+
+	if (curr->group[grp].sectors > prev->group[grp].sectors)
+		sec = curr->group[grp].sectors - prev->group[grp].sectors;
+
+	return sec;
+}
+
+static unsigned long long __nvme_path_get_sectors(nvme_path_t p,
+		enum stat_group grp)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_path_get_stat(p, p->curr_idx);
+	prev = nvme_path_get_stat(p, !p->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_sectors(curr, prev, grp, p->diffstat);
+}
+
+__public unsigned long long nvme_path_get_read_sectors(nvme_path_t p)
+{
+	return __nvme_path_get_sectors(p, READ);
+}
+
+__public unsigned long long nvme_path_get_write_sectors(nvme_path_t p)
+{
+	return __nvme_path_get_sectors(p, WRITE);
+}
+
 void nvme_free_path(struct nvme_path *p)
 {
 	list_del_init(&p->entry);
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index 39d715508..8c42edd71 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -23,6 +23,7 @@
 typedef struct nvme_ns *nvme_ns_t;
 typedef struct nvme_ns_head *nvme_ns_head_t;
 typedef struct nvme_path *nvme_path_t;
+typedef struct nvme_stat *nvme_stat_t;
 typedef struct nvme_ctrl *nvme_ctrl_t;
 typedef struct nvme_subsystem *nvme_subsystem_t;
 typedef struct nvme_host *nvme_host_t;
@@ -719,6 +720,98 @@ nvme_ctrl_t nvme_path_get_ctrl(nvme_path_t p);
  */
 nvme_ns_t nvme_path_get_ns(nvme_path_t p);
 
+/**
+ * nvme_path_reset_stat() - Resets namespace path nvme stat
+ * @p:	&nvme_path_t object
+ */
+void nvme_path_reset_stat(nvme_path_t p);
+
+/**
+ * nvme_path_update_stat() - Update stat of an nvme_path_t object
+ * @p:		&nvme_path_t object
+ * @diffstat:	If set to true then getters return the diff stat otherwise
+ *		return the current absolute stat
+ *
+ * Return:	0 on success, -1 on error
+ */
+int nvme_path_update_stat(nvme_path_t p, bool diffstat);
+
+/**
+ * nvme_path_get_read_ios() - Calculate and return read IOs
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Num of read IOs processed between two stat samples
+ */
+unsigned long nvme_path_get_read_ios(nvme_path_t p);
+
+/**
+ * nvme_path_get_write_ios() - Get write I/Os
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Num of write I/Os processed between two stat samples
+ */
+unsigned long nvme_path_get_write_ios(nvme_path_t p);
+
+/**
+ * nvme_path_get_read_ticks() - Get read I/O ticks
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Time, in milliseconds, sepnt processing read I/O requests
+ *		between two stat samples
+ */
+unsigned int nvme_path_get_read_ticks(nvme_path_t p);
+
+/**
+ * nvme_path_get_read_sectors() - Get read I/O sectors
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Number of sectors read from the device between two stat samples
+ */
+unsigned long long nvme_path_get_read_sectors(nvme_path_t p);
+
+/**
+ * nvme_path_get_write_sectors() - Get write I/O sectors
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Num of sectors written to the device between two stat samples
+ */
+unsigned long long nvme_path_get_write_sectors(nvme_path_t p);
+
+/**
+ * nvme_path_get_write_ticks() - Get write I/O ticks
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Time, in milliseconds, sepnt processing write I/O requests
+ *		between two stat samples
+ */
+unsigned int nvme_path_get_write_ticks(nvme_path_t p);
+
+/**
+ * nvme_path_get_stat_interval() - Get interval between two stat samples
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Interval, in milliseconds between collection of two consecutive
+ *		stat samples
+ */
+double nvme_path_get_stat_interval(nvme_path_t p);
+
+/**
+ * nvme_path_get_io_ticks() - Get I/O ticks
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Time consumed, in milliseconds, processing I/O requests between
+ *		two stat samples
+ */
+unsigned int nvme_path_get_io_ticks(nvme_path_t p);
+
+/**
+ * nvme_path_get_inflights() - Inflight IOs for nvme_path_t object
+ * @p:		&nvme_path_t object
+ *
+ * Return:	Inflight number of IOs
+ */
+unsigned int nvme_path_get_inflights(nvme_path_t p);
+
 /**
  * nvme_ctrl_get_transport_handle() - Get associated transport handle
  * @c:	Controller instance
-- 
2.53.0

[PATCHv2 5/9] libnvme: add support for retrieving namespace gendisk I/O statistics

[Nilay Shroff]

Gendisk I/O statistics provide useful insight into disk activity,
including read/write/discard/flush operations, as well as information
about in-flight I/Os and I/O timing.

