[ndctl PATCH v2] ndctl, list: add a '--health' option

[Dan Williams <dan.j.williams@intel.com>]

Dump dimm smart data in the dimm listing when '--health' is specified.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
Changes in v2:
* add an error message if health retrieval fails unexpectedly (jth)
* add threshold data to the health listing

 Documentation/ndctl-list.txt |   21 ++++++
 builtin-list.c               |   21 ++++++
 util/json.c                  |  150 ++++++++++++++++++++++++++++++++++++++++++
 util/json.h                  |    1 
 4 files changed, 192 insertions(+), 1 deletion(-)

diff --git a/Documentation/ndctl-list.txt b/Documentation/ndctl-list.txt
index 806548196118..a5f209f99408 100644
--- a/Documentation/ndctl-list.txt
+++ b/Documentation/ndctl-list.txt
@@ -3,7 +3,7 @@ ndctl-list(1)
 
 NAME
 ----
-ndctl-list - dump the platform nvdimm device topology in json
+ndctl-list - dump the platform nvdimm device topology and attributes in json
 
 SYNOPSIS
 --------
@@ -72,6 +72,25 @@ include::xable-region-options.txt[]
 --dimms::
 	Include dimm info in the listing
 
+-H::
+--health::
+	Include dimm health info in the listing.  For example:
+[verse]
+{
+  "dev":"nmem0",
+  "health":{
+    "health_state":"non-critical",
+    "temperature_celsius":23,
+    "spares_percentage":75,
+    "alarm_temperature":true,
+    "alarm_spares":true,
+    "temperature_threshold":40,
+    "spares_threshold":5,
+    "life_used_percentage":5,
+    "shutdown_state":"clean"
+  }
+}
+
 -R::
 --regions::
 	Include region info in the listing
diff --git a/builtin-list.c b/builtin-list.c
index df0871ab544a..f930b9e44c2c 100644
--- a/builtin-list.c
+++ b/builtin-list.c
@@ -22,6 +22,7 @@ static struct {
 	bool regions;
 	bool namespaces;
 	bool idle;
+	bool health;
 } list;
 
 static struct {
@@ -200,6 +201,7 @@ int cmd_list(int argc, const char **argv)
 				"filter by region-type"),
 		OPT_BOOLEAN('B', "buses", &list.buses, "include bus info"),
 		OPT_BOOLEAN('D', "dimms", &list.dimms, "include dimm info"),
+		OPT_BOOLEAN('H', "health", &list.health, "include dimm health"),
 		OPT_BOOLEAN('R', "regions", &list.regions,
 				"include region info"),
 		OPT_BOOLEAN('N', "namespaces", &list.namespaces,
@@ -299,6 +301,25 @@ int cmd_list(int argc, const char **argv)
 				continue;
 			}
 
+			if (list.health) {
+				struct json_object *jhealth;
+
+				jhealth = util_dimm_health_to_json(dimm);
+				if (jhealth)
+					json_object_object_add(jdimm, "health",
+							jhealth);
+				else if (ndctl_dimm_is_cmd_supported(dimm,
+							ND_CMD_SMART)) {
+					/*
+					 * Failed to retrieve health data from
+					 * a dimm that otherwise supports smart
+					 * data retrieval commands.
+					 */
+					fail("\n");
+					continue;
+				}
+			}
+
 			/*
 			 * Without a bus we are collecting dimms anonymously
 			 * across the platform.
diff --git a/util/json.c b/util/json.c
index 288efee723ff..6369a4eec291 100644
--- a/util/json.c
+++ b/util/json.c
@@ -61,6 +61,156 @@ struct json_object *util_dimm_to_json(struct ndctl_dimm *dimm)
 	return NULL;
 }
 
