Compare commits

..

2 Commits

Author SHA1 Message Date
3f7c2cd46d fix: works to install on virtual disk 2025-10-30 11:47:25 -04:00
b626d40fcd fix: pxe vm lab setup to work on ubuntu machine 2025-10-28 09:18:32 -04:00
66 changed files with 739 additions and 3165 deletions

27
Cargo.lock generated
View File

@@ -1780,7 +1780,6 @@ dependencies = [
name = "example-nanodc"
version = "0.1.0"
dependencies = [
"brocade",
"cidr",
"env_logger",
"harmony",
@@ -1789,7 +1788,6 @@ dependencies = [
"harmony_tui",
"harmony_types",
"log",
"serde",
"tokio",
"url",
]
@@ -1808,7 +1806,6 @@ dependencies = [
name = "example-okd-install"
version = "0.1.0"
dependencies = [
"brocade",
"cidr",
"env_logger",
"harmony",
@@ -1839,16 +1836,13 @@ dependencies = [
name = "example-opnsense"
version = "0.1.0"
dependencies = [
"brocade",
"cidr",
"env_logger",
"harmony",
"harmony_macros",
"harmony_secret",
"harmony_tui",
"harmony_types",
"log",
"serde",
"tokio",
"url",
]
@@ -1857,7 +1851,6 @@ dependencies = [
name = "example-pxe"
version = "0.1.0"
dependencies = [
"brocade",
"cidr",
"env_logger",
"harmony",
@@ -1872,15 +1865,6 @@ dependencies = [
"url",
]
[[package]]
name = "example-remove-rook-osd"
version = "0.1.0"
dependencies = [
"harmony",
"harmony_cli",
"tokio",
]
[[package]]
name = "example-rust"
version = "0.1.0"
@@ -1934,6 +1918,8 @@ dependencies = [
"env_logger",
"harmony",
"harmony_macros",
"harmony_secret",
"harmony_secret_derive",
"harmony_tui",
"harmony_types",
"log",
@@ -4627,6 +4613,15 @@ version = "0.8.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "caf4aa5b0f434c91fe5c7f1ecb6a5ece2130b02ad2a590589dda5146df959001"
[[package]]
name = "remove_rook_osd"
version = "0.1.0"
dependencies = [
"harmony",
"harmony_cli",
"tokio",
]
[[package]]
name = "reqwest"
version = "0.11.27"

View File

@@ -1,6 +1,4 @@
# Harmony
Open-source infrastructure orchestration that treats your platform like first-class code.
# Harmony : Open-source infrastructure orchestration that treats your platform like first-class code
_By [NationTech](https://nationtech.io)_
@@ -20,7 +18,9 @@ All in **one strongly-typed Rust codebase**.
From a **developer laptop** to a **global production cluster**, a single **source of truth** drives the **full software lifecycle.**
## The Harmony Philosophy
---
## 1 · The Harmony Philosophy
Infrastructure is essential, but it shouldnt be your core business. Harmony is built on three guiding principles that make modern platforms reliable, repeatable, and easy to reason about.
@@ -32,18 +32,9 @@ Infrastructure is essential, but it shouldnt be your core business. Harmony i
These principles surface as simple, ergonomic Rust APIs that let teams focus on their product while trusting the platform underneath.
## Where to Start
---
We have a comprehensive set of documentation right here in the repository.
| I want to... | Start Here |
| ----------------- | ------------------------------------------------------------------ |
| Get Started | [Getting Started Guide](./docs/guides/getting-started.md) |
| See an Example | [Use Case: Deploy a Rust Web App](./docs/use-cases/rust-webapp.md) |
| Explore | [Documentation Hub](./docs/README.md) |
| See Core Concepts | [Core Concepts Explained](./docs/concepts.md) |
## Quick Look: Deploy a Rust Webapp
## 2 · Quick Start
The snippet below spins up a complete **production-grade Rust + Leptos Webapp** with monitoring. Swap it for your own scores to deploy anything from microservices to machine-learning pipelines.
@@ -101,33 +92,63 @@ async fn main() {
}
```
To run this:
Run it:
- Clone the repository: `git clone https://git.nationtech.io/nationtech/harmony`
- Install dependencies: `cargo build --release`
- Run the example: `cargo run --example try_rust_webapp`
```bash
cargo run
```
## Documentation
Harmony analyses the code, shows an execution plan in a TUI, and applies it once you confirm. Same code, same binary—every environment.
All documentation is in the `/docs` directory.
---
- [Documentation Hub](./docs/README.md): The main entry point for all documentation.
- [Core Concepts](./docs/concepts.md): A detailed look at Score, Topology, Capability, Inventory, and Interpret.
- [Component Catalogs](./docs/catalogs/README.md): Discover all available Scores, Topologies, and Capabilities.
- [Developer Guide](./docs/guides/developer-guide.md): Learn how to write your own Scores and Topologies.
## 3 · Core Concepts
## Architectural Decision Records
| Term | One-liner |
| ---------------- | ---------------------------------------------------------------------------------------------------- |
| **Score<T>** | Declarative description of the desired state (e.g., `LAMPScore`). |
| **Interpret<T>** | Imperative logic that realises a `Score` on a specific environment. |
| **Topology** | An environment (local k3d, AWS, bare-metal) exposing verified _Capabilities_ (Kubernetes, DNS, …). |
| **Maestro** | Orchestrator that compiles Scores + Topology, ensuring all capabilities line up **at compile-time**. |
| **Inventory** | Optional catalogue of physical assets for bare-metal and edge deployments. |
- [ADR-001 · Why Rust](adr/001-rust.md)
- [ADR-003 · Infrastructure Abstractions](adr/003-infrastructure-abstractions.md)
- [ADR-006 · Secret Management](adr/006-secret-management.md)
- [ADR-011 · Multi-Tenant Cluster](adr/011-multi-tenant-cluster.md)
A visual overview is in the diagram below.
## Contribute
[Harmony Core Architecture](docs/diagrams/Harmony_Core_Architecture.drawio.svg)
Discussions and roadmap live in [Issues](https://git.nationtech.io/nationtech/harmony/-/issues). PRs, ideas, and feedback are welcome!
---
## License
## 4 · Install
Prerequisites:
- Rust
- Docker (if you deploy locally)
- `kubectl` / `helm` for Kubernetes-based topologies
```bash
git clone https://git.nationtech.io/nationtech/harmony
cd harmony
cargo build --release # builds the CLI, TUI and libraries
```
---
## 5 · Learning More
- **Architectural Decision Records** dive into the rationale
- [ADR-001 · Why Rust](adr/001-rust.md)
- [ADR-003 · Infrastructure Abstractions](adr/003-infrastructure-abstractions.md)
- [ADR-006 · Secret Management](adr/006-secret-management.md)
- [ADR-011 · Multi-Tenant Cluster](adr/011-multi-tenant-cluster.md)
- **Extending Harmony** write new Scores / Interprets, add hardware like OPNsense firewalls, or embed Harmony in your own tooling (`/docs`).
- **Community** discussions and roadmap live in [GitLab issues](https://git.nationtech.io/nationtech/harmony/-/issues). PRs, ideas, and feedback are welcome!
---
## 6 · License
Harmony is released under the **GNU AGPL v3**.

View File

@@ -10,7 +10,6 @@ use log::{debug, info};
use regex::Regex;
use std::{collections::HashSet, str::FromStr};
#[derive(Debug)]
pub struct FastIronClient {
shell: BrocadeShell,
version: BrocadeInfo,

View File

@@ -31,7 +31,6 @@ pub struct BrocadeOptions {
pub struct TimeoutConfig {
pub shell_ready: Duration,
pub command_execution: Duration,
pub command_output: Duration,
pub cleanup: Duration,
pub message_wait: Duration,
}
@@ -41,7 +40,6 @@ impl Default for TimeoutConfig {
Self {
shell_ready: Duration::from_secs(10),
command_execution: Duration::from_secs(60), // Commands like `deploy` (for a LAG) can take a while
command_output: Duration::from_secs(5), // Delay to start logging "waiting for command output"
cleanup: Duration::from_secs(10),
message_wait: Duration::from_millis(500),
}
@@ -164,7 +162,7 @@ pub async fn init(
}
#[async_trait]
pub trait BrocadeClient: std::fmt::Debug {
pub trait BrocadeClient {
/// Retrieves the operating system and version details from the connected Brocade switch.
///
/// This is typically the first call made after establishing a connection to determine

View File

@@ -3,7 +3,6 @@ use std::str::FromStr;
use async_trait::async_trait;
use harmony_types::switch::{PortDeclaration, PortLocation};
use log::{debug, info};
use regex::Regex;
use crate::{
BrocadeClient, BrocadeInfo, Error, ExecutionMode, InterSwitchLink, InterfaceInfo,
@@ -11,7 +10,6 @@ use crate::{
parse_brocade_mac_address, shell::BrocadeShell,
};
#[derive(Debug)]
pub struct NetworkOperatingSystemClient {
shell: BrocadeShell,
version: BrocadeInfo,
@@ -104,37 +102,13 @@ impl NetworkOperatingSystemClient {
};
Some(Ok(InterfaceInfo {
name: format!("{interface_type} {port_location}"),
name: format!("{} {}", interface_type, port_location),
port_location,
interface_type,
operating_mode,
status,
}))
}
fn map_configure_interfaces_error(&self, err: Error) -> Error {
debug!("[Brocade] {err}");
if let Error::CommandError(message) = &err {
if message.contains("switchport")
&& message.contains("Cannot configure aggregator member")
{
let re = Regex::new(r"\(conf-if-([a-zA-Z]+)-([\d/]+)\)#").unwrap();
if let Some(caps) = re.captures(message) {
let interface_type = &caps[1];
let port_location = &caps[2];
let interface = format!("{interface_type} {port_location}");
return Error::CommandError(format!(
"Cannot configure interface '{interface}', it is a member of a port-channel (LAG)"
));
}
}
}
err
}
}
#[async_trait]
@@ -222,10 +196,11 @@ impl BrocadeClient for NetworkOperatingSystemClient {
commands.push("exit".into());
}
commands.push("write memory".into());
self.shell
.run_commands(commands, ExecutionMode::Regular)
.await
.map_err(|err| self.map_configure_interfaces_error(err))?;
.await?;
info!("[Brocade] Interfaces configured.");
@@ -237,7 +212,7 @@ impl BrocadeClient for NetworkOperatingSystemClient {
let output = self
.shell
.run_command("show port-channel summary", ExecutionMode::Regular)
.run_command("show port-channel", ExecutionMode::Regular)
.await?;
let used_ids: Vec<u8> = output
@@ -272,12 +247,7 @@ impl BrocadeClient for NetworkOperatingSystemClient {
ports: &[PortLocation],
) -> Result<(), Error> {
info!(
"[Brocade] Configuring port-channel '{channel_id} {channel_name}' with ports: {}",
ports
.iter()
.map(|p| format!("{p}"))
.collect::<Vec<String>>()
.join(", ")
"[Brocade] Configuring port-channel '{channel_name} {channel_id}' with ports: {ports:?}"
);
let interfaces = self.get_interfaces().await?;
@@ -305,6 +275,8 @@ impl BrocadeClient for NetworkOperatingSystemClient {
commands.push("exit".into());
}
commands.push("write memory".into());
self.shell
.run_commands(commands, ExecutionMode::Regular)
.await?;
@@ -321,6 +293,7 @@ impl BrocadeClient for NetworkOperatingSystemClient {
"configure terminal".into(),
format!("no interface port-channel {}", channel_name),
"exit".into(),
"write memory".into(),
];
self.shell

View File

@@ -13,7 +13,6 @@ use log::info;
use russh::ChannelMsg;
use tokio::time::timeout;
#[derive(Debug)]
pub struct BrocadeShell {
ip: IpAddr,
port: u16,
@@ -211,7 +210,7 @@ impl BrocadeSession {
let mut output = Vec::new();
let start = Instant::now();
let read_timeout = Duration::from_millis(500);
let log_interval = Duration::from_secs(5);
let log_interval = Duration::from_secs(3);
let mut last_log = Instant::now();
loop {
@@ -221,9 +220,7 @@ impl BrocadeSession {
));
}
if start.elapsed() > self.options.timeouts.command_output
&& last_log.elapsed() > log_interval
{
if start.elapsed() > Duration::from_secs(5) && last_log.elapsed() > log_interval {
info!("[Brocade] Waiting for command output...");
last_log = Instant::now();
}
@@ -278,7 +275,7 @@ impl BrocadeSession {
let output_lower = output.to_lowercase();
if ERROR_PATTERNS.iter().any(|&p| output_lower.contains(p)) {
return Err(Error::CommandError(format!(
"Command error: {}",
"Command '{command}' failed: {}",
output.trim()
)));
}

View File

@@ -1,33 +1 @@
# Harmony Documentation Hub
Welcome to the Harmony documentation. This is the main entry point for learning everything from core concepts to building your own Score, Topologies, and Capabilities.
## 1. Getting Started
If you're new to Harmony, start here:
- [**Getting Started Guide**](./guides/getting-started.md): A step-by-step tutorial that takes you from an empty project to deploying your first application.
- [**Core Concepts**](./concepts.md): A high-level overview of the key concepts in Harmony: `Score`, `Topology`, `Capability`, `Inventory`, `Interpret`, ...
## 2. Use Cases & Examples
See how to use Harmony to solve real-world problems.
- [**OKD on Bare Metal**](./use-cases/okd-on-bare-metal.md): A detailed walkthrough of bootstrapping a high-availability OKD cluster from physical hardware.
- [**Deploy a Rust Web App**](./use-cases/deploy-rust-webapp.md): A quick guide to deploying a monitored, containerized web application to a Kubernetes cluster.
## 3. Component Catalogs
Discover existing, reusable components you can use in your Harmony projects.
- [**Scores Catalog**](./catalogs/scores.md): A categorized list of all available `Scores` (the "what").
- [**Topologies Catalog**](./catalogs/topologies.md): A list of all available `Topologies` (the "where").
- [**Capabilities Catalog**](./catalogs/capabilities.md): A list of all available `Capabilities` (the "how").
## 4. Developer Guides
Ready to build your own components? These guides show you how.
- [**Writing a Score**](./guides/writing-a-score.md): Learn how to create your own `Score` and `Interpret` logic to define a new desired state.
- [**Writing a Topology**](./guides/writing-a-topology.md): Learn how to model a new environment (like AWS, GCP, or custom hardware) as a `Topology`.
- [**Adding Capabilities**](./guides/adding-capabilities.md): See how to add a `Capability` to your custom `Topology`.
Not much here yet, see the `adr` folder for now. More to come in time!

View File

@@ -1,7 +0,0 @@
# Component Catalogs
This section is the "dictionary" for Harmony. It lists all the reusable components available out-of-the-box.
- [**Scores Catalog**](./scores.md): Discover all available `Scores` (the "what").
- [**Topologies Catalog**](./topologies.md): A list of all available `Topologies` (the "where").
- [**Capabilities Catalog**](./capabilities.md): A list of all available `Capabilities` (the "how").

View File

@@ -1,40 +0,0 @@
# Capabilities Catalog
A `Capability` is a specific feature or API that a `Topology` offers. `Interpret` logic uses these capabilities to execute a `Score`.
This list is primarily for developers **writing new Topologies or Scores**. As a user, you just need to know that the `Topology` you pick (like `K8sAnywhereTopology`) provides the capabilities your `Scores` (like `ApplicationScore`) need.
<!--toc:start-->
- [Capabilities Catalog](#capabilities-catalog)
- [Kubernetes & Application](#kubernetes-application)
- [Monitoring & Observability](#monitoring-observability)
- [Networking (Core Services)](#networking-core-services)
- [Networking (Hardware & Host)](#networking-hardware-host)
<!--toc:end-->
## Kubernetes & Application
- **K8sClient**: Provides an authenticated client to interact with a Kubernetes API (create/read/update/delete resources).
- **HelmCommand**: Provides the ability to execute Helm commands (install, upgrade, template).
- **TenantManager**: Provides methods for managing tenants in a multi-tenant cluster.
- **Ingress**: Provides an interface for managing ingress controllers and resources.
## Monitoring & Observability
- **Grafana**: Provides an API for configuring Grafana (datasources, dashboards).
- **Monitoring**: A general capability for configuring monitoring (e.g., creating Prometheus rules).
## Networking (Core Services)
- **DnsServer**: Provides an interface for creating and managing DNS records.
- **LoadBalancer**: Provides an interface for configuring a load balancer (e.g., OPNsense, MetalLB).
- **DhcpServer**: Provides an interface for managing DHCP leases and host bindings.
- **TftpServer**: Provides an interface for managing files on a TFTP server (e.g., iPXE boot files).
## Networking (Hardware & Host)
- **Router**: Provides an interface for configuring routing rules, typically on a firewall like OPNsense.
- **Switch**: Provides an interface for configuring a physical network switch (e.g., managing VLANs and port channels).
- **NetworkManager**: Provides an interface for configuring host-level networking (e.g., creating bonds and bridges on a node).

View File

@@ -1,102 +0,0 @@
# Scores Catalog
A `Score` is a declarative description of a desired state. Find the Score you need and add it to your `harmony!` block's `scores` array.
<!--toc:start-->
- [Scores Catalog](#scores-catalog)
- [Application Deployment](#application-deployment)
- [OKD / Kubernetes Cluster Setup](#okd-kubernetes-cluster-setup)
- [Cluster Services & Management](#cluster-services-management)
- [Monitoring & Alerting](#monitoring-alerting)
- [Infrastructure & Networking (Bare Metal)](#infrastructure-networking-bare-metal)
- [Infrastructure & Networking (Cluster)](#infrastructure-networking-cluster)
- [Tenant Management](#tenant-management)
- [Utility](#utility)
<!--toc:end-->
## Application Deployment
Scores for deploying and managing end-user applications.
- **ApplicationScore**: The primary score for deploying a web application. Describes the application, its framework, and the features it requires (e.g., monitoring, CI/CD).
- **HelmChartScore**: Deploys a generic Helm chart to a Kubernetes cluster.
- **ArgoHelmScore**: Deploys an application using an ArgoCD Helm chart.
- **LAMPScore**: A specialized score for deploying a classic LAMP (Linux, Apache, MySQL, PHP) stack.
## OKD / Kubernetes Cluster Setup
This collection of Scores is used to provision an entire OKD cluster from bare metal. They are typically used in order.
- **OKDSetup01InventoryScore**: Discovers and catalogs the physical hardware.
- **OKDSetup02BootstrapScore**: Configures the bootstrap node, renders iPXE files, and kicks off the SCOS installation.
- **OKDSetup03ControlPlaneScore**: Renders iPXE configurations for the control plane nodes.
- **OKDSetupPersistNetworkBondScore**: Configures network bonds on the nodes and port channels on the switches.
- **OKDSetup04WorkersScore**: Renders iPXE configurations for the worker nodes.
- **OKDSetup06InstallationReportScore**: Runs post-installation checks and generates a report.
- **OKDUpgradeScore**: Manages the upgrade process for an existing OKD cluster.
## Cluster Services & Management
Scores for installing and managing services _inside_ a Kubernetes cluster.
- **K3DInstallationScore**: Installs and configes a local K3D (k3s-in-docker) cluster. Used by `K8sAnywhereTopology`.
- **CertManagerHelmScore**: Deploys the `cert-manager` Helm chart.
- **ClusterIssuerScore**: Configures a `ClusterIssuer` for `cert-manager`, (e.g., for Let's Encrypt).
- **K8sNamespaceScore**: Ensures a Kubernetes namespace exists.
- **K8sDeploymentScore**: Deploys a generic `Deployment` resource to Kubernetes.
- **K8sIngressScore**: Configures an `Ingress` resource for a service.
## Monitoring & Alerting
Scores for configuring observability, dashboards, and alerts.
- **ApplicationMonitoringScore**: A generic score to set up monitoring for an application.
- **ApplicationRHOBMonitoringScore**: A specialized score for setting up monitoring via the Red Hat Observability stack.
- **HelmPrometheusAlertingScore**: Configures Prometheus alerts via a Helm chart.
- **K8sPrometheusCRDAlertingScore**: Configures Prometheus alerts using the `PrometheusRule` CRD.
- **PrometheusAlertScore**: A generic score for creating a Prometheus alert.
- **RHOBAlertingScore**: Configures alerts specifically for the Red Hat Observability stack.
- **NtfyScore**: Configures alerts to be sent to a `ntfy.sh` server.
## Infrastructure & Networking (Bare Metal)
Low-level scores for managing physical hardware and network services.
- **DhcpScore**: Configures a DHCP server.
- **OKDDhcpScore**: A specialized DHCP configuration for the OKD bootstrap process.
- **OKDBootstrapDhcpScore**: Configures DHCP specifically for the bootstrap node.
- **DhcpHostBindingScore**: Creates a specific MAC-to-IP binding in the DHCP server.
- **DnsScore**: Configures a DNS server.
- **OKDDnsScore**: A specialized DNS configuration for the OKD cluster (e.g., `api.*`, `*.apps.*`).
- **StaticFilesHttpScore**: Serves a directory of static files (e.g., a documentation site) over HTTP.
- **TftpScore**: Configures a TFTP server, typically for serving iPXE boot files.
- **IPxeMacBootFileScore**: Assigns a specific iPXE boot file to a MAC address in the TFTP server.
