Merge pull request #1395 from webalexeu/feat/add_owner_node

docs/collector.mscluster_resource.md

@@ -23,6 +23,7 @@ Name | Description | Type | Labels
 `IsAlivePollInterval` | Provides access to the resource's IsAlivePollInterval property, which is the recommended interval in milliseconds at which the Cluster Service should poll the resource to determine whether it is operational. If the property is set to 0xFFFFFFFF, the Cluster Service uses the IsAlivePollInterval property for the resource type associated with the resource. | gauge | `type`, `owner_group`, `name`
 `LooksAlivePollInterval` | Provides access to the resource's LooksAlivePollInterval property, which is the recommended interval in milliseconds at which the Cluster Service should poll the resource to determine whether it appears operational. If the property is set to 0xFFFFFFFF, the Cluster Service uses the LooksAlivePollInterval property for the resource type associated with the resource. | gauge | `type`, `owner_group`, `name`
 `MonitorProcessId` | Provides the process ID of the resource host service that is currently hosting the resource. | gauge | `type`, `owner_group`, `name`
+`OwnerNode` | The node hosting the resource. | gauge | `type`, `owner_group`, `node_name`, `name`
 `PendingTimeout` | Provides access to the resource's PendingTimeout property. If a resource cannot be brought online or taken offline in the number of milliseconds specified by the PendingTimeout property, the resource is forcibly terminated. | gauge | `type`, `owner_group`, `name`
 `ResourceClass` | Gets or sets the resource class of a resource. 0: Unknown; 1: Storage; 2: Network; 32768: Unknown | gauge | `type`, `owner_group`, `name`
 `RestartAction` | Provides access to the resource's RestartAction property, which is the action to be taken by the Cluster Service if the resource fails. | gauge | `type`, `owner_group`, `name`
@@ -34,10 +35,16 @@ Name | Description | Type | Labels
 `Subclass` | Provides the list of references to nodes that can be the owner of this resource. | gauge | `type`, `owner_group`, `name`
 
 ### Example metric
-_This collector does not yet have explained examples, we would appreciate your help adding them!_
+Query the state of all cluster resource owned by node1
+```
+windows_mscluster_resource_owner_node{node_name="node1"}
+```
 
 ## Useful queries
-_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
+Counts the number of Network Name cluster resource
+```
+count(windows_mscluster_resource_state{type="Network Name"})
+```
 
 ## Alerting examples
 _This collector does not yet have alerting examples, we would appreciate your help adding them!_

docs/collector.mscluster_resourcegroup.md

@@ -26,16 +26,23 @@ Name | Description | Type | Labels
 `FailoverThreshold` | The FailoverThreshold property specifies the maximum number of failover attempts. | gauge | `name`
 `Flags` | Provides access to the flags set for the group. The cluster defines flags only for resources. For a description of these flags, see [CLUSCTL_RESOURCE_GET_FLAGS](https://docs.microsoft.com/en-us/previous-versions/windows/desktop/mscs/clusctl-resource-get-flags). | gauge | `name`
 `GroupType` | The Type of the resource group. | gauge | `name`
+`OwnerNode` | The node hosting the resource group. | gauge | `node_name`, `name`
 `Priority` | Priority value of the resource group | gauge | `name`
 `ResiliencyPeriod` | The resiliency period for this group, in seconds. | gauge | `name`
 `State` | The current state of the resource group. -1: Unknown; 0: Online; 1: Offline; 2: Failed; 3: Partial Online; 4: Pending | gauge | `name`
 `UpdateDomain` | | gauge | `name`
 
 ### Example metric
-_This collector does not yet have explained examples, we would appreciate your help adding them!_
+Query the state of all cluster group owned by node1
+```
+windows_mscluster_resourcegroup_owner_node{node_name="node1"}
+```
 
 ## Useful queries
-_This collector does not yet have any useful queries added, we would appreciate your help adding them!_
+Counts the number of cluster group by type
+```
+count_values("count", windows_mscluster_resourcegroup_group_type)
+```
 
 ## Alerting examples
 _This collector does not yet have alerting examples, we would appreciate your help adding them!_

pkg/collector/mscluster_node/mscluster_node.go

@@ -15,6 +15,9 @@ type Config struct{}
 
 var ConfigDefaults = Config{}
 
+// Variable used by mscluster_resource and mscluster_resourcegroup
+var NodeName []string
+
 // A collector is a Prometheus collector for WMI MSCluster_Node metrics
 type collector struct {
 	logger log.Logger
@@ -175,6 +178,8 @@ func (c *collector) Collect(_ *types.ScrapeContext, ch chan<- prometheus.Metric)
 		return err
 	}
 
+	NodeName = []string{}
+
 	for _, v := range dst {
 
 		ch <- prometheus.MustNewConstMetric(
@@ -274,6 +279,8 @@ func (c *collector) Collect(_ *types.ScrapeContext, ch chan<- prometheus.Metric)
 			float64(v.StatusInformation),
 			v.Name,
 		)
+
+		NodeName = append(NodeName, v.Name)
 	}
 
 	return nil

pkg/collector/mscluster_resource/mscluster_resource.go

@@ -1,6 +1,7 @@
 package mscluster_resource
 
 import (
+	"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_node"
 	"github.com/prometheus-community/windows_exporter/pkg/types"
 	"github.com/prometheus-community/windows_exporter/pkg/wmi"
 
