Files
harmony/harmony/src/modules/okd/bootstrap_persist_network_bond.rs
Ian Letourneau c80ede706b
Some checks failed
Run Check Script / check (push) Successful in 1m20s
Compile and package harmony_composer / package_harmony_composer (push) Failing after 2m21s
fix(host_network): adjust bond & port-channel configuration (partial) (#175)
## Description
* Replace the CatalogSource approach to install the OperatorHub.io catalog by a more simple & straightforward way to install NMState
* Improve logging
* Add report summarizing the host network configuration that was applied (which host, bonds, port-channels)
* Fix command to find next available port channel id

## Extra info
Using the `apply_url` approach to install the NMState operator isn't the best approach: it's harder to maintain and upgrade. But it helps us achieve waht we wanted for now: install the NMState Operator to configure bonds on a host.

The preferred approach, installing an operator from the OperatorHub.io catalog, didn't work for now. We had a timeout error with DeadlineExceeded probably caused by an insufficient CPU/Memory allocation to query such a big catalog, even though we tweaked the RAM allocation (we couldn't find a way to do it for CPU).

Spent too much time on this so we stopped these efforts for now. It would be good to get back to it when we need to install something else from a custom catalog.

Reviewed-on: #175
2025-10-29 17:09:16 +00:00

131 lines
3.9 KiB
Rust

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(),
)),
}
}
}