feat: azure maintenance events

.gitignore

@@ -7,6 +7,9 @@
 # Language-Specific Build Artifacts & Dependencies
 # ============================================================================
 
+### Version Managers ###
+mise.toml
+
 ### Go ###
 # Binaries for programs and plugins
 *.exe
@@ -451,4 +454,4 @@ labeler/labeler
 metadata-collector/metadata-collector
 node-drainer/node-drainer
 platform-connectors/platform-connectors
-event-exporter/event-exporter
+event-exporter/event-exporter

health-monitors/csp-health-monitor/cmd/csp-health-monitor/main.go

@@ -34,6 +34,7 @@ import (
 	"github.com/nvidia/nvsentinel/health-monitors/csp-health-monitor/pkg/config"
 	"github.com/nvidia/nvsentinel/health-monitors/csp-health-monitor/pkg/csp"
 	awsclient "github.com/nvidia/nvsentinel/health-monitors/csp-health-monitor/pkg/csp/aws"
+	azureclient "github.com/nvidia/nvsentinel/health-monitors/csp-health-monitor/pkg/csp/azure"
 	gcpclient "github.com/nvidia/nvsentinel/health-monitors/csp-health-monitor/pkg/csp/gcp"
 	"github.com/nvidia/nvsentinel/health-monitors/csp-health-monitor/pkg/datastore"
 	eventpkg "github.com/nvidia/nvsentinel/health-monitors/csp-health-monitor/pkg/event"
@@ -256,7 +257,24 @@ func initActiveMonitor(
 		return awsMonitor
 	}
 
-	slog.Info("No CSP is explicitly enabled in the configuration (GCP or AWS).")
+	if cfg.Azure.Enabled {
+		slog.Info("Azure configuration is enabled.")
+
+		azureMonitor, err := azureclient.NewClient(ctx, cfg.Azure, cfg.ClusterName, kubeconfigPath)
+		if err != nil {
+			metrics.CSPMonitorErrors.WithLabelValues(string(model.CSPAzure), "init_error").Inc()
+			slog.Error("Failed to initialize Azure monitor. Azure will not be monitored.", "error", err)
+
+			return nil
+		}
+
+		slog.Info("Azure monitor initialized",
+			"subscriptionID", cfg.Azure.SubscriptionID)
+
+		return azureMonitor
+	}
+
+	slog.Info("No CSP is explicitly enabled in the configuration (GCP, AWS, or Azure).")
 
 	return nil
 }

health-monitors/csp-health-monitor/go.mod

@@ -7,6 +7,9 @@ toolchain go1.25.3
 require (
 	cloud.google.com/go/compute v1.38.0
 	cloud.google.com/go/logging v1.13.1
+	github.com/Azure/azure-sdk-for-go/sdk/azcore v1.20.0
+	github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.0
+	github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/maintenance/armmaintenance v1.3.0
 	github.com/BurntSushi/toml v1.5.0
 	github.com/aws/aws-sdk-go-v2 v1.40.0
 	github.com/aws/aws-sdk-go-v2/config v1.32.1
@@ -31,13 +34,14 @@ require (
 )
 
 require (
-	cel.dev/expr v0.25.1 // indirect
 	cloud.google.com/go v0.121.6 // indirect
 	cloud.google.com/go/auth v0.17.0 // indirect
 	cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect
 	cloud.google.com/go/compute/metadata v0.9.0 // indirect
 	cloud.google.com/go/iam v1.5.2 // indirect
 	cloud.google.com/go/longrunning v0.6.7 // indirect
+	github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 // indirect
+	github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0 // indirect
 	github.com/Masterminds/semver/v3 v3.4.0 // indirect
 	github.com/aws/aws-sdk-go-v2/credentials v1.19.1 // indirect
 	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.14 // indirect
@@ -75,6 +79,7 @@ require (
 	github.com/go-openapi/swag/typeutils v0.25.1 // indirect
 	github.com/go-openapi/swag/yamlutils v0.25.1 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
+	github.com/golang-jwt/jwt/v5 v5.3.0 // indirect
 	github.com/golang/snappy v1.0.0 // indirect
 	github.com/google/gnostic-models v0.7.0 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
@@ -85,11 +90,13 @@ require (
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/klauspost/compress v1.18.0 // indirect
+	github.com/kylelemons/godebug v1.1.0 // indirect
 	github.com/lib/pq v1.10.9 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee // indirect
 	github.com/montanaflynn/stats v0.7.1 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
+	github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
 	github.com/prometheus/common v0.67.2 // indirect
@@ -118,7 +125,6 @@ require (
 	golang.org/x/term v0.37.0 // indirect
 	golang.org/x/text v0.31.0 // indirect
 	golang.org/x/time v0.14.0 // indirect
-	gomodules.xyz/jsonpatch/v2 v2.5.0 // indirect
 	gopkg.in/evanphx/json-patch.v4 v4.13.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect

health-monitors/csp-health-monitor/go.sum

@@ -1,5 +1,5 @@
-cel.dev/expr v0.25.1 h1:1KrZg61W6TWSxuNZ37Xy49ps13NUovb66QLprthtwi4=
-cel.dev/expr v0.25.1/go.mod h1:hrXvqGP6G6gyx8UAHSHJ5RGk//1Oj5nXQ2NI02Nrsg4=
+cel.dev/expr v0.24.0 h1:56OvJKSH3hDGL0ml5uSxZmz3/3Pq4tJ+fb1unVLAFcY=
+cel.dev/expr v0.24.0/go.mod h1:hLPLo1W4QUmuYdA72RBX06QTs6MXw941piREPl3Yfiw=
 cloud.google.com/go v0.121.6 h1:waZiuajrI28iAf40cWgycWNgaXPO06dupuS+sgibK6c=
 cloud.google.com/go v0.121.6/go.mod h1:coChdst4Ea5vUpiALcYKXEpR1S9ZgXbhEzzMcMR66vI=
 cloud.google.com/go/auth v0.17.0 h1:74yCm7hCj2rUyyAocqnFzsAYXgJhrG26XCFimrc/Kz4=
@@ -20,6 +20,20 @@ cloud.google.com/go/monitoring v1.24.2 h1:5OTsoJ1dXYIiMiuL+sYscLc9BumrL3CarVLL7d
 cloud.google.com/go/monitoring v1.24.2/go.mod h1:x7yzPWcgDRnPEv3sI+jJGBkwl5qINf+6qY4eq0I9B4U=
 cloud.google.com/go/storage v1.56.0 h1:iixmq2Fse2tqxMbWhLWC9HfBj1qdxqAmiK8/eqtsLxI=
 cloud.google.com/go/storage v1.56.0/go.mod h1:Tpuj6t4NweCLzlNbw9Z9iwxEkrSem20AetIeH/shgVU=
+github.com/Azure/azure-sdk-for-go/sdk/azcore v1.20.0 h1:JXg2dwJUmPB9JmtVmdEB16APJ7jurfbY5jnfXpJoRMc=
+github.com/Azure/azure-sdk-for-go/sdk/azcore v1.20.0/go.mod h1:YD5h/ldMsG0XiIw7PdyNhLxaM317eFh5yNLccNfGdyw=
+github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.0 h1:KpMC6LFL7mqpExyMC9jVOYRiVhLmamjeZfRsUpB7l4s=
+github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.0/go.mod h1:J7MUC/wtRpfGVbQ5sIItY5/FuVWmvzlY21WAOfQnq/I=
+github.com/Azure/azure-sdk-for-go/sdk/azidentity/cache v0.3.2 h1:yz1bePFlP5Vws5+8ez6T3HWXPmwOK7Yvq8QxDBD3SKY=
+github.com/Azure/azure-sdk-for-go/sdk/azidentity/cache v0.3.2/go.mod h1:Pa9ZNPuoNu/GztvBSKk9J1cDJW6vk/n0zLtV4mgd8N8=
+github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 h1:9iefClla7iYpfYWdzPCRDozdmndjTm8DXdpCzPajMgA=
+github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2/go.mod h1:XtLgD3ZD34DAaVIIAyG3objl5DynM3CQ/vMcbBNJZGI=
+github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/maintenance/armmaintenance v1.3.0 h1:rx/pIYQIlCjb+n7TzMyFUzIJYb+d0Gi7Vh+ozA0fSJA=
+github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/maintenance/armmaintenance v1.3.0/go.mod h1:o8YD+BbSeK8ANH4SpxQFCiz5OIFKgHxV1uwF2FrQJYY=
+github.com/AzureAD/microsoft-authentication-extensions-for-go/cache v0.1.1 h1:WJTmL004Abzc5wDB5VtZG2PJk5ndYDgVacGqfirKxjM=
+github.com/AzureAD/microsoft-authentication-extensions-for-go/cache v0.1.1/go.mod h1:tCcJZ0uHAmvjsVYzEFivsRTN00oz5BEsRgQHu5JZ9WE=
+github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0 h1:XRzhVemXdgvJqCH0sFfrBUTnUJSBrBf7++ypk+twtRs=
+github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0/go.mod h1:HKpQxkWaGLJ+D/5H8QRpyQXA1eKjxkFlOMwck5+33Jk=
 github.com/BurntSushi/toml v1.5.0 h1:W5quZX/G/csjUnuI8SUYlsHs9M38FC7znL0lIO+DvMg=
 github.com/BurntSushi/toml v1.5.0/go.mod h1:ukJfTF/6rtPPRCnwkur4qwRxa8vTRFBF0uk2lLoLwho=