- **OKDIpxeScore**: A specialized score for generating the iPXE boot scripts for OKD.
- **OPNsenseShellCommandScore**: Executes a shell command on an OPNsense firewall.
## Infrastructure & Networking (Cluster)
Network services that run inside the cluster or as part of the topology.
- **LoadBalancerScore**: Configures a general-purpose load balancer.
- **OKDLoadBalancerScore**: Configures the high-availability load balancers for the OKD API and ingress.
- **OKDBootstrapLoadBalancerScore**: Configures the load balancer specifically for the bootstrap-time API endpoint.
- **K8sIngressScore**: Configures an Ingress controller or resource.
- [HighAvailabilityHostNetworkScore](../../harmony/src/modules/okd/host_network.rs): Configures network bonds on a host and the corresponding port-channels on the switch stack for high-availability.
## Tenant Management
Scores for managing multi-tenancy within a cluster.
- **TenantScore**: Creates a new tenant (e.g., a namespace, quotas, network policies).
- **TenantCredentialScore**: Generates and provisions credentials for a new tenant.
## Utility
Helper scores for discovery and inspection.
- **LaunchDiscoverInventoryAgentScore**: Launches the agent responsible for the `OKDSetup01InventoryScore`.
- **DiscoverHostForRoleScore**: A utility score to find a host matching a specific role in the inventory.
- **InspectInventoryScore**: Dumps the discovered inventory for inspection.

View File

@@ -1,59 +0,0 @@
# Topologies Catalog
A `Topology` is the logical representation of your infrastructure and its `Capabilities`. You select a `Topology` in your Harmony project to define _where_ your `Scores` will be applied.
<!--toc:start-->
- [Topologies Catalog](#topologies-catalog)
- [HAClusterTopology](#haclustertopology)
- [K8sAnywhereTopology](#k8sanywheretopology)
<!--toc:end-->
### HAClusterTopology
- **`HAClusterTopology::autoload()`**
This `Topology` represents a high-availability, bare-metal cluster. It is designed for production-grade deployments like OKD.
It models an environment consisting of:
- At least 3 cluster nodes (for control plane/workers)
- 2 redundant firewalls (e.g., OPNsense)
- 2 redundant network switches
**Provided Capabilities:**
This topology provides a rich set of capabilities required for bare-metal provisioning and cluster management, including:
- `K8sClient` (once the cluster is bootstrapped)
- `DnsServer`
- `LoadBalancer`
- `DhcpServer`
- `TftpServer`
- `Router` (via the firewalls)
- `Switch`
- `NetworkManager` (for host-level network config)
---
### K8sAnywhereTopology
- **`K8sAnywhereTopology::from_env()`**
This `Topology` is designed for development and application deployment. It provides a simple, abstract way to deploy to _any_ Kubernetes cluster.
**How it works:**
1. By default (`from_env()` with no env vars), it automatically provisions a **local K3D (k3s-in-docker) cluster** on your machine. This is perfect for local development and testing.
2. If you provide a `KUBECONFIG` environment variable, it will instead connect to that **existing Kubernetes cluster** (e.g., your staging or production OKD cluster).
This allows you to use the _exact same code_ to deploy your application locally as you do to deploy it to production.
**Provided Capabilities:**
- `K8sClient`
- `HelmCommand`
- `TenantManager`
- `Ingress`
- `Monitoring`
- ...and more.

View File

@@ -1,40 +0,0 @@
# Core Concepts
Harmony's design is based on a few key concepts. Understanding them is the key to unlocking the framework's power.
### 1. Score
- **What it is:** A **Score** is a declarative description of a desired state. It's a "resource" that defines _what_ you want to achieve, not _how_ to do it.
- **Example:** `ApplicationScore` declares "I want this web application to be running and monitored."
### 2. Topology
- **What it is:** A **Topology** is the logical representation of your infrastructure and its abilities. It's the "where" your Scores will be applied.
- **Key Job:** A Topology's most important job is to expose which `Capabilities` it supports.
- **Example:** `HAClusterTopology` represents a bare-metal cluster and exposes `Capabilities` like `NetworkManager` and `Switch`. `K8sAnywhereTopology` represents a Kubernetes cluster and exposes the `K8sClient` `Capability`.
### 3. Capability
- **What it is:** A **Capability** is a specific feature or API that a `Topology` offers. It's the "how" a `Topology` can fulfill a `Score`'s request.
- **Example:** The `K8sClient` capability offers a way to interact with a Kubernetes API. The `Switch` capability offers a way to configure a physical network switch.
### 4. Interpret
- **What it is:** An **Interpret** is the execution logic that makes a `Score` a reality. It's the "glue" that connects the _desired state_ (`Score`) to the _environment's abilities_ (`Topology`'s `Capabilities`).
- **How it works:** When you apply a `Score`, Harmony finds the matching `Interpret` for your `Topology`. This `Interpret` then uses the `Capabilities` provided by the `Topology` to execute the necessary steps.
### 5. Inventory
- **What it is:** An **Inventory** is the physical material (the "what") used in a cluster. This is most relevant for bare-metal or on-premise topologies.
- **Example:** A list of nodes with their roles (control plane, worker), CPU, RAM, and network interfaces. For the `K8sAnywhereTopology`, the inventory might be empty or autoloaded, as the infrastructure is more abstract.
---
### How They Work Together (The Compile-Time Check)
1. You **write a `Score`** (e.g., `ApplicationScore`).
2. Your `Score`'s `Interpret` logic requires certain **`Capabilities`** (e.g., `K8sClient` and `Ingress`).
3. You choose a **`Topology`** to run it on (e.g., `HAClusterTopology`).
4. **At compile-time**, Harmony checks: "Does `HAClusterTopology` provide the `K8sClient` and `Ingress` capabilities that `ApplicationScore` needs?"
- **If Yes:** Your code compiles. You can be confident it will run.
- **If No:** The compiler gives you an error. You've just prevented a "config-is-valid-but-platform-is-wrong" runtime error before you even deployed.

View File

@@ -1,42 +0,0 @@
# Getting Started Guide
Welcome to Harmony! This guide will walk you through installing the Harmony framework, setting up a new project, and deploying your first application.
We will build and deploy the "Rust Web App" example, which automatically:
1. Provisions a local K3D (Kubernetes in Docker) cluster.
2. Deploys a sample Rust web application.
3. Sets up monitoring for the application.
## Prerequisites
Before you begin, you'll need a few tools installed on your system:
- **Rust & Cargo:** [Install Rust](https://www.rust-lang.org/tools/install)
- **Docker:** [Install Docker](https://docs.docker.com/get-docker/) (Required for the K3D local cluster)
- **kubectl:** [Install kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/) (For inspecting the cluster)
## 1. Install Harmony
First, clone the Harmony repository and build the project. This gives you the `harmony` CLI and all the core libraries.
```bash
# Clone the main repository
git clone https://git.nationtech.io/nationtech/harmony
cd harmony
# Build the project (this may take a few minutes)
cargo build --release
```
...
## Next Steps
Congratulations, you've just deployed an application using true infrastructure-as-code!
From here, you can:
- [Explore the Catalogs](../catalogs/README.md): See what other [Scores](../catalogs/scores.md) and [Topologies](../catalogs/topologies.md) are available.
- [Read the Use Cases](../use-cases/README.md): Check out the [OKD on Bare Metal](./use-cases/okd-on-bare-metal.md) guide for a more advanced scenario.
- [Write your own Score](../guides/writing-a-score.md): Dive into the [Developer Guide](./guides/developer-guide.md) to start building your own components.

View File

@@ -122,6 +122,7 @@ EOF
fi
echo "Creating OPNsense VM using serial image..."
virt-install \
--connect "${CONNECT_URI}" \
--name "${VM_OPN}" \
@@ -131,11 +132,12 @@ EOF
--os-variant "${OS_VARIANT_OPN}" \
--graphics none \
--noautoconsole \
--disk path="${disk_opn}",device=disk,bus=virtio,boot.order=1 \
--disk path="${OPN_IMG_PATH}",device=disk,bus=usb,readonly=on,boot.order=2 \
--import \
--disk path="${OPN_IMG_PATH}",device=disk,bus=sata,boot.order=1 \
--disk path="${disk_opn}",device=disk,bus=virtio,boot.order=2 \
--network network=default,model=virtio \
--network network="${NET_HARMONYLAN}",model=virtio \
--boot uefi,menu=on
--boot hd,menu=on
echo "OPNsense VM created. Connect with: sudo virsh console ${VM_OPN}"
echo "The VM will boot from the serial installation image."

View File

@@ -17,5 +17,3 @@ harmony_secret = { path = "../../harmony_secret" }
log = { workspace = true }
env_logger = { workspace = true }
url = { workspace = true }
serde = { workspace = true }
brocade = { path = "../../brocade" }

View File

@@ -1,15 +1,14 @@
use std::{
net::{IpAddr, Ipv4Addr},
sync::{Arc, OnceLock},
sync::Arc,
};
use brocade::BrocadeOptions;
use cidr::Ipv4Cidr;
use harmony::{
config::secret::SshKeyPair,
data::{FileContent, FilePath},
hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
infra::opnsense::OPNSenseManagementInterface,
inventory::Inventory,
modules::{
http::StaticFilesHttpScore,
@@ -23,9 +22,8 @@ use harmony::{
topology::{LogicalHost, UnmanagedRouter},
};
use harmony_macros::{ip, mac_address};
use harmony_secret::{Secret, SecretManager};
use harmony_secret::SecretManager;
use harmony_types::net::Url;
use serde::{Deserialize, Serialize};
#[tokio::main]
async fn main() {
@@ -34,26 +32,6 @@ async fn main() {
name: String::from("fw0"),
};
let switch_auth = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
.await
.expect("Failed to get credentials");
let switches: Vec<IpAddr> = vec![ip!("192.168.33.101")];
let brocade_options = Some(BrocadeOptions {
dry_run: *harmony::config::DRY_RUN,
..Default::default()
});
let switch_client = BrocadeSwitchClient::init(
&switches,
&switch_auth.username,
&switch_auth.password,
brocade_options,
)
.await
.expect("Failed to connect to switch");
let switch_client = Arc::new(switch_client);
let opnsense = Arc::new(
harmony::infra::opnsense::OPNSenseFirewall::new(firewall, None, "root", "opnsense").await,
);
@@ -61,7 +39,6 @@ async fn main() {
let gateway_ipv4 = Ipv4Addr::new(192, 168, 33, 1);
let gateway_ip = IpAddr::V4(gateway_ipv4);
let topology = harmony::topology::HAClusterTopology {
kubeconfig: None,
domain_name: "ncd0.harmony.mcd".to_string(), // TODO this must be set manually correctly
// when setting up the opnsense firewall
router: Arc::new(UnmanagedRouter::new(
@@ -106,8 +83,7 @@ async fn main() {
name: "wk2".to_string(),
},
],
switch_client: switch_client.clone(),
network_manager: OnceLock::new(),
switch: vec![],
};
let inventory = Inventory {
@@ -190,9 +166,3 @@ async fn main() {
.await
.unwrap();
}
#[derive(Secret, Serialize, Deserialize, Debug)]
pub struct BrocadeSwitchAuth {
pub username: String,
pub password: String,
}

View File

@@ -19,4 +19,3 @@ log = { workspace = true }
env_logger = { workspace = true }
url = { workspace = true }
serde.workspace = true
brocade = { path = "../../brocade" }

View File

@@ -1,18 +1,14 @@
use brocade::BrocadeOptions;
use cidr::Ipv4Cidr;
use harmony::{
hardware::{Location, SwitchGroup},
infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
infra::opnsense::OPNSenseManagementInterface,
inventory::Inventory,
topology::{HAClusterTopology, LogicalHost, UnmanagedRouter},
};
use harmony_macros::{ip, ipv4};
use harmony_secret::{Secret, SecretManager};
use serde::{Deserialize, Serialize};
use std::{
net::IpAddr,
sync::{Arc, OnceLock},
};
use std::{net::IpAddr, sync::Arc};
#[derive(Secret, Serialize, Deserialize, Debug, PartialEq)]
struct OPNSenseFirewallConfig {
@@ -26,26 +22,6 @@ pub async fn get_topology() -> HAClusterTopology {
name: String::from("opnsense-1"),
};
let switch_auth = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
.await
.expect("Failed to get credentials");
let switches: Vec<IpAddr> = vec![ip!("192.168.1.101")]; // TODO: Adjust me
let brocade_options = Some(BrocadeOptions {
dry_run: *harmony::config::DRY_RUN,
..Default::default()
});
let switch_client = BrocadeSwitchClient::init(
&switches,
&switch_auth.username,
&switch_auth.password,
brocade_options,
)
.await
.expect("Failed to connect to switch");
let switch_client = Arc::new(switch_client);
let config = SecretManager::get_or_prompt::<OPNSenseFirewallConfig>().await;
let config = config.unwrap();
@@ -62,7 +38,6 @@ pub async fn get_topology() -> HAClusterTopology {
let gateway_ipv4 = ipv4!("192.168.1.1");
let gateway_ip = IpAddr::V4(gateway_ipv4);
harmony::topology::HAClusterTopology {
kubeconfig: None,
domain_name: "demo.harmony.mcd".to_string(),
router: Arc::new(UnmanagedRouter::new(
gateway_ip,
@@ -83,8 +58,7 @@ pub async fn get_topology() -> HAClusterTopology {
name: "bootstrap".to_string(),
},
workers: vec![],
switch_client: switch_client.clone(),
network_manager: OnceLock::new(),
switch: vec![],
}
}
@@ -101,9 +75,3 @@ pub fn get_inventory() -> Inventory {
control_plane_host: vec![],
}
}
#[derive(Secret, Serialize, Deserialize, Debug)]
pub struct BrocadeSwitchAuth {
pub username: String,
pub password: String,
}

View File

@@ -19,4 +19,3 @@ log = { workspace = true }
env_logger = { workspace = true }
url = { workspace = true }
serde.workspace = true
brocade = { path = "../../brocade" }

View File

@@ -1,19 +1,14 @@
use brocade::BrocadeOptions;
use cidr::Ipv4Cidr;
use harmony::{
config::secret::OPNSenseFirewallCredentials,
hardware::{Location, SwitchGroup},
infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
infra::opnsense::OPNSenseManagementInterface,
inventory::Inventory,
topology::{HAClusterTopology, LogicalHost, UnmanagedRouter},
};
use harmony_macros::{ip, ipv4};
use harmony_secret::{Secret, SecretManager};
use serde::{Deserialize, Serialize};
use std::{
net::IpAddr,
sync::{Arc, OnceLock},
};
use harmony_secret::SecretManager;
use std::{net::IpAddr, sync::Arc};
pub async fn get_topology() -> HAClusterTopology {
let firewall = harmony::topology::LogicalHost {
@@ -21,26 +16,6 @@ pub async fn get_topology() -> HAClusterTopology {
name: String::from("opnsense-1"),
};
let switch_auth = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
.await
.expect("Failed to get credentials");
let switches: Vec<IpAddr> = vec![ip!("192.168.1.101")]; // TODO: Adjust me
let brocade_options = Some(BrocadeOptions {
dry_run: *harmony::config::DRY_RUN,
..Default::default()
});
let switch_client = BrocadeSwitchClient::init(
&switches,
&switch_auth.username,
&switch_auth.password,
brocade_options,
)
.await
.expect("Failed to connect to switch");
let switch_client = Arc::new(switch_client);
let config = SecretManager::get_or_prompt::<OPNSenseFirewallCredentials>().await;
let config = config.unwrap();
@@ -57,7 +32,6 @@ pub async fn get_topology() -> HAClusterTopology {
let gateway_ipv4 = ipv4!("192.168.1.1");
let gateway_ip = IpAddr::V4(gateway_ipv4);
harmony::topology::HAClusterTopology {
kubeconfig: None,
domain_name: "demo.harmony.mcd".to_string(),
router: Arc::new(UnmanagedRouter::new(
gateway_ip,
@@ -78,8 +52,7 @@ pub async fn get_topology() -> HAClusterTopology {
name: "cp0".to_string(),
},
workers: vec![],
switch_client: switch_client.clone(),
network_manager: OnceLock::new(),
switch: vec![],
}
}
@@ -96,9 +69,3 @@ pub fn get_inventory() -> Inventory {
control_plane_host: vec![],
}
}
#[derive(Secret, Serialize, Deserialize, Debug)]
pub struct BrocadeSwitchAuth {
pub username: String,
pub password: String,
}

View File

@@ -16,6 +16,3 @@ harmony_macros = { path = "../../harmony_macros" }
log = { workspace = true }
env_logger = { workspace = true }
url = { workspace = true }
harmony_secret = { path = "../../harmony_secret" }
brocade = { path = "../../brocade" }
serde = { workspace = true }

View File

@@ -1,13 +1,12 @@
use std::{
net::{IpAddr, Ipv4Addr},
sync::{Arc, OnceLock},
sync::Arc,
};
use brocade::BrocadeOptions;
use cidr::Ipv4Cidr;
use harmony::{
hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
infra::{brocade::BrocadeSwitchClient, opnsense::OPNSenseManagementInterface},
infra::opnsense::OPNSenseManagementInterface,
inventory::Inventory,
modules::{
dummy::{ErrorScore, PanicScore, SuccessScore},
@@ -19,9 +18,7 @@ use harmony::{
topology::{LogicalHost, UnmanagedRouter},
};
use harmony_macros::{ip, mac_address};
use harmony_secret::{Secret, SecretManager};
use harmony_types::net::Url;
use serde::{Deserialize, Serialize};
#[tokio::main]
async fn main() {
@@ -30,26 +27,6 @@ async fn main() {
name: String::from("opnsense-1"),
};
let switch_auth = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
.await
.expect("Failed to get credentials");
let switches: Vec<IpAddr> = vec![ip!("192.168.5.101")]; // TODO: Adjust me
let brocade_options = Some(BrocadeOptions {
dry_run: *harmony::config::DRY_RUN,
..Default::default()
});
let switch_client = BrocadeSwitchClient::init(
&switches,
&switch_auth.username,
&switch_auth.password,
brocade_options,
)
.await
.expect("Failed to connect to switch");
let switch_client = Arc::new(switch_client);
let opnsense = Arc::new(
harmony::infra::opnsense::OPNSenseFirewall::new(firewall, None, "root", "opnsense").await,
);
@@ -57,7 +34,6 @@ async fn main() {
let gateway_ipv4 = Ipv4Addr::new(10, 100, 8, 1);
let gateway_ip = IpAddr::V4(gateway_ipv4);
let topology = harmony::topology::HAClusterTopology {
kubeconfig: None,
domain_name: "demo.harmony.mcd".to_string(),
router: Arc::new(UnmanagedRouter::new(
gateway_ip,
@@ -78,8 +54,7 @@ async fn main() {
name: "cp0".to_string(),
},
workers: vec![],
switch_client: switch_client.clone(),
network_manager: OnceLock::new(),
switch: vec![],
};
let inventory = Inventory {
@@ -134,9 +109,3 @@ async fn main() {
.await
.unwrap();
}
#[derive(Secret, Serialize, Deserialize, Debug)]
pub struct BrocadeSwitchAuth {
pub username: String,
pub password: String,
}

View File

@@ -5,10 +5,6 @@ version.workspace = true
readme.workspace = true
license.workspace = true
[[example]]
name = "try_rust_webapp"
path = "src/main.rs"
[dependencies]
harmony = { path = "../../harmony" }
harmony_cli = { path = "../../harmony_cli" }

View File

@@ -3,7 +3,7 @@ use harmony::{
modules::{
application::{
ApplicationScore, RustWebFramework, RustWebapp,
features::{Monitoring, PackagingDeployment},
features::{PackagingDeployment, rhob_monitoring::Monitoring},
},
monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
},

View File

@@ -1,25 +1,37 @@
use async_trait::async_trait;
use brocade::BrocadeOptions;
use harmony_macros::ip;
use harmony_secret::SecretManager;
use harmony_types::{
id::Id,
net::{MacAddress, Url},
switch::PortLocation,
};
use k8s_openapi::api::core::v1::Namespace;
use kube::api::ObjectMeta;
use log::debug;
use log::info;
use crate::infra::network_manager::OpenShiftNmStateNetworkManager;