Parsing these statistics allows users to determine the number of I/Os
processed, time spent servicing I/O, number of sectors accessed, and
the count of in-flight requests.

Add support for retrieving namespace gendisk I/O statistics. Also add
support for computing deltas of these statistics between samples, such
as I/O ticks, number of sectors, and number of serviced I/Os.

These metrics can be used by tools such as nvme-top to display real-time
disk activity.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/libnvme.ld     |  11 +++
 libnvme/src/nvme/private.h |   5 ++
 libnvme/src/nvme/tree.c    | 140 +++++++++++++++++++++++++++++++++++++
 libnvme/src/nvme/tree.h    |  94 +++++++++++++++++++++++++
 4 files changed, 250 insertions(+)

diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index 53b5f90e5..c32198324 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -131,6 +131,17 @@ LIBNVME_3 {
 		nvme_ns_get_serial;
 		nvme_ns_get_subsystem;
 		nvme_ns_get_uuid;
+		nvme_ns_reset_stat;
+		nvme_ns_update_stat;
+		nvme_ns_get_stat_interval;
+		nvme_ns_get_read_ios;
+		nvme_ns_get_write_ios;
+		nvme_ns_get_read_ticks;
+		nvme_ns_get_write_ticks;
+		nvme_ns_get_read_sectors;
+		nvme_ns_get_write_sectors;
+		nvme_ns_get_inflights;
+		nvme_ns_get_io_ticks;
 		nvme_ns_identify;
 		nvme_ns_read;
 		nvme_ns_verify;
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index 2e8e792b9..f09c0d83f 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -187,6 +187,11 @@ struct nvme_ns { /*!generate-accessors*/
 	struct nvme_ns_head *head;
 
 	struct nvme_global_ctx *ctx;
+
+	struct nvme_stat stat[2];	/* gendisk I/O stat */
+	unsigned int curr_idx;		/* current index into the stat[] */
+	bool diffstat;
+
 	struct nvme_transport_handle *hdl;
 	__u32 nsid;
 	char *name;
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index b5f8c219d..2949b5cf8 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -867,6 +867,21 @@ __public void nvme_path_reset_stat(nvme_path_t p)
 	memset(stat, 0, 2 * sizeof(struct nvme_stat));
 }
 
+static nvme_stat_t nvme_ns_get_stat(nvme_ns_t n, unsigned int idx)
+{
+	if (idx > 1)
+		return NULL;
+
+	return &n->stat[idx];
+}
+
+__public void nvme_ns_reset_stat(nvme_ns_t n)
+{
+	nvme_stat_t stat = &n->stat[0];
+
+	memset(stat, 0, 2 * sizeof(struct nvme_stat));
+}
+
 static int nvme_update_stat(const char *sysfs_stat_path, nvme_stat_t stat)
 {
 	int n;
@@ -941,6 +956,24 @@ __public int nvme_path_update_stat(nvme_path_t p, bool diffstat)
 	return nvme_update_stat(sysfs_stat_path, stat);
 }
 
+__public int nvme_ns_update_stat(nvme_ns_t n, bool diffstat)
+{
+	_cleanup_free_ char *sysfs_stat_path = NULL;
+	nvme_stat_t stat;
+
+	n->diffstat = diffstat;
+	n->curr_idx ^= 1;
+	stat = nvme_ns_get_stat(n, n->curr_idx);
+	if (!stat)
+		return -EINVAL;
+
+	sysfs_stat_path = nvme_get_ns_attr(n, "stat");
+	if (!sysfs_stat_path)
+		return -EINVAL;
+
+	return nvme_update_stat(sysfs_stat_path, stat);
+}
+
 static int nvme_stat_get_inflights(nvme_stat_t stat)
 {
 	return stat->inflights;
@@ -957,6 +990,17 @@ __public unsigned int nvme_path_get_inflights(nvme_path_t p)
 	return nvme_stat_get_inflights(curr);
 }
 
+__public unsigned int nvme_ns_get_inflights(nvme_ns_t n)
+{
+	nvme_stat_t curr;
+
+	curr = nvme_ns_get_stat(n, n->curr_idx);
+	if (!curr)
+		return 0;
+
+	return nvme_stat_get_inflights(curr);
+}
+
 static int nvme_stat_get_io_ticks(nvme_stat_t curr, nvme_stat_t prev,
 		bool diffstat)
 {
@@ -984,6 +1028,19 @@ __public unsigned int nvme_path_get_io_ticks(nvme_path_t p)
 	return nvme_stat_get_io_ticks(curr, prev, p->diffstat);
 }
 
+__public unsigned int nvme_ns_get_io_ticks(nvme_ns_t n)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_ns_get_stat(n, n->curr_idx);
+	prev = nvme_ns_get_stat(n, !n->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_io_ticks(curr, prev, n->diffstat);
+}
+
 static unsigned int nvme_stat_get_ticks(nvme_stat_t curr,
 		nvme_stat_t prev, enum stat_group grp, bool diffstat)
 {
@@ -1021,6 +1078,29 @@ __public unsigned int nvme_path_get_write_ticks(nvme_path_t p)
 	return __nvme_path_get_ticks(p, WRITE);
 }
 
+static unsigned int __nvme_ns_get_ticks(nvme_ns_t n, enum stat_group grp)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_ns_get_stat(n, n->curr_idx);
+	prev = nvme_ns_get_stat(n, !n->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_ticks(curr, prev, grp, n->diffstat);
+}
+
+__public unsigned int nvme_ns_get_read_ticks(nvme_ns_t n)
+{
+	return __nvme_ns_get_ticks(n, READ);
+}
+
+__public unsigned int nvme_ns_get_write_ticks(nvme_ns_t n)
+{
+	return __nvme_ns_get_ticks(n, WRITE);
+}
+
 static double nvme_stat_get_interval(nvme_stat_t curr, nvme_stat_t prev)
 {
 	double delta = 0.0;
@@ -1044,6 +1124,19 @@ __public double nvme_path_get_stat_interval(nvme_path_t p)
 	return nvme_stat_get_interval(curr, prev);
 }
 
+__public double nvme_ns_get_stat_interval(nvme_ns_t n)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_ns_get_stat(n, n->curr_idx);
+	prev = nvme_ns_get_stat(n, !n->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_interval(curr, prev);
+}
+
 static unsigned long nvme_stat_get_ios(nvme_stat_t curr, nvme_stat_t prev,
 		enum stat_group grp, bool diffstat)
 {
@@ -1081,6 +1174,29 @@ __public unsigned long nvme_path_get_write_ios(nvme_path_t p)
 	return __nvme_path_get_ios(p, WRITE);
 }
 
+static unsigned long __nvme_ns_get_ios(nvme_ns_t n, enum stat_group grp)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_ns_get_stat(n, n->curr_idx);
+	prev = nvme_ns_get_stat(n, !n->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_ios(curr, prev, grp, n->diffstat);
+}
+
+__public unsigned long nvme_ns_get_read_ios(nvme_ns_t n)
+{
+	return __nvme_ns_get_ios(n, READ);
+}
+
+__public unsigned long nvme_ns_get_write_ios(nvme_ns_t n)
+{
+	return __nvme_ns_get_ios(n, WRITE);
+}
+
 static unsigned long long nvme_stat_get_sectors(nvme_stat_t curr,
 		nvme_stat_t prev, enum stat_group grp, bool diffstat)
 {
@@ -1119,6 +1235,30 @@ __public unsigned long long nvme_path_get_write_sectors(nvme_path_t p)
 	return __nvme_path_get_sectors(p, WRITE);
 }
 
