Compare commits

..

10 Commits

Author SHA1 Message Date
c2fa4f1869 fix:cargo fmt
All checks were successful
Run Check Script / check (pull_request) Successful in 1m21s
2025-10-29 13:53:58 -04:00
ee278ac817 Merge remote-tracking branch 'origin/master' into feat/install_opnsense_node_exporter
Some checks failed
Run Check Script / check (pull_request) Failing after 25s
2025-10-29 13:49:56 -04:00
09a06f136e Merge remote-tracking branch 'origin/master' into feat/install_opnsense_node_exporter
All checks were successful
Run Check Script / check (pull_request) Successful in 1m21s
2025-10-29 13:42:12 -04:00
5f147fa672 fix: opnsense-config reload_config() returns live config.xml rather than dropping it, allows function is_package_installed() to read live state after package installation rather than old config before installation
All checks were successful
Run Check Script / check (pull_request) Successful in 1m17s
2025-10-29 13:25:37 -04:00
c80ede706b fix(host_network): adjust bond & port-channel configuration (partial) (#175)
Some checks failed
Run Check Script / check (push) Successful in 1m20s
Compile and package harmony_composer / package_harmony_composer (push) Failing after 2m21s
## 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
9ba939bde1 wip: cargo fmt
All checks were successful
Run Check Script / check (pull_request) Successful in 1m16s
2025-10-28 15:45:02 -04:00
44bf21718c wip: example score with impl topolgy for opnsense topology 2025-10-28 14:41:15 -04:00
5ab58f0253 fix: added impl node exporter for hacluster topology and dummy infra
All checks were successful
Run Check Script / check (pull_request) Successful in 1m26s
2025-10-22 14:39:12 -04:00
5af13800b7 fix: removed unimplemnted marco and returned Err instead
Some checks failed
Run Check Script / check (pull_request) Failing after 29s
some formatting error
2025-10-22 11:51:22 -04:00
8126b233d8 feat: implementation for opnsense os-node_exporter
Some checks failed
Run Check Script / check (pull_request) Failing after 41s
2025-10-22 11:27:28 -04:00
44 changed files with 1024 additions and 810 deletions

View File

@@ -31,6 +31,7 @@ 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,
}
@@ -40,6 +41,7 @@ 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),
}

View File

@@ -3,6 +3,7 @@ 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,
@@ -103,13 +104,37 @@ 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]
@@ -197,11 +222,10 @@ impl BrocadeClient for NetworkOperatingSystemClient {
commands.push("exit".into());
}
commands.push("write memory".into());
self.shell
.run_commands(commands, ExecutionMode::Regular)
.await?;
.await
.map_err(|err| self.map_configure_interfaces_error(err))?;
info!("[Brocade] Interfaces configured.");
@@ -213,7 +237,7 @@ impl BrocadeClient for NetworkOperatingSystemClient {
let output = self
.shell
.run_command("show port-channel", ExecutionMode::Regular)
.run_command("show port-channel summary", ExecutionMode::Regular)
.await?;
let used_ids: Vec<u8> = output
@@ -248,7 +272,12 @@ impl BrocadeClient for NetworkOperatingSystemClient {
ports: &[PortLocation],
) -> Result<(), Error> {
info!(
"[Brocade] Configuring port-channel '{channel_name} {channel_id}' with ports: {ports:?}"
"[Brocade] Configuring port-channel '{channel_id} {channel_name}' with ports: {}",
ports
.iter()
.map(|p| format!("{p}"))
.collect::<Vec<String>>()
.join(", ")
);
let interfaces = self.get_interfaces().await?;
@@ -276,8 +305,6 @@ impl BrocadeClient for NetworkOperatingSystemClient {
commands.push("exit".into());
}
commands.push("write memory".into());
self.shell
.run_commands(commands, ExecutionMode::Regular)
.await?;
@@ -294,7 +321,6 @@ impl BrocadeClient for NetworkOperatingSystemClient {
"configure terminal".into(),
format!("no interface port-channel {}", channel_name),
"exit".into(),
"write memory".into(),
];
self.shell

View File

@@ -211,7 +211,7 @@ impl BrocadeSession {
let mut output = Vec::new();
let start = Instant::now();
let read_timeout = Duration::from_millis(500);
let log_interval = Duration::from_secs(3);
let log_interval = Duration::from_secs(5);
let mut last_log = Instant::now();
loop {
@@ -221,7 +221,9 @@ impl BrocadeSession {
));
}
if start.elapsed() > Duration::from_secs(5) && last_log.elapsed() > log_interval {
if start.elapsed() > self.options.timeouts.command_output
&& last_log.elapsed() > log_interval
{
info!("[Brocade] Waiting for command output...");
last_log = Instant::now();
}
@@ -276,7 +278,7 @@ impl BrocadeSession {
let output_lower = output.to_lowercase();
if ERROR_PATTERNS.iter().any(|&p| output_lower.contains(p)) {
return Err(Error::CommandError(format!(
"Command '{command}' failed: {}",
"Command error: {}",
output.trim()
)));
}

View File

@@ -61,6 +61,7 @@ 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(
@@ -105,6 +106,7 @@ async fn main() {
name: "wk2".to_string(),
},
],
node_exporter: opnsense.clone(),
switch_client: switch_client.clone(),
};

View File

@@ -1,26 +0,0 @@
use harmony::{
inventory::Inventory,
modules::monitoring::{
alert_channel::discord_alert_channel::DiscordWebhook,
okd::cluster_monitoring::OpenshiftClusterAlertScore,
},
topology::K8sAnywhereTopology,
};
use harmony_macros::hurl;
#[tokio::main]
async fn main() {
harmony_cli::run(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(OpenshiftClusterAlertScore {
receivers: vec![Box::new(DiscordWebhook {
name: "Webhook example".to_string(),
url: hurl!("http://something.o"),
})],
})],
None,
)
.await
.unwrap();
}

View File

@@ -59,6 +59,7 @@ 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,
@@ -79,6 +80,7 @@ pub async fn get_topology() -> HAClusterTopology {
name: "bootstrap".to_string(),
},
workers: vec![],
node_exporter: opnsense.clone(),
switch_client: switch_client.clone(),
}
}

View File

@@ -54,6 +54,7 @@ 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,
@@ -74,6 +75,7 @@ pub async fn get_topology() -> HAClusterTopology {
name: "cp0".to_string(),
},
workers: vec![],
node_exporter: opnsense.clone(),
switch_client: switch_client.clone(),
}
}

View File

@@ -57,6 +57,7 @@ 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,
@@ -77,6 +78,7 @@ async fn main() {
name: "cp0".to_string(),
},
workers: vec![],
node_exporter: opnsense.clone(),
switch_client: switch_client.clone(),
};

View File

@@ -1,10 +1,9 @@
[package]
name = "example-okd-cluster-alerts"
name = "example-opnsense-node-exporter"
edition = "2024"
version.workspace = true
readme.workspace = true
license.workspace = true
publish = false
[dependencies]
harmony = { path = "../../harmony" }
@@ -19,4 +18,4 @@ log = { workspace = true }
env_logger = { workspace = true }
url = { workspace = true }
serde.workspace = true
brocade = { path = "../../brocade" }
async-trait.workspace = true