 github.com/DATA-DOG/go-sqlmock v1.5.2 h1:OcvFkGmslmlZibjAjaHm3L//6LiuBgolP7OputlJIzU=
@@ -132,6 +146,8 @@ github.com/go-task/slim-sprig/v3 v3.0.0 h1:sUs3vkvUymDpBKi3qH1YSqBQk9+9D/8M2mN1v
 github.com/go-task/slim-sprig/v3 v3.0.0/go.mod h1:W848ghGpv3Qj3dhTPRyJypKRiqCdHZiAzKg9hl15HA8=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
+github.com/golang-jwt/jwt/v5 v5.3.0 h1:pv4AsKCKKZuqlgs5sUmn4x8UlGa0kEVt/puTpKx9vvo=
+github.com/golang-jwt/jwt/v5 v5.3.0/go.mod h1:fxCRLWMO43lRc8nhHWY6LGqRcf+1gQWArsqaEUEa5bE=
 github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
 github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
 github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
@@ -160,6 +176,8 @@ github.com/hashicorp/go-multierror v1.1.1 h1:H5DkEtf6CXdFp0N0Em5UCwQpXMWke8IA0+l
 github.com/hashicorp/go-multierror v1.1.1/go.mod h1:iw975J/qwKPdAO1clOe2L8331t/9/fmwbPZ6JB6eMoM=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
+github.com/keybase/go-keychain v0.0.1 h1:way+bWYa6lDppZoZcgMbYsvC7GxljxrskdNInRtuthU=
+github.com/keybase/go-keychain v0.0.1/go.mod h1:PdEILRW3i9D8JcdM+FmY6RwkHGnhHxXwkPPMeUgOK1k=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
@@ -186,6 +204,8 @@ github.com/onsi/ginkgo/v2 v2.26.0 h1:1J4Wut1IlYZNEAWIV3ALrT9NfiaGW2cDCJQSFQMs/gE
 github.com/onsi/ginkgo/v2 v2.26.0/go.mod h1:qhEywmzWTBUY88kfO0BRvX4py7scov9yR+Az2oavUzw=
 github.com/onsi/gomega v1.38.2 h1:eZCjf2xjZAqe+LeWvKb5weQ+NcPwX84kqJ0cZNxok2A=
 github.com/onsi/gomega v1.38.2/go.mod h1:W2MJcYxRGV63b418Ai34Ud0hEdTVXq9NW9+Sx6uXf3k=
+github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=
+github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=
 github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 h1:GFCKgmp0tecUJ0sJuv4pzYCqS9+RGSn52M3FUwPs+uo=
 github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10/go.mod h1:t/avpk3KcrXxUnYOhZhMXJlSEyie6gQbtLq5NM3loB8=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
@@ -294,6 +314,7 @@ golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.38.0 h1:3yZWxaJjBmCWXqhN1qh02AkOnCQ1poK6oF+a7xWL6Gc=
 golang.org/x/sys v0.38.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
@@ -319,8 +340,8 @@ golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-gomodules.xyz/jsonpatch/v2 v2.5.0 h1:JELs8RLM12qJGXU4u/TO3V25KW8GreMKl9pdkk14RM0=
-gomodules.xyz/jsonpatch/v2 v2.5.0/go.mod h1:AH3dM2RI6uoBZxn3LVrfvJ3E0/9dG4cSrbuBJT4moAY=
+gomodules.xyz/jsonpatch/v2 v2.4.0 h1:Ci3iUJyx9UeRx7CeFN8ARgGbkESwJK+KB9lLcWxY/Zw=
+gomodules.xyz/jsonpatch/v2 v2.4.0/go.mod h1:AH3dM2RI6uoBZxn3LVrfvJ3E0/9dG4cSrbuBJT4moAY=
 gonum.org/v1/gonum v0.16.0 h1:5+ul4Swaf3ESvrOnidPp4GZbzf0mxVQpDCYUQE7OJfk=
 gonum.org/v1/gonum v0.16.0/go.mod h1:fef3am4MQ93R2HHpKnLk4/Tbh/s0+wqD5nfa6Pnwy4E=
 google.golang.org/api v0.256.0 h1:u6Khm8+F9sxbCTYNoBHg6/Hwv0N/i+V94MvkOSor6oI=