+static unsigned long long __nvme_ns_get_sectors(nvme_ns_t n,
+		enum stat_group grp)
+{
+	nvme_stat_t curr, prev;
+
+	curr = nvme_ns_get_stat(n, n->curr_idx);
+	prev = nvme_ns_get_stat(n, !n->curr_idx);
+
+	if (!curr || !prev)
+		return 0;
+
+	return nvme_stat_get_sectors(curr, prev, grp, n->diffstat);
+}
+
+__public unsigned long long nvme_ns_get_read_sectors(nvme_ns_t n)
+{
+	return __nvme_ns_get_sectors(n, READ);
+}
+
+__public unsigned long long nvme_ns_get_write_sectors(nvme_ns_t n)
+{
+	return __nvme_ns_get_sectors(n, WRITE);
+}
+
 void nvme_free_path(struct nvme_path *p)
 {
 	list_del_init(&p->entry);
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index 8c42edd71..01f7fda86 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -867,6 +867,100 @@ nvme_subsystem_t nvme_ctrl_get_subsystem(nvme_ctrl_t c);
  */
 const char *nvme_ns_head_get_sysfs_dir(nvme_ns_head_t head);
 
+/**
+ * nvme_ns_update_stat() - update the nvme namespace stat
+ * @n:		&nvme_ns_t object
+ * @diffstat:	If set to true then getters return the diff stat otherwise
+ *		return the current absolute stat
+ *
+ * Returns:	0 on success, -1 on error
+ */
+int nvme_ns_update_stat(nvme_ns_t n, bool diffstat);
+
+/**
+ * nvme_ns_reset_stat() - Resets nvme namespace stat
+ * @n:	&nvme_ns_t object
+ *
+ */
+void nvme_ns_reset_stat(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_inflights() - Inflight IOs for nvme_ns_t object
+ *
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Inflight number of IOs
+ */
+unsigned int nvme_ns_get_inflights(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_io_ticks() - Get IO ticks
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Time consumed, in milliseconds, processing I/O requests between
+ *		two stat samples
+ */
+unsigned int nvme_ns_get_io_ticks(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_read_ticks() - Get read I/O ticks
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Time, in milliseconds, sepnt processing read I/O requests
+ *		between two stat samples
+ */
+unsigned int nvme_ns_get_read_ticks(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_write_ticks() - Get write I/O ticks
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Time, in milliseconds, sepnt processing write I/O requests
+ *		between two stat samples
+ */
+unsigned int nvme_ns_get_write_ticks(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_stat_interval() - Get interval between two stat samples
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Interval, in milliseconds, between collection of two consecutive
+ *		stat samples
+ */
+double nvme_ns_get_stat_interval(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_read_ios() - Get num of read I/Os
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Num of read IOs processed between two stat samples
+ */
+unsigned long nvme_ns_get_read_ios(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_write_ios() - Get num of write I/Os
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Num of write IOs processed between two consecutive stat samples
+ */
+unsigned long nvme_ns_get_write_ios(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_read_sectors() - Get num of read sectors
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Num of sectors read from the device between two stat samples
+ */
+unsigned long long nvme_ns_get_read_sectors(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_write_sectors() - Get num of write sectors
+ * @n:		&nvme_ns_t object
+ *
+ * Return:	Num of sectors written to the device between two stat samples
+ */
+unsigned long long nvme_ns_get_write_sectors(nvme_ns_t n);
+
 /**
  * nvme_ctrl_get_config() - Fabrics configuration of a controller
  * @c:	Controller instance
-- 
2.53.0

[PATCHv2 6/9] libnvme: add support for per-path diagnostic counters

[Nilay Shroff]

Add support for retrieving per-path diagnostic counters such as
command_retry_count, command_error_count, and multipath_failover_count.
These counters improve visibility into NVMe native multipath behavior
and can be useful for tools such as nvme-top to display real-time
statistics.