View File

@@ -0,0 +1,79 @@
use std::{
net::{IpAddr, Ipv4Addr},
sync::Arc,
};
use async_trait::async_trait;
use cidr::Ipv4Cidr;
use harmony::{
executors::ExecutorError,
hardware::{HostCategory, Location, PhysicalHost, SwitchGroup},
infra::opnsense::OPNSenseManagementInterface,
inventory::Inventory,
modules::opnsense::node_exporter::NodeExporterScore,
topology::{
HAClusterTopology, LogicalHost, PreparationError, PreparationOutcome, Topology,
UnmanagedRouter, node_exporter::NodeExporter,
},
};
use harmony_macros::{ip, ipv4, mac_address};
struct OpnSenseTopology {
node_exporter: Arc<dyn NodeExporter>,
}
#[async_trait]
impl Topology for OpnSenseTopology {
async fn ensure_ready(&self) -> Result<PreparationOutcome, PreparationError> {
Ok(PreparationOutcome::Success {
details: "Success".to_string(),
})
}
fn name(&self) -> &str {
"OpnsenseTopology"
}
}
#[async_trait]
impl NodeExporter for OpnSenseTopology {
async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
self.node_exporter.ensure_initialized().await
}
async fn commit_config(&self) -> Result<(), ExecutorError> {
self.node_exporter.commit_config().await
}
async fn reload_restart(&self) -> Result<(), ExecutorError> {
self.node_exporter.reload_restart().await
}
}
#[tokio::main]
async fn main() {
let firewall = harmony::topology::LogicalHost {
ip: ip!("192.168.1.1"),
name: String::from("fw0"),
};
let opnsense = Arc::new(
harmony::infra::opnsense::OPNSenseFirewall::new(firewall, None, "root", "opnsense").await,
);
let topology = OpnSenseTopology {
node_exporter: opnsense.clone(),
};
let inventory = Inventory::empty();
let node_exporter_score = NodeExporterScore {};
harmony_cli::run(
inventory,
topology,
vec![Box::new(node_exporter_score)],
None,
)
.await
.unwrap();
}

View File

@@ -4,19 +4,19 @@ use harmony_types::{
net::{MacAddress, Url},
switch::PortLocation,
};
use k8s_openapi::api::core::v1::Namespace;
use kube::api::ObjectMeta;
use log::debug;
use log::info;
use crate::data::FileContent;
use crate::executors::ExecutorError;
use crate::hardware::PhysicalHost;
use crate::modules::okd::crd::{
InstallPlanApproval, OperatorGroup, OperatorGroupSpec, Subscription, SubscriptionSpec,
nmstate::{self, NMState, NodeNetworkConfigurationPolicy, NodeNetworkConfigurationPolicySpec},
};
use crate::topology::PxeOptions;
use crate::{data::FileContent, modules::okd::crd::nmstate::NMState};
use crate::{
executors::ExecutorError, modules::okd::crd::nmstate::NodeNetworkConfigurationPolicySpec,
};
use crate::{
modules::okd::crd::nmstate::{self, NodeNetworkConfigurationPolicy},
topology::node_exporter::NodeExporter,
};
use super::{
DHCPStaticEntry, DhcpServer, DnsRecord, DnsRecordType, DnsServer, Firewall, HostNetworkConfig,
@@ -38,10 +38,12 @@ pub struct HAClusterTopology {
pub tftp_server: Arc<dyn TftpServer>,
pub http_server: Arc<dyn HttpServer>,
pub dns_server: Arc<dyn DnsServer>,
pub node_exporter: Arc<dyn NodeExporter>,
pub switch_client: Arc<dyn SwitchClient>,
pub bootstrap_host: LogicalHost,
pub control_plane: Vec<LogicalHost>,
pub workers: Vec<LogicalHost>,
pub kubeconfig: Option<String>,
}
#[async_trait]
@@ -60,9 +62,17 @@ impl Topology for HAClusterTopology {
#[async_trait]
impl K8sclient for HAClusterTopology {
async fn k8s_client(&self) -> Result<Arc<K8sClient>, String> {
Ok(Arc::new(
K8sClient::try_default().await.map_err(|e| e.to_string())?,
))
match &self.kubeconfig {
None => 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))
}
}
}
}
@@ -88,60 +98,48 @@ impl HAClusterTopology {
}
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?;
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)
debug!("Installing NMState controller...");
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
.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)
debug!("Creating NMState namespace...");
k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/namespace.yaml
").unwrap(), Some("nmstate"))
.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)
debug!("Creating NMState service account...");
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
.map_err(|e| e.to_string())?;
debug!("Creating NMState role...");
k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/role.yaml
").unwrap(), Some("nmstate"))
.await
.map_err(|e| e.to_string())?;
debug!("Creating NMState role binding...");
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
.map_err(|e| e.to_string())?;
debug!("Creating NMState operator...");
k8s_client.apply_url(url::Url::parse("https://github.com/nmstate/kubernetes-nmstate/releases/download/v0.84.0/operator.yaml
").unwrap(), Some("nmstate"))
.await
.map_err(|e| e.to_string())?;
k8s_client
.wait_until_deployment_ready("nmstate-operator", Some("nmstate"), None)
.await?;
let nmstate = NMState {
metadata: ObjectMeta {
name: Some("nmstate".to_string()),
@@ -162,11 +160,7 @@ impl HAClusterTopology {
42 // FIXME: Find a better way to declare the bond id
}
async fn configure_bond(
&self,
host: &PhysicalHost,
config: &HostNetworkConfig,
) -> Result<(), SwitchError> {
async fn configure_bond(&self, config: &HostNetworkConfig) -> Result<(), SwitchError> {
self.ensure_nmstate_operator_installed()
.await
.map_err(|e| {
@@ -175,29 +169,33 @@ impl HAClusterTopology {
))
})?;
let bond_config = self.create_bond_configuration(host, config);
debug!("Configuring bond for host {host:?}: {bond_config:#?}");
let bond_config = self.create_bond_configuration(config);
debug!(
"Applying NMState bond config for host {}: {bond_config:#?}",
config.host_id
);
self.k8s_client()
.await
.unwrap()
.apply(&bond_config, None)
.await
.unwrap();
.map_err(|e| SwitchError::new(format!("Failed to configure bond: {e}")))?;
todo!()
Ok(())
}
fn create_bond_configuration(
&self,
host: &PhysicalHost,
config: &HostNetworkConfig,
) -> NodeNetworkConfigurationPolicy {
let host_name = host.id.clone();
let host_name = &config.host_id;
let bond_id = self.get_next_bond_id();
let bond_name = format!("bond{bond_id}");
info!("Configuring bond '{bond_name}' for host '{host_name}'...");
let mut bond_mtu: Option<u32> = None;
let mut bond_mac_address: Option<String> = None;
let mut copy_mac_from: Option<String> = None;
let mut bond_ports = Vec::new();
let mut interfaces: Vec<nmstate::InterfaceSpec> = Vec::new();
@@ -223,14 +221,14 @@ impl HAClusterTopology {
..Default::default()
});
bond_ports.push(interface_name);
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 bond_mac_address.is_none() {
bond_mac_address = Some(switch_port.interface.mac_address.to_string());
if copy_mac_from.is_none() {
copy_mac_from = Some(interface_name);
}
}
@@ -239,8 +237,7 @@ impl HAClusterTopology {
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,
copy_mac_from,
ipv4: Some(nmstate::IpStackSpec {
dhcp: Some(true),
enabled: Some(true),
@@ -275,16 +272,12 @@ impl HAClusterTopology {
}
}
async fn configure_port_channel(
&self,
host: &PhysicalHost,
config: &HostNetworkConfig,
) -> Result<(), SwitchError> {
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_{}", host.id), switch_ports)
.configure_port_channel(&format!("Harmony_{}", config.host_id), switch_ports)
.await
.map_err(|e| SwitchError::new(format!("Failed to configure switch: {e}")))?;
@@ -299,6 +292,7 @@ impl HAClusterTopology {
};
Self {
kubeconfig: None,
domain_name: "DummyTopology".to_string(),
router: dummy_infra.clone(),
load_balancer: dummy_infra.clone(),
@@ -307,6 +301,7 @@ impl HAClusterTopology {
tftp_server: dummy_infra.clone(),
http_server: dummy_infra.clone(),
dns_server: dummy_infra.clone(),
node_exporter: dummy_infra.clone(),
switch_client: dummy_infra.clone(),
bootstrap_host: dummy_host,
control_plane: vec![],
@@ -480,13 +475,26 @@ impl Switch for HAClusterTopology {
Ok(port)
}
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
async fn configure_host_network(&self, config: &HostNetworkConfig) -> Result<(), SwitchError> {
self.configure_bond(config).await?;
self.configure_port_channel(config).await
}
//TODO add snmp here
}
#[async_trait]
impl NodeExporter for HAClusterTopology {
async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
self.node_exporter.ensure_initialized().await
}
async fn commit_config(&self) -> Result<(), ExecutorError> {
self.node_exporter.commit_config().await
}
async fn reload_restart(&self) -> Result<(), ExecutorError> {
self.node_exporter.reload_restart().await
}
}
@@ -677,6 +685,21 @@ impl DnsServer for DummyInfra {
}
}
#[async_trait]
impl NodeExporter for DummyInfra {
async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
}
async fn commit_config(&self) -> Result<(), ExecutorError> {
unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
}
async fn reload_restart(&self) -> Result<(), ExecutorError> {
unimplemented!("{}", UNIMPLEMENTED_DUMMY_INFRA)
}
}
#[async_trait]
impl SwitchClient for DummyInfra {
async fn setup(&self) -> Result<(), SwitchError> {

