Merge branch 'master' into feat/detect_k8s_flavour

docs/doc-remove-worker-flag.md

@@ -1,56 +0,0 @@
-## **Remove Worker flag from OKD Control Planes** 
-
-### **Context**
-On OKD user provisioned infrastructure the control plane nodes can have the flag node-role.kubernetes.io/worker which allows non critical workloads to be scheduled on the control-planes
-
-### **Observed Symptoms**
-- After adding HAProxy servers to the backend each back end appears down 
-- Traffic is redirected to the control planes instead of workers
-- The pods router-default are incorrectly applied on the control planes rather than on the workers
-- Pods are being scheduled on the control planes causing cluster instability
-
-```
-  ss -tlnp | grep 80
-```
-- shows process haproxy  is listening at 0.0.0.0:80 on cps
-- same problem for port 443
-- In namespace rook-ceph certain pods are deploted on cps rather than on worker nodes
-
- ### **Cause**
- - when intalling UPI, the roles (master, worker) are not managed by the Machine Config operator and the cps are made schedulable by default.
-
- ### **Diagnostic**
-check node labels:
-```
-   oc get nodes --show-labels | grep control-plane
-```
-Inspecter kubelet configuration:
-
-```
-cat /etc/systemd/system/kubelet.service
-```
-
-find the line:
-```
-   --node-labels=node-role.kubernetes.io/control-plane,node-role.kubernetes.io/master,node-role.kubernetes.io/worker
-```
-   → presence of label worker confirms the problem.
-
-Verify the flag doesnt come from MCO
-```
-   oc get machineconfig | grep rendered-master
-```
-
-**Solution:**
-To make the control planes non schedulable you must patch the cluster scheduler resource
-
-```	
-oc patch scheduler cluster --type merge -p '{"spec":{"mastersSchedulable":false}}'
-```
-after the patch is applied the workloads can be deplaced by draining the nodes
-
-```
-oc adm cordon <cp-node>
-oc adm drain <cp-node> --ignore-daemonsets –delete-emptydir-data
-```
-

harmony/src/domain/topology/k8s.rs

@@ -3,13 +3,11 @@ use std::time::Duration;
 use derive_new::new;
 use k8s_openapi::{
     ClusterResourceScope, NamespaceResourceScope,
-    api::{
-        apps::v1::Deployment,
-        core::v1::{Pod, PodStatus},
-    },
+    api::{apps::v1::Deployment, core::v1::Pod},
+    apimachinery::pkg::version::Info,
 };
 use kube::{
-    Client, Config, Error, Resource,
+    Client, Config, Discovery, Error, Resource,
     api::{Api, AttachParams, DeleteParams, ListParams, Patch, PatchParams, ResourceExt},
     config::{KubeConfigOptions, Kubeconfig},
     core::ErrorResponse,
@@ -59,6 +57,17 @@ impl K8sClient {
         })
     }
 
+    pub async fn get_apiserver_version(&self) -> Result<Info, Error> {
+        let client: Client = self.client.clone();
+        let version_info: Info = client.apiserver_version().await?;
+        Ok(version_info)
+    }
+
+    pub async fn discovery(&self) -> Result<Discovery, Error> {
+        let discovery: Discovery = Discovery::new(self.client.clone()).run().await?;
+        Ok(discovery)
+    }
+
     pub async fn get_resource_json_value(
         &self,
         name: &str,

harmony/src/domain/topology/k8s_anywhere.rs

@@ -47,6 +47,13 @@ struct K8sState {
     message: String,
 }
 
+#[derive(Debug, Clone)]
+pub enum KubernetesDistribution {
+    OpenshiftFamily,
+    K3sFamily,
+    Default,
+}
+
 #[derive(Debug, Clone)]
 enum K8sSource {
     LocalK3d,
@@ -57,6 +64,7 @@ enum K8sSource {
 pub struct K8sAnywhereTopology {
     k8s_state: Arc<OnceCell<Option<K8sState>>>,
     tenant_manager: Arc<OnceCell<K8sTenantManager>>,
+    flavour: Arc<OnceCell<KubernetesDistribution>>,
     config: Arc<K8sAnywhereConfig>,
 }
 
@@ -162,6 +170,7 @@ impl K8sAnywhereTopology {
         Self {
             k8s_state: Arc::new(OnceCell::new()),
             tenant_manager: Arc::new(OnceCell::new()),
+            flavour: Arc::new(OnceCell::new()),
             config: Arc::new(K8sAnywhereConfig::from_env()),
         }
     }
@@ -170,10 +179,42 @@ impl K8sAnywhereTopology {
         Self {
             k8s_state: Arc::new(OnceCell::new()),
             tenant_manager: Arc::new(OnceCell::new()),
+            flavour: Arc::new(OnceCell::new()),
             config: Arc::new(config),
         }
     }
 
+    pub async fn get_k8s_distribution(&self) -> Result<&KubernetesDistribution, PreparationError> {
+        self.flavour
+            .get_or_try_init(async || {
+                let client = self.k8s_client().await.unwrap();
+
+                let discovery = client.discovery().await.map_err(|e| {
+                    PreparationError::new(format!("Could not discover API groups: {}", e))
+                })?;
+
+                let version = client.get_apiserver_version().await.map_err(|e| {
+                    PreparationError::new(format!("Could not get server version: {}", e))
+                })?;
+
+                // OpenShift / OKD
+                if discovery
+                    .groups()
+                    .any(|g| g.name() == "project.openshift.io")
+                {
+                    return Ok(KubernetesDistribution::OpenshiftFamily);
+                }
+
+                // K3d / K3s
+                if version.git_version.contains("k3s") {
+                    return Ok(KubernetesDistribution::K3sFamily);
+                }
+
+                return Ok(KubernetesDistribution::Default);
+            })
+            .await
+    }
+
     async fn get_cluster_observability_operator_prometheus_application_score(
         &self,
         sender: RHOBObservability,