Unlike other sysfs attributes, these counters can change dynamically.
Annotate them with "!accessors:none" and provide custom implementations
to always retrieve the latest (non-cached) values.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/libnvme.ld     |  3 +++
 libnvme/src/nvme/private.h |  3 +++
 libnvme/src/nvme/tree.c    | 33 +++++++++++++++++++++++++++++++++
 libnvme/src/nvme/tree.h    | 27 +++++++++++++++++++++++++++
 4 files changed, 66 insertions(+)

diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index c32198324..a10629dce 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -167,6 +167,9 @@ LIBNVME_3 {
 		nvme_path_get_write_sectors;
 		nvme_path_reset_stat;
 		nvme_path_update_stat;
+		nvme_path_get_command_retry_count;
+		nvme_path_get_command_error_count;
+		nvme_path_get_multipath_failover_count;
 		nvme_random_uuid;
 		nvme_read_config;
 		nvme_read_hostid;
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index f09c0d83f..3d7dfb3c4 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -170,6 +170,9 @@ struct nvme_path { /*!generate-accessors*/
 	char *numa_nodes; //!accessors:none
 	int grpid;
 	int queue_depth; //!accessors:none
+	long multipath_failover_count; //!accessors:none
+	long command_retry_count; //!accessors:none
+	long command_error_count; //!accessors:none
 };
 
 struct nvme_ns_head {
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index 2949b5cf8..844e18b5c 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -852,6 +852,39 @@ __public char *nvme_path_get_numa_nodes(nvme_path_t p)
 	return p->numa_nodes;
 }
 
+__public long nvme_path_get_multipath_failover_count(nvme_path_t p)
+{
+	_cleanup_free_ char *failover_count = NULL;
+
+	failover_count = nvme_get_path_attr(p, "multipath_failover_count");
+	if (failover_count)
+		sscanf(failover_count, "%ld", &p->multipath_failover_count);
+
+	return p->multipath_failover_count;
+}
+
+__public long nvme_path_get_command_retry_count(nvme_path_t p)
+{
+	_cleanup_free_ char *retry_count = NULL;
+
+	retry_count = nvme_get_path_attr(p, "command_retry_count");
+	if (retry_count)
+		sscanf(retry_count, "%ld", &p->command_retry_count);
+
+	return p->command_retry_count;
+}
+
+__public long nvme_path_get_command_error_count(nvme_path_t p)
+{
+	_cleanup_free_ char *error_count = NULL;
+
+	error_count = nvme_get_path_attr(p, "command_error_count");
+	if (error_count)
+		sscanf(error_count, "%ld", &p->command_error_count);
+
+	return p->command_error_count;
+}
+
 static nvme_stat_t nvme_path_get_stat(nvme_path_t p, unsigned int idx)
 {
 	if (idx > 1)
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index 01f7fda86..4b5d3fd70 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -704,6 +704,33 @@ char *nvme_path_get_ana_state(nvme_path_t p);
  */
 char *nvme_path_get_numa_nodes(nvme_path_t p);
 
+/**
+ * nvme_path_get_multipath_failover_count() - Get multipath failover count
+ * @p: &nvme_path_t object
+ *
+ * Return: Number of times I/Os have to be failed over to another active path
+ * from path @p maybe due to any transient error observed on path @p
+ */
+long nvme_path_get_multipath_failover_count(nvme_path_t p);
+
+/**
+ * nvme_path_get_command_retry_count() - Get command retry count
+ * @p: &nvme_path_t object
+ *
+ * Return: Number of times any command issued to the namespace represented by
+ * path @p has to be retried
+ */
+long nvme_path_get_command_retry_count(nvme_path_t p);
+
+/**
+ * nvme_path_get_command_error_count() - Get command error count
+ * @p: &nvme_path_t object
+ *
+ * Return: Number of times command issued to the namespace represented by path
+ * @p returns non-zero status or error
+ */
+long nvme_path_get_command_error_count(nvme_path_t p);
+
 /**
  * nvme_path_get_ctrl() - Parent controller of an nvme_path_t object
  * @p:	&nvme_path_t object
-- 
2.53.0

[PATCHv2 7/9] libnvme: add support for namespace diagnostic counters

[Nilay Shroff]

Add support for retrieving namespace diagnostic counters such as
command_retry_count and command_error_count. These counters improve
visibility and can be useful for tools such as nvme-top to display
real-time statistics.