View File

@@ -14,6 +14,7 @@ use kube::{
api::{Api, AttachParams, DeleteParams, ListParams, Patch, PatchParams, ResourceExt},
config::{KubeConfigOptions, Kubeconfig},
core::ErrorResponse,
discovery::{ApiCapabilities, Scope},
error::DiscoveryError,
runtime::reflector::Lookup,
};
@@ -22,11 +23,12 @@ use kube::{
api::{ApiResource, GroupVersionKind},
runtime::wait::await_condition,
};
use log::{debug, error, info, trace};
use log::{debug, error, info, trace, warn};
use serde::{Serialize, de::DeserializeOwned};
use serde_json::json;
use similar::TextDiff;
use tokio::{io::AsyncReadExt, time::sleep};
use url::Url;
#[derive(new, Clone)]
pub struct K8sClient {
@@ -88,7 +90,8 @@ impl K8sClient {
} else {
Api::default_namespaced_with(self.client.clone(), &gvk)
};
Ok(resource.get(name).await?)
resource.get(name).await
}
pub async fn get_deployment(
@@ -103,8 +106,9 @@ impl K8sClient {
debug!("getting default namespace deployment");
Api::default_namespaced(self.client.clone())
};
debug!("getting deployment {} in ns {}", name, namespace.unwrap());
Ok(deps.get_opt(name).await?)
deps.get_opt(name).await
}
pub async fn get_pod(&self, name: &str, namespace: Option<&str>) -> Result<Option<Pod>, Error> {
@@ -113,7 +117,8 @@ impl K8sClient {
} else {
Api::default_namespaced(self.client.clone())
};
Ok(pods.get_opt(name).await?)
pods.get_opt(name).await
}
pub async fn scale_deployment(
@@ -156,9 +161,9 @@ impl K8sClient {
pub async fn wait_until_deployment_ready(
&self,
name: String,
name: &str,
namespace: Option<&str>,
timeout: Option<u64>,
timeout: Option<Duration>,
) -> Result<(), String> {
let api: Api<Deployment>;
@@ -168,9 +173,9 @@ impl K8sClient {
api = Api::default_namespaced(self.client.clone());
}
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;
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;
if res.is_ok() {
Ok(())
@@ -260,7 +265,7 @@ impl K8sClient {
if let Some(s) = status.status {
let mut stdout_buf = String::new();
if let Some(mut stdout) = process.stdout().take() {
if let Some(mut stdout) = process.stdout() {
stdout
.read_to_string(&mut stdout_buf)
.await
@@ -366,14 +371,14 @@ 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 {}/{}",
@@ -402,14 +407,14 @@ 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:"
);
@@ -418,14 +423,14 @@ 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)
}
}
@@ -440,7 +445,7 @@ impl K8sClient {
where
K: Resource + Clone + std::fmt::Debug + DeserializeOwned + serde::Serialize,
<K as Resource>::Scope: ApplyStrategy<K>,
<K as kube::Resource>::DynamicType: Default,
<K as Resource>::DynamicType: Default,
{
let mut result = Vec::new();
for r in resource.iter() {
@@ -505,10 +510,7 @@ 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 Argo Application '{}' in namespace '{}'...",
name, namespace
);
println!("Applying '{name}' in namespace '{namespace}'...",);
let patch_params = PatchParams::apply("harmony"); // Use a unique field manager name
let result = api.patch(name, &patch_params, &Patch::Apply(&obj)).await?;
@@ -517,6 +519,51 @@ 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(())
}
pub(crate) async fn from_kubeconfig(path: &str) -> Option<K8sClient> {
let k = match Kubeconfig::read_from(path) {
Ok(k) => k,
@@ -536,6 +583,31 @@ 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

@@ -1,4 +1,4 @@
use std::{collections::BTreeMap, process::Command, sync::Arc};
use std::{collections::BTreeMap, process::Command, sync::Arc, time::Duration};
use async_trait::async_trait;
use base64::{Engine, engine::general_purpose};
@@ -155,9 +155,9 @@ impl Grafana for K8sAnywhereTopology {
//TODO change this to a ensure ready or something better than just a timeout
client
.wait_until_deployment_ready(
"grafana-grafana-deployment".to_string(),
"grafana-grafana-deployment",
Some("grafana"),
Some(30),
Some(Duration::from_secs(30)),
)
.await?;