@@ -26,6 +27,7 @@ type collector struct {
 	IsAlivePollInterval    *prometheus.Desc
 	LooksAlivePollInterval *prometheus.Desc
 	MonitorProcessId       *prometheus.Desc
+	OwnerNode              *prometheus.Desc
 	PendingTimeout         *prometheus.Desc
 	ResourceClass          *prometheus.Desc
 	RestartAction          *prometheus.Desc
@@ -102,6 +104,18 @@ func (c *collector) Build() error {
 		[]string{"type", "owner_group", "name"},
 		nil,
 	)
+	c.OwnerNode = prometheus.NewDesc(
+		prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
+		"The node hosting the resource. 0: Not hosted; 1: Hosted",
+		[]string{"type", "owner_group", "node_name", "name"},
+		nil,
+	)
+	c.OwnerNode = prometheus.NewDesc(
+		prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
+		"The node hosting the resource. 0: Not hosted; 1: Hosted",
+		[]string{"type", "owner_group", "node_name", "name"},
+		nil,
+	)
 	c.PendingTimeout = prometheus.NewDesc(
 		prometheus.BuildFQName(types.Namespace, Name, "pending_timeout"),
 		"Provides access to the resource's PendingTimeout property. If a resource cannot be brought online or taken offline in the number of milliseconds specified by the PendingTimeout property, the resource is forcibly terminated.",
@@ -165,6 +179,7 @@ type MSCluster_Resource struct {
 	Name       string
 	Type       string
 	OwnerGroup string
+	OwnerNode  string
 
 	Characteristics        uint
 	DeadlockTimeout        uint
@@ -244,6 +259,21 @@ func (c *collector) Collect(_ *types.ScrapeContext, ch chan<- prometheus.Metric)
 			v.Type, v.OwnerGroup, v.Name,
 		)
 
+		if mscluster_node.NodeName != nil {
+			for _, node_name := range mscluster_node.NodeName {
+				isCurrentState := 0.0
+				if v.OwnerNode == node_name {
+					isCurrentState = 1.0
+				}
+				ch <- prometheus.MustNewConstMetric(
+					c.OwnerNode,
+					prometheus.GaugeValue,
+					isCurrentState,
+					v.Type, v.OwnerGroup, node_name, v.Name,
+				)
+			}
+		}
+
 		ch <- prometheus.MustNewConstMetric(
 			c.PendingTimeout,
 			prometheus.GaugeValue,

pkg/collector/mscluster_resourcegroup/mscluster_resourcegroup.go

@@ -1,6 +1,7 @@
 package mscluster_resourcegroup
 
 import (
+	"github.com/prometheus-community/windows_exporter/pkg/collector/mscluster_node"
 	"github.com/prometheus-community/windows_exporter/pkg/types"
 	"github.com/prometheus-community/windows_exporter/pkg/wmi"
 
@@ -31,6 +32,7 @@ type collector struct {
 	Flags               *prometheus.Desc
 	GroupType           *prometheus.Desc
 	PlacementOptions    *prometheus.Desc
+	OwnerNode           *prometheus.Desc
 	Priority            *prometheus.Desc
 	ResiliencyPeriod    *prometheus.Desc
 	State               *prometheus.Desc
@@ -119,6 +121,18 @@ func (c *collector) Build() error {
 		[]string{"name"},
 		nil,
 	)
+	c.OwnerNode = prometheus.NewDesc(
+		prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
+		"The node hosting the resource group. 0: Not hosted; 1: Hosted",
+		[]string{"node_name", "name"},
+		nil,
+	)
+	c.OwnerNode = prometheus.NewDesc(
+		prometheus.BuildFQName(types.Namespace, Name, "owner_node"),
+		"The node hosting the resource group. 0: Not hosted; 1: Hosted",
+		[]string{"node_name", "name"},
+		nil,
+	)
 	c.Priority = prometheus.NewDesc(
 		prometheus.BuildFQName(types.Namespace, Name, "priority"),
 		"Priority value of the resource group",
@@ -155,6 +169,7 @@ type MSCluster_ResourceGroup struct {
 	FailoverThreshold   uint
 	Flags               uint
 	GroupType           uint
+	OwnerNode           string
 	Priority            uint
 	ResiliencyPeriod    uint
 	State               uint
@@ -241,6 +256,21 @@ func (c *collector) Collect(_ *types.ScrapeContext, ch chan<- prometheus.Metric)
 			v.Name,
 		)
 
+		if mscluster_node.NodeName != nil {
+			for _, node_name := range mscluster_node.NodeName {
+				isCurrentState := 0.0
+				if v.OwnerNode == node_name {
+					isCurrentState = 1.0
+				}
+				ch <- prometheus.MustNewConstMetric(
+					c.OwnerNode,
+					prometheus.GaugeValue,
+					isCurrentState,
+					node_name, v.Name,
+				)
+			}
+		}
+
 		ch <- prometheus.MustNewConstMetric(
 			c.Priority,
 			prometheus.GaugeValue,