health-monitors/csp-health-monitor/pkg/config/config.go

@@ -37,13 +37,14 @@ const (
 )
 
 type Config struct {
-	MaintenanceEventPollIntervalSeconds       int       `toml:"maintenanceEventPollIntervalSeconds"`
-	TriggerQuarantineWorkflowTimeLimitMinutes int       `toml:"triggerQuarantineWorkflowTimeLimitMinutes"`
-	PostMaintenanceHealthyDelayMinutes        int       `toml:"postMaintenanceHealthyDelayMinutes"`
-	NodeReadinessTimeoutMinutes               int       `toml:"nodeReadinessTimeoutMinutes"`
-	ClusterName                               string    `toml:"clusterName"`
-	GCP                                       GCPConfig `toml:"gcp"`
-	AWS                                       AWSConfig `toml:"aws"`
+	MaintenanceEventPollIntervalSeconds       int         `toml:"maintenanceEventPollIntervalSeconds"`
+	TriggerQuarantineWorkflowTimeLimitMinutes int         `toml:"triggerQuarantineWorkflowTimeLimitMinutes"`
+	PostMaintenanceHealthyDelayMinutes        int         `toml:"postMaintenanceHealthyDelayMinutes"`
+	NodeReadinessTimeoutMinutes               int         `toml:"nodeReadinessTimeoutMinutes"`
+	ClusterName                               string      `toml:"clusterName"`
+	GCP                                       GCPConfig   `toml:"gcp"`
+	AWS                                       AWSConfig   `toml:"aws"`
+	Azure                                     AzureConfig `toml:"azure"`
 }
 
 // GCPConfig holds GCP specific configuration.
@@ -62,6 +63,13 @@ type AWSConfig struct {
 	Region                 string `toml:"region"`
 }
 
+// AzureConfig holds Azure specific configuration.
+type AzureConfig struct {
+	Enabled                bool   `toml:"enabled"`
+	SubscriptionID         string `toml:"subscriptionId"`
+	PollingIntervalSeconds int    `toml:"pollingIntervalSeconds"`
+}
+
 // LoadConfig reads the configuration from a TOML file.
 func LoadConfig(filePath string) (*Config, error) {
 	var cfg Config
@@ -174,7 +182,7 @@ func validateGeneralConfig(cfg *Config) error {
 	return nil
 }
 
-// validateCSPConfig checks GCP/AWS polling intervals and ensures only one CSP is enabled.
+// validateCSPConfig checks GCP/AWS/Azure polling intervals and ensures only one CSP is enabled.
 func validateCSPConfig(cfg *Config) error {
 	// Validate GCP polling interval
 	if cfg.GCP.Enabled && cfg.GCP.APIPollingIntervalSeconds < minCSPSpecificPollingIntervalSeconds {
@@ -194,9 +202,28 @@ func validateCSPConfig(cfg *Config) error {
 		)
 	}
 
+	// Validate Azure polling interval
+	if cfg.Azure.Enabled && cfg.Azure.PollingIntervalSeconds < minCSPSpecificPollingIntervalSeconds {
+		return fmt.Errorf(
+			"azure.pollingIntervalSeconds must be at least %d seconds (got %d)",
+			minCSPSpecificPollingIntervalSeconds,
+			cfg.Azure.PollingIntervalSeconds,
+		)
+	}
+
 	// Ensure only one CSP is enabled
-	if cfg.GCP.Enabled && cfg.AWS.Enabled {
-		return fmt.Errorf("multiple CSPs enabled: only one of GCP or AWS can be enabled at a time in the configuration")
+	count := 0
+
+	for _, csp := range []bool{cfg.GCP.Enabled, cfg.AWS.Enabled, cfg.Azure.Enabled} {
+		if csp {
+			count++
+		}
+	}
+
+	if count > 1 {
+		return fmt.Errorf(
+			"multiple CSPs enabled: only one of GCP, AWS, or Azure can be enabled at a time in the configuration",
+		)
 	}
 
 	return nil