View File

@@ -1,5 +1,6 @@
mod ha_cluster;
pub mod ingress;
pub mod node_exporter;
use harmony_types::net::IpAddress;
mod host_binding;
mod http;

View File

@@ -9,6 +9,7 @@ use std::{
use async_trait::async_trait;
use derive_new::new;
use harmony_types::{
id::Id,
net::{IpAddress, MacAddress},
switch::PortLocation,
};
@@ -191,15 +192,12 @@ pub trait Switch: Send + Sync {
mac_address: &MacAddress,
) -> Result<Option<PortLocation>, SwitchError>;
async fn configure_host_network(
&self,
host: &PhysicalHost,
config: HostNetworkConfig,
) -> Result<(), SwitchError>;
async fn configure_host_network(&self, config: &HostNetworkConfig) -> Result<(), SwitchError>;
}
#[derive(Clone, Debug, PartialEq)]
pub struct HostNetworkConfig {
pub host_id: Id,
pub switch_ports: Vec<SwitchPort>,
}

View File

@@ -0,0 +1,17 @@
use async_trait::async_trait;
use crate::executors::ExecutorError;
#[async_trait]
pub trait NodeExporter: Send + Sync {
async fn ensure_initialized(&self) -> Result<(), ExecutorError>;
async fn commit_config(&self) -> Result<(), ExecutorError>;
async fn reload_restart(&self) -> Result<(), ExecutorError>;
}
//TODO complete this impl
impl std::fmt::Debug for dyn NodeExporter {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.write_fmt(format_args!("NodeExporter ",))
}
}

View File

@@ -1,7 +1,6 @@
use std::any::Any;
use async_trait::async_trait;
use kube::api::DynamicObject;
use log::debug;
use crate::{
@@ -77,14 +76,6 @@ pub trait AlertReceiver<S: AlertSender>: std::fmt::Debug + Send + Sync {
fn name(&self) -> String;
fn clone_box(&self) -> Box<dyn AlertReceiver<S>>;
fn as_any(&self) -> &dyn Any;
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver;
}
#[derive(Debug)]
pub struct AlertManagerReceiver {
pub receiver_config: serde_json::Value,
// FIXME we should not leak k8s here. DynamicObject is k8s specific
pub additional_ressources: Vec<DynamicObject>,
}
#[async_trait]

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

@@ -3,6 +3,5 @@ pub mod executors;
pub mod hp_ilo;
pub mod intel_amt;
pub mod inventory;
pub mod kube;
pub mod opnsense;
mod sqlx;

View File

@@ -4,6 +4,7 @@ mod firewall;
mod http;
mod load_balancer;
mod management;
pub mod node_exporter;
mod tftp;
use std::sync::Arc;

View File

@@ -0,0 +1,47 @@
use async_trait::async_trait;
use log::debug;
use crate::{
executors::ExecutorError, infra::opnsense::OPNSenseFirewall,
topology::node_exporter::NodeExporter,
};
#[async_trait]
impl NodeExporter for OPNSenseFirewall {
async fn ensure_initialized(&self) -> Result<(), ExecutorError> {
let mut config = self.opnsense_config.write().await;
let node_exporter = config.node_exporter();
if let Some(config) = node_exporter.get_full_config() {
debug!(
"Node exporter available in opnsense config, assuming it is already installed. {config:?}"
);
} else {
config
.install_package("os-node_exporter")
.await
.map_err(|e| {
ExecutorError::UnexpectedError(format!("Executor failed when trying to install os-node_exporter package with error {e:?}"
))
})?;
}
config
.node_exporter()
.enable(true)
.map_err(|e| ExecutorError::UnexpectedError(e.to_string()))?;
Ok(())
}
async fn commit_config(&self) -> Result<(), ExecutorError> {
OPNSenseFirewall::commit_config(self).await
}
async fn reload_restart(&self) -> Result<(), ExecutorError> {
self.opnsense_config
.write()
.await
.node_exporter()
.reload_restart()
.await
.map_err(|e| ExecutorError::UnexpectedError(e.to_string()))
}
}

View File

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

View File

@@ -3,8 +3,7 @@ use std::collections::BTreeMap;
use async_trait::async_trait;
use k8s_openapi::api::core::v1::Secret;
use kube::Resource;
use kube::api::{DynamicObject, ObjectMeta};
use kube::api::ObjectMeta;
use log::debug;
use serde::Serialize;
use serde_json::json;
@@ -14,8 +13,6 @@ use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::{
AlertmanagerConfig, AlertmanagerConfigSpec, CRDPrometheus,
};
use crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::RHOBObservability;
use crate::modules::monitoring::okd::OpenshiftClusterAlertSender;
use crate::topology::oberservability::monitoring::AlertManagerReceiver;
use crate::{
interpret::{InterpretError, Outcome},
modules::monitoring::{
@@ -35,8 +32,10 @@ pub struct DiscordWebhook {
pub url: Url,
}
impl DiscordWebhook {
fn get_receiver_config(&self) -> AlertManagerReceiver {
#[async_trait]
impl AlertReceiver<RHOBObservability> for DiscordWebhook {
async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
let ns = sender.namespace.clone();
let secret_name = format!("{}-secret", self.name.clone());
let webhook_key = format!("{}", self.url.clone());
@@ -53,74 +52,26 @@ impl DiscordWebhook {
..Default::default()
};
AlertManagerReceiver {
additional_ressources: vec![],
receiver_config: json!({
"name": self.name,
"discordConfigs": [
{
"apiURL": {
"name": secret_name,
"key": "webhook-url",
},
"title": "{{ template \"discord.default.title\" . }}",
"message": "{{ template \"discord.default.message\" . }}"
}
]
}),
}
}
}
#[async_trait]
impl AlertReceiver<OpenshiftClusterAlertSender> for DiscordWebhook {
async fn install(
&self,
sender: &OpenshiftClusterAlertSender,
) -> Result<Outcome, InterpretError> {
todo!()
}
fn name(&self) -> String {
todo!()
}
fn clone_box(&self) -> Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
Box::new(self.clone())
}
fn as_any(&self) -> &dyn Any {
todo!()
}
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
self.get_receiver_config()
}
}
#[async_trait]
impl AlertReceiver<RHOBObservability> for DiscordWebhook {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
let ns = sender.namespace.clone();
let config = self.get_receiver_config();
for resource in config.additional_ressources.iter() {
todo!("can I apply a dynamicresource");
// sender.client.apply(resource, Some(&ns)).await;
}
let _ = sender.client.apply(&secret, Some(&ns)).await;
let spec = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfigSpec {
data: json!({
"route": {
"receiver": self.name,
},
"receivers": [
config.receiver_config
{
"name": self.name,
"discordConfigs": [
{
"apiURL": {
"name": secret_name,
"key": "webhook-url",
},
"title": "{{ template \"discord.default.title\" . }}",
"message": "{{ template \"discord.default.message\" . }}"
}
]
}
]
}),
};
@@ -171,9 +122,6 @@ impl AlertReceiver<RHOBObservability> for DiscordWebhook {
#[async_trait]
impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
let ns = sender.namespace.clone();
let secret_name = format!("{}-secret", self.name.clone());
@@ -252,9 +200,6 @@ impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
#[async_trait]
impl AlertReceiver<Prometheus> for DiscordWebhook {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
sender.install_receiver(self).await
}
@@ -281,9 +226,6 @@ impl PrometheusReceiver for DiscordWebhook {
#[async_trait]
impl AlertReceiver<KubePrometheus> for DiscordWebhook {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
sender.install_receiver(self).await
}