use crate::data::FileContent;
use crate::executors::ExecutorError;
use crate::hardware::PhysicalHost;
use crate::infra::brocade::BrocadeSwitchAuth;
use crate::infra::brocade::BrocadeSwitchClient;
use crate::modules::okd::crd::{
InstallPlanApproval, OperatorGroup, OperatorGroupSpec, Subscription, SubscriptionSpec,
nmstate::{self, NMState, NodeNetworkConfigurationPolicy, NodeNetworkConfigurationPolicySpec},
};
use crate::topology::PxeOptions;
use crate::{data::FileContent, executors::ExecutorError};
use super::{
DHCPStaticEntry, DhcpServer, DnsRecord, DnsRecordType, DnsServer, Firewall, HostNetworkConfig,
HttpServer, IpAddress, K8sclient, LoadBalancer, LoadBalancerService, LogicalHost, NetworkError,
NetworkManager, PreparationError, PreparationOutcome, Router, Switch, SwitchClient,
SwitchError, TftpServer, Topology, k8s::K8sClient,
HttpServer, IpAddress, K8sclient, LoadBalancer, LoadBalancerService, LogicalHost,
PreparationError, PreparationOutcome, Router, Switch, SwitchClient, SwitchError, TftpServer,
Topology, k8s::K8sClient,
};
use std::sync::{Arc, OnceLock};
use std::collections::BTreeMap;
use std::net::IpAddr;
use std::sync::Arc;
#[derive(Debug, Clone)]
pub struct HAClusterTopology {
@@ -31,12 +43,10 @@ pub struct HAClusterTopology {
pub tftp_server: Arc<dyn TftpServer>,
pub http_server: Arc<dyn HttpServer>,
pub dns_server: Arc<dyn DnsServer>,
pub switch_client: Arc<dyn SwitchClient>,
pub bootstrap_host: LogicalHost,
pub control_plane: Vec<LogicalHost>,
pub workers: Vec<LogicalHost>,
pub kubeconfig: Option<String>,
pub network_manager: OnceLock<Arc<dyn NetworkManager>>,
pub switch: Vec<LogicalHost>,
}
#[async_trait]
@@ -55,17 +65,9 @@ impl Topology for HAClusterTopology {
#[async_trait]
impl K8sclient for HAClusterTopology {
async fn k8s_client(&self) -> Result<Arc<K8sClient>, String> {
match &self.kubeconfig {
None => Ok(Arc::new(
Ok(Arc::new(
K8sClient::try_default().await.map_err(|e| e.to_string())?,
)),
Some(kubeconfig) => {
let Some(client) = K8sClient::from_kubeconfig(kubeconfig).await else {
return Err("Failed to create k8s client".to_string());
};
Ok(Arc::new(client))
}
}
))
}
}
@@ -90,12 +92,229 @@ impl HAClusterTopology {
.to_string()
}
pub async fn network_manager(&self) -> &dyn NetworkManager {
let k8s_client = self.k8s_client().await.unwrap();
async fn ensure_nmstate_operator_installed(&self) -> Result<(), String> {
// FIXME: Find a way to check nmstate is already available (get pod -n openshift-nmstate)
debug!("Installing NMState operator...");
let k8s_client = self.k8s_client().await?;
self.network_manager
.get_or_init(|| Arc::new(OpenShiftNmStateNetworkManager::new(k8s_client.clone())))
.as_ref()
let nmstate_namespace = Namespace {
metadata: ObjectMeta {
name: Some("openshift-nmstate".to_string()),
finalizers: Some(vec!["kubernetes".to_string()]),
..Default::default()
},
..Default::default()
};
debug!("Creating NMState namespace: {nmstate_namespace:#?}");
k8s_client
.apply(&nmstate_namespace, None)
.await
.map_err(|e| e.to_string())?;
let nmstate_operator_group = OperatorGroup {
metadata: ObjectMeta {
name: Some("openshift-nmstate".to_string()),
namespace: Some("openshift-nmstate".to_string()),
..Default::default()
},
spec: OperatorGroupSpec {
target_namespaces: vec!["openshift-nmstate".to_string()],
},
};
debug!("Creating NMState operator group: {nmstate_operator_group:#?}");
k8s_client
.apply(&nmstate_operator_group, None)
.await
.map_err(|e| e.to_string())?;
let nmstate_subscription = Subscription {
metadata: ObjectMeta {
name: Some("kubernetes-nmstate-operator".to_string()),
namespace: Some("openshift-nmstate".to_string()),
..Default::default()
},
spec: SubscriptionSpec {
channel: Some("stable".to_string()),
install_plan_approval: Some(InstallPlanApproval::Automatic),
name: "kubernetes-nmstate-operator".to_string(),
source: "redhat-operators".to_string(),
source_namespace: "openshift-marketplace".to_string(),
},
};
debug!("Subscribing to NMState Operator: {nmstate_subscription:#?}");
k8s_client
.apply(&nmstate_subscription, None)
.await
.map_err(|e| e.to_string())?;
let nmstate = NMState {
metadata: ObjectMeta {
name: Some("nmstate".to_string()),
..Default::default()
},
..Default::default()
};
debug!("Creating NMState: {nmstate:#?}");
k8s_client
.apply(&nmstate, None)
.await
.map_err(|e| e.to_string())?;
Ok(())
}
fn get_next_bond_id(&self) -> u8 {
42 // FIXME: Find a better way to declare the bond id
}
async fn configure_bond(
&self,
host: &PhysicalHost,
config: &HostNetworkConfig,
) -> Result<(), SwitchError> {
self.ensure_nmstate_operator_installed()
.await
.map_err(|e| {
SwitchError::new(format!(
"Can't configure bond, NMState operator not available: {e}"
))
})?;
let bond_config = self.create_bond_configuration(host, config);
debug!("Configuring bond for host {host:?}: {bond_config:#?}");
self.k8s_client()
.await
.unwrap()
.apply(&bond_config, None)
.await
.unwrap();
todo!()
}
fn create_bond_configuration(
&self,
host: &PhysicalHost,
config: &HostNetworkConfig,
) -> NodeNetworkConfigurationPolicy {
let host_name = host.id.clone();
let bond_id = self.get_next_bond_id();
let bond_name = format!("bond{bond_id}");
let mut bond_mtu: Option<u32> = None;
let mut bond_mac_address: Option<String> = None;
let mut bond_ports = Vec::new();
let mut interfaces: Vec<nmstate::InterfaceSpec> = Vec::new();
for switch_port in &config.switch_ports {
let interface_name = switch_port.interface.name.clone();
interfaces.push(nmstate::InterfaceSpec {
name: interface_name.clone(),
description: Some(format!("Member of bond {bond_name}")),
r#type: "ethernet".to_string(),
state: "up".to_string(),
mtu: Some(switch_port.interface.mtu),
mac_address: Some(switch_port.interface.mac_address.to_string()),
ipv4: Some(nmstate::IpStackSpec {
enabled: Some(false),
..Default::default()
}),
ipv6: Some(nmstate::IpStackSpec {
enabled: Some(false),
..Default::default()
}),
link_aggregation: None,
..Default::default()
});
bond_ports.push(interface_name);
// Use the first port's details for the bond mtu and mac address
if bond_mtu.is_none() {
bond_mtu = Some(switch_port.interface.mtu);
}
if bond_mac_address.is_none() {
bond_mac_address = Some(switch_port.interface.mac_address.to_string());
}
}
interfaces.push(nmstate::InterfaceSpec {
name: bond_name.clone(),
description: Some(format!("Network bond for host {host_name}")),
r#type: "bond".to_string(),
state: "up".to_string(),
mtu: bond_mtu,
mac_address: bond_mac_address,
ipv4: Some(nmstate::IpStackSpec {
dhcp: Some(true),
enabled: Some(true),
..Default::default()
}),
ipv6: Some(nmstate::IpStackSpec {
dhcp: Some(true),
autoconf: Some(true),
enabled: Some(true),
..Default::default()
}),
link_aggregation: Some(nmstate::BondSpec {
mode: "802.3ad".to_string(),
ports: bond_ports,
..Default::default()
}),
..Default::default()
});
NodeNetworkConfigurationPolicy {
metadata: ObjectMeta {
name: Some(format!("{host_name}-bond-config")),
..Default::default()
},
spec: NodeNetworkConfigurationPolicySpec {
node_selector: Some(BTreeMap::from([(
"kubernetes.io/hostname".to_string(),
host_name.to_string(),
)])),
desired_state: nmstate::DesiredStateSpec { interfaces },
},
}
}
async fn get_switch_client(&self) -> Result<Box<dyn SwitchClient>, SwitchError> {
let auth = SecretManager::get_or_prompt::<BrocadeSwitchAuth>()
.await
.map_err(|e| SwitchError::new(format!("Failed to get credentials: {e}")))?;
// FIXME: We assume Brocade switches
let switches: Vec<IpAddr> = self.switch.iter().map(|s| s.ip).collect();
let brocade_options = Some(BrocadeOptions {
dry_run: *crate::config::DRY_RUN,
..Default::default()
});
let client =
BrocadeSwitchClient::init(&switches, &auth.username, &auth.password, brocade_options)
.await
.map_err(|e| SwitchError::new(format!("Failed to connect to switch: {e}")))?;
Ok(Box::new(client))
}
async fn configure_port_channel(
&self,
host: &PhysicalHost,
config: &HostNetworkConfig,
) -> Result<(), SwitchError> {
debug!("Configuring port channel: {config:#?}");
let client = self.get_switch_client().await?;
let switch_ports = config.switch_ports.iter().map(|s| s.port.clone()).collect();
client
.configure_port_channel(&format!("Harmony_{}", host.id), switch_ports)
.await
.map_err(|e| SwitchError::new(format!("Failed to configure switch: {e}")))?;
Ok(())
}
pub fn autoload() -> Self {
@@ -106,7 +325,6 @@ impl HAClusterTopology {
};
Self {
kubeconfig: None,
domain_name: "DummyTopology".to_string(),
router: dummy_infra.clone(),
load_balancer: dummy_infra.clone(),
@@ -115,11 +333,10 @@ impl HAClusterTopology {
tftp_server: dummy_infra.clone(),
http_server: dummy_infra.clone(),
dns_server: dummy_infra.clone(),
switch_client: dummy_infra.clone(),
bootstrap_host: dummy_host,
control_plane: vec![],
workers: vec![],
network_manager: OnceLock::new(),
switch: vec![],
}
}
}
@@ -277,40 +494,27 @@ impl HttpServer for HAClusterTopology {
#[async_trait]
impl Switch for HAClusterTopology {
async fn setup_switch(&self) -> Result<(), SwitchError> {
self.switch_client.setup().await.map(|_| ())
let client = self.get_switch_client().await?;
client.setup().await?;
Ok(())
}
async fn get_port_for_mac_address(
&self,
mac_address: &MacAddress,
) -> Result<Option<PortLocation>, SwitchError> {
self.switch_client.find_port(mac_address).await
let client = self.get_switch_client().await?;
let port = client.find_port(mac_address).await?;
Ok(port)
}
async fn configure_port_channel(&self, config: &HostNetworkConfig) -> Result<(), SwitchError> {
debug!("Configuring port channel: {config:#?}");
let switch_ports = config.switch_ports.iter().map(|s| s.port.clone()).collect();
self.switch_client
.configure_port_channel(&format!("Harmony_{}", config.host_id), switch_ports)
.await
.map_err(|e| SwitchError::new(format!("Failed to configure port-channel: {e}")))?;
Ok(())
}
}
#[async_trait]
impl NetworkManager for HAClusterTopology {
async fn ensure_network_manager_installed(&self) -> Result<(), NetworkError> {
self.network_manager()
.await
.ensure_network_manager_installed()
.await
}
async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), NetworkError> {
self.network_manager().await.configure_bond(config).await
async fn configure_host_network(
&self,
host: &PhysicalHost,
config: HostNetworkConfig,
) -> Result<(), SwitchError> {
self.configure_bond(host, &config).await?;
self.configure_port_channel(host, &config).await
}
}
@@ -500,25 +704,3 @@ impl DnsServer for DummyInfra {
unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
}
}
#[async_trait]
impl SwitchClient for DummyInfra {
async fn setup(&self) -> Result<(), SwitchError> {
unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
}
async fn find_port(
&self,
_mac_address: &MacAddress,
) -> Result<Option<PortLocation>, SwitchError> {
unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
}
async fn configure_port_channel(
&self,
_channel_name: &str,
_switch_ports: Vec<PortLocation>,
) -> Result<u8, SwitchError> {
unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
}
}

View File

@@ -3,20 +3,14 @@ use std::time::Duration;
use derive_new::new;
use k8s_openapi::{
ClusterResourceScope, NamespaceResourceScope,
api::{
apps::v1::Deployment,
core::v1::{Node, Pod, ServiceAccount},
},
api::{apps::v1::Deployment, core::v1::Pod},
apimachinery::pkg::version::Info,
};
use kube::{
Client, Config, Discovery, Error, Resource,
api::{
Api, AttachParams, DeleteParams, ListParams, ObjectList, Patch, PatchParams, ResourceExt,
},
api::{Api, AttachParams, DeleteParams, ListParams, Patch, PatchParams, ResourceExt},
config::{KubeConfigOptions, Kubeconfig},
core::ErrorResponse,
discovery::{ApiCapabilities, Scope},
error::DiscoveryError,
runtime::reflector::Lookup,
};
@@ -25,12 +19,11 @@ use kube::{
api::{ApiResource, GroupVersionKind},
runtime::wait::await_condition,
};
use log::{debug, error, trace, warn};
use log::{debug, error, info, trace};
use serde::{Serialize, de::DeserializeOwned};
use serde_json::json;
use serde_json::{Value, json};
use similar::TextDiff;
use tokio::{io::AsyncReadExt, time::sleep};
use url::Url;
#[derive(new, Clone)]
pub struct K8sClient {
@@ -64,11 +57,6 @@ impl K8sClient {
})
}
pub async fn service_account_api(&self, namespace: &str) -> Api<ServiceAccount> {
let api: Api<ServiceAccount> = Api::namespaced(self.client.clone(), namespace);
api
}
pub async fn get_apiserver_version(&self) -> Result<Info, Error> {
let client: Client = self.client.clone();
let version_info: Info = client.apiserver_version().await?;
@@ -92,8 +80,7 @@ impl K8sClient {
} else {
Api::default_namespaced_with(self.client.clone(), &gvk)
};
resource.get(name).await
Ok(resource.get(name).await?)
}
pub async fn get_deployment(
@@ -108,9 +95,8 @@ impl K8sClient {
debug!("getting default namespace deployment");
Api::default_namespaced(self.client.clone())
};
debug!("getting deployment {} in ns {}", name, namespace.unwrap());
deps.get_opt(name).await
Ok(deps.get_opt(name).await?)
}
pub async fn get_pod(&self, name: &str, namespace: Option<&str>) -> Result<Option<Pod>, Error> {
@@ -119,8 +105,7 @@ impl K8sClient {
} else {
Api::default_namespaced(self.client.clone())
};
pods.get_opt(name).await
Ok(pods.get_opt(name).await?)
}
pub async fn scale_deployment(
@@ -163,9 +148,9 @@ impl K8sClient {
pub async fn wait_until_deployment_ready(
&self,
name: &str,
name: String,
namespace: Option<&str>,
timeout: Option<Duration>,
timeout: Option<u64>,
) -> Result<(), String> {
let api: Api<Deployment>;
@@ -175,9 +160,9 @@ impl K8sClient {
api = Api::default_namespaced(self.client.clone());
}
let establish = await_condition(api, name, conditions::is_deployment_completed());
let timeout = timeout.unwrap_or(Duration::from_secs(120));
let res = tokio::time::timeout(timeout, establish).await;
let establish = await_condition(api, name.as_str(), conditions::is_deployment_completed());
let t = timeout.unwrap_or(300);
let res = tokio::time::timeout(std::time::Duration::from_secs(t), establish).await;
if res.is_ok() {
Ok(())
@@ -267,7 +252,7 @@ impl K8sClient {
if let Some(s) = status.status {
let mut stdout_buf = String::new();
if let Some(mut stdout) = process.stdout() {
if let Some(mut stdout) = process.stdout().take() {
stdout
.read_to_string(&mut stdout_buf)
.await
@@ -373,14 +358,14 @@ impl K8sClient {
Ok(current) => {
trace!("Received current value {current:#?}");
// The resource exists, so we calculate and display a diff.
println!("\nPerforming dry-run for resource: '{name}'");
println!("\nPerforming dry-run for resource: '{}'", name);
let mut current_yaml = serde_yaml::to_value(&current).unwrap_or_else(|_| {
panic!("Could not serialize current value : {current:#?}")
});
if current_yaml.is_mapping() && current_yaml.get("status").is_some() {
let map = current_yaml.as_mapping_mut().unwrap();
let removed = map.remove_entry("status");
trace!("Removed status {removed:?}");
trace!("Removed status {:?}", removed);
} else {
trace!(
"Did not find status entry for current object {}/{}",
@@ -409,14 +394,14 @@ impl K8sClient {
similar::ChangeTag::Insert => "+",
similar::ChangeTag::Equal => " ",
};
print!("{sign}{change}");
print!("{}{}", sign, change);
}
// In a dry run, we return the new resource state that would have been applied.
Ok(resource.clone())
}
Err(Error::Api(ErrorResponse { code: 404, .. })) => {
// The resource does not exist, so the "diff" is the entire new resource.
println!("\nPerforming dry-run for new resource: '{name}'");
println!("\nPerforming dry-run for new resource: '{}'", name);
println!(
"Resource does not exist. It would be created with the following content:"
);
@@ -425,14 +410,14 @@ impl K8sClient {
// Print each line of the new resource with a '+' prefix.
for line in new_yaml.lines() {
println!("+{line}");
println!("+{}", line);
}
// In a dry run, we return the new resource state that would have been created.
Ok(resource.clone())
}
Err(e) => {
// Another API error occurred.
error!("Failed to get resource '{name}': {e}");
error!("Failed to get resource '{}': {}", name, e);
Err(e)
}
}
@@ -447,7 +432,7 @@ impl K8sClient {
where
K: Resource + Clone + std::fmt::Debug + DeserializeOwned + serde::Serialize,
<K as Resource>::Scope: ApplyStrategy<K>,
<K as Resource>::DynamicType: Default,
<K as kube::Resource>::DynamicType: Default,
{
let mut result = Vec::new();
for r in resource.iter() {
@@ -512,7 +497,10 @@ impl K8sClient {
// 6. Apply the object to the cluster using Server-Side Apply.
// This will create the resource if it doesn't exist, or update it if it does.
println!("Applying '{name}' in namespace '{namespace}'...",);
println!(
"Applying Argo Application '{}' in namespace '{}'...",
name, namespace
);
let patch_params = PatchParams::apply("harmony"); // Use a unique field manager name
let result = api.patch(name, &patch_params, &Patch::Apply(&obj)).await?;
@@ -521,103 +509,7 @@ impl K8sClient {
Ok(())
}
/// Apply a resource from a URL
///
/// It is the equivalent of `kubectl apply -f <url>`
pub async fn apply_url(&self, url: Url, ns: Option<&str>) -> Result<(), Error> {
let patch_params = PatchParams::apply("harmony");
let discovery = kube::Discovery::new(self.client.clone()).run().await?;
let yaml = reqwest::get(url)
.await
.expect("Could not get URL")
.text()
.await
.expect("Could not get content from URL");
for doc in multidoc_deserialize(&yaml).expect("failed to parse YAML from file") {
let obj: DynamicObject =
serde_yaml::from_value(doc).expect("cannot apply without valid YAML");
let namespace = obj.metadata.namespace.as_deref().or(ns);
let type_meta = obj
.types
.as_ref()
.expect("cannot apply object without valid TypeMeta");
let gvk = GroupVersionKind::try_from(type_meta)
.expect("cannot apply object without valid GroupVersionKind");
let name = obj.name_any();
if let Some((ar, caps)) = discovery.resolve_gvk(&gvk) {
let api = get_dynamic_api(ar, caps, self.client.clone(), namespace, false);
trace!(
"Applying {}: \n{}",
gvk.kind,
serde_yaml::to_string(&obj).expect("Failed to serialize YAML")
);
let data: serde_json::Value =
serde_json::to_value(&obj).expect("Failed to serialize JSON");
let _r = api.patch(&name, &patch_params, &Patch::Apply(data)).await?;
debug!("applied {} {}", gvk.kind, name);
} else {
warn!("Cannot apply document for unknown {gvk:?}");
}
}
Ok(())
}
/// Gets a single named resource of a specific type `K`.
///
/// This function uses the `ApplyStrategy` trait to correctly determine
/// whether to look in a specific namespace or in the entire cluster.
///
/// Returns `Ok(None)` if the resource is not found (404).
pub async fn get_resource<K>(
&self,
name: &str,
namespace: Option<&str>,
) -> Result<Option<K>, Error>
where
K: Resource + Clone + std::fmt::Debug + DeserializeOwned,
<K as Resource>::Scope: ApplyStrategy<K>,
<K as kube::Resource>::DynamicType: Default,
{
let api: Api<K> =
<<K as Resource>::Scope as ApplyStrategy<K>>::get_api(&self.client, namespace);
api.get_opt(name).await
}
/// Lists all resources of a specific type `K`.
