[Feature] [Platform] Storage Debug (#1928)

Author: ajanikow

CHANGELOG.md

@@ -1,6 +1,7 @@
 # Change Log
 
 ## [master](https://github.com/arangodb/kube-arangodb/tree/master) (N/A)
+- (Feature) (Platform) Storage Debug
 
 ## [1.2.50](https://github.com/arangodb/kube-arangodb/tree/1.2.50) (2025-07-04)
 - (Feature) (Platform) MetaV1 Integration Service

README.md

@@ -204,7 +204,7 @@ Flags:
       --kubernetes.qps float32                                 Number of queries per second for k8s API (default 32)
       --leader.label.skip                                      Skips Leader Label for the Pod
       --log.format string                                      Set log format. Allowed values: 'pretty', 'JSON'. If empty, default format is used (default "pretty")
-      --log.level stringArray                                  Set log levels in format <level> or <logger>=<level>. Possible loggers: action, agency, api-server, assertion, backup-operator, chaos-monkey, crd, deployment, deployment-ci, deployment-reconcile, deployment-replication, deployment-resilience, deployment-resources, deployment-storage, deployment-storage-pc, deployment-storage-service, generic-parent-operator, helm, http, inspector, integration-authn-v1, integration-config-v1, integration-envoy-auth-v3, integration-envoy-auth-v3-impl-auth-bearer, integration-envoy-auth-v3-impl-auth-cookie, integration-envoy-auth-v3-impl-custom-openid, integration-envoy-auth-v3-impl-pass-mode, integration-meta-v1, integration-scheduler-v2, integration-storage-v1-s3, integration-storage-v2, integrations, k8s-client, kubernetes, kubernetes-access, kubernetes-client, kubernetes-informer, monitor, networking-route-operator, operator, operator-arangojob-handler, operator-v2, operator-v2-event, operator-v2-worker, panics, platform-chart-operator, platform-pod-shutdown, platform-service-operator, platform-storage-operator, pod_compare, root, root-event-recorder, scheduler-batchjob-operator, scheduler-cronjob-operator, scheduler-deployment-operator, scheduler-pod-operator, scheduler-profile-operator, server, server-authentication, webhook (default [info])
+      --log.level stringArray                                  Set log levels in format <level> or <logger>=<level>. Possible loggers: action, agency, api-server, assertion, backup-operator, chaos-monkey, crd, deployment, deployment-ci, deployment-reconcile, deployment-replication, deployment-resilience, deployment-resources, deployment-storage, deployment-storage-pc, deployment-storage-service, generic-parent-operator, helm, http, inspector, integration-authn-v1, integration-config-v1, integration-envoy-auth-v3, integration-envoy-auth-v3-impl-auth-bearer, integration-envoy-auth-v3-impl-auth-cookie, integration-envoy-auth-v3-impl-custom-openid, integration-envoy-auth-v3-impl-pass-mode, integration-meta-v1, integration-scheduler-v2, integration-shutdown-v1, integration-storage-v1-s3, integration-storage-v2, integrations, k8s-client, kubernetes, kubernetes-access, kubernetes-client, kubernetes-informer, monitor, networking-route-operator, operator, operator-arangojob-handler, operator-v2, operator-v2-event, operator-v2-worker, panics, platform-chart-operator, platform-pod-shutdown, platform-service-operator, platform-storage-operator, pod_compare, root, root-event-recorder, scheduler-batchjob-operator, scheduler-cronjob-operator, scheduler-deployment-operator, scheduler-pod-operator, scheduler-profile-operator, server, server-authentication, webhook (default [info])
       --log.sampling                                           If true, operator will try to minimize duplication of logging events (default true)
       --log.stdout                                             If true, operator will log to the stdout (default true)
       --memory-limit uint                                      Define memory limit for hard shutdown and the dump of goroutines. Used for testing

cmd/cmd.go

@@ -282,7 +282,7 @@ func Command() *cobra.Command {
 func Execute() int {
 	flag.CommandLine.AddGoFlagSet(goflag.CommandLine)
 