View File

@@ -19,7 +19,7 @@ use crate::{
},
prometheus::prometheus::{Prometheus, PrometheusReceiver},
},
topology::oberservability::monitoring::{AlertManagerReceiver, AlertReceiver},
topology::oberservability::monitoring::AlertReceiver,
};
use harmony_types::net::Url;
@@ -31,9 +31,6 @@ pub struct WebhookReceiver {
#[async_trait]
impl AlertReceiver<RHOBObservability> for WebhookReceiver {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
let spec = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfigSpec {
data: json!({
@@ -100,9 +97,6 @@ impl AlertReceiver<RHOBObservability> for WebhookReceiver {
#[async_trait]
impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
let spec = crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::AlertmanagerConfigSpec {
data: json!({
@@ -164,9 +158,6 @@ impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
#[async_trait]
impl AlertReceiver<Prometheus> for WebhookReceiver {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
sender.install_receiver(self).await
}
@@ -193,9 +184,6 @@ impl PrometheusReceiver for WebhookReceiver {
#[async_trait]
impl AlertReceiver<KubePrometheus> for WebhookReceiver {
fn as_alertmanager_receiver(&self) -> AlertManagerReceiver {
todo!()
}
async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
sender.install_receiver(self).await
}

View File

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

View File

@@ -1,139 +0,0 @@
use base64::prelude::*;
use std::sync::Arc;
use async_trait::async_trait;
use harmony_types::id::Id;
use kube::api::DynamicObject;
use log::{debug, info, trace};
use serde::Serialize;
use crate::{
data::Version,
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
modules::{
application::Application,
monitoring::{
grafana::grafana::Grafana,
kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
okd::OpenshiftClusterAlertSender,
},
prometheus::prometheus::PrometheusMonitoring,
},
score::Score,
topology::{
K8sclient, Topology,
k8s::K8sClient,
oberservability::monitoring::{AlertReceiver, AlertingInterpret, ScrapeTarget},
},
};
impl Clone for Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
fn clone(&self) -> Self {
self.clone_box()
}
}
impl Serialize for Box<dyn AlertReceiver<OpenshiftClusterAlertSender>> {
fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
todo!()
}
}
#[derive(Debug, Clone, Serialize)]
pub struct OpenshiftClusterAlertScore {
pub receivers: Vec<Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>>,
}
impl<T: Topology + K8sclient> Score<T> for OpenshiftClusterAlertScore {
fn name(&self) -> String {
"ClusterAlertScore".to_string()
}
#[doc(hidden)]
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
Box::new(OpenshiftClusterAlertInterpret {
receivers: self.receivers.clone(),
})
}
}
#[derive(Debug)]
pub struct OpenshiftClusterAlertInterpret {
receivers: Vec<Box<dyn AlertReceiver<OpenshiftClusterAlertSender>>>,
}
#[async_trait]
impl<T: Topology + K8sclient> Interpret<T> for OpenshiftClusterAlertInterpret {
async fn execute(
&self,
_inventory: &Inventory,
topology: &T,
) -> Result<Outcome, InterpretError> {
let client = topology.k8s_client().await?;
let secret: DynamicObject = client
.get_secret_json_value("alertmanager-main", Some("openshift-monitoring"))
.await?;
trace!("Got secret {secret:?}");
let data: serde_json::Value = secret.data;
// TODO : get config in base64 by drilling into the value
let config_b64 = match data.get("alertmanager.yaml") {
Some(value) => value.as_str().unwrap_or(""),
None => "",
};
// TODO : base64 decode it
let config_bytes = BASE64_STANDARD.decode(config_b64).unwrap_or_default();
// TODO : use serde_yaml to deserialize the string
let am_config: serde_yaml::Value =
serde_yaml::from_str(&String::from_utf8(config_bytes).unwrap_or_default())
.unwrap_or_default();
// Merge current alert receivers from this config with self.receivers
if let Some(existing_receivers) = am_config.get("receivers") {
for receiver in existing_receivers.as_sequence().unwrap_or(&vec![]) {
match serde_json::to_string(receiver) {
Ok(yaml_str) => {
// TODO: validate that each receiver implements to_alertmanager_yaml()
// and compare with our receivers
info!("Found existing receiver config: {}", yaml_str);
}
Err(e) => debug!("Failed to serialize receiver: {}", e),
}
}
}
for custom_receiver in &self.receivers {
trace!("Processing custom receiver");
debug!(
"Custom receiver YAML output: {:?}",
custom_receiver.as_alertmanager_receiver()
);
}
Ok(Outcome::success(todo!("whats up")))
}
fn get_name(&self) -> InterpretName {
InterpretName::Custom("OpenshiftClusterAlertInterpret")
}
fn get_version(&self) -> Version {
todo!()
}
fn get_status(&self) -> InterpretStatus {
todo!()
}
fn get_children(&self) -> Vec<Id> {
todo!()
}
}

View File

@@ -1,90 +0,0 @@
use std::{collections::BTreeMap, sync::Arc};
use crate::{
interpret::{InterpretError, Outcome},
topology::k8s::K8sClient,
};
use k8s_openapi::api::core::v1::ConfigMap;
use kube::api::ObjectMeta;
pub(crate) struct Config;
impl Config {
pub async fn create_cluster_monitoring_config_cm(
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let mut data = BTreeMap::new();
data.insert(
"config.yaml".to_string(),
r#"
enableUserWorkload: true
alertmanagerMain:
enableUserAlertmanagerConfig: true
"#
.to_string(),
);
let cm = ConfigMap {
metadata: ObjectMeta {
name: Some("cluster-monitoring-config".to_string()),
namespace: Some("openshift-monitoring".to_string()),
..Default::default()
},
data: Some(data),
..Default::default()
};
client.apply(&cm, Some("openshift-monitoring")).await?;
Ok(Outcome::success(
"updated cluster-monitoring-config-map".to_string(),
))
}
pub async fn create_user_workload_monitoring_config_cm(
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let mut data = BTreeMap::new();
data.insert(
"config.yaml".to_string(),
r#"
alertmanager:
enabled: true
enableAlertmanagerConfig: true
"#
.to_string(),
);
let cm = ConfigMap {
metadata: ObjectMeta {
name: Some("user-workload-monitoring-config".to_string()),
namespace: Some("openshift-user-workload-monitoring".to_string()),
..Default::default()
},
data: Some(data),
..Default::default()
};
client
.apply(&cm, Some("openshift-user-workload-monitoring"))
.await?;
Ok(Outcome::success(
"updated openshift-user-monitoring-config-map".to_string(),
))
}
pub async fn verify_user_workload(client: &Arc<K8sClient>) -> Result<Outcome, InterpretError> {
let namespace = "openshift-user-workload-monitoring";
let alertmanager_name = "alertmanager-user-workload-0";
let prometheus_name = "prometheus-user-workload-0";
client
.wait_for_pod_ready(alertmanager_name, Some(namespace))
.await?;
client
.wait_for_pod_ready(prometheus_name, Some(namespace))
.await?;
Ok(Outcome::success(format!(
"pods: {}, {} ready in ns: {}",
alertmanager_name, prometheus_name, namespace
)))
}
}