///
/// This function uses the `ApplyStrategy` trait to correctly determine
/// whether to list from a specific namespace or from the entire cluster.
pub async fn list_resources<K>(
&self,
namespace: Option<&str>,
list_params: Option<ListParams>,
) -> Result<ObjectList<K>, Error>
where
K: Resource + Clone + std::fmt::Debug + DeserializeOwned,
<K as Resource>::Scope: ApplyStrategy<K>,
<K as kube::Resource>::DynamicType: Default,
{
let api: Api<K> =
<<K as Resource>::Scope as ApplyStrategy<K>>::get_api(&self.client, namespace);
let list_params = list_params.unwrap_or_default();
api.list(&list_params).await
}
/// Fetches a list of all Nodes in the cluster.
pub async fn get_nodes(
&self,
list_params: Option<ListParams>,
) -> Result<ObjectList<Node>, Error> {
self.list_resources(None, list_params).await
}
pub async fn from_kubeconfig(path: &str) -> Option<K8sClient> {
pub(crate) async fn from_kubeconfig(path: &str) -> Option<K8sClient> {
let k = match Kubeconfig::read_from(path) {
Ok(k) => k,
Err(e) => {
@@ -636,31 +528,6 @@ impl K8sClient {
}
}
fn get_dynamic_api(
resource: ApiResource,
capabilities: ApiCapabilities,
client: Client,
ns: Option<&str>,
all: bool,
) -> Api<DynamicObject> {
if capabilities.scope == Scope::Cluster || all {
Api::all_with(client, &resource)
} else if let Some(namespace) = ns {
Api::namespaced_with(client, namespace, &resource)
} else {
Api::default_namespaced_with(client, &resource)
}
}
fn multidoc_deserialize(data: &str) -> Result<Vec<serde_yaml::Value>, serde_yaml::Error> {
use serde::Deserialize;
let mut docs = vec![];
for de in serde_yaml::Deserializer::from_str(data) {
docs.push(serde_yaml::Value::deserialize(de)?);
}
Ok(docs)
}
pub trait ApplyStrategy<K: Resource> {
fn get_api(client: &Client, ns: Option<&str>) -> Api<K>;
}

View File

@@ -1,12 +1,7 @@
use std::{collections::BTreeMap, process::Command, sync::Arc, time::Duration};
use std::{process::Command, sync::Arc};
use async_trait::async_trait;
use base64::{Engine, engine::general_purpose};
use k8s_openapi::api::{
core::v1::Secret,
rbac::v1::{ClusterRoleBinding, RoleRef, Subject},
};
use kube::api::{DynamicObject, GroupVersionKind, ObjectMeta};
use kube::api::GroupVersionKind;
use log::{debug, info, warn};
use serde::Serialize;
use tokio::sync::OnceCell;
@@ -17,26 +12,14 @@ use crate::{
inventory::Inventory,
modules::{
k3d::K3DInstallationScore,
k8s::ingress::{K8sIngressScore, PathType},
monitoring::{
grafana::{grafana::Grafana, helm::helm_grafana::grafana_helm_chart_score},
kube_prometheus::crd::{
monitoring::kube_prometheus::crd::{
crd_alertmanager_config::CRDPrometheus,
crd_grafana::{
Grafana as GrafanaCRD, GrafanaCom, GrafanaDashboard,
GrafanaDashboardDatasource, GrafanaDashboardSpec, GrafanaDatasource,
GrafanaDatasourceConfig, GrafanaDatasourceJsonData,
GrafanaDatasourceSecureJsonData, GrafanaDatasourceSpec, GrafanaSpec,
},
crd_prometheuses::LabelSelector,
prometheus_operator::prometheus_operator_helm_chart_score,
rhob_alertmanager_config::RHOBObservability,
service_monitor::ServiceMonitor,
},
},
prometheus::{
k8s_prometheus_alerting_score::K8sPrometheusCRDAlertingScore,
prometheus::PrometheusMonitoring, rhob_alerting_score::RHOBAlertingScore,
prometheus::PrometheusApplicationMonitoring, rhob_alerting_score::RHOBAlertingScore,
},
},
score::Score,
@@ -103,172 +86,41 @@ impl K8sclient for K8sAnywhereTopology {
}
#[async_trait]
impl Grafana for K8sAnywhereTopology {
async fn ensure_grafana_operator(
&self,
inventory: &Inventory,
) -> Result<PreparationOutcome, PreparationError> {
debug!("ensure grafana operator");
let client = self.k8s_client().await.unwrap();
let grafana_gvk = GroupVersionKind {
group: "grafana.integreatly.org".to_string(),
version: "v1beta1".to_string(),
kind: "Grafana".to_string(),
};
let name = "grafanas.grafana.integreatly.org";
let ns = "grafana";
let grafana_crd = client
.get_resource_json_value(name, Some(ns), &grafana_gvk)
.await;
match grafana_crd {
Ok(_) => {
return Ok(PreparationOutcome::Success {
details: "Found grafana CRDs in cluster".to_string(),
});
}
Err(_) => {
return self
.install_grafana_operator(inventory, Some("grafana"))
.await;
}
};
}
async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError> {
let ns = "grafana";
let mut label = BTreeMap::new();
label.insert("dashboards".to_string(), "grafana".to_string());
let label_selector = LabelSelector {
match_labels: label.clone(),
match_expressions: vec![],
};
let client = self.k8s_client().await?;
let grafana = self.build_grafana(ns, &label);
client.apply(&grafana, Some(ns)).await?;
//TODO change this to a ensure ready or something better than just a timeout
client
.wait_until_deployment_ready(
"grafana-grafana-deployment",
Some("grafana"),
Some(Duration::from_secs(30)),
)
.await?;
let sa_name = "grafana-grafana-sa";
let token_secret_name = "grafana-sa-token-secret";
let sa_token_secret = self.build_sa_token_secret(token_secret_name, sa_name, ns);
client.apply(&sa_token_secret, Some(ns)).await?;
let secret_gvk = GroupVersionKind {
group: "".to_string(),
version: "v1".to_string(),
kind: "Secret".to_string(),
};
let secret = client
.get_resource_json_value(token_secret_name, Some(ns), &secret_gvk)
.await?;
let token = format!(
"Bearer {}",
self.extract_and_normalize_token(&secret).unwrap()
);
debug!("creating grafana clusterrole binding");
let clusterrolebinding =
self.build_cluster_rolebinding(sa_name, "cluster-monitoring-view", ns);
client.apply(&clusterrolebinding, Some(ns)).await?;
debug!("creating grafana datasource crd");
let thanos_url = format!(
"https://{}",
self.get_domain("thanos-querier-openshift-monitoring")
.await
.unwrap()
);
let thanos_openshift_datasource = self.build_grafana_datasource(
"thanos-openshift-monitoring",
ns,
&label_selector,
&thanos_url,
&token,
);
client.apply(&thanos_openshift_datasource, Some(ns)).await?;
debug!("creating grafana dashboard crd");
let dashboard = self.build_grafana_dashboard(ns, &label_selector);
client.apply(&dashboard, Some(ns)).await?;
debug!("creating grafana ingress");
let grafana_ingress = self.build_grafana_ingress(ns).await;
grafana_ingress
.interpret(&Inventory::empty(), self)
.await
.map_err(|e| PreparationError::new(e.to_string()))?;
Ok(PreparationOutcome::Success {
details: "Installed grafana composants".to_string(),
})
}
}
#[async_trait]
impl PrometheusMonitoring<CRDPrometheus> for K8sAnywhereTopology {
impl PrometheusApplicationMonitoring<CRDPrometheus> for K8sAnywhereTopology {
async fn install_prometheus(
&self,
sender: &CRDPrometheus,
_inventory: &Inventory,
_receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
) -> Result<PreparationOutcome, PreparationError> {
let client = self.k8s_client().await?;
for monitor in sender.service_monitor.iter() {
client
.apply(monitor, Some(&sender.namespace))
.await
.map_err(|e| PreparationError::new(e.to_string()))?;
}
Ok(PreparationOutcome::Success {
details: "successfuly installed prometheus components".to_string(),
})
}
async fn ensure_prometheus_operator(
&self,
sender: &CRDPrometheus,
_inventory: &Inventory,
inventory: &Inventory,
receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
) -> Result<PreparationOutcome, PreparationError> {
let po_result = self.ensure_prometheus_operator(sender).await?;
match po_result {
PreparationOutcome::Success { details: _ } => {
debug!("Detected prometheus crds operator present in cluster.");
return Ok(po_result);
}
PreparationOutcome::Noop => {
if po_result == PreparationOutcome::Noop {
debug!("Skipping Prometheus CR installation due to missing operator.");
return Ok(po_result);
}
let result = self
.get_k8s_prometheus_application_score(sender.clone(), receivers)
.await
.interpret(inventory, self)
.await;
match result {
Ok(outcome) => match outcome.status {
InterpretStatus::SUCCESS => Ok(PreparationOutcome::Success {
details: outcome.message,
}),
InterpretStatus::NOOP => Ok(PreparationOutcome::Noop),
_ => Err(PreparationError::new(outcome.message)),
},
Err(err) => Err(PreparationError::new(err.to_string())),
}
}
}
#[async_trait]
impl PrometheusMonitoring<RHOBObservability> for K8sAnywhereTopology {
impl PrometheusApplicationMonitoring<RHOBObservability> for K8sAnywhereTopology {
async fn install_prometheus(
&self,
sender: &RHOBObservability,
@@ -302,14 +154,6 @@ impl PrometheusMonitoring<RHOBObservability> for K8sAnywhereTopology {
Err(err) => Err(PreparationError::new(err.to_string())),
}
}
async fn ensure_prometheus_operator(
&self,
sender: &RHOBObservability,
inventory: &Inventory,
) -> Result<PreparationOutcome, PreparationError> {
todo!()
}
}
impl Serialize for K8sAnywhereTopology {
@@ -371,180 +215,6 @@ impl K8sAnywhereTopology {
.await
}
fn extract_and_normalize_token(&self, secret: &DynamicObject) -> Option<String> {
let token_b64 = secret
.data
.get("token")
.or_else(|| secret.data.get("data").and_then(|d| d.get("token")))
.and_then(|v| v.as_str())?;
let bytes = general_purpose::STANDARD.decode(token_b64).ok()?;
let s = String::from_utf8(bytes).ok()?;
let cleaned = s
.trim_matches(|c: char| c.is_whitespace() || c == '\0')
.to_string();
Some(cleaned)
}
pub fn build_cluster_rolebinding(
&self,
service_account_name: &str,
clusterrole_name: &str,
ns: &str,
) -> ClusterRoleBinding {
ClusterRoleBinding {
metadata: ObjectMeta {
name: Some(format!("{}-view-binding", service_account_name)),
..Default::default()
},
role_ref: RoleRef {
api_group: "rbac.authorization.k8s.io".into(),
kind: "ClusterRole".into(),
name: clusterrole_name.into(),
},
subjects: Some(vec![Subject {
kind: "ServiceAccount".into(),
name: service_account_name.into(),
namespace: Some(ns.into()),
..Default::default()
}]),
}
}
pub fn build_sa_token_secret(
&self,
secret_name: &str,
service_account_name: &str,
ns: &str,
) -> Secret {
let mut annotations = BTreeMap::new();
annotations.insert(
"kubernetes.io/service-account.name".to_string(),
service_account_name.to_string(),
);
Secret {
metadata: ObjectMeta {
name: Some(secret_name.into()),
namespace: Some(ns.into()),
annotations: Some(annotations),
..Default::default()
},
type_: Some("kubernetes.io/service-account-token".to_string()),
..Default::default()
}
}
fn build_grafana_datasource(
&self,
name: &str,
ns: &str,
label_selector: &LabelSelector,
url: &str,
token: &str,
) -> GrafanaDatasource {
let mut json_data = BTreeMap::new();
json_data.insert("timeInterval".to_string(), "5s".to_string());
GrafanaDatasource {
metadata: ObjectMeta {
name: Some(name.to_string()),
namespace: Some(ns.to_string()),
..Default::default()
},
spec: GrafanaDatasourceSpec {
instance_selector: label_selector.clone(),
allow_cross_namespace_import: Some(true),
values_from: None,
datasource: GrafanaDatasourceConfig {
access: "proxy".to_string(),
name: name.to_string(),
r#type: "prometheus".to_string(),
url: url.to_string(),
database: None,
json_data: Some(GrafanaDatasourceJsonData {
time_interval: Some("60s".to_string()),
http_header_name1: Some("Authorization".to_string()),
tls_skip_verify: Some(true),
oauth_pass_thru: Some(true),
}),
secure_json_data: Some(GrafanaDatasourceSecureJsonData {
http_header_value1: Some(format!("Bearer {token}")),
}),
is_default: Some(false),
editable: Some(true),
},
},
}
}
fn build_grafana_dashboard(
&self,
ns: &str,
label_selector: &LabelSelector,
) -> GrafanaDashboard {
let graf_dashboard = GrafanaDashboard {
metadata: ObjectMeta {
name: Some(format!("grafana-dashboard-{}", ns)),
namespace: Some(ns.to_string()),
..Default::default()
},
spec: GrafanaDashboardSpec {
resync_period: Some("30s".to_string()),
instance_selector: label_selector.clone(),
datasources: Some(vec![GrafanaDashboardDatasource {
input_name: "DS_PROMETHEUS".to_string(),
datasource_name: "thanos-openshift-monitoring".to_string(),
}]),
json: None,
grafana_com: Some(GrafanaCom {
id: 17406,
revision: None,
}),
},
};
graf_dashboard
}
fn build_grafana(&self, ns: &str, labels: &BTreeMap<String, String>) -> GrafanaCRD {
let grafana = GrafanaCRD {
metadata: ObjectMeta {
name: Some(format!("grafana-{}", ns)),
namespace: Some(ns.to_string()),
labels: Some(labels.clone()),
..Default::default()
},
spec: GrafanaSpec {
config: None,
admin_user: None,
admin_password: None,
ingress: None,
persistence: None,
resources: None,
},
};
grafana
}
async fn build_grafana_ingress(&self, ns: &str) -> K8sIngressScore {
let domain = self.get_domain(&format!("grafana-{}", ns)).await.unwrap();
let name = format!("{}-grafana", ns);
let backend_service = format!("grafana-{}-service", ns);
K8sIngressScore {
name: fqdn::fqdn!(&name),
host: fqdn::fqdn!(&domain),
backend_service: fqdn::fqdn!(&backend_service),
port: 3000,
path: Some("/".to_string()),
path_type: Some(PathType::Prefix),
namespace: Some(fqdn::fqdn!(&ns)),
ingress_class_name: Some("openshift-default".to_string()),
}
}
async fn get_cluster_observability_operator_prometheus_application_score(
&self,
sender: RHOBObservability,
@@ -562,14 +232,13 @@ impl K8sAnywhereTopology {
&self,
sender: CRDPrometheus,
receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
service_monitors: Option<Vec<ServiceMonitor>>,
) -> K8sPrometheusCRDAlertingScore {
return K8sPrometheusCRDAlertingScore {
K8sPrometheusCRDAlertingScore {
sender,
receivers: receivers.unwrap_or_default(),
service_monitors: service_monitors.unwrap_or_default(),
service_monitors: vec![],
prometheus_rules: vec![],
};
}
}
async fn openshift_ingress_operator_available(&self) -> Result<(), PreparationError> {
@@ -837,30 +506,6 @@ impl K8sAnywhereTopology {
details: "prometheus operator present in cluster".into(),
})
}
async fn install_grafana_operator(
&self,
inventory: &Inventory,
ns: Option<&str>,
) -> Result<PreparationOutcome, PreparationError> {
let namespace = ns.unwrap_or("grafana");
info!("installing grafana operator in ns {namespace}");
let tenant = self.get_k8s_tenant_manager()?.get_tenant_config().await;
let mut namespace_scope = false;
if tenant.is_some() {
namespace_scope = true;
}
let _grafana_operator_score = grafana_helm_chart_score(namespace, namespace_scope)
.interpret(inventory, self)
.await
.map_err(|e| PreparationError::new(e.to_string()));
Ok(PreparationOutcome::Success {
details: format!(
"Successfully installed grafana operator in ns {}",
ns.unwrap()
),
})
}
}
#[derive(Clone, Debug)]

View File

@@ -1,21 +1,14 @@
use std::{
error::Error,
fmt::{self, Debug},
net::Ipv4Addr,
str::FromStr,
sync::Arc,
};
use std::{error::Error, net::Ipv4Addr, str::FromStr, sync::Arc};
use async_trait::async_trait;
use derive_new::new;
use harmony_types::{
id::Id,
net::{IpAddress, MacAddress},
switch::PortLocation,
};
use serde::Serialize;
use crate::executors::ExecutorError;
use crate::{executors::ExecutorError, hardware::PhysicalHost};
use super::{LogicalHost, k8s::K8sClient};
@@ -26,8 +19,8 @@ pub struct DHCPStaticEntry {
pub ip: Ipv4Addr,
}
impl fmt::Display for DHCPStaticEntry {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
impl std::fmt::Display for DHCPStaticEntry {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
let mac = self
.mac
.iter()
@@ -49,8 +42,8 @@ pub trait Firewall: Send + Sync {
fn get_host(&self) -> LogicalHost;
}
impl Debug for dyn Firewall {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
impl std::fmt::Debug for dyn Firewall {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_fmt(format_args!("Firewall {}", self.get_ip()))
}
}
@@ -72,7 +65,7 @@ pub struct PxeOptions {
}
#[async_trait]
pub trait DhcpServer: Send + Sync + Debug {
pub trait DhcpServer: Send + Sync + std::fmt::Debug {
async fn add_static_mapping(&self, entry: &DHCPStaticEntry) -> Result<(), ExecutorError>;
async fn remove_static_mapping(&self, mac: &MacAddress) -> Result<(), ExecutorError>;
async fn list_static_mappings(&self) -> Vec<(MacAddress, IpAddress)>;
@@ -111,8 +104,8 @@ pub trait DnsServer: Send + Sync {
}
}
impl Debug for dyn DnsServer {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
impl std::fmt::Debug for dyn DnsServer {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_fmt(format_args!("DnsServer {}", self.get_ip()))
}
}
@@ -148,8 +141,8 @@ pub enum DnsRecordType {
TXT,
}
impl fmt::Display for DnsRecordType {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
impl std::fmt::Display for DnsRecordType {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
DnsRecordType::A => write!(f, "A"),
DnsRecordType::AAAA => write!(f, "AAAA"),
@@ -183,37 +176,6 @@ impl FromStr for DnsRecordType {
}
}
#[async_trait]
pub trait NetworkManager: Debug + Send + Sync {
async fn ensure_network_manager_installed(&self) -> Result<(), NetworkError>;
async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), NetworkError>;
}
#[derive(Debug, Clone, new)]
pub struct NetworkError {
msg: String,
}
impl fmt::Display for NetworkError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.write_str(&self.msg)
}
}
impl Error for NetworkError {}
impl From<kube::Error> for NetworkError {
fn from(value: kube::Error) -> Self {
NetworkError::new(value.to_string())
}
}
impl From<String> for NetworkError {
fn from(value: String) -> Self {
NetworkError::new(value)
}
}
#[async_trait]
pub trait Switch: Send + Sync {
async fn setup_switch(&self) -> Result<(), SwitchError>;
@@ -223,12 +185,15 @@ pub trait Switch: Send + Sync {
mac_address: &MacAddress,
) -> Result<Option<PortLocation>, SwitchError>;
async fn configure_port_channel(&self, config: &HostNetworkConfig) -> Result<(), SwitchError>;
async fn configure_host_network(
&self,
host: &PhysicalHost,
config: HostNetworkConfig,
) -> Result<(), SwitchError>;
}
#[derive(Clone, Debug, PartialEq)]
pub struct HostNetworkConfig {
pub host_id: Id,
pub switch_ports: Vec<SwitchPort>,
}
@@ -251,8 +216,8 @@ pub struct SwitchError {
msg: String,
}
impl fmt::Display for SwitchError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
impl std::fmt::Display for SwitchError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_str(&self.msg)
}
}
@@ -260,7 +225,7 @@ impl fmt::Display for SwitchError {
impl Error for SwitchError {}
#[async_trait]
pub trait SwitchClient: Debug + Send + Sync {
pub trait SwitchClient: Send + Sync {
/// Executes essential, idempotent, one-time initial configuration steps.
///
/// This is an opiniated procedure that setups a switch to provide high availability

View File

@@ -21,7 +21,6 @@ pub struct AlertingInterpret<S: AlertSender> {
pub sender: S,
pub receivers: Vec<Box<dyn AlertReceiver<S>>>,
pub rules: Vec<Box<dyn AlertRule<S>>>,
pub scrape_targets: Option<Vec<Box<dyn ScrapeTarget<S>>>>,
}
#[async_trait]
@@ -31,7 +30,6 @@ impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInte
inventory: &Inventory,
topology: &T,
) -> Result<Outcome, InterpretError> {
debug!("hit sender configure for AlertingInterpret");
self.sender.configure(inventory, topology).await?;
for receiver in self.receivers.iter() {
receiver.install(&self.sender).await?;
@@ -40,12 +38,6 @@ impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInte
debug!("installing rule: {:#?}", rule);
rule.install(&self.sender).await?;
}
if let Some(targets) = &self.scrape_targets {
for target in targets.iter() {
debug!("installing scrape_target: {:#?}", target);
target.install(&self.sender).await?;
}
}
self.sender.ensure_installed(inventory, topology).await?;
Ok(Outcome::success(format!(
"successfully installed alert sender {}",
@@ -85,7 +77,6 @@ pub trait AlertRule<S: AlertSender>: std::fmt::Debug + Send + Sync {
}
#[async_trait]
pub trait ScrapeTarget<S: AlertSender>: std::fmt::Debug + Send + Sync {
async fn install(&self, sender: &S) -> Result<Outcome, InterpretError>;
fn clone_box(&self) -> Box<dyn ScrapeTarget<S>>;
pub trait ScrapeTarget<S: AlertSender> {
async fn install(&self, sender: &S) -> Result<(), InterpretError>;
}

View File

@@ -1,14 +1,15 @@
use async_trait::async_trait;
use brocade::{BrocadeClient, BrocadeOptions, InterSwitchLink, InterfaceStatus, PortOperatingMode};
use harmony_secret::Secret;
use harmony_types::{
net::{IpAddress, MacAddress},
switch::{PortDeclaration, PortLocation},
};
use option_ext::OptionExt;
use serde::{Deserialize, Serialize};
use crate::topology::{SwitchClient, SwitchError};
#[derive(Debug)]
pub struct BrocadeSwitchClient {
brocade: Box<dyn BrocadeClient + Send + Sync>,
}
@@ -113,6 +114,12 @@ impl SwitchClient for BrocadeSwitchClient {
}
}
#[derive(Secret, Serialize, Deserialize, Debug)]
pub struct BrocadeSwitchAuth {
pub username: String,
pub password: String,
}
#[cfg(test)]
mod tests {
use std::sync::{Arc, Mutex};
@@ -228,7 +235,7 @@ mod tests {
assert_that!(*configured_interfaces).is_empty();
}
#[derive(Debug, Clone)]
#[derive(Clone)]
struct FakeBrocadeClient {
stack_topology: Vec<InterSwitchLink>,
interfaces: Vec<InterfaceInfo>,

View File

@@ -11,7 +11,7 @@ pub struct InventoryRepositoryFactory;
impl InventoryRepositoryFactory {
pub async fn build() -> Result<Box<dyn InventoryRepository>, RepoError> {
Ok(Box::new(
SqliteInventoryRepository::new(&DATABASE_URL).await?,
SqliteInventoryRepository::new(&(*DATABASE_URL)).await?,
))
}
}

View File

@@ -1,182 +0,0 @@
use k8s_openapi::Resource as K8sResource;
use kube::api::{ApiResource, DynamicObject, GroupVersionKind};
use kube::core::TypeMeta;
use serde::Serialize;
use serde::de::DeserializeOwned;
use serde_json::Value;
/// Convert a typed Kubernetes resource `K` into a `DynamicObject`.