Unlike other sysfs attributes, these counters can change dynamically.
Annotate them with "!accessors:none" and provide custom implementations
to always retrieve the latest (non-cached) values.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/libnvme.ld     |  2 ++
 libnvme/src/nvme/private.h |  3 +++
 libnvme/src/nvme/tree.c    | 22 ++++++++++++++++++++++
 libnvme/src/nvme/tree.h    | 17 +++++++++++++++++
 4 files changed, 44 insertions(+)

diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index a10629dce..aa24adf59 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -142,6 +142,8 @@ LIBNVME_3 {
 		nvme_ns_get_write_sectors;
 		nvme_ns_get_inflights;
 		nvme_ns_get_io_ticks;
+		nvme_ns_get_command_retry_count;
+		nvme_ns_get_command_error_count;
 		nvme_ns_identify;
 		nvme_ns_read;
 		nvme_ns_verify;
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index 3d7dfb3c4..b2ba1948a 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -211,6 +211,9 @@ struct nvme_ns { /*!generate-accessors*/
 	uint8_t nguid[16];
 	unsigned char uuid[NVME_UUID_LEN];
 	enum nvme_csi csi;
+
+	long command_retry_count; //!accessors:none
+	long command_error_count; //!accessors:none
 };
 
 struct nvme_ctrl { /*!generate-accessors*/
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index 844e18b5c..a8069072d 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -2592,6 +2592,28 @@ __public void nvme_ns_get_uuid(nvme_ns_t n, unsigned char out[NVME_UUID_LEN])
 	memcpy(out, n->uuid, NVME_UUID_LEN);
 }
 
+__public long nvme_ns_get_command_retry_count(nvme_ns_t n)
+{
+	_cleanup_free_ char *retry_count = NULL;
+
+	retry_count = nvme_get_ns_attr(n, "command_retry_count");
+	if (retry_count)
+		sscanf(retry_count, "%ld", &n->command_retry_count);
+
+	return n->command_retry_count;
+}
+
+__public long nvme_ns_get_command_error_count(nvme_ns_t n)
+{
+	_cleanup_free_ char *error_count = NULL;
+
+	error_count = nvme_get_ns_attr(n, "command_error_count");
+	if (error_count)
+		sscanf(error_count, "%ld", &n->command_error_count);
+
+	return n->command_error_count;
+}
+
 __public int nvme_ns_identify(nvme_ns_t n, struct nvme_id_ns *ns)
 {
 	struct nvme_transport_handle *hdl;
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index 4b5d3fd70..ea5dc09a5 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -529,6 +529,23 @@ const uint8_t *nvme_ns_get_nguid(nvme_ns_t n);
  */
 void nvme_ns_get_uuid(nvme_ns_t n, unsigned char out[NVME_UUID_LEN]);
 
+/**
+ * nvme_ns_get_command_retry_count() - Get command retry count
+ * @n: &nvme_ns_t object
+ *
+ * Return: Number of times any command issued to namespace @n has to be retried
+ */
+long nvme_ns_get_command_retry_count(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_command_error_count() - Get command error count
+ * @n: &nvme_ns_t object
+ *
+ * Return: Number of times command issued to namespace @n returns non-zero
+ * status or error
+ */
+long nvme_ns_get_command_error_count(nvme_ns_t n);
+
 /**
  * nvme_ns_get_generic_name() - Returns name of generic namespace chardev.
  * @n:	Namespace instance
-- 
2.53.0

[PATCHv2 8/9] libnvme: add support for nshead diagnostic counters

[Nilay Shroff]

Add support for retrieving nshead diagnostic counters such as requeue_
no_usable_path_count and fail_no_available_path_count.

The requeue_no_usable_path_count counter represents the number of I/Os
requeued to the namespace head when no usable path is available (for
example, due to transient link issues). The fail_no_available_path_count
counter represents the number of I/Os failed when no I/O path is
available (for example, when all paths are removed).

These counters improve visibility into NVMe native multipath behavior
and can be useful for tools such as nvme-top to display real-time
statistics.