View File

@@ -1,13 +1,16 @@
use std::{collections::BTreeMap, sync::Arc};
use crate::{
data::Version,
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
modules::monitoring::okd::config::Config,
score::Score,
topology::{K8sclient, Topology},
topology::{K8sclient, Topology, k8s::K8sClient},
};
use async_trait::async_trait;
use harmony_types::id::Id;
use k8s_openapi::api::core::v1::ConfigMap;
use kube::api::ObjectMeta;
use serde::Serialize;
#[derive(Clone, Debug, Serialize)]
@@ -34,9 +37,10 @@ impl<T: Topology + K8sclient> Interpret<T> for OpenshiftUserWorkloadMonitoringIn
topology: &T,
) -> Result<Outcome, InterpretError> {
let client = topology.k8s_client().await.unwrap();
Config::create_cluster_monitoring_config_cm(&client).await?;
Config::create_user_workload_monitoring_config_cm(&client).await?;
Config::verify_user_workload(&client).await?;
self.update_cluster_monitoring_config_cm(&client).await?;
self.update_user_workload_monitoring_config_cm(&client)
.await?;
self.verify_user_workload(&client).await?;
Ok(Outcome::success(
"successfully enabled user-workload-monitoring".to_string(),
))
@@ -58,3 +62,88 @@ impl<T: Topology + K8sclient> Interpret<T> for OpenshiftUserWorkloadMonitoringIn
todo!()
}
}
impl OpenshiftUserWorkloadMonitoringInterpret {
pub async fn update_cluster_monitoring_config_cm(
&self,
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let mut data = BTreeMap::new();
data.insert(
"config.yaml".to_string(),
r#"
enableUserWorkload: true
alertmanagerMain:
enableUserAlertmanagerConfig: true
"#
.to_string(),
);
let cm = ConfigMap {
metadata: ObjectMeta {
name: Some("cluster-monitoring-config".to_string()),
namespace: Some("openshift-monitoring".to_string()),
..Default::default()
},
data: Some(data),
..Default::default()
};
client.apply(&cm, Some("openshift-monitoring")).await?;
Ok(Outcome::success(
"updated cluster-monitoring-config-map".to_string(),
))
}
pub async fn update_user_workload_monitoring_config_cm(
&self,
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let mut data = BTreeMap::new();
data.insert(
"config.yaml".to_string(),
r#"
alertmanager:
enabled: true
enableAlertmanagerConfig: true
"#
.to_string(),
);
let cm = ConfigMap {
metadata: ObjectMeta {
name: Some("user-workload-monitoring-config".to_string()),
namespace: Some("openshift-user-workload-monitoring".to_string()),
..Default::default()
},
data: Some(data),
..Default::default()
};
client
.apply(&cm, Some("openshift-user-workload-monitoring"))
.await?;
Ok(Outcome::success(
"updated openshift-user-monitoring-config-map".to_string(),
))
}
pub async fn verify_user_workload(
&self,
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let namespace = "openshift-user-workload-monitoring";
let alertmanager_name = "alertmanager-user-workload-0";
let prometheus_name = "prometheus-user-workload-0";
client
.wait_for_pod_ready(alertmanager_name, Some(namespace))
.await?;
client
.wait_for_pod_ready(prometheus_name, Some(namespace))
.await?;
Ok(Outcome::success(format!(
"pods: {}, {} ready in ns: {}",
alertmanager_name, prometheus_name, namespace
)))
}
}

View File

@@ -1,14 +1 @@
use crate::topology::oberservability::monitoring::AlertSender;
pub mod cluster_monitoring;
pub(crate) mod config;
pub mod enable_user_workload;
#[derive(Debug)]
pub struct OpenshiftClusterAlertSender;
impl AlertSender for OpenshiftClusterAlertSender {
fn name(&self) -> String {
"OpenshiftClusterAlertSender".to_string()
}
}

View File

@@ -5,10 +5,8 @@ use crate::{
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::{HostRole, Inventory},
modules::{
dhcp::DhcpHostBindingScore,
http::IPxeMacBootFileScore,
inventory::DiscoverHostForRoleScore,
okd::{host_network::HostNetworkConfigurationScore, templates::BootstrapIpxeTpl},
dhcp::DhcpHostBindingScore, http::IPxeMacBootFileScore,
inventory::DiscoverHostForRoleScore, okd::templates::BootstrapIpxeTpl,
},
score::Score,
topology::{HAClusterTopology, HostBinding},
@@ -205,28 +203,6 @@ 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]
@@ -265,10 +241,6 @@ 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