///
/// Requirements:
/// - `K` must be a k8s_openapi resource (provides static GVK via `Resource`).
/// - `K` must have standard Kubernetes shape (metadata + payload fields).
///
/// Notes:
/// - We set `types` (apiVersion/kind) and copy `metadata`.
/// - We place the remaining top-level fields into `obj.data` as JSON.
/// - Scope is not encoded on the object itself; you still need the corresponding
/// `DynamicResource` (derived from K::group/version/kind) when constructing an Api.
///
/// Example usage:
/// let dyn_obj = kube_resource_to_dynamic(secret)?;
/// let api: Api<DynamicObject> = Api::namespaced_with(client, "ns", &dr);
/// api.patch(&dyn_obj.name_any(), &PatchParams::apply("mgr"), &Patch::Apply(dyn_obj)).await?;
pub fn kube_resource_to_dynamic<K>(res: &K) -> Result<DynamicObject, String>
where
K: K8sResource + Serialize + DeserializeOwned,
{
// Serialize the typed resource to JSON so we can split metadata and payload
let mut v = serde_json::to_value(res).map_err(|e| format!("Failed to serialize : {e}"))?;
let obj = v
.as_object_mut()
.ok_or_else(|| "expected object JSON".to_string())?;
// Extract and parse metadata into kube::core::ObjectMeta
let metadata_value = obj
.remove("metadata")
.ok_or_else(|| "missing metadata".to_string())?;
let metadata: kube::core::ObjectMeta = serde_json::from_value(metadata_value)
.map_err(|e| format!("Failed to deserialize : {e}"))?;
// Name is required for DynamicObject::new; prefer metadata.name
let name = metadata
.name
.clone()
.ok_or_else(|| "metadata.name is required".to_string())?;
// Remaining fields (spec/status/data/etc.) become the dynamic payload
let payload = Value::Object(obj.clone());
// Construct the DynamicObject
let mut dyn_obj = DynamicObject::new(
&name,
&ApiResource::from_gvk(&GroupVersionKind::gvk(K::GROUP, K::VERSION, K::KIND)),
);
dyn_obj.types = Some(TypeMeta {
api_version: api_version_for::<K>(),
kind: K::KIND.into(),
});
// Preserve namespace/labels/annotations/etc.
dyn_obj.metadata = metadata;
// Attach payload
dyn_obj.data = payload;
Ok(dyn_obj)
}
/// Helper: compute apiVersion string ("group/version" or "v1" for core).
fn api_version_for<K>() -> String
where
K: K8sResource,
{
let group = K::GROUP;
let version = K::VERSION;
if group.is_empty() {
version.to_string() // core/v1 => "v1"
} else {
format!("{}/{}", group, version)
}
}
#[cfg(test)]
mod test {
use super::*;
use k8s_openapi::api::{
apps::v1::{Deployment, DeploymentSpec},
core::v1::{PodTemplateSpec, Secret},
};
use kube::api::ObjectMeta;
use pretty_assertions::assert_eq;
#[test]
fn secret_to_dynamic_roundtrip() {
// Create a sample Secret resource
let mut secret = Secret {
metadata: ObjectMeta {
name: Some("my-secret".to_string()),
..Default::default()
},
type_: Some("kubernetes.io/service-account-token".to_string()),
..Default::default()
};
// Convert to DynamicResource
let dynamic: DynamicObject =
kube_resource_to_dynamic(&secret).expect("Failed to convert Secret to DynamicResource");
// Serialize both the original and dynamic resources to Value
let original_value = serde_json::to_value(&secret).expect("Failed to serialize Secret");
let dynamic_value =
serde_json::to_value(&dynamic).expect("Failed to serialize DynamicResource");
// Assert that they are identical
assert_eq!(original_value, dynamic_value);
secret.metadata.namespace = Some("false".to_string());
let modified_value = serde_json::to_value(&secret).expect("Failed to serialize Secret");
assert_ne!(modified_value, dynamic_value);
}
#[test]
fn deployment_to_dynamic_roundtrip() {
// Create a sample Deployment with nested structures
let mut deployment = Deployment {
metadata: ObjectMeta {
name: Some("my-deployment".to_string()),
labels: Some({
let mut map = std::collections::BTreeMap::new();
map.insert("app".to_string(), "nginx".to_string());
map
}),
..Default::default()
},
spec: Some(DeploymentSpec {
replicas: Some(3),
selector: Default::default(),
template: PodTemplateSpec {
metadata: Some(ObjectMeta {
labels: Some({
let mut map = std::collections::BTreeMap::new();
map.insert("app".to_string(), "nginx".to_string());
map
}),
..Default::default()
}),
spec: Some(Default::default()), // PodSpec with empty containers for simplicity
},
..Default::default()
}),
..Default::default()
};
let dynamic = kube_resource_to_dynamic(&deployment).expect("Failed to convert Deployment");
let original_value = serde_json::to_value(&deployment).unwrap();
let dynamic_value = serde_json::to_value(&dynamic).unwrap();
assert_eq!(original_value, dynamic_value);
assert_eq!(
dynamic.data.get("spec").unwrap().get("replicas").unwrap(),
3
);
assert_eq!(
dynamic
.data
.get("spec")
.unwrap()
.get("template")
.unwrap()
.get("metadata")
.unwrap()
.get("labels")
.unwrap()
.get("app")
.unwrap()
.as_str()
.unwrap(),
"nginx".to_string()
);
}
}

View File

@@ -3,7 +3,5 @@ pub mod executors;
pub mod hp_ilo;
pub mod intel_amt;
pub mod inventory;
pub mod kube;
pub mod network_manager;
pub mod opnsense;
mod sqlx;

View File

@@ -1,257 +0,0 @@
use std::{
collections::{BTreeMap, HashSet},
sync::Arc,
};
use async_trait::async_trait;
use harmony_types::id::Id;
use k8s_openapi::api::core::v1::Node;
use kube::{
ResourceExt,
api::{ObjectList, ObjectMeta},
};
use log::{debug, info};
use crate::{
modules::okd::crd::nmstate,
topology::{HostNetworkConfig, NetworkError, NetworkManager, k8s::K8sClient},
};
pub struct OpenShiftNmStateNetworkManager {
k8s_client: Arc<K8sClient>,
}
impl std::fmt::Debug for OpenShiftNmStateNetworkManager {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_struct("OpenShiftNmStateNetworkManager").finish()
}
}
#[async_trait]
impl NetworkManager for OpenShiftNmStateNetworkManager {
async fn ensure_network_manager_installed(&self) -> Result<(), NetworkError> {
debug!("Installing NMState controller...");
self.k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/nmstate.io_nmstates.yaml
").unwrap(), Some("nmstate"))
.await?;
debug!("Creating NMState namespace...");
self.k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/namespace.yaml
").unwrap(), Some("nmstate"))
.await?;
debug!("Creating NMState service account...");
self.k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/service_account.yaml
").unwrap(), Some("nmstate"))
.await?;
debug!("Creating NMState role...");
self.k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/role.yaml
").unwrap(), Some("nmstate"))
.await?;
debug!("Creating NMState role binding...");
self.k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/role_binding.yaml
").unwrap(), Some("nmstate"))
.await?;
debug!("Creating NMState operator...");
self.k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/operator.yaml
").unwrap(), Some("nmstate"))
.await?;
self.k8s_client
.wait_until_deployment_ready("nmstate-operator", Some("nmstate"), None)
.await?;
let nmstate = nmstate::NMState {
metadata: ObjectMeta {
name: Some("nmstate".to_string()),
..Default::default()
},
..Default::default()
};
debug!(
"Creating NMState:\n{}",
serde_yaml::to_string(&nmstate).unwrap()
);
self.k8s_client.apply(&nmstate, None).await?;
Ok(())
}
async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), NetworkError> {
let hostname = self.get_hostname(&config.host_id).await.map_err(|e| {
NetworkError::new(format!(
"Can't configure bond, can't get hostname for host '{}': {e}",
config.host_id
))
})?;
let bond_id = self.get_next_bond_id(&hostname).await.map_err(|e| {
NetworkError::new(format!(
"Can't configure bond, can't get an available bond id for host '{}': {e}",
config.host_id
))
})?;
let bond_config = self.create_bond_configuration(&hostname, &bond_id, config);
debug!(
"Applying NMState bond config for host {}:\n{}",
config.host_id,
serde_yaml::to_string(&bond_config).unwrap(),
);
self.k8s_client
.apply(&bond_config, None)
.await
.map_err(|e| NetworkError::new(format!("Failed to configure bond: {e}")))?;
Ok(())
}
}
impl OpenShiftNmStateNetworkManager {
pub fn new(k8s_client: Arc<K8sClient>) -> Self {
Self { k8s_client }
}
fn create_bond_configuration(
&self,
host: &str,
bond_name: &str,
config: &HostNetworkConfig,
) -> nmstate::NodeNetworkConfigurationPolicy {
info!("Configuring bond '{bond_name}' for host '{host}'...");
let mut bond_mtu: Option<u32> = None;
let mut copy_mac_from: Option<String> = None;
let mut bond_ports = Vec::new();
let mut interfaces: Vec<nmstate::Interface> = Vec::new();
for switch_port in &config.switch_ports {
let interface_name = switch_port.interface.name.clone();
interfaces.push(nmstate::Interface {
name: interface_name.clone(),
description: Some(format!("Member of bond {bond_name}")),
r#type: nmstate::InterfaceType::Ethernet,
state: "up".to_string(),
ipv4: Some(nmstate::IpStackSpec {
enabled: Some(false),
..Default::default()
}),
ipv6: Some(nmstate::IpStackSpec {
enabled: Some(false),
..Default::default()
}),
link_aggregation: None,
..Default::default()
});
bond_ports.push(interface_name.clone());
// Use the first port's details for the bond mtu and mac address
if bond_mtu.is_none() {
bond_mtu = Some(switch_port.interface.mtu);
}
if copy_mac_from.is_none() {
copy_mac_from = Some(interface_name);
}
}
interfaces.push(nmstate::Interface {
name: bond_name.to_string(),
description: Some(format!("HARMONY - Network bond for host {host}")),
r#type: nmstate::InterfaceType::Bond,
state: "up".to_string(),
copy_mac_from,
ipv4: Some(nmstate::IpStackSpec {
dhcp: Some(true),
enabled: Some(true),
..Default::default()
}),
ipv6: Some(nmstate::IpStackSpec {
dhcp: Some(true),
autoconf: Some(true),
enabled: Some(true),
..Default::default()
}),
link_aggregation: Some(nmstate::BondSpec {
mode: "802.3ad".to_string(),
ports: bond_ports,
..Default::default()
}),
..Default::default()
});
nmstate::NodeNetworkConfigurationPolicy {
metadata: ObjectMeta {
name: Some(format!("{host}-bond-config")),
..Default::default()
},
spec: nmstate::NodeNetworkConfigurationPolicySpec {
node_selector: Some(BTreeMap::from([(
"kubernetes.io/hostname".to_string(),
host.to_string(),
)])),
desired_state: nmstate::NetworkState {
interfaces,
..Default::default()
},
},
}
}
async fn get_hostname(&self, host_id: &Id) -> Result<String, String> {
let nodes: ObjectList<Node> = self
.k8s_client
.list_resources(None, None)
.await
.map_err(|e| format!("Failed to list nodes: {e}"))?;
let Some(node) = nodes.iter().find(|n| {
n.status
.as_ref()
.and_then(|s| s.node_info.as_ref())
.map(|i| i.system_uuid == host_id.to_string())
.unwrap_or(false)
}) else {
return Err(format!("No node found for host '{host_id}'"));
};
node.labels()
.get("kubernetes.io/hostname")
.ok_or(format!(
"Node '{host_id}' has no kubernetes.io/hostname label"
))
.cloned()
}
async fn get_next_bond_id(&self, hostname: &str) -> Result<String, String> {
let network_state: Option<nmstate::NodeNetworkState> = self
.k8s_client
.get_resource(hostname, None)
.await
.map_err(|e| format!("Failed to list nodes: {e}"))?;
let interfaces = vec![];
let existing_bonds: Vec<&nmstate::Interface> = network_state
.as_ref()
.and_then(|network_state| network_state.status.current_state.as_ref())
.map_or(&interfaces, |current_state| &current_state.interfaces)
.iter()
.filter(|i| i.r#type == nmstate::InterfaceType::Bond)
.collect();
let used_ids: HashSet<u32> = existing_bonds
.iter()
.filter_map(|i| {
i.name
.strip_prefix("bond")
.and_then(|id| id.parse::<u32>().ok())
})
.collect();
let next_id = (0..).find(|id| !used_ids.contains(id)).unwrap();
Ok(format!("bond{next_id}"))
}
}

View File

@@ -2,11 +2,7 @@ use crate::modules::application::{
Application, ApplicationFeature, InstallationError, InstallationOutcome,
};
use crate::modules::monitoring::application_monitoring::application_monitoring_score::ApplicationMonitoringScore;
use crate::modules::monitoring::grafana::grafana::Grafana;
use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus;
use crate::modules::monitoring::kube_prometheus::crd::service_monitor::{
ServiceMonitor, ServiceMonitorSpec,
};
use crate::topology::MultiTargetTopology;
use crate::topology::ingress::Ingress;
use crate::{
@@ -18,7 +14,7 @@ use crate::{
topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
};
use crate::{
modules::prometheus::prometheus::PrometheusMonitoring,
modules::prometheus::prometheus::PrometheusApplicationMonitoring,
topology::oberservability::monitoring::AlertReceiver,
};
use async_trait::async_trait;
@@ -26,7 +22,6 @@ use base64::{Engine as _, engine::general_purpose};
use harmony_secret::SecretManager;
use harmony_secret_derive::Secret;
use harmony_types::net::Url;
use kube::api::ObjectMeta;
use log::{debug, info};
use serde::{Deserialize, Serialize};
use std::sync::Arc;
@@ -45,8 +40,7 @@ impl<
+ TenantManager
+ K8sclient
+ MultiTargetTopology
+ PrometheusMonitoring<CRDPrometheus>
+ Grafana
+ PrometheusApplicationMonitoring<CRDPrometheus>
+ Ingress
+ std::fmt::Debug,
> ApplicationFeature<T> for Monitoring
@@ -63,20 +57,10 @@ impl<
.unwrap_or_else(|| self.application.name());
let domain = topology.get_domain("ntfy").await.unwrap();
let app_service_monitor = ServiceMonitor {
metadata: ObjectMeta {
name: Some(self.application.name()),
namespace: Some(namespace.clone()),
..Default::default()
},
spec: ServiceMonitorSpec::default(),
};
let mut alerting_score = ApplicationMonitoringScore {
sender: CRDPrometheus {
namespace: namespace.clone(),
client: topology.k8s_client().await.unwrap(),
service_monitor: vec![app_service_monitor],
},
application: self.application.clone(),
receivers: self.alert_receiver.clone(),

View File

@@ -18,7 +18,7 @@ use crate::{
topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
};
use crate::{
modules::prometheus::prometheus::PrometheusMonitoring,
modules::prometheus::prometheus::PrometheusApplicationMonitoring,
topology::oberservability::monitoring::AlertReceiver,
};
use async_trait::async_trait;
@@ -42,7 +42,7 @@ impl<
+ MultiTargetTopology
+ Ingress
+ std::fmt::Debug
+ PrometheusMonitoring<RHOBObservability>,
+ PrometheusApplicationMonitoring<RHOBObservability>,
> ApplicationFeature<T> for Monitoring
{
async fn ensure_installed(

View File

@@ -74,11 +74,7 @@ impl<T: Topology> Interpret<T> for DiscoverHostForRoleInterpret {
match ans {
Ok(choice) => {
info!(
"Selected {} as the {:?} node.",
choice.summary(),
self.score.role
);
info!("Selected {} as the bootstrap node.", choice.summary());
host_repo
.save_role_mapping(&self.score.role, &choice)
.await?;
@@ -94,7 +90,10 @@ impl<T: Topology> Interpret<T> for DiscoverHostForRoleInterpret {
"Failed to select node for role {:?} : {}",
self.score.role, e
);
return Err(InterpretError::new(format!("Could not select host : {e}")));
return Err(InterpretError::new(format!(
"Could not select host : {}",
e.to_string()
)));
}
}
}

View File

@@ -38,15 +38,13 @@ impl<
+ 'static
+ Send
+ Clone,
T: Topology + K8sclient,
T: Topology,
> Score<T> for K8sResourceScore<K>
where
<K as kube::Resource>::DynamicType: Default,
{
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
Box::new(K8sResourceInterpret {
score: self.clone(),
})
todo!()
}
fn name(&self) -> String {

View File

@@ -1,23 +1,21 @@
use std::sync::Arc;
use log::debug;
use async_trait::async_trait;
use serde::Serialize;
use crate::{
interpret::Interpret,
data::Version,
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
modules::{
application::Application,
monitoring::{
grafana::grafana::Grafana, kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
},
prometheus::prometheus::PrometheusMonitoring,
monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
prometheus::prometheus::PrometheusApplicationMonitoring,
},
score::Score,
topology::{
K8sclient, Topology,
oberservability::monitoring::{AlertReceiver, AlertingInterpret, ScrapeTarget},
},
topology::{PreparationOutcome, Topology, oberservability::monitoring::AlertReceiver},
};
use harmony_types::id::Id;
#[derive(Debug, Clone, Serialize)]
pub struct ApplicationMonitoringScore {
@@ -26,16 +24,12 @@ pub struct ApplicationMonitoringScore {
pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
}
impl<T: Topology + PrometheusMonitoring<CRDPrometheus> + K8sclient + Grafana> Score<T>
impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
for ApplicationMonitoringScore
{
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
debug!("creating alerting interpret");
Box::new(AlertingInterpret {
sender: self.sender.clone(),
receivers: self.receivers.clone(),
rules: vec![],
scrape_targets: None,
Box::new(ApplicationMonitoringInterpret {
score: self.clone(),
})
}
@@ -46,3 +40,55 @@ impl<T: Topology + PrometheusMonitoring<CRDPrometheus> + K8sclient + Grafana> Sc
)
}
}
#[derive(Debug)]
pub struct ApplicationMonitoringInterpret {
score: ApplicationMonitoringScore,
}
#[async_trait]
impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
for ApplicationMonitoringInterpret
{
async fn execute(
&self,
inventory: &Inventory,
topology: &T,
) -> Result<Outcome, InterpretError> {
let result = topology
.install_prometheus(
&self.score.sender,
inventory,
Some(self.score.receivers.clone()),
)
.await;
match result {
Ok(outcome) => match outcome {
PreparationOutcome::Success { details: _ } => {
Ok(Outcome::success("Prometheus installed".into()))
}
PreparationOutcome::Noop => {
Ok(Outcome::noop("Prometheus installation skipped".into()))
}
},
Err(err) => Err(InterpretError::from(err)),
}
}
fn get_name(&self) -> InterpretName {
InterpretName::ApplicationMonitoring
}
fn get_version(&self) -> Version {
todo!()
}
fn get_status(&self) -> InterpretStatus {
todo!()
}
fn get_children(&self) -> Vec<Id> {
todo!()
}
}

View File

@@ -12,7 +12,7 @@ use crate::{
monitoring::kube_prometheus::crd::{
crd_alertmanager_config::CRDPrometheus, rhob_alertmanager_config::RHOBObservability,
},
prometheus::prometheus::PrometheusMonitoring,
prometheus::prometheus::PrometheusApplicationMonitoring,
},
score::Score,
topology::{PreparationOutcome, Topology, oberservability::monitoring::AlertReceiver},
@@ -26,7 +26,7 @@ pub struct ApplicationRHOBMonitoringScore {
pub receivers: Vec<Box<dyn AlertReceiver<RHOBObservability>>>,
}
impl<T: Topology + PrometheusMonitoring<RHOBObservability>> Score<T>
impl<T: Topology + PrometheusApplicationMonitoring<RHOBObservability>> Score<T>
for ApplicationRHOBMonitoringScore
{
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
@@ -49,7 +49,7 @@ pub struct ApplicationRHOBMonitoringInterpret {
}
#[async_trait]
impl<T: Topology + PrometheusMonitoring<RHOBObservability>> Interpret<T>
impl<T: Topology + PrometheusApplicationMonitoring<RHOBObservability>> Interpret<T>
for ApplicationRHOBMonitoringInterpret
{
async fn execute(

View File

@@ -1,17 +0,0 @@
use async_trait::async_trait;
use k8s_openapi::Resource;
use crate::{
inventory::Inventory,
topology::{PreparationError, PreparationOutcome},
};
#[async_trait]
pub trait Grafana {
async fn ensure_grafana_operator(
&self,
inventory: &Inventory,
) -> Result<PreparationOutcome, PreparationError>;
async fn install_grafana(&self) -> Result<PreparationOutcome, PreparationError>;
}

View File

@@ -1,28 +1,27 @@
use harmony_macros::hurl;
use non_blank_string_rs::NonBlankString;
use std::{collections::HashMap, str::FromStr};
use std::str::FromStr;
use crate::modules::helm::chart::{HelmChartScore, HelmRepository};
use crate::modules::helm::chart::HelmChartScore;
pub fn grafana_helm_chart_score(ns: &str) -> HelmChartScore {
let values = r#"
rbac:
namespaced: true
sidecar:
dashboards:
enabled: true
"#
.to_string();
pub fn grafana_helm_chart_score(ns: &str, namespace_scope: bool) -> HelmChartScore {
let mut values_overrides = HashMap::new();
values_overrides.insert(
NonBlankString::from_str("namespaceScope").unwrap(),
namespace_scope.to_string(),
);
HelmChartScore {
namespace: Some(NonBlankString::from_str(ns).unwrap()),
release_name: NonBlankString::from_str("grafana-operator").unwrap(),
chart_name: NonBlankString::from_str("grafana/grafana-operator").unwrap(),
release_name: NonBlankString::from_str("grafana").unwrap(),
chart_name: NonBlankString::from_str("oci://ghcr.io/grafana/helm-charts/grafana").unwrap(),