Unlike other sysfs attributes, these counters can change dynamically.
Annotate them with "!accessors:none" and provide custom implementations
to always retrieve the latest (non-cached) values.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/libnvme.ld     |  2 ++
 libnvme/src/nvme/private.h |  2 ++
 libnvme/src/nvme/tree.c    | 22 ++++++++++++++++++++++
 libnvme/src/nvme/tree.h    | 17 +++++++++++++++++
 4 files changed, 43 insertions(+)

diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index aa24adf59..13bd3995c 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -144,6 +144,8 @@ LIBNVME_3 {
 		nvme_ns_get_io_ticks;
 		nvme_ns_get_command_retry_count;
 		nvme_ns_get_command_error_count;
+		nvme_ns_get_requeue_no_usable_path_count;
+		nvme_ns_get_fail_no_available_path_count;
 		nvme_ns_identify;
 		nvme_ns_read;
 		nvme_ns_verify;
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index b2ba1948a..ae0b8507e 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -214,6 +214,8 @@ struct nvme_ns { /*!generate-accessors*/
 
 	long command_retry_count; //!accessors:none
 	long command_error_count; //!accessors:none
+	long requeue_no_usable_path_count; //!accessors:none
+	long fail_no_available_path_count; //!accessors:none
 };
 
 struct nvme_ctrl { /*!generate-accessors*/
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index a8069072d..77aed7eee 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -2614,6 +2614,28 @@ __public long nvme_ns_get_command_error_count(nvme_ns_t n)
 	return n->command_error_count;
 }
 
+__public long nvme_ns_get_requeue_no_usable_path_count(nvme_ns_t n)
+{
+	_cleanup_free_ char *requeue_count = NULL;
+
+	requeue_count = nvme_get_ns_attr(n, "requeue_no_usable_path_count");
+	if (requeue_count)
+		sscanf(requeue_count, "%ld", &n->requeue_no_usable_path_count);
+
+	return n->requeue_no_usable_path_count;
+}
+
+__public long nvme_ns_get_fail_no_available_path_count(nvme_ns_t n)
+{
+	_cleanup_free_ char *fail_count = NULL;
+
+	fail_count = nvme_get_ns_attr(n, "fail_no_available_path_count");
+	if (fail_count)
+		sscanf(fail_count, "%ld", &n->fail_no_available_path_count);
+
+	return n->fail_no_available_path_count;
+}
+
 __public int nvme_ns_identify(nvme_ns_t n, struct nvme_id_ns *ns)
 {
 	struct nvme_transport_handle *hdl;
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index ea5dc09a5..e6a26efb1 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -546,6 +546,23 @@ long nvme_ns_get_command_retry_count(nvme_ns_t n);
  */
 long nvme_ns_get_command_error_count(nvme_ns_t n);
 
+/**
+ * nvme_ns_get_requeue_no_usable_path_count() - Get num of I/O requeue count
+ * @n: &nvme_ns_t object
+ *
+ * Return: Number of I/Os which are re-queued due to the unavalibility of
+ * any usable path (maybe path is currently experiencing transinet link failure)
+ */
+long nvme_ns_get_requeue_no_usable_path_count(nvme_ns_t n);
+
+/**
+ * nvme_ns_get_fail_no_available_path_count() - Get num of I/Os forced to fail
+ * @n: &nvme_ns_t object
+ *
+ * Return: Number of I/Os which are forced to fail due to no path available
+ */
+long nvme_ns_get_fail_no_available_path_count(nvme_ns_t n);
+
 /**
  * nvme_ns_get_generic_name() - Returns name of generic namespace chardev.
  * @n:	Namespace instance
-- 
2.53.0

[PATCHv2 9/9] libnvme: add support for ctrl diagnostic counters

[Nilay Shroff]

Add support for retrieving ctrl diagnostic counters such as command_
error_count, reset_count and reconnect_count. These counters improve
visibility and can be useful for tools such as nvme-top to display
real-time statistics.

Unlike other sysfs attributes, these counters can change dynamically.
Annotate them with "!accessors:none" and provide custom implementations
to always retrieve the latest (non-cached) values.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 libnvme/src/libnvme.ld     |  3 +++
 libnvme/src/nvme/private.h |  3 +++
 libnvme/src/nvme/tree.c    | 33 +++++++++++++++++++++++++++++++++
 libnvme/src/nvme/tree.h    | 25 +++++++++++++++++++++++++
 4 files changed, 64 insertions(+)