-	if err := cmdMain.Execute(); err != nil {
+	if err := cmdMain.ExecuteContext(shutdown.Context()); err != nil {
 		var v cli.CommandExitCode
 		if errors.As(err, &v) {
 			return v.ExitCode

cmd/cmd_ops.go

@@ -27,6 +27,7 @@ import (
 	flag "github.com/spf13/pflag"
 
 	"github.com/arangodb/kube-arangodb/pkg/util/cli"
+	"github.com/arangodb/kube-arangodb/pkg/util/shutdown"
 )
 
 var (
@@ -43,7 +44,7 @@ func CommandOps() *cobra.Command {
 func ExecuteOps() int {
 	flag.CommandLine.AddGoFlagSet(goflag.CommandLine)
 
-	if err := cmdOps.Execute(); err != nil {
+	if err := cmdOps.ExecuteContext(shutdown.Context()); err != nil {
 		return 1
 	}
 

cmd/integration/init.go

@@ -28,6 +28,7 @@ import (
 
 	integrations "github.com/arangodb/kube-arangodb/pkg/integrations"
 	"github.com/arangodb/kube-arangodb/pkg/util/cli"
+	"github.com/arangodb/kube-arangodb/pkg/util/shutdown"
 )
 
 var (
@@ -51,7 +52,7 @@ func Command() *cobra.Command {
 func Execute() int {
 	flag.CommandLine.AddGoFlagSet(goflag.CommandLine)
 
-	if err := cmd.Execute(); err != nil {
+	if err := cmd.ExecuteContext(shutdown.Context()); err != nil {
 		return 1
 	}
 

cmd/main-platform/main_int.go

@@ -27,6 +27,7 @@ import (
 	"github.com/arangodb/kube-arangodb/pkg/logging"
 	"github.com/arangodb/kube-arangodb/pkg/platform"
 	"github.com/arangodb/kube-arangodb/pkg/util/cli"
+	"github.com/arangodb/kube-arangodb/pkg/util/shutdown"
 )
 
 func main() {
@@ -50,7 +51,7 @@ func mainE() error {
 		return err
 	}
 
-	if err := c.Execute(); err != nil {
+	if err := c.ExecuteContext(shutdown.Context()); err != nil {
 		return err
 	}
 

docs/cli/arangodb_operator.md

@@ -86,7 +86,7 @@ Flags:
       --kubernetes.qps float32                                 Number of queries per second for k8s API (default 32)
       --leader.label.skip                                      Skips Leader Label for the Pod
       --log.format string                                      Set log format. Allowed values: 'pretty', 'JSON'. If empty, default format is used (default "pretty")
-      --log.level stringArray                                  Set log levels in format <level> or <logger>=<level>. Possible loggers: action, agency, api-server, assertion, backup-operator, chaos-monkey, crd, deployment, deployment-ci, deployment-reconcile, deployment-replication, deployment-resilience, deployment-resources, deployment-storage, deployment-storage-pc, deployment-storage-service, generic-parent-operator, helm, http, inspector, integration-authn-v1, integration-config-v1, integration-envoy-auth-v3, integration-envoy-auth-v3-impl-auth-bearer, integration-envoy-auth-v3-impl-auth-cookie, integration-envoy-auth-v3-impl-custom-openid, integration-envoy-auth-v3-impl-pass-mode, integration-meta-v1, integration-scheduler-v2, integration-storage-v1-s3, integration-storage-v2, integrations, k8s-client, kubernetes, kubernetes-access, kubernetes-client, kubernetes-informer, monitor, networking-route-operator, operator, operator-arangojob-handler, operator-v2, operator-v2-event, operator-v2-worker, panics, platform-chart-operator, platform-pod-shutdown, platform-service-operator, platform-storage-operator, pod_compare, root, root-event-recorder, scheduler-batchjob-operator, scheduler-cronjob-operator, scheduler-deployment-operator, scheduler-pod-operator, scheduler-profile-operator, server, server-authentication, webhook (default [info])
+      --log.level stringArray                                  Set log levels in format <level> or <logger>=<level>. Possible loggers: action, agency, api-server, assertion, backup-operator, chaos-monkey, crd, deployment, deployment-ci, deployment-reconcile, deployment-replication, deployment-resilience, deployment-resources, deployment-storage, deployment-storage-pc, deployment-storage-service, generic-parent-operator, helm, http, inspector, integration-authn-v1, integration-config-v1, integration-envoy-auth-v3, integration-envoy-auth-v3-impl-auth-bearer, integration-envoy-auth-v3-impl-auth-cookie, integration-envoy-auth-v3-impl-custom-openid, integration-envoy-auth-v3-impl-pass-mode, integration-meta-v1, integration-scheduler-v2, integration-shutdown-v1, integration-storage-v1-s3, integration-storage-v2, integrations, k8s-client, kubernetes, kubernetes-access, kubernetes-client, kubernetes-informer, monitor, networking-route-operator, operator, operator-arangojob-handler, operator-v2, operator-v2-event, operator-v2-worker, panics, platform-chart-operator, platform-pod-shutdown, platform-service-operator, platform-storage-operator, pod_compare, root, root-event-recorder, scheduler-batchjob-operator, scheduler-cronjob-operator, scheduler-deployment-operator, scheduler-pod-operator, scheduler-profile-operator, server, server-authentication, webhook (default [info])
       --log.sampling                                           If true, operator will try to minimize duplication of logging events (default true)
       --log.stdout                                             If true, operator will log to the stdout (default true)
       --memory-limit uint                                      Define memory limit for hard shutdown and the dump of goroutines. Used for testing