chart_version: None,
values_overrides: Some(values_overrides),
values_yaml: None,
values_overrides: None,
values_yaml: Some(values.to_string()),
create_namespace: true,
install_only: true,
repository: Some(HelmRepository::new(
"grafana".to_string(),
hurl!("https://grafana.github.io/helm-charts"),
true,
)),
repository: None,
}
}

View File

@@ -1,2 +1 @@
pub mod grafana;
pub mod helm;

View File

@@ -1,25 +1,12 @@
use std::sync::Arc;
use async_trait::async_trait;
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use crate::{
interpret::{InterpretError, Outcome},
inventory::Inventory,
modules::{
monitoring::{
grafana::grafana::Grafana, kube_prometheus::crd::service_monitor::ServiceMonitor,
},
prometheus::prometheus::PrometheusMonitoring,
},
topology::{
K8sclient, Topology,
installable::Installable,
use crate::topology::{
k8s::K8sClient,
oberservability::monitoring::{AlertReceiver, AlertSender, ScrapeTarget},
},
oberservability::monitoring::{AlertReceiver, AlertSender},
};
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
@@ -39,7 +26,6 @@ pub struct AlertmanagerConfigSpec {
pub struct CRDPrometheus {
pub namespace: String,
pub client: Arc<K8sClient>,
pub service_monitor: Vec<ServiceMonitor>,
}
impl AlertSender for CRDPrometheus {
@@ -54,12 +40,6 @@ impl Clone for Box<dyn AlertReceiver<CRDPrometheus>> {
}
}
impl Clone for Box<dyn ScrapeTarget<CRDPrometheus>> {
fn clone(&self) -> Self {
self.clone_box()
}
}
impl Serialize for Box<dyn AlertReceiver<CRDPrometheus>> {
fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
where
@@ -68,24 +48,3 @@ impl Serialize for Box<dyn AlertReceiver<CRDPrometheus>> {
todo!()
}
}
#[async_trait]
impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus> + Grafana> Installable<T>
for CRDPrometheus
{
async fn configure(&self, inventory: &Inventory, topology: &T) -> Result<(), InterpretError> {
topology.ensure_grafana_operator(inventory).await?;
topology.ensure_prometheus_operator(self, inventory).await?;
Ok(())
}
async fn ensure_installed(
&self,
inventory: &Inventory,
topology: &T,
) -> Result<(), InterpretError> {
topology.install_grafana().await?;
topology.install_prometheus(&self, inventory, None).await?;
Ok(())
}
}

View File

@@ -103,34 +103,9 @@ pub struct GrafanaDashboardSpec {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub resync_period: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub datasources: Option<Vec<GrafanaDashboardDatasource>>,
pub instance_selector: LabelSelector,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub json: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub grafana_com: Option<GrafanaCom>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaDashboardDatasource {
pub input_name: String,
pub datasource_name: String,
}
// ------------------------------------------------------------------------------------------------
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaCom {
pub id: u32,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub revision: Option<u32>,
pub json: String,
}
// ------------------------------------------------------------------------------------------------
@@ -151,79 +126,20 @@ pub struct GrafanaDatasourceSpec {
pub allow_cross_namespace_import: Option<bool>,
pub datasource: GrafanaDatasourceConfig,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub values_from: Option<Vec<GrafanaValueFrom>>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaValueFrom {
pub target_path: String,
pub value_from: GrafanaValueSource,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaValueSource {
pub secret_key_ref: GrafanaSecretKeyRef,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaSecretKeyRef {
pub name: String,
pub key: String,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaDatasourceConfig {
pub access: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub database: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub json_data: Option<BTreeMap<String, String>>,
pub name: String,
pub r#type: String,
pub url: String,
/// Represents jsonData in the GrafanaDatasource spec
#[serde(default, skip_serializing_if = "Option::is_none")]
pub json_data: Option<GrafanaDatasourceJsonData>,
/// Represents secureJsonData (secrets)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub secure_json_data: Option<GrafanaDatasourceSecureJsonData>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub is_default: Option<bool>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub editable: Option<bool>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaDatasourceJsonData {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub time_interval: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub http_header_name1: Option<String>,
/// Disable TLS skip verification (false = verify)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub tls_skip_verify: Option<bool>,
/// Auth type - set to "forward" for OpenShift OAuth identity
#[serde(default, skip_serializing_if = "Option::is_none")]
pub oauth_pass_thru: Option<bool>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaDatasourceSecureJsonData {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub http_header_value1: Option<String>,
}
// ------------------------------------------------------------------------------------------------
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]

View File

@@ -1,187 +0,0 @@
use std::net::IpAddr;
use async_trait::async_trait;
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use crate::{
modules::monitoring::kube_prometheus::crd::{
crd_alertmanager_config::CRDPrometheus, crd_prometheuses::LabelSelector,
},
topology::oberservability::monitoring::ScrapeTarget,
};
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "monitoring.coreos.com",
version = "v1alpha1",
kind = "ScrapeConfig",
plural = "scrapeconfigs",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct ScrapeConfigSpec {
/// List of static configurations.
pub static_configs: Option<Vec<StaticConfig>>,
/// Kubernetes service discovery.
pub kubernetes_sd_configs: Option<Vec<KubernetesSDConfig>>,
/// HTTP-based service discovery.
pub http_sd_configs: Option<Vec<HttpSDConfig>>,
/// File-based service discovery.
pub file_sd_configs: Option<Vec<FileSDConfig>>,
/// DNS-based service discovery.
pub dns_sd_configs: Option<Vec<DnsSDConfig>>,
/// Consul service discovery.
pub consul_sd_configs: Option<Vec<ConsulSDConfig>>,
/// Relabeling configuration applied to discovered targets.
pub relabel_configs: Option<Vec<RelabelConfig>>,
/// Metric relabeling configuration applied to scraped samples.
pub metric_relabel_configs: Option<Vec<RelabelConfig>>,
/// Path to scrape metrics from (defaults to `/metrics`).
pub metrics_path: Option<String>,
/// Interval at which Prometheus scrapes targets (e.g., "30s").
pub scrape_interval: Option<String>,
/// Timeout for scraping (e.g., "10s").
pub scrape_timeout: Option<String>,
/// Optional job name override.
pub job_name: Option<String>,
/// Optional scheme (http or https).
pub scheme: Option<String>,
/// Authorization paramaters for snmp walk
pub params: Option<Params>,
}
/// Static configuration section of a ScrapeConfig.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct StaticConfig {
pub targets: Vec<String>,
pub labels: Option<LabelSelector>,
}
/// Relabeling configuration for target or metric relabeling.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct RelabelConfig {
pub source_labels: Option<Vec<String>>,
pub separator: Option<String>,
pub target_label: Option<String>,
pub regex: Option<String>,
pub modulus: Option<u64>,
pub replacement: Option<String>,
pub action: Option<String>,
}
/// Kubernetes service discovery configuration.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct KubernetesSDConfig {
///"pod", "service", "endpoints"pub role: String,
pub namespaces: Option<NamespaceSelector>,
pub selectors: Option<Vec<LabelSelector>>,
pub api_server: Option<String>,
pub bearer_token_file: Option<String>,
pub tls_config: Option<TLSConfig>,
}
/// Namespace selector for Kubernetes service discovery.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct NamespaceSelector {
pub any: Option<bool>,
pub match_names: Option<Vec<String>>,
}
/// HTTP-based service discovery configuration.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct HttpSDConfig {
pub url: String,
pub refresh_interval: Option<String>,
pub basic_auth: Option<BasicAuth>,
pub authorization: Option<Authorization>,
pub tls_config: Option<TLSConfig>,
}
/// File-based service discovery configuration.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct FileSDConfig {
pub files: Vec<String>,
pub refresh_interval: Option<String>,
}
/// DNS-based service discovery configuration.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct DnsSDConfig {
pub names: Vec<String>,
pub refresh_interval: Option<String>,
pub type_: Option<String>, // SRV, A, AAAA
pub port: Option<u16>,
}
/// Consul service discovery configuration.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct ConsulSDConfig {
pub server: String,
pub services: Option<Vec<String>>,
pub scheme: Option<String>,
pub datacenter: Option<String>,
pub tag_separator: Option<String>,
pub refresh_interval: Option<String>,
pub tls_config: Option<TLSConfig>,
}
/// Basic authentication credentials.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct BasicAuth {
pub username: String,
pub password: Option<String>,
pub password_file: Option<String>,
}
/// Bearer token or other auth mechanisms.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct Authorization {
pub credentials: Option<String>,
pub credentials_file: Option<String>,
pub type_: Option<String>,
}
/// TLS configuration for secure scraping.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct TLSConfig {
pub ca_file: Option<String>,
pub cert_file: Option<String>,
pub key_file: Option<String>,
pub server_name: Option<String>,
pub insecure_skip_verify: Option<bool>,
}
/// Authorization parameters for SNMP walk.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct Params {
pub auth: Option<Vec<String>>,
pub module: Option<Vec<String>>,
}

View File

@@ -4,7 +4,6 @@ pub mod crd_default_rules;
pub mod crd_grafana;
pub mod crd_prometheus_rules;
pub mod crd_prometheuses;
pub mod crd_scrape_config;
pub mod grafana_default_dashboard;
pub mod grafana_operator;
pub mod prometheus_operator;

View File

@@ -31,7 +31,6 @@ impl<T: Topology + HelmCommand + TenantManager> Score<T> for HelmPrometheusAlert
sender: KubePrometheus { config },
receivers: self.receivers.clone(),
rules: self.rules.clone(),
scrape_targets: None,
})
}
fn name(&self) -> String {

View File

@@ -6,4 +6,3 @@ pub mod kube_prometheus;
pub mod ntfy;
pub mod okd;
pub mod prometheus;
pub mod scrape_target;

View File

@@ -100,7 +100,11 @@ impl<T: Topology + HelmCommand + K8sclient + MultiTargetTopology> Interpret<T> f
info!("deploying ntfy...");
client
.wait_until_deployment_ready("ntfy", Some(self.score.namespace.as_str()), None)
.wait_until_deployment_ready(
"ntfy".to_string(),
Some(self.score.namespace.as_str()),
None,
)
.await?;
info!("ntfy deployed");

View File

@@ -114,7 +114,7 @@ impl Prometheus {
};
if let Some(ns) = namespace.as_deref() {
grafana_helm_chart_score(ns, false)
grafana_helm_chart_score(ns)
.interpret(inventory, topology)
.await
} else {

View File

@@ -1 +0,0 @@
pub mod server;

View File

@@ -1,80 +0,0 @@
use std::net::IpAddr;
use async_trait::async_trait;
use kube::api::ObjectMeta;
use serde::Serialize;
use crate::{
interpret::{InterpretError, Outcome},
modules::monitoring::kube_prometheus::crd::{
crd_alertmanager_config::CRDPrometheus,
crd_scrape_config::{Params, RelabelConfig, ScrapeConfig, ScrapeConfigSpec, StaticConfig},
},
topology::oberservability::monitoring::ScrapeTarget,
};
#[derive(Debug, Clone, Serialize)]
pub struct Server {
pub name: String,
pub ip: IpAddr,
pub auth: String,
pub module: String,
pub domain: String,
}
#[async_trait]
impl ScrapeTarget<CRDPrometheus> for Server {
async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
let scrape_config_spec = ScrapeConfigSpec {
static_configs: Some(vec![StaticConfig {
targets: vec![self.ip.to_string()],
labels: None,
}]),
scrape_interval: Some("2m".to_string()),
kubernetes_sd_configs: None,
http_sd_configs: None,
file_sd_configs: None,
dns_sd_configs: None,
params: Some(Params {
auth: Some(vec![self.auth.clone()]),
module: Some(vec![self.module.clone()]),
}),
consul_sd_configs: None,
relabel_configs: Some(vec![RelabelConfig {
action: None,
source_labels: Some(vec!["__address__".to_string()]),
separator: None,
target_label: Some("__param_target".to_string()),
regex: None,
replacement: Some(format!("snmp.{}:31080", self.domain.clone())),
modulus: None,
}]),
metric_relabel_configs: None,
metrics_path: Some("/snmp".to_string()),
scrape_timeout: Some("2m".to_string()),
job_name: Some(format!("snmp_exporter/cloud/{}", self.name.clone())),
scheme: None,
};
let scrape_config = ScrapeConfig {
metadata: ObjectMeta {
name: Some(self.name.clone()),
namespace: Some(sender.namespace.clone()),
..Default::default()
},
spec: scrape_config_spec,
};
sender
.client
.apply(&scrape_config, Some(&sender.namespace.clone()))
.await?;
Ok(Outcome::success(format!(
"installed scrape target {}",
self.name.clone()
)))
}
fn clone_box(&self) -> Box<dyn ScrapeTarget<CRDPrometheus>> {
Box::new(self.clone())
}
}

View File

@@ -5,8 +5,10 @@ use crate::{
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::{HostRole, Inventory},
modules::{
dhcp::DhcpHostBindingScore, http::IPxeMacBootFileScore,
inventory::DiscoverHostForRoleScore, okd::templates::BootstrapIpxeTpl,
dhcp::DhcpHostBindingScore,
http::IPxeMacBootFileScore,
inventory::DiscoverHostForRoleScore,
okd::{host_network::HostNetworkConfigurationScore, templates::BootstrapIpxeTpl},
},
score::Score,
topology::{HAClusterTopology, HostBinding},
@@ -203,6 +205,28 @@ impl OKDSetup03ControlPlaneInterpret {
Ok(())
}
/// Placeholder for automating network bonding configuration.
async fn persist_network_bond(
&self,
inventory: &Inventory,
topology: &HAClusterTopology,
hosts: &Vec<PhysicalHost>,
) -> Result<(), InterpretError> {
info!("[ControlPlane] Ensuring persistent bonding");
let score = HostNetworkConfigurationScore {
hosts: hosts.clone(),
};
score.interpret(inventory, topology).await?;
inquire::Confirm::new(
"Network configuration for control plane nodes is not automated yet. Configure it manually if needed.",
)
.prompt()
.map_err(|e| InterpretError::new(format!("User prompt failed: {e}")))?;
Ok(())
}
}
#[async_trait]
@@ -241,6 +265,10 @@ impl Interpret<HAClusterTopology> for OKDSetup03ControlPlaneInterpret {
// 4. Reboot the nodes to start the OS installation.
self.reboot_targets(&nodes).await?;
// 5. Placeholder for post-boot network configuration (e.g., bonding).
self.persist_network_bond(inventory, topology, &nodes)
.await?;
// TODO: Implement a step to wait for the control plane nodes to join the cluster
// and for the cluster operators to become available. This would be similar to
// the `wait-for bootstrap-complete` command.

View File

@@ -1,130 +0,0 @@
use crate::{
data::Version,
hardware::PhysicalHost,
infra::inventory::InventoryRepositoryFactory,
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::{HostRole, Inventory},
modules::okd::host_network::HostNetworkConfigurationScore,
score::Score,
topology::HAClusterTopology,
};
use async_trait::async_trait;
use derive_new::new;
use harmony_types::id::Id;
use log::info;
use serde::Serialize;
// -------------------------------------------------------------------------------------------------
// Persist Network Bond
// - Persist bonding via NMState
// - Persist port channels on the Switch
// -------------------------------------------------------------------------------------------------
#[derive(Debug, Clone, Serialize, new)]
pub struct OKDSetupPersistNetworkBondScore {}
impl Score<HAClusterTopology> for OKDSetupPersistNetworkBondScore {
fn create_interpret(&self) -> Box<dyn Interpret<HAClusterTopology>> {
Box::new(OKDSetupPersistNetworkBondInterpet::new())
}
fn name(&self) -> String {
"OKDSetupPersistNetworkBondScore".to_string()
}
}
#[derive(Debug, Clone)]
pub struct OKDSetupPersistNetworkBondInterpet {
version: Version,
status: InterpretStatus,
}
impl OKDSetupPersistNetworkBondInterpet {
pub fn new() -> Self {
let version = Version::from("1.0.0").unwrap();
Self {
version,
status: InterpretStatus::QUEUED,
}
}
/// 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 = 3;
let repo = InventoryRepositoryFactory::build().await?;
let control_plane_hosts = repo.get_host_for_role(&HostRole::ControlPlane).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())
}
}
async fn persist_network_bond(
&self,
inventory: &Inventory,
topology: &HAClusterTopology,
hosts: &Vec<PhysicalHost>,
) -> Result<(), InterpretError> {
info!("Ensuring persistent bonding");
let score = HostNetworkConfigurationScore {
hosts: hosts.clone(),
};
score.interpret(inventory, topology).await?;
Ok(())
}
}
#[async_trait]
impl Interpret<HAClusterTopology> for OKDSetupPersistNetworkBondInterpet {
fn get_name(&self) -> InterpretName {
InterpretName::Custom("OKDSetupPersistNetworkBondInterpet")
}
fn get_version(&self) -> Version {
self.version.clone()
}
fn get_status(&self) -> InterpretStatus {
self.status.clone()
}
fn get_children(&self) -> Vec<Id> {
vec![]
}
async fn execute(
&self,
inventory: &Inventory,
topology: &HAClusterTopology,
) -> Result<Outcome, InterpretError> {
let nodes = self.get_nodes(inventory, topology).await?;
let res = self.persist_network_bond(inventory, topology, &nodes).await;
match res {
Ok(_) => Ok(Outcome::success(
"Network bond successfully persisted".into(),
)),
Err(_) => Err(InterpretError::new(
"Failed to persist network bond".to_string(),
)),
}
}
}

View File

@@ -1 +1,41 @@
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
pub mod nmstate;
#[derive(CustomResource, Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[kube(
group = "operators.coreos.com",
version = "v1",
kind = "OperatorGroup",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct OperatorGroupSpec {
pub target_namespaces: Vec<String>,
}
#[derive(CustomResource, Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[kube(
group = "operators.coreos.com",
version = "v1alpha1",
kind = "Subscription",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct SubscriptionSpec {
pub name: String,
pub source: String,
pub source_namespace: String,
pub channel: Option<String>,
pub install_plan_approval: Option<InstallPlanApproval>,
}
#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
pub enum InstallPlanApproval {
#[serde(rename = "Automatic")]
Automatic,
#[serde(rename = "Manual")]
Manual,
}

View File

@@ -1,22 +1,14 @@
use std::collections::BTreeMap;
use k8s_openapi::{ClusterResourceScope, Resource};
use kube::{CustomResource, api::ObjectMeta};
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use serde_json::Value;
#[derive(CustomResource, Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[kube(
group = "nmstate.io",
version = "v1",
kind = "NMState",
plural = "nmstates",
namespaced = false
)]
#[kube(group = "nmstate.io", version = "v1", kind = "NMState", namespaced)]
#[serde(rename_all = "camelCase")]
pub struct NMStateSpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub probe_configuration: Option<ProbeConfig>,
}
@@ -48,350 +40,55 @@ pub struct ProbeDns {
group = "nmstate.io",
version = "v1",
kind = "NodeNetworkConfigurationPolicy",
namespaced = false
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct NodeNetworkConfigurationPolicySpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub node_selector: Option<BTreeMap<String, String>>,
pub desired_state: NetworkState,
}
// Currently, kube-rs derive doesn't support resources without a `spec` field, so we have
// to implement it ourselves.