@@ -0,0 +1,130 @@
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

@@ -1,41 +1 @@
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

@@ -6,9 +6,16 @@ use serde::{Deserialize, Serialize};
use serde_json::Value;
#[derive(CustomResource, Deserialize, Serialize, Clone, Debug, JsonSchema)]
#[kube(group = "nmstate.io", version = "v1", kind = "NMState", namespaced)]
#[kube(
group = "nmstate.io",
version = "v1",
kind = "NMState",
plural = "nmstates",
namespaced = false
)]
#[serde(rename_all = "camelCase")]
pub struct NMStateSpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub probe_configuration: Option<ProbeConfig>,
}
@@ -44,6 +51,7 @@ pub struct ProbeDns {
)]
#[serde(rename_all = "camelCase")]
pub struct NodeNetworkConfigurationPolicySpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub node_selector: Option<BTreeMap<String, String>>,
pub desired_state: DesiredStateSpec,
}
@@ -58,37 +66,64 @@ pub struct DesiredStateSpec {
#[serde(rename_all = "kebab-case")]
pub struct InterfaceSpec {
pub name: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub description: Option<String>,
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")]
pub ovs_bridge: Option<OvsBridgeSpec>,
#[serde(skip_serializing_if = "Option::is_none")]
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>,
}
@@ -102,8 +137,11 @@ 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>,
}
@@ -112,6 +150,7 @@ pub struct EthernetSpec {
pub struct BondSpec {
pub mode: String,
pub ports: Vec<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub options: Option<BTreeMap<String, Value>>,
}
@@ -120,6 +159,7 @@ pub struct BondSpec {
pub struct VlanSpec {
pub base_iface: String,
pub id: u16,
#[serde(skip_serializing_if = "Option::is_none")]
pub protocol: Option<String>,
}
@@ -129,8 +169,11 @@ 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>,
}
@@ -139,6 +182,7 @@ pub struct VxlanSpec {
pub struct MacVtapSpec {
pub base_iface: String,
pub mode: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub promiscuous: Option<bool>,
}
@@ -147,6 +191,7 @@ pub struct MacVtapSpec {
pub struct MacVlanSpec {
pub base_iface: String,
pub mode: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub promiscuous: Option<bool>,
}
@@ -161,25 +206,35 @@ 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>,
}
@@ -187,15 +242,20 @@ 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>,
}
@@ -203,6 +263,7 @@ 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>,
}
@@ -216,15 +277,20 @@ 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<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub rstp: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mcast_snooping_enable: Option<bool>,
}
@@ -232,8 +298,11 @@ pub struct OvsBridgeOptions {
#[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>,
}
@@ -246,6 +315,8 @@ pub struct EthtoolSpec {
#[derive(Deserialize, Serialize, Clone, Debug, Default, JsonSchema)]
#[serde(rename_all = "kebab-case")]
pub struct EthtoolFecSpec {
#[serde(skip_serializing_if = "Option::is_none")]
pub auto: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub mode: Option<String>,
}

View File

@@ -39,30 +39,70 @@ impl HostNetworkConfigurationInterpret {
&self,
topology: &T,
host: &PhysicalHost,
) -> Result<(), InterpretError> {
let switch_ports = self.collect_switch_ports_for_host(topology, host).await?;
if !switch_ports.is_empty() {
topology
.configure_host_network(host, HostNetworkConfig { switch_ports })
.await
.map_err(|e| InterpretError::new(format!("Failed to configure host: {e}")))?;
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![],
});
}
Ok(())
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.is_empty() {
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_host_network(&config)
.await
.map_err(|e| InterpretError::new(format!("Failed to configure host: {e}")))?;
} else {
info!(
"[Host {current_host}/{total_hosts}] No ports found for {} interfaces, skipping",
host.network.len()
);
}
Ok(config)
}
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(),
@@ -73,7 +113,7 @@ impl HostNetworkConfigurationInterpret {
port,
});
}
Ok(None) => debug!("No port found for host '{}', skipping", host.id),
Ok(None) => debug!("No port found for '{mac_address}', skipping"),
Err(e) => {
return Err(InterpretError::new(format!(
"Failed to get port for host '{}': {}",
@@ -85,6 +125,47 @@ 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 {
let host = self
.score
.hosts
.iter()
.find(|h| h.id == config.host_id)
.unwrap();
println!("[Host] {host}");
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]
@@ -114,27 +195,38 @@ impl<T: Topology + Switch> Interpret<T> for HostNetworkConfigurationInterpret {
return Ok(Outcome::noop("No hosts to configure".into()));
}
info!(
"Started network configuration for {} host(s)...",
self.score.hosts.len()
);
let host_count = self.score.hosts.len();
info!("Started network configuration for {host_count} host(s)...",);
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 {
self.configure_network_for_host(topology, host).await?;
configured_host_count += 1;
}
let host_configuration = self
.configure_network_for_host(topology, host, &current_host, &host_count)
.await?;
if configured_host_count > 0 {
Ok(Outcome::success(format!(
"Configured {configured_host_count}/{} host(s)",
self.score.hosts.len()
)))
host_configurations.push(host_configuration);
current_host += 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,
self.score.hosts.len()
),
details,
))
} else {
Ok(Outcome::noop("No hosts configured".into()))
}
@@ -209,6 +301,7 @@ mod tests {
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(),
port: PORT.clone(),
@@ -234,6 +327,7 @@ mod tests {
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(),
@@ -263,6 +357,7 @@ mod tests {
(
HOST_ID.clone(),
HostNetworkConfig {
host_id: HOST_ID.clone(),
switch_ports: vec![SwitchPort {
interface: EXISTING_INTERFACE.clone(),
port: PORT.clone(),
@@ -272,6 +367,7 @@ mod tests {
(
ANOTHER_HOST_ID.clone(),
HostNetworkConfig {
host_id: ANOTHER_HOST_ID.clone(),
switch_ports: vec![SwitchPort {
interface: ANOTHER_EXISTING_INTERFACE.clone(),
port: ANOTHER_PORT.clone(),
@@ -382,11 +478,10 @@ mod tests {
async fn configure_host_network(
&self,
host: &PhysicalHost,
config: HostNetworkConfig,
config: &HostNetworkConfig,
) -> Result<(), SwitchError> {
let mut configured_host_networks = self.configured_host_networks.lock().unwrap();
configured_host_networks.push((host.id.clone(), config.clone()));
configured_host_networks.push((config.host_id.clone(), config.clone()));
Ok(())
}

View File

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

@@ -6,6 +6,7 @@ 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;
@@ -19,5 +20,6 @@ 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

@@ -1,3 +1,4 @@
pub mod node_exporter;
mod shell;
mod upgrade;
pub use shell::*;

View File

@@ -0,0 +1,70 @@
use async_trait::async_trait;
use harmony_types::id::Id;
use log::info;
use serde::Serialize;
use crate::{
data::Version,
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
score::Score,
topology::{Topology, node_exporter::NodeExporter},
};
#[derive(Debug, Clone, Serialize)]
pub struct NodeExporterScore {}
impl<T: Topology + NodeExporter> Score<T> for NodeExporterScore {
fn name(&self) -> String {
"NodeExporterScore".to_string()
}
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
Box::new(NodeExporterInterpret {})
}
}
#[derive(Debug)]
pub struct NodeExporterInterpret {}
#[async_trait]
impl<T: Topology + NodeExporter> Interpret<T> for NodeExporterInterpret {
async fn execute(
&self,
_inventory: &Inventory,
node_exporter: &T,
) -> Result<Outcome, InterpretError> {
info!(
"Making sure node exporter is initiailized: {:?}",
node_exporter.ensure_initialized().await?
);
info!("Applying Node Exporter configuration");
node_exporter.commit_config().await?;
info!("Reloading and restarting Node Exporter");
node_exporter.reload_restart().await?;
Ok(Outcome::success(format!(
"NodeExporter successfully configured"
)))
}
fn get_name(&self) -> InterpretName {
InterpretName::Custom("NodeExporter")
}
fn get_version(&self) -> Version {
todo!()
}
fn get_status(&self) -> InterpretStatus {
todo!()
}
fn get_children(&self) -> Vec<Id> {
todo!()
}
}

View File

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

View File

@@ -17,7 +17,7 @@ pub struct OPNsense {
pub interfaces: NamedList<Interface>,
pub dhcpd: NamedList<DhcpInterface>,
pub snmpd: Snmpd,
pub syslog: Syslog,
pub syslog: Option<Syslog>,
pub nat: Nat,
pub filter: Filters,
pub load_balancer: Option<LoadBalancer>,
@@ -190,7 +190,7 @@ pub struct System {
pub webgui: WebGui,
pub usevirtualterminal: u8,
pub disablenatreflection: Option<String>,
pub disableconsolemenu: u8,
pub disableconsolemenu: Option<u8>,
pub disablevlanhwfilter: u8,
pub disablechecksumoffloading: u8,
pub disablesegmentationoffloading: u8,
@@ -216,7 +216,7 @@ pub struct System {
pub maximumfrags: Option<MaybeString>,
pub aliasesresolveinterval: Option<MaybeString>,
pub maximumtableentries: Option<MaybeString>,
pub language: String,
pub language: Option<String>,
pub dnsserver: Option<MaybeString>,
pub dns1gw: Option<String>,
pub dns2gw: Option<String>,
@@ -233,16 +233,16 @@ pub struct System {
#[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
pub struct Ssh {
pub group: String,
pub noauto: u8,
pub interfaces: MaybeString,
pub kex: MaybeString,
pub ciphers: MaybeString,
pub macs: MaybeString,
pub keys: MaybeString,
pub enabled: String,
pub passwordauth: u8,
pub keysig: MaybeString,
pub permitrootlogin: u8,
pub noauto: Option<u8>,
pub interfaces: Option<MaybeString>,
pub kex: Option<MaybeString>,
pub ciphers: Option<MaybeString>,
pub macs: Option<MaybeString>,
pub keys: Option<MaybeString>,
pub enabled: Option<String>,
pub passwordauth: Option<u8>,
pub keysig: Option<MaybeString>,
pub permitrootlogin: Option<u8>,
pub rekeylimit: Option<MaybeString>,
}
@@ -306,11 +306,11 @@ pub struct WebGui {
pub protocol: String,
#[yaserde(rename = "ssl-certref")]
pub ssl_certref: String,
pub port: MaybeString,
pub port: Option<MaybeString>,
#[yaserde(rename = "ssl-ciphers")]
pub ssl_ciphers: MaybeString,
pub interfaces: MaybeString,
pub compression: MaybeString,
pub ssl_ciphers: Option<MaybeString>,
pub interfaces: Option<MaybeString>,
pub compression: Option<MaybeString>,
pub nohttpreferercheck: Option<u8>,
}
@@ -433,7 +433,7 @@ pub struct OPNsenseXmlSection {
#[yaserde(rename = "Interfaces")]
pub interfaces: Option<ConfigInterfaces>,
#[yaserde(rename = "NodeExporter")]
pub node_exporter: Option<RawXml>,
pub node_exporter: Option<NodeExporter>,
#[yaserde(rename = "Kea")]
pub kea: Option<RawXml>,
pub monit: Option<Monit>,
@@ -1595,3 +1595,21 @@ pub struct Ifgroups {
#[yaserde(attribute = true)]
pub version: String,
}
#[derive(Default, PartialEq, Debug, YaSerialize, YaDeserialize)]
pub struct NodeExporter {
pub enabled: u8,
pub listenaddress: Option<MaybeString>,
pub listenport: u16,
pub cpu: u8,
pub exec: u8,
pub filesystem: u8,
pub loadavg: u8,
pub meminfo: u8,
pub netdev: u8,
pub time: u8,
pub devstat: u8,
pub interrupts: u8,
pub ntp: u8,
pub zfs: u8,
}

View File

@@ -5,7 +5,8 @@ use crate::{
error::Error,
modules::{
caddy::CaddyConfig, dhcp_legacy::DhcpConfigLegacyISC, dns::UnboundDnsConfig,
dnsmasq::DhcpConfigDnsMasq, load_balancer::LoadBalancerConfig, tftp::TftpConfig,
dnsmasq::DhcpConfigDnsMasq, load_balancer::LoadBalancerConfig,
node_exporter::NodeExporterConfig, tftp::TftpConfig,
},
};
use log::{debug, info, trace, warn};
@@ -13,6 +14,7 @@ use opnsense_config_xml::OPNsense;
use russh::client;
use serde::Serialize;
use sha2::Digest;
use tokio::time::{sleep, Duration};
use super::{ConfigManager, OPNsenseShell};
@@ -71,6 +73,10 @@ impl Config {
LoadBalancerConfig::new(&mut self.opnsense, self.shell.clone())
}
pub fn node_exporter(&mut self) -> NodeExporterConfig<'_> {
NodeExporterConfig::new(&mut self.opnsense, self.shell.clone())
}
pub async fn upload_files(&self, source: &str, destination: &str) -> Result<String, Error> {
self.shell.upload_folder(source, destination).await
}
@@ -150,7 +156,8 @@ impl Config {
async fn reload_config(&mut self) -> Result<(), Error> {
info!("Reloading opnsense live config");
let (opnsense, sha2) = Self::get_opnsense_instance(self.repository.clone()).await?;
let (opnsense, _sha2) = Self::get_opnsense_instance(self.repository.clone()).await?;
self.opnsense = opnsense;
Ok(())
}

View File

@@ -4,4 +4,5 @@ pub mod dhcp_legacy;
pub mod dns;
pub mod dnsmasq;
pub mod load_balancer;
pub mod node_exporter;
pub mod tftp;

View File

@@ -0,0 +1,54 @@
use std::sync::Arc;
use opnsense_config_xml::{NodeExporter, OPNsense};
use crate::{config::OPNsenseShell, Error};
pub struct NodeExporterConfig<'a> {
opnsense: &'a mut OPNsense,
opnsense_shell: Arc<dyn OPNsenseShell>,
}
impl<'a> NodeExporterConfig<'a> {
pub fn new(opnsense: &'a mut OPNsense, opnsense_shell: Arc<dyn OPNsenseShell>) -> Self {
Self {
opnsense,
opnsense_shell,
}
}
pub fn get_full_config(&self) -> &Option<NodeExporter> {
&self.opnsense.opnsense.node_exporter
}
fn with_node_exporter<F, R>(&mut self, f: F) -> Result<R, &'static str>
where
F: FnOnce(&mut NodeExporter) -> R,
{
match &mut self.opnsense.opnsense.node_exporter.as_mut() {
Some(node_exporter) => Ok(f(node_exporter)),
None => Err("node exporter is not yet installed"),
}
}
pub fn enable(&mut self, enabled: bool) -> Result<(), &'static str> {
self.with_node_exporter(|node_exporter| node_exporter.enabled = enabled as u8)
.map(|_| ())
}
pub async fn reload_restart(&self) -> Result<(), Error> {
self.opnsense_shell
.exec("configctl node_exporter stop")
.await?;
self.opnsense_shell
.exec("configctl template reload OPNsense/NodeExporter")
.await?;
self.opnsense_shell
.exec("configctl node_exporter configtest")
.await?;
self.opnsense_shell
.exec("configctl node_exporter start")
.await?;
Ok(())
}
}