feat: added steps for bootstrap install worker node

harmony/src/modules/okd/bootstrap_04_workers.rs

@@ -1,15 +1,21 @@
 use async_trait::async_trait;
 use derive_new::new;
 use harmony_types::id::Id;
-use log::info;
+use log::{debug, info};
 use serde::Serialize;
 
 use crate::{
     data::Version,
+    hardware::PhysicalHost,
+    infra::inventory::InventoryRepositoryFactory,
     interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
-    inventory::Inventory,
+    inventory::{HostRole, Inventory},
+    modules::{
+        dhcp::DhcpHostBindingScore, http::IPxeMacBootFileScore,
+        inventory::DiscoverHostForRoleScore, okd::templates::BootstrapIpxeTpl,
+    },
     score::Score,
-    topology::HAClusterTopology,
+    topology::{HAClusterTopology, HostBinding},
 };
 
 // -------------------------------------------------------------------------------------------------
@@ -52,6 +58,159 @@ impl OKDSetup04WorkersInterpret {
         info!("[Workers] Rendering per-MAC PXE for workers and rebooting");
         Ok(())
     }
+
+    /// Ensures that three physical hosts are discovered and available for the ControlPlane role.
+    /// It will trigger discovery if not enough hosts are found.
+    async fn get_nodes(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+    ) -> Result<Vec<PhysicalHost>, InterpretError> {
+        const REQUIRED_HOSTS: usize = 2;
+        let repo = InventoryRepositoryFactory::build().await?;
+        let mut control_plane_hosts = repo.get_host_for_role(&HostRole::Worker).await?;
+
+        while control_plane_hosts.len() < REQUIRED_HOSTS {
+            info!(
+                "Discovery of {} control plane hosts in progress, current number {}",
+                REQUIRED_HOSTS,
+                control_plane_hosts.len()
+            );
+            // This score triggers the discovery agent for a specific role.
+            DiscoverHostForRoleScore {
+                role: HostRole::Worker,
+            }
+            .interpret(inventory, topology)
+            .await?;
+            control_plane_hosts = repo.get_host_for_role(&HostRole::Worker).await?;
+        }
+
+        if control_plane_hosts.len() < REQUIRED_HOSTS {
+            Err(InterpretError::new(format!(
+                "OKD Requires at least {} control plane hosts, but only found {}. Cannot proceed.",
+                REQUIRED_HOSTS,
+                control_plane_hosts.len()
+            )))
+        } else {
+            // Take exactly the number of required hosts to ensure consistency.
+            Ok(control_plane_hosts
+                .into_iter()
+                .take(REQUIRED_HOSTS)
+                .collect())
+        }
+    }
+
+    /// Configures DHCP host bindings for all control plane nodes.
+    async fn configure_host_binding(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+        nodes: &Vec<PhysicalHost>,
+    ) -> Result<(), InterpretError> {
+        info!("[Worker] Configuring host bindings for worker nodes.");
+
+        // Ensure the topology definition matches the number of physical nodes found.
+        if topology.control_plane.len() != nodes.len() {
+            return Err(InterpretError::new(format!(
+                "Mismatch between logical control plane hosts defined in topology ({}) and physical nodes found ({}).",
+                topology.control_plane.len(),
+                nodes.len()
+            )));
+        }
+
+        // Create a binding for each physical host to its corresponding logical host.
+        let bindings: Vec<HostBinding> = topology
+            .control_plane
+            .iter()
+            .zip(nodes.iter())
+            .map(|(logical_host, physical_host)| {
+                info!(
+                    "Creating binding: Logical Host '{}' -> Physical Host ID '{}'",
+                    logical_host.name, physical_host.id
+                );
+                HostBinding {
+                    logical_host: logical_host.clone(),
+                    physical_host: physical_host.clone(),
+                }
+            })
+            .collect();
+
+        DhcpHostBindingScore {
+            host_binding: bindings,
+            domain: Some(topology.domain_name.clone()),
+        }
+        .interpret(inventory, topology)
+        .await?;
+
+        Ok(())
+    }
+
+    /// Renders and deploys a per-MAC iPXE boot file for each control plane node.
+    async fn configure_ipxe(
+        &self,
+        inventory: &Inventory,
+        topology: &HAClusterTopology,
+        nodes: &Vec<PhysicalHost>,
+    ) -> Result<(), InterpretError> {
+        info!("[Worker] Rendering per-MAC iPXE configurations.");
+
+        // The iPXE script content is the same for all control plane nodes,
+        // pointing to the 'master.ign' ignition file.
+        let content = BootstrapIpxeTpl {
+            http_ip: &topology.http_server.get_ip().to_string(),
+            scos_path: "scos",
+            ignition_http_path: "okd_ignition_files",
+            installation_device: "/dev/sda", // This might need to be configurable per-host in the future
+            ignition_file_name: "worker.ign", // Worker nodes use the worker ignition file
+        }
+        .to_string();
+
+        debug!("[Worker] iPXE content template:\n{content}");
+
+        // Create and apply an iPXE boot file for each node.
+        for node in nodes {
+            let mac_address = node.get_mac_address();
+            if mac_address.is_empty() {
+                return Err(InterpretError::new(format!(
+                    "Physical host with ID '{}' has no MAC addresses defined.",
+                    node.id
+                )));
+            }
+            info!(
+                "[Worker] Applying iPXE config for node ID '{}' with MACs: {:?}",
+                node.id, mac_address
+            );
+
+            IPxeMacBootFileScore {
+                mac_address,
+                content: content.clone(),
+            }
+            .interpret(inventory, topology)
+            .await?;
+        }
+
+        Ok(())
+    }
+
+    /// Prompts the user to reboot the target control plane nodes.
+    async fn reboot_targets(&self, nodes: &Vec<PhysicalHost>) -> Result<(), InterpretError> {
+        let node_ids: Vec<String> = nodes.iter().map(|n| n.id.to_string()).collect();
+        info!("[Worker] Requesting reboot for control plane nodes: {node_ids:?}",);
+
+        let confirmation = inquire::Confirm::new(
+                &format!("Please reboot the {} worker nodes ({}) to apply their PXE configuration. Press enter when ready.", nodes.len(), node_ids.join(", ")),
+        )
+        .prompt()
+        .map_err(|e| InterpretError::new(format!("User prompt failed: {e}")))?;
+
+        if !confirmation {
+            return Err(InterpretError::new(
+                "User aborted the operation.".to_string(),
+            ));
+        }
+
+        Ok(())
+    }
 }
 
 #[async_trait]
@@ -74,10 +233,23 @@ impl Interpret<HAClusterTopology> for OKDSetup04WorkersInterpret {
 
     async fn execute(
         &self,
-        _inventory: &Inventory,
+        inventory: &Inventory,
-        _topology: &HAClusterTopology,
+        topology: &HAClusterTopology,
     ) -> Result<Outcome, InterpretError> {
         self.render_and_reboot().await?;
+        // 1. Ensure we have 2 physical hosts for the worker nodes.
+        let nodes = self.get_nodes(inventory, topology).await?;
+
+        // 2. Create DHCP reservations for the worker nodes.
+        self.configure_host_binding(inventory, topology, &nodes)
+            .await?;
+
+        // 3. Create iPXE files for each worker node to boot from the worker ignition.
+        self.configure_ipxe(inventory, topology, &nodes).await?;
+
+        // 4. Reboot the nodes to start the OS installation.
+        self.reboot_targets(&nodes).await?;
+
         Ok(Outcome::success("Workers provisioned".into()))
     }
 }