//
// Ref:
// - https://github.com/kube-rs/kube/issues/1763
// - https://github.com/kube-rs/kube/discussions/1762
#[derive(Deserialize, Serialize, Clone, Debug)]
#[serde(rename_all = "camelCase")]
pub struct NodeNetworkState {
metadata: ObjectMeta,
pub status: NodeNetworkStateStatus,
}
impl Resource for NodeNetworkState {
const API_VERSION: &'static str = "nmstate.io/v1beta1";
const GROUP: &'static str = "nmstate.io";
const VERSION: &'static str = "v1beta1";
const KIND: &'static str = "NodeNetworkState";
const URL_PATH_SEGMENT: &'static str = "nodenetworkstates";
type Scope = ClusterResourceScope;
}
impl k8s_openapi::Metadata for NodeNetworkState {
type Ty = ObjectMeta;
fn metadata(&self) -> &Self::Ty {
&self.metadata
}
fn metadata_mut(&mut self) -> &mut Self::Ty {
&mut self.metadata
}
}
#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct NodeNetworkStateStatus {
#[serde(skip_serializing_if = "Option::is_none")]
pub current_state: Option<NetworkState>,
#[serde(skip_serializing_if = "Option::is_none")]
pub handler_nmstate_version: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub host_network_manager_version: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub last_successful_update_time: Option<String>,
}
/// The NetworkState is the top-level struct, representing the entire
/// desired or current network state.
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
#[serde(deny_unknown_fields)]
pub struct NetworkState {
#[serde(skip_serializing_if = "Option::is_none")]
pub hostname: Option<HostNameState>,
#[serde(rename = "dns-resolver", skip_serializing_if = "Option::is_none")]
pub dns: Option<DnsState>,
#[serde(rename = "route-rules", skip_serializing_if = "Option::is_none")]
pub rules: Option<RouteRuleState>,
#[serde(skip_serializing_if = "Option::is_none")]
pub routes: Option<RouteState>,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub interfaces: Vec<Interface>,
#[serde(rename = "ovs-db", skip_serializing_if = "Option::is_none")]
pub ovsdb: Option<OvsDbGlobalConfig>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ovn: Option<OvnConfiguration>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct HostNameState {
#[serde(skip_serializing_if = "Option::is_none")]
pub running: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub config: Option<String>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct DnsState {
#[serde(skip_serializing_if = "Option::is_none")]
pub running: Option<DnsResolverConfig>,
#[serde(skip_serializing_if = "Option::is_none")]
pub config: Option<DnsResolverConfig>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct DnsResolverConfig {
#[serde(skip_serializing_if = "Option::is_none")]
pub search: Option<Vec<String>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub server: Option<Vec<String>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct RouteRuleState {
#[serde(skip_serializing_if = "Option::is_none")]
pub config: Option<Vec<RouteRule>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub running: Option<Vec<RouteRule>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct RouteState {
#[serde(skip_serializing_if = "Option::is_none")]
pub config: Option<Vec<Route>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub running: Option<Vec<Route>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct RouteRule {
#[serde(rename = "ip-from", skip_serializing_if = "Option::is_none")]
pub ip_from: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub priority: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub route_table: Option<u32>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct Route {
#[serde(skip_serializing_if = "Option::is_none")]
pub destination: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub metric: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub next_hop_address: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub next_hop_interface: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub table_id: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mtu: Option<u32>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct OvsDbGlobalConfig {
#[serde(skip_serializing_if = "Option::is_none")]
pub external_ids: Option<BTreeMap<String, String>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub other_config: Option<BTreeMap<String, String>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct OvnConfiguration {
#[serde(skip_serializing_if = "Option::is_none")]
pub bridge_mappings: Option<Vec<OvnBridgeMapping>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct OvnBridgeMapping {
#[serde(skip_serializing_if = "Option::is_none")]
pub localnet: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub bridge: Option<String>,
}
#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[serde(untagged)]
#[serde(rename_all = "kebab-case")]
pub enum StpSpec {
Bool(bool),
Options(StpOptions),
pub desired_state: DesiredStateSpec,
}
#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct LldpState {
#[serde(skip_serializing_if = "Option::is_none")]
pub enabled: Option<bool>,
}
#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct OvsDb {
#[serde(skip_serializing_if = "Option::is_none")]
pub external_ids: Option<BTreeMap<String, String>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub other_config: Option<BTreeMap<String, String>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct PatchState {
#[serde(skip_serializing_if = "Option::is_none")]
pub peer: Option<String>,
pub struct DesiredStateSpec {
pub interfaces: Vec<InterfaceSpec>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct Interface {
pub struct InterfaceSpec {
pub name: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub description: Option<String>,
pub r#type: InterfaceType,
pub r#type: String,
pub state: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub mac_address: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub copy_mac_from: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mtu: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub controller: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ipv4: Option<IpStackSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ipv6: Option<IpStackSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ethernet: Option<EthernetSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub link_aggregation: Option<BondSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub vlan: Option<VlanSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub vxlan: Option<VxlanSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mac_vtap: Option<MacVtapSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mac_vlan: Option<MacVlanSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub infiniband: Option<InfinibandSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub linux_bridge: Option<LinuxBridgeSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
#[serde(alias = "bridge")]
pub ovs_bridge: Option<OvsBridgeSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ethtool: Option<Value>,
#[serde(skip_serializing_if = "Option::is_none")]
pub accept_all_mac_addresses: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub identifier: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub lldp: Option<LldpState>,
#[serde(skip_serializing_if = "Option::is_none")]
pub permanent_mac_address: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub max_mtu: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub min_mtu: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mptcp: Option<Value>,
#[serde(skip_serializing_if = "Option::is_none")]
pub profile_name: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub wait_ip: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ovs_db: Option<OvsDb>,
#[serde(skip_serializing_if = "Option::is_none")]
pub driver: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub patch: Option<PatchState>,
}
#[derive(Deserialize, Serialize, Clone, PartialEq, Eq, PartialOrd, Ord, Debug, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub enum InterfaceType {
#[serde(rename = "unknown")]
Unknown,
#[serde(rename = "dummy")]
Dummy,
#[serde(rename = "loopback")]
Loopback,
#[serde(rename = "linux-bridge")]
LinuxBridge,
#[serde(rename = "ovs-bridge")]
OvsBridge,
#[serde(rename = "ovs-interface")]
OvsInterface,
#[serde(rename = "bond")]
Bond,
#[serde(rename = "ipvlan")]
IpVlan,
#[serde(rename = "vlan")]
Vlan,
#[serde(rename = "vxlan")]
Vxlan,
#[serde(rename = "mac-vlan")]
Macvlan,
#[serde(rename = "mac-vtap")]
Macvtap,
#[serde(rename = "ethernet")]
Ethernet,
#[serde(rename = "infiniband")]
Infiniband,
#[serde(rename = "vrf")]
Vrf,
#[serde(rename = "veth")]
Veth,
#[serde(rename = "ipsec")]
Ipsec,
#[serde(rename = "hsr")]
Hrs,
}
impl Default for InterfaceType {
fn default() -> Self {
Self::Loopback
}
pub ethtool: Option<EthtoolSpec>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct IpStackSpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub enabled: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub dhcp: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub autoconf: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub address: Option<Vec<IpAddressSpec>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub auto_dns: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub auto_gateway: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub auto_routes: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub dhcp_client_id: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub dhcp_duid: Option<String>,
}
@@ -405,11 +102,8 @@ pub struct IpAddressSpec {
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct EthernetSpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub speed: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub duplex: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub auto_negotiation: Option<bool>,
}
@@ -417,9 +111,7 @@ pub struct EthernetSpec {
#[serde(rename_all = "kebab-case")]
pub struct BondSpec {
pub mode: String,
#[serde(alias = "port")]
pub ports: Vec<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub options: Option<BTreeMap<String, Value>>,
}
@@ -428,7 +120,6 @@ pub struct BondSpec {
pub struct VlanSpec {
pub base_iface: String,
pub id: u16,
#[serde(skip_serializing_if = "Option::is_none")]
pub protocol: Option<String>,
}
@@ -438,11 +129,8 @@ pub struct VxlanSpec {
pub base_iface: String,
pub id: u32,
pub remote: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub local: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub learning: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub destination_port: Option<u16>,
}
@@ -451,7 +139,6 @@ pub struct VxlanSpec {
pub struct MacVtapSpec {
pub base_iface: String,
pub mode: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub promiscuous: Option<bool>,
}
@@ -460,7 +147,6 @@ pub struct MacVtapSpec {
pub struct MacVlanSpec {
pub base_iface: String,
pub mode: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub promiscuous: Option<bool>,
}
@@ -475,35 +161,25 @@ pub struct InfinibandSpec {
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct LinuxBridgeSpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub options: Option<LinuxBridgeOptions>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ports: Option<Vec<LinuxBridgePort>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct LinuxBridgeOptions {
#[serde(skip_serializing_if = "Option::is_none")]
pub mac_ageing_time: Option<u32>,
#[serde(skip_serializing_if = "Option::is_none")]
pub multicast_snooping: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub stp: Option<StpOptions>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct StpOptions {
#[serde(skip_serializing_if = "Option::is_none")]
pub enabled: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub forward_delay: Option<u16>,
#[serde(skip_serializing_if = "Option::is_none")]
pub hello_time: Option<u16>,
#[serde(skip_serializing_if = "Option::is_none")]
pub max_age: Option<u16>,
#[serde(skip_serializing_if = "Option::is_none")]
pub priority: Option<u16>,
}
@@ -511,20 +187,15 @@ pub struct StpOptions {
#[serde(rename_all = "kebab-case")]
pub struct LinuxBridgePort {
pub name: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub vlan: Option<LinuxBridgePortVlan>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct LinuxBridgePortVlan {
#[serde(skip_serializing_if = "Option::is_none")]
pub mode: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub trunk_tags: Option<Vec<VlanTag>>,
#[serde(skip_serializing_if = "Option::is_none")]
pub tag: Option<u16>,
#[serde(skip_serializing_if = "Option::is_none")]
pub enable_native: Option<bool>,
}
@@ -532,7 +203,6 @@ pub struct LinuxBridgePortVlan {
#[serde(rename_all = "kebab-case")]
pub struct VlanTag {
pub id: u16,
#[serde(skip_serializing_if = "Option::is_none")]
pub id_range: Option<VlanIdRange>,
}
@@ -546,35 +216,36 @@ pub struct VlanIdRange {
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct OvsBridgeSpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub options: Option<OvsBridgeOptions>,
#[serde(skip_serializing_if = "Option::is_none")]
pub ports: Option<Vec<OvsPortSpec>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct OvsBridgeOptions {
#[serde(skip_serializing_if = "Option::is_none")]
pub stp: Option<StpSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub stp: Option<bool>,
pub rstp: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mcast_snooping_enable: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub datapath: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub fail_mode: Option<String>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct OvsPortSpec {
pub name: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub link_aggregation: Option<BondSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
pub vlan: Option<LinuxBridgePortVlan>,
#[serde(skip_serializing_if = "Option::is_none")]
pub r#type: Option<String>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct EthtoolSpec {
// TODO: Properly describe this spec (https://nmstate.io/devel/yaml_api.html#ethtool)
}
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct EthtoolFecSpec {
pub auto: Option<bool>,
pub mode: Option<String>,
}

View File

@@ -1,6 +1,6 @@
use async_trait::async_trait;
use harmony_types::id::Id;
use log::{info, warn};
use log::{debug, info};
use serde::Serialize;
use crate::{
@@ -9,83 +9,15 @@ use crate::{
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
score::Score,
topology::{HostNetworkConfig, NetworkInterface, NetworkManager, Switch, SwitchPort, Topology},
topology::{HostNetworkConfig, NetworkInterface, Switch, SwitchPort, Topology},
};
/// Configures high-availability networking for a set of physical hosts.
///
/// This is an opinionated Score that creates a resilient network configuration.
/// It assumes hosts have at least two network interfaces connected
/// to redundant switches for high availability.
///
/// The Score's `Interpret` logic will:
/// 1. Setup the switch with sane defaults (e.g. mark interfaces as switchports for discoverability).
/// 2. Discover which switch ports each host's interfaces are connected to (via MAC address).
/// 3. Create a network bond (e.g. LACP) on the host itself using these interfaces.
/// 4. Configure a corresponding port-channel on the switch(es) for those ports.
///
/// This ensures that both the host and the switch are configured to treat the
/// multiple links as a single, aggregated, and redundant connection.
///
/// Hosts with 0 or 1 detected interfaces will be skipped, as bonding is not
/// applicable.
///
/// <div class="warning">
/// The implementation is currently _not_ idempotent, even though it should be.
/// Running it more than once on the same host might result in duplicated bond configurations.
/// </div>
///
/// <div class="warning">
/// This Score is not named well. A better name would be
/// `HighAvailabilityHostNetworkScore`, or something similar to better express the intent.
/// </div>
///
/// # Requirements
///
/// This Score can only be applied to a [Topology] that implements both the
/// [NetworkManager] (to configure the host-side bond) and [Switch]
/// (to configure the switch-side port-channel) capabilities.
///
/// # Current limitations
///
/// ## 1. No rollback logic & limited idempotency
///
/// If any of the steps described above fails, the Score will not attempt to revert any changes
/// already applied. Which could render the host or switch in an inconsistent state.
///
/// ## 2. Propagation delays on the switch
///
/// It might take some time for the sane defaults in step 1) to be applied. In some cases,
/// it was observed that the switch takes up to 5min to actually apply the config.
///
/// But this Score's Interpret doesn't wait and directly proceeds to step 2) to discover
/// the MAC addresses. Which could result interfaces being skipped because their corresponding port
/// on the switch couldn't be found.
///
/// TODO: Validate that the switch is in the expected state before continuing.
///
/// ## 3. Bond configuration
///
/// To find the next available bond id, the current
/// [NetworkManager](crate::infra::network_manager::OpenShiftNmStateNetworkManager) implementation
/// simply checks for existing bonds named `bond[n]` and take the next available `n` number.
///
/// It doesn't check that there are already a bond for the interfaces that should be bonded. Which
/// might result in a duplicate bond being created.
///
/// TODO: Make sure the interfaces to aggregate are not already bonded.
///
/// # Future improvements
///
/// Along with the `TODO` items above, splitting this Score into multiple smaller ones would be
/// beneficial. It has a lot of moving parts and some of them could be used on their own to make
/// operations on a cluster easier.