docs/cli/arangodb_operator_integration.md

@@ -74,6 +74,9 @@ Flags:
       --integration.scheduler.v2.internal                           Defines if Internal access to service scheduler.v2 is enabled (Env: INTEGRATION_SCHEDULER_V2_INTERNAL) (default true)
       --integration.scheduler.v2.namespace string                   Kubernetes Namespace (Env: INTEGRATION_SCHEDULER_V2_NAMESPACE) (default "default")
       --integration.shutdown.v1                                     ShutdownV1 Handler (Env: INTEGRATION_SHUTDOWN_V1)
+      --integration.shutdown.v1.debug.enabled                       Defines if debug extension is enabled (Env: INTEGRATION_SHUTDOWN_V1_DEBUG_ENABLED)
+      --integration.shutdown.v1.debug.path string                   Path of the Debug Directory (Env: INTEGRATION_SHUTDOWN_V1_DEBUG_PATH) (default "/debug")
+      --integration.shutdown.v1.debug.timeout duration              Timeout of the Debug action (Env: INTEGRATION_SHUTDOWN_V1_DEBUG_TIMEOUT) (default 1m0s)
       --integration.shutdown.v1.external                            Defines if External access to service shutdown.v1 is enabled (Env: INTEGRATION_SHUTDOWN_V1_EXTERNAL)
       --integration.shutdown.v1.internal                            Defines if Internal access to service shutdown.v1 is enabled (Env: INTEGRATION_SHUTDOWN_V1_INTERNAL) (default true)
       --integration.storage.v2                                      StorageBucket V2 Integration (Env: INTEGRATION_STORAGE_V2)

docs/integration-sidecar.md

@@ -19,6 +19,8 @@ Integration Sidecar is supported in a few resources managed by Operator:
 - ArangoSchedulerCronJob (scheduler.arangodb.com/v1beta1)
 - ArangoSchedulerPod (scheduler.arangodb.com/v1beta1)
 
+Standard Kubernetes Resources (like Pod) are also supported with Webhook extension is enabled.
+
 To enable integration sidecar for specific deployment label needs to be defined:
 
 ```yaml
@@ -97,6 +99,9 @@ To enable:
 metadata:
   labels:
     integration.profiles.arangodb.com/storage: v1
+    
+    # Optionally, enable DebugPackage integration
+    storage.integration.profiles.arangodb.com/debug: "enabled"
 ```
 
 #### [Storage V2](./integration/storage.v2.md)

docs/integration/shutdown.v1.md

@@ -31,3 +31,15 @@ spec:
 ```
 
 Pod will receive shutdown request on port `port1` if containers `app` and `app2` will be in non running state.
+
+## Extensions
+
+### DebugPackage PreShutdown Hook
+
+Example:
+
+```yaml
+metadata:
+  labels:
+    core.shutdown.arangodb.com/app: "wait"
+```