diff --git a/libnvme/src/libnvme.ld b/libnvme/src/libnvme.ld
index 13bd3995c..52611f38b 100644
--- a/libnvme/src/libnvme.ld
+++ b/libnvme/src/libnvme.ld
@@ -16,6 +16,9 @@ LIBNVME_3 {
 		nvme_ctrl_get_subsysnqn;
 		nvme_ctrl_get_subsystem;
 		nvme_ctrl_get_transport_handle;
+		nvme_ctrl_get_command_error_count;
+		nvme_ctrl_get_reset_count;
+		nvme_ctrl_get_reconnect_count;
 		nvme_ctrl_identify;
 		nvme_ctrl_match_config;
 		nvme_ctrl_next_ns;
diff --git a/libnvme/src/nvme/private.h b/libnvme/src/nvme/private.h
index ae0b8507e..2009ac3c0 100644
--- a/libnvme/src/nvme/private.h
+++ b/libnvme/src/nvme/private.h
@@ -255,6 +255,9 @@ struct nvme_ctrl { /*!generate-accessors*/
 	bool unique_discovery_ctrl;
 	bool discovered;
 	bool persistent;
+	long command_error_count; //!accessors:none
+	long reset_count; //!accessors:none
+	long reconnect_count; //!accessors:none
 	struct nvme_fabrics_config cfg;
 };
 
diff --git a/libnvme/src/nvme/tree.c b/libnvme/src/nvme/tree.c
index 77aed7eee..210952785 100644
--- a/libnvme/src/nvme/tree.c
+++ b/libnvme/src/nvme/tree.c
@@ -1414,6 +1414,39 @@ __public const char *nvme_ctrl_get_state(nvme_ctrl_t c)
 	return c->state;
 }
 
+__public long nvme_ctrl_get_command_error_count(nvme_ctrl_t c)
+{
+	_cleanup_free_ char *error_count = NULL;
+
+	error_count = nvme_get_ctrl_attr(c, "command_error_count");
+	if (error_count)
+		sscanf(error_count, "%ld", &c->command_error_count);
+
+	return c->command_error_count;
+}
+
+__public long nvme_ctrl_get_reset_count(nvme_ctrl_t c)
+{
+	_cleanup_free_ char *reset_count = NULL;
+
+	reset_count = nvme_get_ctrl_attr(c, "reset_count");
+	if (reset_count)
+		sscanf(reset_count, "%ld", &c->reset_count);
+
+	return c->reset_count;
+}
+
+__public long nvme_ctrl_get_reconnect_count(nvme_ctrl_t c)
+{
+	_cleanup_free_ char *reconnect_count = NULL;
+
+	reconnect_count = nvme_get_ctrl_attr(c, "reconnect_count");
+	if (reconnect_count)
+		sscanf(reconnect_count, "%ld", &c->reconnect_count);
+
+	return c->reconnect_count;
+}
+
 __public struct nvme_fabrics_config *nvme_ctrl_get_config(nvme_ctrl_t c)
 {
 	return &c->cfg;
diff --git a/libnvme/src/nvme/tree.h b/libnvme/src/nvme/tree.h
index e6a26efb1..3a86208ef 100644
--- a/libnvme/src/nvme/tree.h
+++ b/libnvme/src/nvme/tree.h
@@ -1030,6 +1030,31 @@ unsigned long long nvme_ns_get_write_sectors(nvme_ns_t n);
  */
 struct nvme_fabrics_config *nvme_ctrl_get_config(nvme_ctrl_t c);
 
+/**
+ * nvme_ctrl_get_command_error_count() - Get admin command error count
+ * @c: Controller instance
+ *
+ * Return: Number of times admin command issued to controller @c failed or
+ * returned error status
+ */
+long nvme_ctrl_get_command_error_count(nvme_ctrl_t c);
+
+/**
+ * nvme_ctrl_get_reset_count() - Get controller reset count
+ * @c: Controller instance
+ *
+ * Return: Number of timer controller @c is reset
+ */
+long nvme_ctrl_get_reset_count(nvme_ctrl_t c);
+
+/**
+ * nvme_ctrl_get_reconnect_count() - Get controller reconnect count
+ * @c: Controller instance
+ *
+ * Return: Number of times controller has to reconnect to the target
+ */
+long nvme_ctrl_get_reconnect_count(nvme_ctrl_t c);
+
 /**
  * nvme_ctrl_identify() - Issues an 'identify controller' command
  * @c:	Controller instance
-- 
2.53.0