#[derive(Debug, Clone, Serialize)]
pub struct HostNetworkConfigurationScore {
pub hosts: Vec<PhysicalHost>,
}
impl<T: Topology + NetworkManager + Switch> Score<T> for HostNetworkConfigurationScore {
impl<T: Topology + Switch> Score<T> for HostNetworkConfigurationScore {
fn name(&self) -> String {
"HostNetworkConfigurationScore".into()
}
@@ -103,91 +35,34 @@ pub struct HostNetworkConfigurationInterpret {
}
impl HostNetworkConfigurationInterpret {
async fn configure_network_for_host<T: Topology + NetworkManager + Switch>(
async fn configure_network_for_host<T: Topology + Switch>(
&self,
topology: &T,
host: &PhysicalHost,
current_host: &usize,
total_hosts: &usize,
) -> Result<HostNetworkConfig, InterpretError> {
if host.network.is_empty() {
info!("[Host {current_host}/{total_hosts}] No interfaces to configure, skipping");
return Ok(HostNetworkConfig {
host_id: host.id.clone(),
switch_ports: vec![],
});
}
if host.network.len() == 1 {
info!("[Host {current_host}/{total_hosts}] Only one interface to configure, skipping");
return Ok(HostNetworkConfig {
host_id: host.id.clone(),
switch_ports: vec![],
});
}
let switch_ports = self
.collect_switch_ports_for_host(topology, host, current_host, total_hosts)
.await?;
let config = HostNetworkConfig {
host_id: host.id.clone(),
switch_ports,
};
if config.switch_ports.len() > 1 {
info!(
"[Host {current_host}/{total_hosts}] Found {} ports for {} interfaces",
config.switch_ports.len(),
host.network.len()
);
info!("[Host {current_host}/{total_hosts}] Configuring host network...");
topology.configure_bond(&config).await.map_err(|e| {
InterpretError::new(format!("Failed to configure host network: {e}"))
})?;
) -> Result<(), InterpretError> {
let switch_ports = self.collect_switch_ports_for_host(topology, host).await?;
if !switch_ports.is_empty() {
topology
.configure_port_channel(&config)
.configure_host_network(host, HostNetworkConfig { switch_ports })
.await
.map_err(|e| {
InterpretError::new(format!("Failed to configure host network: {e}"))
})?;
} else if config.switch_ports.is_empty() {
info!(
"[Host {current_host}/{total_hosts}] No ports found for {} interfaces, skipping",
host.network.len()
);
} else {
warn!(
"[Host {current_host}/{total_hosts}] Found a single port for {} interfaces, skipping",
host.network.len()
);
.map_err(|e| InterpretError::new(format!("Failed to configure host: {e}")))?;
}
Ok(config)
Ok(())
}
async fn collect_switch_ports_for_host<T: Topology + Switch>(
&self,
topology: &T,
host: &PhysicalHost,
current_host: &usize,
total_hosts: &usize,
) -> Result<Vec<SwitchPort>, InterpretError> {
let mut switch_ports = vec![];
if host.network.is_empty() {
return Ok(switch_ports);
}
info!("[Host {current_host}/{total_hosts}] Collecting ports on switch...");
for network_interface in &host.network {
let mac_address = network_interface.mac_address;
match topology.get_port_for_mac_address(&mac_address).await {
Ok(Some(port)) => {
info!(
"[Host {current_host}/{total_hosts}] Found port '{port}' for '{mac_address}'"
);
switch_ports.push(SwitchPort {
interface: NetworkInterface {
name: network_interface.name.clone(),
@@ -198,7 +73,7 @@ impl HostNetworkConfigurationInterpret {
port,
});
}
Ok(None) => {}
Ok(None) => debug!("No port found for host '{}', skipping", host.id),
Err(e) => {
return Err(InterpretError::new(format!(
"Failed to get port for host '{}': {}",
@@ -210,42 +85,10 @@ impl HostNetworkConfigurationInterpret {
Ok(switch_ports)
}
fn format_host_configuration(&self, configs: Vec<HostNetworkConfig>) -> Vec<String> {
let mut report = vec![
"Network Configuration Report".to_string(),
"------------------------------------------------------------------".to_string(),
];
for config in configs {
if config.switch_ports.is_empty() {
report.push(format!(
"⏭️ Host {}: SKIPPED (No matching switch ports found)",
config.host_id
));
} else {
let mappings: Vec<String> = config
.switch_ports
.iter()
.map(|p| format!("[{} -> {}]", p.interface.name, p.port))
.collect();
report.push(format!(
"✅ Host {}: Bonded {} port(s) {}",
config.host_id,
config.switch_ports.len(),
mappings.join(", ")
));
}
}
report
.push("------------------------------------------------------------------".to_string());
report
}
}
#[async_trait]
impl<T: Topology + NetworkManager + Switch> Interpret<T> for HostNetworkConfigurationInterpret {
impl<T: Topology + Switch> Interpret<T> for HostNetworkConfigurationInterpret {
fn get_name(&self) -> InterpretName {
InterpretName::Custom("HostNetworkConfigurationInterpret")
}
@@ -271,45 +114,27 @@ impl<T: Topology + NetworkManager + Switch> Interpret<T> for HostNetworkConfigur
return Ok(Outcome::noop("No hosts to configure".into()));
}
let host_count = self.score.hosts.len();
info!("Started network configuration for {host_count} host(s)...",);
info!(
"Started network configuration for {} host(s)...",
self.score.hosts.len()
);
info!("Setting up NetworkManager...",);
topology
.ensure_network_manager_installed()
.await
.map_err(|e| InterpretError::new(format!("NetworkManager setup failed: {e}")))?;
info!("Setting up switch with sane defaults...");
topology
.setup_switch()
.await
.map_err(|e| InterpretError::new(format!("Switch setup failed: {e}")))?;
info!("Switch ready");
let mut current_host = 1;
let mut host_configurations = vec![];
let mut configured_host_count = 0;
for host in &self.score.hosts {
let host_configuration = self
.configure_network_for_host(topology, host, &current_host, &host_count)
.await?;
host_configurations.push(host_configuration);
current_host += 1;
self.configure_network_for_host(topology, host).await?;
configured_host_count += 1;
}
if current_host > 1 {
let details = self.format_host_configuration(host_configurations);
Ok(Outcome::success_with_details(
format!(
"Configured {}/{} host(s)",
current_host - 1,
if configured_host_count > 0 {
Ok(Outcome::success(format!(
"Configured {configured_host_count}/{} host(s)",
self.score.hosts.len()
),
details,
))
)))
} else {
Ok(Outcome::noop("No hosts configured".into()))
}
@@ -325,8 +150,7 @@ mod tests {
use crate::{
hardware::HostCategory,
topology::{
HostNetworkConfig, NetworkError, PreparationError, PreparationOutcome, SwitchError,
SwitchPort,
HostNetworkConfig, PreparationError, PreparationOutcome, SwitchError, SwitchPort,
},
};
use std::{
@@ -351,18 +175,6 @@ mod tests {
speed_mbps: None,
mtu: 1,
};
pub static ref YET_ANOTHER_EXISTING_INTERFACE: NetworkInterface = NetworkInterface {
mac_address: MacAddress::try_from("AA:BB:CC:DD:EE:F3".to_string()).unwrap(),
name: "interface-3".into(),
speed_mbps: None,
mtu: 1,
};
pub static ref LAST_EXISTING_INTERFACE: NetworkInterface = NetworkInterface {
mac_address: MacAddress::try_from("AA:BB:CC:DD:EE:F4".to_string()).unwrap(),
name: "interface-4".into(),
speed_mbps: None,
mtu: 1,
};
pub static ref UNKNOWN_INTERFACE: NetworkInterface = NetworkInterface {
mac_address: MacAddress::try_from("11:22:33:44:55:61".to_string()).unwrap(),
name: "unknown-interface".into(),
@@ -371,8 +183,6 @@ mod tests {
};
pub static ref PORT: PortLocation = PortLocation(1, 0, 42);
pub static ref ANOTHER_PORT: PortLocation = PortLocation(2, 0, 42);
pub static ref YET_ANOTHER_PORT: PortLocation = PortLocation(1, 0, 45);
pub static ref LAST_PORT: PortLocation = PortLocation(2, 0, 45);
}
#[tokio::test]
@@ -388,33 +198,27 @@ mod tests {
}
#[tokio::test]
async fn should_setup_network_manager() {
async fn host_with_one_mac_address_should_create_bond_with_one_interface() {
let host = given_host(&HOST_ID, vec![EXISTING_INTERFACE.clone()]);
let score = given_score(vec![host]);
let topology = TopologyWithSwitch::new();
let _ = score.interpret(&Inventory::empty(), &topology).await;
let network_manager_setup = topology.network_manager_setup.lock().unwrap();
assert_that!(*network_manager_setup).is_true();
let configured_host_networks = topology.configured_host_networks.lock().unwrap();
assert_that!(*configured_host_networks).contains_exactly(vec![(
HOST_ID.clone(),
HostNetworkConfig {
switch_ports: vec![SwitchPort {
interface: EXISTING_INTERFACE.clone(),
port: PORT.clone(),
}],
},
)]);
}
#[tokio::test]
async fn host_with_one_mac_address_should_skip_host_configuration() {
let host = given_host(&HOST_ID, vec![EXISTING_INTERFACE.clone()]);
let score = given_score(vec![host]);
let topology = TopologyWithSwitch::new();
let _ = score.interpret(&Inventory::empty(), &topology).await;
let config = topology.configured_bonds.lock().unwrap();
assert_that!(*config).is_empty();
let config = topology.configured_port_channels.lock().unwrap();
assert_that!(*config).is_empty();
}
#[tokio::test]
async fn host_with_multiple_mac_addresses_should_configure_one_bond_with_all_interfaces() {
async fn host_with_multiple_mac_addresses_should_create_one_bond_with_all_interfaces() {
let score = given_score(vec![given_host(
&HOST_ID,
vec![
@@ -426,11 +230,10 @@ mod tests {
let _ = score.interpret(&Inventory::empty(), &topology).await;
let config = topology.configured_bonds.lock().unwrap();
assert_that!(*config).contains_exactly(vec![(
let configured_host_networks = topology.configured_host_networks.lock().unwrap();
assert_that!(*configured_host_networks).contains_exactly(vec![(
HOST_ID.clone(),
HostNetworkConfig {
host_id: HOST_ID.clone(),
switch_ports: vec![
SwitchPort {
interface: EXISTING_INTERFACE.clone(),
@@ -446,183 +249,47 @@ mod tests {
}
#[tokio::test]
async fn host_with_multiple_mac_addresses_should_configure_one_port_channel_with_all_interfaces()
{
let score = given_score(vec![given_host(
&HOST_ID,
vec![
EXISTING_INTERFACE.clone(),
ANOTHER_EXISTING_INTERFACE.clone(),
],
)]);
let topology = TopologyWithSwitch::new();
let _ = score.interpret(&Inventory::empty(), &topology).await;
let config = topology.configured_port_channels.lock().unwrap();
assert_that!(*config).contains_exactly(vec![(
HOST_ID.clone(),
HostNetworkConfig {
host_id: HOST_ID.clone(),
switch_ports: vec![
SwitchPort {
interface: EXISTING_INTERFACE.clone(),
port: PORT.clone(),
},
SwitchPort {
interface: ANOTHER_EXISTING_INTERFACE.clone(),
port: ANOTHER_PORT.clone(),
},
],
},
)]);
}
#[tokio::test]
async fn multiple_hosts_should_configure_one_bond_per_host() {
async fn multiple_hosts_should_create_one_bond_per_host() {
let score = given_score(vec![
given_host(
&HOST_ID,
vec![
EXISTING_INTERFACE.clone(),
ANOTHER_EXISTING_INTERFACE.clone(),
],
),
given_host(
&ANOTHER_HOST_ID,
vec![
YET_ANOTHER_EXISTING_INTERFACE.clone(),
LAST_EXISTING_INTERFACE.clone(),
],
),
given_host(&HOST_ID, vec![EXISTING_INTERFACE.clone()]),
given_host(&ANOTHER_HOST_ID, vec![ANOTHER_EXISTING_INTERFACE.clone()]),
]);
let topology = TopologyWithSwitch::new();
let _ = score.interpret(&Inventory::empty(), &topology).await;
let config = topology.configured_bonds.lock().unwrap();
assert_that!(*config).contains_exactly(vec![
let configured_host_networks = topology.configured_host_networks.lock().unwrap();
assert_that!(*configured_host_networks).contains_exactly(vec![
(
HOST_ID.clone(),
HostNetworkConfig {
host_id: HOST_ID.clone(),
switch_ports: vec![
SwitchPort {
switch_ports: vec![SwitchPort {
interface: EXISTING_INTERFACE.clone(),
port: PORT.clone(),
},
SwitchPort {
interface: ANOTHER_EXISTING_INTERFACE.clone(),
port: ANOTHER_PORT.clone(),
},
],
}],
},
),
(
ANOTHER_HOST_ID.clone(),
HostNetworkConfig {
host_id: ANOTHER_HOST_ID.clone(),
switch_ports: vec![
SwitchPort {
interface: YET_ANOTHER_EXISTING_INTERFACE.clone(),
port: YET_ANOTHER_PORT.clone(),
},
SwitchPort {
interface: LAST_EXISTING_INTERFACE.clone(),
port: LAST_PORT.clone(),
},
],
},
),
]);
}
#[tokio::test]
async fn multiple_hosts_should_configure_one_port_channel_per_host() {
let score = given_score(vec![
given_host(
&HOST_ID,
vec![
EXISTING_INTERFACE.clone(),
ANOTHER_EXISTING_INTERFACE.clone(),
],
),
given_host(
&ANOTHER_HOST_ID,
vec![
YET_ANOTHER_EXISTING_INTERFACE.clone(),
LAST_EXISTING_INTERFACE.clone(),
],
),
]);
let topology = TopologyWithSwitch::new();
let _ = score.interpret(&Inventory::empty(), &topology).await;
let config = topology.configured_port_channels.lock().unwrap();
assert_that!(*config).contains_exactly(vec![
(
HOST_ID.clone(),
HostNetworkConfig {
host_id: HOST_ID.clone(),
switch_ports: vec![
SwitchPort {
interface: EXISTING_INTERFACE.clone(),
port: PORT.clone(),
},
SwitchPort {
switch_ports: vec![SwitchPort {
interface: ANOTHER_EXISTING_INTERFACE.clone(),
port: ANOTHER_PORT.clone(),
},
],
},
),
(
ANOTHER_HOST_ID.clone(),
HostNetworkConfig {
host_id: ANOTHER_HOST_ID.clone(),
switch_ports: vec![
SwitchPort {
interface: YET_ANOTHER_EXISTING_INTERFACE.clone(),
port: YET_ANOTHER_PORT.clone(),
},
SwitchPort {
interface: LAST_EXISTING_INTERFACE.clone(),
port: LAST_PORT.clone(),
},
],
}],
},
),
]);
}
#[tokio::test]
async fn port_not_found_for_mac_address_should_not_configure_host() {
async fn port_not_found_for_mac_address_should_not_configure_interface() {
let score = given_score(vec![given_host(&HOST_ID, vec![UNKNOWN_INTERFACE.clone()])]);
let topology = TopologyWithSwitch::new_port_not_found();
let _ = score.interpret(&Inventory::empty(), &topology).await;
let config = topology.configured_port_channels.lock().unwrap();
assert_that!(*config).is_empty();
let config = topology.configured_bonds.lock().unwrap();
assert_that!(*config).is_empty();
}
#[tokio::test]
async fn only_one_port_found_for_multiple_mac_addresses_should_not_configure_host() {
let score = given_score(vec![given_host(
&HOST_ID,
vec![EXISTING_INTERFACE.clone(), UNKNOWN_INTERFACE.clone()],
)]);
let topology = TopologyWithSwitch::new_single_port_found();
let _ = score.interpret(&Inventory::empty(), &topology).await;
let config = topology.configured_port_channels.lock().unwrap();
assert_that!(*config).is_empty();
let config = topology.configured_bonds.lock().unwrap();
assert_that!(*config).is_empty();
let configured_host_networks = topology.configured_host_networks.lock().unwrap();
assert_that!(*configured_host_networks).is_empty();
}
fn given_score(hosts: Vec<PhysicalHost>) -> HostNetworkConfigurationScore {
@@ -659,48 +326,26 @@ mod tests {
}
}
#[derive(Debug)]
struct TopologyWithSwitch {
available_ports: Arc<Mutex<Vec<PortLocation>>>,
configured_port_channels: Arc<Mutex<Vec<(Id, HostNetworkConfig)>>>,
configured_host_networks: Arc<Mutex<Vec<(Id, HostNetworkConfig)>>>,
switch_setup: Arc<Mutex<bool>>,
network_manager_setup: Arc<Mutex<bool>>,
configured_bonds: Arc<Mutex<Vec<(Id, HostNetworkConfig)>>>,
}
impl TopologyWithSwitch {
fn new() -> Self {
Self {
available_ports: Arc::new(Mutex::new(vec![
PORT.clone(),
ANOTHER_PORT.clone(),
YET_ANOTHER_PORT.clone(),
LAST_PORT.clone(),
])),
configured_port_channels: Arc::new(Mutex::new(vec![])),
available_ports: Arc::new(Mutex::new(vec![PORT.clone(), ANOTHER_PORT.clone()])),
configured_host_networks: Arc::new(Mutex::new(vec![])),
switch_setup: Arc::new(Mutex::new(false)),
network_manager_setup: Arc::new(Mutex::new(false)),
configured_bonds: Arc::new(Mutex::new(vec![])),
}
}
fn new_port_not_found() -> Self {
Self {
available_ports: Arc::new(Mutex::new(vec![])),
configured_port_channels: Arc::new(Mutex::new(vec![])),
configured_host_networks: Arc::new(Mutex::new(vec![])),
switch_setup: Arc::new(Mutex::new(false)),
network_manager_setup: Arc::new(Mutex::new(false)),
configured_bonds: Arc::new(Mutex::new(vec![])),
}
}
fn new_single_port_found() -> Self {
Self {
available_ports: Arc::new(Mutex::new(vec![PORT.clone()])),
configured_port_channels: Arc::new(Mutex::new(vec![])),
switch_setup: Arc::new(Mutex::new(false)),
network_manager_setup: Arc::new(Mutex::new(false)),
configured_bonds: Arc::new(Mutex::new(vec![])),
}
}
}
@@ -716,22 +361,6 @@ mod tests {
}
}
#[async_trait]
impl NetworkManager for TopologyWithSwitch {
async fn ensure_network_manager_installed(&self) -> Result<(), NetworkError> {
let mut network_manager_installed = self.network_manager_setup.lock().unwrap();
*network_manager_installed = true;
Ok(())
}
async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), NetworkError> {
let mut configured_bonds = self.configured_bonds.lock().unwrap();
configured_bonds.push((config.host_id.clone(), config.clone()));
Ok(())
}
}
#[async_trait]
impl Switch for TopologyWithSwitch {
async fn setup_switch(&self) -> Result<(), SwitchError> {
@@ -751,12 +380,13 @@ mod tests {
Ok(Some(ports.remove(0)))
}
async fn configure_port_channel(
async fn configure_host_network(
&self,
config: &HostNetworkConfig,
host: &PhysicalHost,
config: HostNetworkConfig,
) -> Result<(), SwitchError> {
let mut configured_port_channels = self.configured_port_channels.lock().unwrap();
configured_port_channels.push((config.host_id.clone(), config.clone()));
let mut configured_host_networks = self.configured_host_networks.lock().unwrap();
configured_host_networks.push((host.id.clone(), config.clone()));
Ok(())
}

View File

@@ -50,7 +50,7 @@
use crate::{
modules::okd::{
OKDSetup01InventoryScore, OKDSetup02BootstrapScore, OKDSetup03ControlPlaneScore,
OKDSetup04WorkersScore, OKDSetup05SanityCheckScore, OKDSetupPersistNetworkBondScore,
OKDSetup04WorkersScore, OKDSetup05SanityCheckScore,
bootstrap_06_installation_report::OKDSetup06InstallationReportScore,
},
score::Score,
@@ -65,7 +65,6 @@ impl OKDInstallationPipeline {
Box::new(OKDSetup01InventoryScore::new()),
Box::new(OKDSetup02BootstrapScore::new()),
Box::new(OKDSetup03ControlPlaneScore::new()),
Box::new(OKDSetupPersistNetworkBondScore::new()),
Box::new(OKDSetup04WorkersScore::new()),
Box::new(OKDSetup05SanityCheckScore::new()),
Box::new(OKDSetup06InstallationReportScore::new()),

View File

@@ -6,7 +6,6 @@ mod bootstrap_05_sanity_check;
mod bootstrap_06_installation_report;
pub mod bootstrap_dhcp;
pub mod bootstrap_load_balancer;
mod bootstrap_persist_network_bond;
pub mod dhcp;
pub mod dns;
pub mod installation;
@@ -20,6 +19,5 @@ pub use bootstrap_03_control_plane::*;
pub use bootstrap_04_workers::*;
pub use bootstrap_05_sanity_check::*;
pub use bootstrap_06_installation_report::*;
pub use bootstrap_persist_network_bond::*;
pub mod crd;
pub mod host_network;

View File

@@ -12,8 +12,7 @@ use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::C
use crate::modules::monitoring::kube_prometheus::crd::crd_default_rules::build_default_application_rules;
use crate::modules::monitoring::kube_prometheus::crd::crd_grafana::{
Grafana, GrafanaDashboard, GrafanaDashboardSpec, GrafanaDatasource, GrafanaDatasourceConfig,
GrafanaDatasourceJsonData, GrafanaDatasourceSpec, GrafanaSecretKeyRef, GrafanaSpec,
GrafanaValueFrom, GrafanaValueSource,
GrafanaDatasourceSpec, GrafanaSpec,
};
use crate::modules::monitoring::kube_prometheus::crd::crd_prometheus_rules::{
PrometheusRule, PrometheusRuleSpec, RuleGroup,
@@ -40,7 +39,7 @@ use crate::{
};
use harmony_types::id::Id;
use super::prometheus::PrometheusMonitoring;
use super::prometheus::PrometheusApplicationMonitoring;
#[derive(Clone, Debug, Serialize)]
pub struct K8sPrometheusCRDAlertingScore {
@@ -50,7 +49,7 @@ pub struct K8sPrometheusCRDAlertingScore {
pub prometheus_rules: Vec<RuleGroup>,
}
impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus>> Score<T>
impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
for K8sPrometheusCRDAlertingScore
{
fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
@@ -76,7 +75,7 @@ pub struct K8sPrometheusCRDAlertingInterpret {
}
#[async_trait]
impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus>> Interpret<T>
impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
for K8sPrometheusCRDAlertingInterpret
{
async fn execute(
@@ -467,13 +466,10 @@ impl K8sPrometheusCRDAlertingInterpret {
match_labels: label.clone(),
match_expressions: vec![],
};
let mut json_data = BTreeMap::new();
json_data.insert("timeInterval".to_string(), "5s".to_string());
let namespace = self.sender.namespace.clone();
let json_data = GrafanaDatasourceJsonData {
time_interval: Some("5s".to_string()),
http_header_name1: None,
tls_skip_verify: Some(true),
oauth_pass_thru: Some(true),
};
let json = build_default_dashboard(&namespace);
let graf_data_source = GrafanaDatasource {
@@ -499,11 +495,7 @@ impl K8sPrometheusCRDAlertingInterpret {
"http://prometheus-operated.{}.svc.cluster.local:9090",
self.sender.namespace.clone()
),
secure_json_data: None,
is_default: None,
editable: None,
},
values_from: None,
},
};
@@ -524,9 +516,7 @@ impl K8sPrometheusCRDAlertingInterpret {
spec: GrafanaDashboardSpec {
resync_period: Some("30s".to_string()),
instance_selector: labels.clone(),
json: Some(json),
grafana_com: None,
datasources: None,
json,
},
};

View File

@@ -9,17 +9,11 @@ use crate::{
};
#[async_trait]
pub trait PrometheusMonitoring<S: AlertSender> {
pub trait PrometheusApplicationMonitoring<S: AlertSender> {
async fn install_prometheus(
&self,
sender: &S,
inventory: &Inventory,
receivers: Option<Vec<Box<dyn AlertReceiver<S>>>>,
) -> Result<PreparationOutcome, PreparationError>;
async fn ensure_prometheus_operator(
&self,
sender: &S,
inventory: &Inventory,
) -> Result<PreparationOutcome, PreparationError>;
}

View File

@@ -38,7 +38,7 @@ use crate::{
};
use harmony_types::id::Id;
use super::prometheus::PrometheusMonitoring;
use super::prometheus::PrometheusApplicationMonitoring;
#[derive(Clone, Debug, Serialize)]
pub struct RHOBAlertingScore {
@@ -48,8 +48,8 @@ pub struct RHOBAlertingScore {
pub prometheus_rules: Vec<RuleGroup>,
}
impl<T: Topology + K8sclient + Ingress + PrometheusMonitoring<RHOBObservability>> Score<T>
for RHOBAlertingScore
impl<T: Topology + K8sclient + Ingress + PrometheusApplicationMonitoring<RHOBObservability>>
Score<T> for RHOBAlertingScore
{
fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
Box::new(RHOBAlertingInterpret {
@@ -74,8 +74,8 @@ pub struct RHOBAlertingInterpret {
}
#[async_trait]
impl<T: Topology + K8sclient + Ingress + PrometheusMonitoring<RHOBObservability>> Interpret<T>
for RHOBAlertingInterpret
impl<T: Topology + K8sclient + Ingress + PrometheusApplicationMonitoring<RHOBObservability>>
Interpret<T> for RHOBAlertingInterpret
{
async fn execute(
&self,

View File

@@ -40,7 +40,7 @@ pub fn init() {
HarmonyEvent::HarmonyFinished => {
if !details.is_empty() {
println!(
"\n{} All done! Here's a few info for you:",
"\n{} All done! Here's what's next for you:",
theme::EMOJI_SUMMARY
);
for detail in details.iter() {

View File

@@ -1,6 +1,6 @@
use serde::{Deserialize, Serialize};
#[derive(Copy, Clone, PartialEq, Eq, Hash, Serialize, Deserialize, PartialOrd, Ord)]
#[derive(Copy, Clone, Debug, PartialEq, Eq, Hash, Serialize, Deserialize, PartialOrd, Ord)]
pub struct MacAddress(pub [u8; 6]);
impl MacAddress {
@@ -19,14 +19,6 @@ impl From<&MacAddress> for String {
}
}
impl std::fmt::Debug for MacAddress {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_tuple("MacAddress")
.field(&String::from(self))
.finish()
}
}
impl std::fmt::Display for MacAddress {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_str(&String::from(self))

View File

@@ -9,7 +9,7 @@ pub struct Interface {
pub physical_interface_name: String,
pub descr: Option<MaybeString>,
pub mtu: Option<MaybeString>,
pub enable: Option<MaybeString>,
pub enable: MaybeString,
pub lock: Option<MaybeString>,
#[yaserde(rename = "spoofmac")]
pub spoof_mac: Option<MaybeString>,
@@ -134,15 +134,19 @@ mod test {
<interfaces>
<paul>
<if></if>
<enable/>
</paul>
<anotherpaul>
<if></if>
<enable/>
</anotherpaul>
<thirdone>
<if></if>
<enable/>
</thirdone>
<andgofor4>
<if></if>
<enable/>
</andgofor4>
</interfaces>
<bar>foo</bar>