+static double parse_smart_temperature(unsigned int temp)
+{
+	bool negative = !!(temp & (1 << 15));
+	double t;
+
+	temp &= ~(1 << 15);
+	t = temp;
+	t /= 16;
+	if (negative)
+		t *= -1;
+	return t;
+}
+
+static void smart_threshold_to_json(struct ndctl_dimm *dimm,
+		struct json_object *jhealth)
+{
+	unsigned int alarm_control;
+	struct json_object *jobj;
+	struct ndctl_cmd *cmd;
+	int rc;
+
+	cmd = ndctl_dimm_cmd_new_smart_threshold(dimm);
+	if (!cmd)
+		return;
+
+	rc = ndctl_cmd_submit(cmd);
+	if (rc || ndctl_cmd_get_firmware_status(cmd))
+		goto out;
+
+	alarm_control = ndctl_cmd_smart_threshold_get_alarm_control(cmd);
+	if (alarm_control & ND_SMART_TEMP_TRIP) {
+		unsigned int temp;
+		double t;
+
+		temp = ndctl_cmd_smart_threshold_get_temperature(cmd);
+		t = parse_smart_temperature(temp);
+		jobj = json_object_new_double(t);
+		if (jobj)
+			json_object_object_add(jhealth,
+					"temperature_threshold", jobj);
+	}
+
+	if (alarm_control & ND_SMART_SPARE_TRIP) {
+		unsigned int spares;
+
+		spares = ndctl_cmd_smart_threshold_get_spares(cmd);
+		jobj = json_object_new_int(spares);
+		if (jobj)
+			json_object_object_add(jhealth,
+					"spares_threshold", jobj);
+	}
+
+ out:
+	ndctl_cmd_unref(cmd);
+}
+
+struct json_object *util_dimm_health_to_json(struct ndctl_dimm *dimm)
+{
+	struct json_object *jhealth = json_object_new_object();
+	struct json_object *jobj;
+	struct ndctl_cmd *cmd;
+	unsigned int flags;
+	int rc;
+
+	if (!jhealth)
+		return NULL;
+
+	cmd = ndctl_dimm_cmd_new_smart(dimm);
+	if (!cmd)
+		goto err;
+
+	rc = ndctl_cmd_submit(cmd);
+	if (rc || ndctl_cmd_get_firmware_status(cmd))
+		goto err;
+
+	flags = ndctl_cmd_smart_get_flags(cmd);
+	if (flags & ND_SMART_HEALTH_VALID) {
+		unsigned int health = ndctl_cmd_smart_get_health(cmd);
+
+		if (health & ND_SMART_FATAL_HEALTH)
+			jobj = json_object_new_string("fatal");
+		else if (health & ND_SMART_CRITICAL_HEALTH)
+			jobj = json_object_new_string("critical");
+		else if (health & ND_SMART_NON_CRITICAL_HEALTH)
+			jobj = json_object_new_string("non-critical");
+		else
+			jobj = json_object_new_string("ok");
+		if (jobj)
+			json_object_object_add(jhealth, "health_state", jobj);
+	}
+
+	if (flags & ND_SMART_TEMP_VALID) {
+		unsigned int temp = ndctl_cmd_smart_get_temperature(cmd);
+		double t = parse_smart_temperature(temp);
+
+		jobj = json_object_new_double(t);
+		if (jobj)
+			json_object_object_add(jhealth, "temperature_celsius", jobj);
+	}
+
+	if (flags & ND_SMART_SPARES_VALID) {
+		unsigned int spares = ndctl_cmd_smart_get_spares(cmd);
+
+		jobj = json_object_new_int(spares);
+		if (jobj)
+			json_object_object_add(jhealth, "spares_percentage", jobj);
+	}
+
+	if (flags & ND_SMART_ALARM_VALID) {
+		unsigned int alarm_flags = ndctl_cmd_smart_get_spares(cmd);
+		bool temp_flag = !!(alarm_flags & ND_SMART_TEMP_TRIP);
+		bool spares_flag = !!(alarm_flags & ND_SMART_SPARE_TRIP);
+
+		jobj = json_object_new_boolean(temp_flag);
+		if (jobj)
+			json_object_object_add(jhealth, "alarm_temperature", jobj);
+
+		jobj = json_object_new_boolean(spares_flag);
+		if (jobj)
+			json_object_object_add(jhealth, "alarm_spares", jobj);
+	}
+
+	smart_threshold_to_json(dimm, jhealth);
+
+	if (flags & ND_SMART_USED_VALID) {
+		unsigned int life_used = ndctl_cmd_smart_get_life_used(cmd);
+
+		jobj = json_object_new_int(life_used);
+		if (jobj)
+			json_object_object_add(jhealth, "life_used_percentage", jobj);
+	}
+
+	if (flags & ND_SMART_SHUTDOWN_VALID) {
+		unsigned int shutdown = ndctl_cmd_smart_get_shutdown_state(cmd);
+
+		jobj = json_object_new_string(shutdown ? "dirty" : "clean");
+		if (jobj)
+			json_object_object_add(jhealth, "shutdown_state", jobj);
+	}
+
+	ndctl_cmd_unref(cmd);
+	return jhealth;
+ err:
+	json_object_put(jhealth);
+	if (cmd)
+		ndctl_cmd_unref(cmd);
+	return NULL;
+}
+
+
 bool util_namespace_active(struct ndctl_namespace *ndns)
 {
 	struct ndctl_btt *btt = ndctl_namespace_get_btt(ndns);
diff --git a/util/json.h b/util/json.h
index 653bbd9beef1..79962cacc35c 100644
--- a/util/json.h
+++ b/util/json.h
@@ -6,6 +6,7 @@
 bool util_namespace_active(struct ndctl_namespace *ndns);
 struct json_object *util_bus_to_json(struct ndctl_bus *bus);
 struct json_object *util_dimm_to_json(struct ndctl_dimm *dimm);
+struct json_object *util_dimm_health_to_json(struct ndctl_dimm *dimm);
 struct json_object *util_mapping_to_json(struct ndctl_mapping *mapping);
 struct json_object *util_namespace_to_json(struct ndctl_namespace *ndns);
 #endif /* __NDCTL_JSON_H__ */

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm