Compare commits
14 Commits
feat/webap
...
a12d12aa4f
| Author | SHA1 | Date | |
|---|---|---|---|
| a12d12aa4f | |||
| cefb65933a | |||
| 95cfc03518 | |||
| b2825ec1ef | |||
| 609d7acb5d | |||
| de761cf538 | |||
| ce91ee0168 | |||
| c0d54a4466 | |||
| fc384599a1 | |||
| 7dff70edcf | |||
| 06a0c44c3c | |||
| 85bec66e58 | |||
| 1f3796f503 | |||
| 58b6268989 |
@@ -27,7 +27,6 @@ async fn main() {
|
||||
};
|
||||
let application = Arc::new(RustWebapp {
|
||||
name: "example-monitoring".to_string(),
|
||||
dns: "example-monitoring.harmony.mcd".to_string(),
|
||||
project_root: PathBuf::from("./examples/rust/webapp"),
|
||||
framework: Some(RustWebFramework::Leptos),
|
||||
service_port: 3000,
|
||||
|
||||
22
examples/okd_cluster_alerts/Cargo.toml
Normal file
22
examples/okd_cluster_alerts/Cargo.toml
Normal file
@@ -0,0 +1,22 @@
|
||||
[package]
|
||||
name = "example-okd-cluster-alerts"
|
||||
edition = "2024"
|
||||
version.workspace = true
|
||||
readme.workspace = true
|
||||
license.workspace = true
|
||||
publish = false
|
||||
|
||||
[dependencies]
|
||||
harmony = { path = "../../harmony" }
|
||||
harmony_cli = { path = "../../harmony_cli" }
|
||||
harmony_types = { path = "../../harmony_types" }
|
||||
harmony_secret = { path = "../../harmony_secret" }
|
||||
harmony_secret_derive = { path = "../../harmony_secret_derive" }
|
||||
cidr = { workspace = true }
|
||||
tokio = { workspace = true }
|
||||
harmony_macros = { path = "../../harmony_macros" }
|
||||
log = { workspace = true }
|
||||
env_logger = { workspace = true }
|
||||
url = { workspace = true }
|
||||
serde.workspace = true
|
||||
brocade = { path = "../../brocade" }
|
||||
26
examples/okd_cluster_alerts/src/main.rs
Normal file
26
examples/okd_cluster_alerts/src/main.rs
Normal file
@@ -0,0 +1,26 @@
|
||||
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();
|
||||
}
|
||||
@@ -16,7 +16,6 @@ use harmony_types::net::Url;
|
||||
async fn main() {
|
||||
let application = Arc::new(RustWebapp {
|
||||
name: "test-rhob-monitoring".to_string(),
|
||||
dns: "test-rhob-monitoring.harmony.mcd".to_string(),
|
||||
project_root: PathBuf::from("./webapp"), // Relative from 'harmony-path' param
|
||||
framework: Some(RustWebFramework::Leptos),
|
||||
service_port: 3000,
|
||||
|
||||
@@ -19,7 +19,6 @@ use harmony_macros::hurl;
|
||||
async fn main() {
|
||||
let application = Arc::new(RustWebapp {
|
||||
name: "harmony-example-rust-webapp".to_string(),
|
||||
dns: "harmony-example-rust-webapp.harmony.mcd".to_string(),
|
||||
project_root: PathBuf::from("./webapp"),
|
||||
framework: Some(RustWebFramework::Leptos),
|
||||
service_port: 3000,
|
||||
|
||||
@@ -2,11 +2,12 @@ use harmony::{
|
||||
inventory::Inventory,
|
||||
modules::{
|
||||
application::{
|
||||
features::{rhob_monitoring::Monitoring, PackagingDeployment}, ApplicationScore, RustWebFramework, RustWebapp
|
||||
ApplicationScore, RustWebFramework, RustWebapp,
|
||||
features::{PackagingDeployment, rhob_monitoring::Monitoring},
|
||||
},
|
||||
monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
|
||||
},
|
||||
topology::{K8sAnywhereTopology, LocalhostTopology},
|
||||
topology::K8sAnywhereTopology,
|
||||
};
|
||||
use harmony_macros::hurl;
|
||||
use std::{path::PathBuf, sync::Arc};
|
||||
@@ -21,8 +22,8 @@ async fn main() {
|
||||
});
|
||||
|
||||
let discord_webhook = DiscordWebhook {
|
||||
name: "harmony-demo".to_string(),
|
||||
url: hurl!("https://discord.com/api/webhooks/1415391405681021050/V6KzV41vQ7yvbn7BchejRu9C8OANxy0i2ESZOz2nvCxG8xAY3-2i3s5MS38k568JKTzH"),
|
||||
name: "harmony_demo".to_string(),
|
||||
url: hurl!("http://not_a_url.com"),
|
||||
};
|
||||
|
||||
let app = ApplicationScore {
|
||||
|
||||
@@ -3,7 +3,7 @@ use harmony::{
|
||||
modules::{
|
||||
application::{
|
||||
ApplicationScore, RustWebFramework, RustWebapp,
|
||||
features::{PackagingDeployment, rhob_monitoring::Monitoring},
|
||||
features::{Monitoring, PackagingDeployment},
|
||||
},
|
||||
monitoring::alert_channel::discord_alert_channel::DiscordWebhook,
|
||||
},
|
||||
@@ -16,7 +16,6 @@ use std::{path::PathBuf, sync::Arc};
|
||||
async fn main() {
|
||||
let application = Arc::new(RustWebapp {
|
||||
name: "harmony-example-tryrust".to_string(),
|
||||
dns: "tryrust.example.harmony.mcd".to_string(),
|
||||
project_root: PathBuf::from("./tryrust.org"), // <== Project root, in this case it is a
|
||||
// submodule
|
||||
framework: Some(RustWebFramework::Leptos),
|
||||
|
||||
@@ -1,10 +1,12 @@
|
||||
use std::{collections::HashMap, time::Duration};
|
||||
use std::time::Duration;
|
||||
|
||||
use derive_new::new;
|
||||
use k8s_openapi::{
|
||||
ClusterResourceScope, NamespaceResourceScope,
|
||||
api::{apps::v1::Deployment, core::v1::Pod},
|
||||
apiextensions_apiserver::pkg::apis::apiextensions::v1::CustomResourceDefinition,
|
||||
api::{
|
||||
apps::v1::Deployment,
|
||||
core::v1::{Pod, ServiceAccount},
|
||||
},
|
||||
apimachinery::pkg::version::Info,
|
||||
};
|
||||
use kube::{
|
||||
@@ -22,7 +24,7 @@ use kube::{
|
||||
};
|
||||
use log::{debug, error, info, trace};
|
||||
use serde::{Serialize, de::DeserializeOwned};
|
||||
use serde_json::{json, Value};
|
||||
use serde_json::json;
|
||||
use similar::TextDiff;
|
||||
use tokio::{io::AsyncReadExt, time::sleep};
|
||||
|
||||
@@ -58,146 +60,9 @@ impl K8sClient {
|
||||
})
|
||||
}
|
||||
|
||||
// Returns true if any deployment in the given namespace matching the label selector
|
||||
// has status.availableReplicas > 0 (or condition Available=True).
|
||||
pub async fn has_healthy_deployment_with_label(
|
||||
&self,
|
||||
namespace: &str,
|
||||
label_selector: &str,
|
||||
) -> Result<bool, Error> {
|
||||
let api: Api<Deployment> = Api::namespaced(self.client.clone(), namespace);
|
||||
let lp = ListParams::default().labels(label_selector);
|
||||
let list = api.list(&lp).await?;
|
||||
for d in list.items {
|
||||
// Check AvailableReplicas > 0 or Available condition
|
||||
let available = d
|
||||
.status
|
||||
.as_ref()
|
||||
.and_then(|s| s.available_replicas)
|
||||
.unwrap_or(0);
|
||||
if available > 0 {
|
||||
return Ok(true);
|
||||
}
|
||||
// Fallback: scan conditions
|
||||
if let Some(conds) = d.status.as_ref().and_then(|s| s.conditions.as_ref()) {
|
||||
if conds.iter().any(|c| {
|
||||
c.type_ == "Available"
|
||||
&& c.status == "True"
|
||||
}) {
|
||||
return Ok(true);
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(false)
|
||||
}
|
||||
|
||||
// Cluster-wide: returns namespaces that have at least one healthy deployment
|
||||
// matching the label selector (equivalent to kubectl -A -l ...).
|
||||
pub async fn list_namespaces_with_healthy_deployments(
|
||||
&self,
|
||||
label_selector: &str,
|
||||
) -> Result<Vec<String>, Error> {
|
||||
let api: Api<Deployment> = Api::all(self.client.clone());
|
||||
let lp = ListParams::default().labels(label_selector);
|
||||
let list = api.list(&lp).await?;
|
||||
|
||||
let mut healthy_ns: HashMap<String, bool> = HashMap::new();
|
||||
for d in list.items {
|
||||
let ns = match d.metadata.namespace.clone() {
|
||||
Some(n) => n,
|
||||
None => continue,
|
||||
};
|
||||
let available = d
|
||||
.status
|
||||
.as_ref()
|
||||
.and_then(|s| s.available_replicas)
|
||||
.unwrap_or(0);
|
||||
let is_healthy = if available > 0 {
|
||||
true
|
||||
} else {
|
||||
d.status
|
||||
.as_ref()
|
||||
.and_then(|s| s.conditions.as_ref())
|
||||
.map(|conds| {
|
||||
conds.iter().any(|c| {
|
||||
c.type_ == "Available"
|
||||
&& c.status == "True"
|
||||
})
|
||||
})
|
||||
.unwrap_or(false)
|
||||
};
|
||||
if is_healthy {
|
||||
healthy_ns.insert(ns, true);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(healthy_ns.into_keys().collect())
|
||||
}
|
||||
|
||||
// Get the application-controller ServiceAccount name (fallback to default)
|
||||
pub async fn get_argocd_controller_sa_name(&self, ns: &str) -> Result<String, Error> {
|
||||
let api: Api<Deployment> = Api::namespaced(self.client.clone(), ns);
|
||||
let lp = ListParams::default().labels("app.kubernetes.io/component=controller");
|
||||
let list = api.list(&lp).await?;
|
||||
if let Some(dep) = list.items.get(0) {
|
||||
if let Some(sa) = dep
|
||||
.spec
|
||||
.as_ref()
|
||||
.and_then(|ds| ds.template.spec.as_ref())
|
||||
.and_then(|ps| ps.service_account_name.clone())
|
||||
{
|
||||
return Ok(sa);
|
||||
}
|
||||
}
|
||||
Ok("argocd-application-controller".to_string())
|
||||
}
|
||||
|
||||
// List ClusterRoleBindings dynamically and return as JSON values
|
||||
pub async fn list_clusterrolebindings_json(&self) -> Result<Vec<Value>, Error> {
|
||||
let gvk = kube::api::GroupVersionKind::gvk(
|
||||
"rbac.authorization.k8s.io",
|
||||
"v1",
|
||||
"ClusterRoleBinding",
|
||||
);
|
||||
let ar = kube::api::ApiResource::from_gvk(&gvk);
|
||||
let api: Api<kube::api::DynamicObject> = Api::all_with(self.client.clone(), &ar);
|
||||
let crbs = api.list(&ListParams::default()).await?;
|
||||
let mut out = Vec::new();
|
||||
for o in crbs {
|
||||
let v = serde_json::to_value(&o).unwrap_or(Value::Null);
|
||||
out.push(v);
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
// Determine if Argo controller in ns has cluster-wide permissions via CRBs
|
||||
// TODO This does not belong in the generic k8s client, should be refactored at some point
|
||||
pub async fn is_argocd_cluster_wide(&self, ns: &str) -> Result<bool, Error> {
|
||||
let sa = self.get_argocd_controller_sa_name(ns).await?;
|
||||
let crbs = self.list_clusterrolebindings_json().await?;
|
||||
let sa_user = format!("system:serviceaccount:{}:{}", ns, sa);
|
||||
for crb in crbs {
|
||||
if let Some(subjects) = crb.get("subjects").and_then(|s| s.as_array()) {
|
||||
for subj in subjects {
|
||||
let kind = subj.get("kind").and_then(|v| v.as_str()).unwrap_or("");
|
||||
let name = subj.get("name").and_then(|v| v.as_str()).unwrap_or("");
|
||||
let subj_ns = subj.get("namespace").and_then(|v| v.as_str()).unwrap_or("");
|
||||
if (kind == "ServiceAccount" && name == sa && subj_ns == ns)
|
||||
|| (kind == "User" && name == sa_user)
|
||||
{
|
||||
return Ok(true);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(false)
|
||||
}
|
||||
|
||||
pub async fn has_crd(&self, name: &str) -> Result<bool, Error> {
|
||||
let api: Api<CustomResourceDefinition> = Api::all(self.client.clone());
|
||||
let lp = ListParams::default().fields(&format!("metadata.name={}", name));
|
||||
let crds = api.list(&lp).await?;
|
||||
Ok(!crds.items.is_empty())
|
||||
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> {
|
||||
@@ -226,6 +91,23 @@ impl K8sClient {
|
||||
Ok(resource.get(name).await?)
|
||||
}
|
||||
|
||||
pub async fn get_secret_json_value(
|
||||
&self,
|
||||
name: &str,
|
||||
namespace: Option<&str>,
|
||||
) -> Result<DynamicObject, Error> {
|
||||
self.get_resource_json_value(
|
||||
name,
|
||||
namespace,
|
||||
&GroupVersionKind {
|
||||
group: "".to_string(),
|
||||
version: "v1".to_string(),
|
||||
kind: "Secret".to_string(),
|
||||
},
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
pub async fn get_deployment(
|
||||
&self,
|
||||
name: &str,
|
||||
|
||||
@@ -1,8 +1,13 @@
|
||||
use std::{process::Command, sync::Arc};
|
||||
use std::{collections::BTreeMap, process::Command, sync::Arc};
|
||||
|
||||
use async_trait::async_trait;
|
||||
use kube::api::GroupVersionKind;
|
||||
use log::{debug, info, trace, warn};
|
||||
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 log::{debug, info, warn};
|
||||
use serde::Serialize;
|
||||
use tokio::sync::OnceCell;
|
||||
|
||||
@@ -12,14 +17,26 @@ use crate::{
|
||||
inventory::Inventory,
|
||||
modules::{
|
||||
k3d::K3DInstallationScore,
|
||||
monitoring::kube_prometheus::crd::{
|
||||
crd_alertmanager_config::CRDPrometheus,
|
||||
prometheus_operator::prometheus_operator_helm_chart_score,
|
||||
rhob_alertmanager_config::RHOBObservability,
|
||||
k8s::ingress::{K8sIngressScore, PathType},
|
||||
monitoring::{
|
||||
grafana::{grafana::Grafana, helm::helm_grafana::grafana_helm_chart_score},
|
||||
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::PrometheusApplicationMonitoring, rhob_alerting_score::RHOBAlertingScore,
|
||||
prometheus::PrometheusMonitoring, rhob_alerting_score::RHOBAlertingScore,
|
||||
},
|
||||
},
|
||||
score::Score,
|
||||
@@ -71,7 +88,6 @@ pub struct K8sAnywhereTopology {
|
||||
#[async_trait]
|
||||
impl K8sclient for K8sAnywhereTopology {
|
||||
async fn k8s_client(&self) -> Result<Arc<K8sClient>, String> {
|
||||
trace!("getting k8s client");
|
||||
let state = match self.k8s_state.get() {
|
||||
Some(state) => state,
|
||||
None => return Err("K8s state not initialized yet".to_string()),
|
||||
@@ -87,41 +103,172 @@ impl K8sclient for K8sAnywhereTopology {
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl PrometheusApplicationMonitoring<CRDPrometheus> for K8sAnywhereTopology {
|
||||
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".to_string(),
|
||||
Some("grafana"),
|
||||
Some(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 {
|
||||
async fn install_prometheus(
|
||||
&self,
|
||||
sender: &CRDPrometheus,
|
||||
inventory: &Inventory,
|
||||
receivers: Option<Vec<Box<dyn AlertReceiver<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,
|
||||
) -> Result<PreparationOutcome, PreparationError> {
|
||||
let po_result = self.ensure_prometheus_operator(sender).await?;
|
||||
|
||||
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())),
|
||||
match po_result {
|
||||
PreparationOutcome::Success { details: _ } => {
|
||||
debug!("Detected prometheus crds operator present in cluster.");
|
||||
return Ok(po_result);
|
||||
}
|
||||
PreparationOutcome::Noop => {
|
||||
debug!("Skipping Prometheus CR installation due to missing operator.");
|
||||
return Ok(po_result);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl PrometheusApplicationMonitoring<RHOBObservability> for K8sAnywhereTopology {
|
||||
impl PrometheusMonitoring<RHOBObservability> for K8sAnywhereTopology {
|
||||
async fn install_prometheus(
|
||||
&self,
|
||||
sender: &RHOBObservability,
|
||||
@@ -155,6 +302,14 @@ impl PrometheusApplicationMonitoring<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 {
|
||||
@@ -216,6 +371,180 @@ 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,
|
||||
@@ -233,13 +562,14 @@ impl K8sAnywhereTopology {
|
||||
&self,
|
||||
sender: CRDPrometheus,
|
||||
receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
|
||||
service_monitors: Option<Vec<ServiceMonitor>>,
|
||||
) -> K8sPrometheusCRDAlertingScore {
|
||||
K8sPrometheusCRDAlertingScore {
|
||||
return K8sPrometheusCRDAlertingScore {
|
||||
sender,
|
||||
receivers: receivers.unwrap_or_default(),
|
||||
service_monitors: vec![],
|
||||
service_monitors: service_monitors.unwrap_or_default(),
|
||||
prometheus_rules: vec![],
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
async fn openshift_ingress_operator_available(&self) -> Result<(), PreparationError> {
|
||||
@@ -507,6 +837,30 @@ 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)]
|
||||
@@ -621,56 +975,36 @@ impl TenantManager for K8sAnywhereTopology {
|
||||
|
||||
#[async_trait]
|
||||
impl Ingress for K8sAnywhereTopology {
|
||||
//TODO this is specifically for openshift/okd which violates the k8sanywhere idea
|
||||
async fn get_domain(&self, service: &str) -> Result<String, PreparationError> {
|
||||
use log::{trace, debug, warn};
|
||||
|
||||
let client = self.k8s_client().await?;
|
||||
|
||||
if let Some(Some(k8s_state)) = self.k8s_state.get() {
|
||||
match k8s_state.source {
|
||||
K8sSource::LocalK3d => {
|
||||
// Local developer UX
|
||||
return Ok(format!("{service}.local.k3d"));
|
||||
}
|
||||
K8sSource::LocalK3d => Ok(format!("{service}.local.k3d")),
|
||||
K8sSource::Kubeconfig => {
|
||||
trace!("K8sSource is kubeconfig; attempting to detect domain");
|
||||
self.openshift_ingress_operator_available().await?;
|
||||
|
||||
// 1) Try OpenShift IngressController domain (backward compatible)
|
||||
if self.openshift_ingress_operator_available().await.is_ok() {
|
||||
trace!("OpenShift ingress operator detected; using IngressController");
|
||||
let gvk = GroupVersionKind {
|
||||
group: "operator.openshift.io".into(),
|
||||
version: "v1".into(),
|
||||
kind: "IngressController".into(),
|
||||
};
|
||||
let ic = client
|
||||
.get_resource_json_value("default", Some("openshift-ingress-operator"), &gvk)
|
||||
.await
|
||||
.map_err(|_| PreparationError::new("Failed to fetch IngressController".to_string()))?;
|
||||
let gvk = GroupVersionKind {
|
||||
group: "operator.openshift.io".into(),
|
||||
version: "v1".into(),
|
||||
kind: "IngressController".into(),
|
||||
};
|
||||
let ic = client
|
||||
.get_resource_json_value(
|
||||
"default",
|
||||
Some("openshift-ingress-operator"),
|
||||
&gvk,
|
||||
)
|
||||
.await
|
||||
.map_err(|_| {
|
||||
PreparationError::new("Failed to fetch IngressController".to_string())
|
||||
})?;
|
||||
|
||||
if let Some(domain) = ic.data["status"]["domain"].as_str() {
|
||||
return Ok(format!("{service}.{domain}"));
|
||||
} else {
|
||||
warn!("OpenShift IngressController present but no status.domain set");
|
||||
}
|
||||
} else {
|
||||
trace!("OpenShift ingress operator not detected; trying generic Kubernetes");
|
||||
match ic.data["status"]["domain"].as_str() {
|
||||
Some(domain) => Ok(format!("{service}.{domain}")),
|
||||
None => Err(PreparationError::new("Could not find domain".to_string())),
|
||||
}
|
||||
|
||||
// 2) Try NGINX Ingress Controller common setups
|
||||
// 2.a) Well-known namespace/name for the controller Service
|
||||
// - upstream default: namespace "ingress-nginx", service "ingress-nginx-controller"
|
||||
// - some distros: "ingress-nginx-controller" svc in "ingress-nginx" ns
|
||||
// If found with LoadBalancer ingress hostname, use its base domain.
|
||||
if let Some(domain) = try_nginx_lb_domain(&client).await? {
|
||||
return Ok(format!("{service}.{domain}"));
|
||||
}
|
||||
|
||||
// 3) Fallback: internal cluster DNS suffix (service.namespace.svc.cluster.local)
|
||||
// We don't have tenant namespace here, so we fallback to 'default' with a warning.
|
||||
warn!("Could not determine external ingress domain; falling back to internal-only DNS");
|
||||
let internal = format!("{service}.default.svc.cluster.local");
|
||||
Ok(internal)
|
||||
}
|
||||
}
|
||||
} else {
|
||||
@@ -680,57 +1014,3 @@ impl Ingress for K8sAnywhereTopology {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn try_nginx_lb_domain(client: &K8sClient) -> Result<Option<String>, PreparationError> {
|
||||
use log::{trace, debug};
|
||||
|
||||
// Try common service path: svc/ingress-nginx-controller in ns/ingress-nginx
|
||||
let svc_gvk = GroupVersionKind {
|
||||
group: "".into(), // core
|
||||
version: "v1".into(),
|
||||
kind: "Service".into(),
|
||||
};
|
||||
|
||||
let candidates = [
|
||||
("ingress-nginx", "ingress-nginx-controller"),
|
||||
("ingress-nginx", "ingress-nginx-controller-internal"),
|
||||
("ingress-nginx", "ingress-nginx"), // some charts name the svc like this
|
||||
("kube-system", "ingress-nginx-controller"), // less common but seen
|
||||
];
|
||||
|
||||
for (ns, name) in candidates {
|
||||
trace!("Checking NGINX Service {ns}/{name} for LoadBalancer hostname");
|
||||
if let Ok(svc) = client.get_resource_json_value(ns, Some(name), &svc_gvk).await {
|
||||
let lb_hosts = svc.data["status"]["loadBalancer"]["ingress"].as_array().cloned().unwrap_or_default();
|
||||
for entry in lb_hosts {
|
||||
if let Some(host) = entry.get("hostname").and_then(|v| v.as_str()) {
|
||||
debug!("Found NGINX LB hostname: {host}");
|
||||
if let Some(domain) = extract_base_domain(host) {
|
||||
return Ok(Some(domain.to_string()));
|
||||
} else {
|
||||
return Ok(Some(host.to_string())); // already a domain
|
||||
}
|
||||
}
|
||||
if let Some(ip) = entry.get("ip").and_then(|v| v.as_str()) {
|
||||
// If only an IP is exposed, we can't create a hostname; return None to keep searching
|
||||
debug!("NGINX LB exposes IP {ip} (no hostname); skipping");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(None)
|
||||
}
|
||||
|
||||
fn extract_base_domain(host: &str) -> Option<String> {
|
||||
// For a host like a1b2c3d4e5f6abcdef.elb.amazonaws.com -> base domain elb.amazonaws.com
|
||||
// For a managed DNS like xyz.example.com -> base domain example.com (keep 2+ labels)
|
||||
// Heuristic: keep last 2 labels by default; special-case known multi-label TLDs if needed.
|
||||
let parts: Vec<&str> = host.split('.').collect();
|
||||
if parts.len() >= 2 {
|
||||
// Very conservative: last 2 labels
|
||||
Some(parts[parts.len() - 2..].join("."))
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
@@ -186,7 +186,7 @@ impl TopologyState {
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, PartialEq)]
|
||||
#[derive(Debug)]
|
||||
pub enum DeploymentTarget {
|
||||
LocalDev,
|
||||
Staging,
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
use std::any::Any;
|
||||
|
||||
use async_trait::async_trait;
|
||||
use kube::api::DynamicObject;
|
||||
use log::debug;
|
||||
|
||||
use crate::{
|
||||
@@ -31,6 +32,7 @@ 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?;
|
||||
@@ -75,6 +77,14 @@ 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]
|
||||
@@ -86,4 +96,5 @@ 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>>;
|
||||
}
|
||||
|
||||
182
harmony/src/infra/kube.rs
Normal file
182
harmony/src/infra/kube.rs
Normal file
@@ -0,0 +1,182 @@
|
||||
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()
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -3,5 +3,6 @@ pub mod executors;
|
||||
pub mod hp_ilo;
|
||||
pub mod intel_amt;
|
||||
pub mod inventory;
|
||||
pub mod kube;
|
||||
pub mod opnsense;
|
||||
mod sqlx;
|
||||
|
||||
@@ -10,7 +10,7 @@ use super::OPNSenseFirewall;
|
||||
|
||||
#[async_trait]
|
||||
impl DnsServer for OPNSenseFirewall {
|
||||
async fn register_hosts(&self, _hosts: Vec<DnsRecord>) -> Result<(), ExecutorError> {
|
||||
async fn register_hosts(&self, hosts: Vec<DnsRecord>) -> Result<(), ExecutorError> {
|
||||
todo!("Refactor this to use dnsmasq")
|
||||
// let mut writable_opnsense = self.opnsense_config.write().await;
|
||||
// let mut dns = writable_opnsense.dns();
|
||||
@@ -68,7 +68,7 @@ impl DnsServer for OPNSenseFirewall {
|
||||
self.host.clone()
|
||||
}
|
||||
|
||||
async fn register_dhcp_leases(&self, _register: bool) -> Result<(), ExecutorError> {
|
||||
async fn register_dhcp_leases(&self, register: bool) -> Result<(), ExecutorError> {
|
||||
todo!("Refactor this to use dnsmasq")
|
||||
// let mut writable_opnsense = self.opnsense_config.write().await;
|
||||
// let mut dns = writable_opnsense.dns();
|
||||
|
||||
@@ -21,7 +21,7 @@ pub struct Helm {
|
||||
pub skip_schema_validation: Option<bool>,
|
||||
pub version: Option<String>,
|
||||
pub kube_version: Option<String>,
|
||||
// pub api_versions: Vec<String>,
|
||||
pub api_versions: Vec<String>,
|
||||
pub namespace: Option<String>,
|
||||
}
|
||||
|
||||
@@ -105,7 +105,7 @@ impl Default for ArgoApplication {
|
||||
skip_schema_validation: None,
|
||||
version: None,
|
||||
kube_version: None,
|
||||
// api_versions: vec![],
|
||||
api_versions: vec![],
|
||||
namespace: None,
|
||||
},
|
||||
path: "".to_string(),
|
||||
@@ -155,7 +155,7 @@ impl From<CDApplicationConfig> for ArgoApplication {
|
||||
skip_schema_validation: None,
|
||||
version: None,
|
||||
kube_version: None,
|
||||
// api_versions: vec![],
|
||||
api_versions: vec![],
|
||||
namespace: None,
|
||||
},
|
||||
},
|
||||
@@ -181,11 +181,13 @@ impl From<CDApplicationConfig> for ArgoApplication {
|
||||
}
|
||||
|
||||
impl ArgoApplication {
|
||||
pub fn to_yaml(&self, target_namespace: Option<&str>) -> serde_yaml::Value {
|
||||
pub fn to_yaml(&self) -> serde_yaml::Value {
|
||||
let name = &self.name;
|
||||
let default_ns = "argocd".to_string();
|
||||
let namespace: &str =
|
||||
target_namespace.unwrap_or(self.namespace.as_ref().unwrap_or(&default_ns));
|
||||
let namespace = if let Some(ns) = self.namespace.as_ref() {
|
||||
ns
|
||||
} else {
|
||||
"argocd"
|
||||
};
|
||||
let project = &self.project;
|
||||
|
||||
let yaml_str = format!(
|
||||
@@ -283,7 +285,7 @@ mod tests {
|
||||
skip_schema_validation: None,
|
||||
version: None,
|
||||
kube_version: None,
|
||||
// api_versions: vec![],
|
||||
api_versions: vec![],
|
||||
namespace: None,
|
||||
},
|
||||
path: "".to_string(),
|
||||
@@ -343,7 +345,7 @@ spec:
|
||||
|
||||
assert_eq!(
|
||||
expected_yaml_output.trim(),
|
||||
serde_yaml::to_string(&app.clone().to_yaml(None))
|
||||
serde_yaml::to_string(&app.clone().to_yaml())
|
||||
.unwrap()
|
||||
.trim()
|
||||
);
|
||||
|
||||
@@ -1,21 +1,22 @@
|
||||
use async_trait::async_trait;
|
||||
use harmony_macros::hurl;
|
||||
use kube::{Api, api::GroupVersionKind};
|
||||
use log::{debug, info, trace, warn};
|
||||
use log::{debug, warn};
|
||||
use non_blank_string_rs::NonBlankString;
|
||||
use serde::Serialize;
|
||||
use std::{str::FromStr, sync::Arc};
|
||||
use serde::de::DeserializeOwned;
|
||||
use std::{process::Command, str::FromStr, sync::Arc};
|
||||
|
||||
use crate::{
|
||||
data::Version,
|
||||
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
|
||||
inventory::Inventory,
|
||||
modules::{
|
||||
argocd::{ArgoDeploymentType, detect_argo_deployment_type},
|
||||
helm::chart::{HelmChartScore, HelmRepository},
|
||||
},
|
||||
modules::helm::chart::{HelmChartScore, HelmRepository},
|
||||
score::Score,
|
||||
topology::{HelmCommand, K8sclient, Topology, ingress::Ingress, k8s::K8sClient},
|
||||
topology::{
|
||||
HelmCommand, K8sclient, PreparationError, PreparationOutcome, Topology, ingress::Ingress,
|
||||
k8s::K8sClient,
|
||||
},
|
||||
};
|
||||
use harmony_types::id::Id;
|
||||
|
||||
@@ -24,7 +25,6 @@ use super::ArgoApplication;
|
||||
#[derive(Debug, Serialize, Clone)]
|
||||
pub struct ArgoHelmScore {
|
||||
pub namespace: String,
|
||||
// TODO: remove and rely on topology (it now knows the flavor)
|
||||
pub openshift: bool,
|
||||
pub argo_apps: Vec<ArgoApplication>,
|
||||
}
|
||||
@@ -55,101 +55,29 @@ impl<T: Topology + K8sclient + HelmCommand + Ingress> Interpret<T> for ArgoInter
|
||||
inventory: &Inventory,
|
||||
topology: &T,
|
||||
) -> Result<Outcome, InterpretError> {
|
||||
trace!("Starting ArgoInterpret execution {self:?}");
|
||||
let k8s_client: Arc<K8sClient> = topology.k8s_client().await?;
|
||||
trace!("Got k8s client");
|
||||
let desired_ns = self.score.namespace.clone();
|
||||
|
||||
debug!("ArgoInterpret detecting cluster configuration");
|
||||
let svc = format!("argo-{}", desired_ns);
|
||||
let k8s_client = topology.k8s_client().await?;
|
||||
let svc = format!("argo-{}", self.score.namespace.clone());
|
||||
let domain = topology.get_domain(&svc).await?;
|
||||
debug!("Resolved Argo service domain for '{}': {}", svc, domain);
|
||||
let helm_score =
|
||||
argo_helm_chart_score(&self.score.namespace, self.score.openshift, &domain);
|
||||
|
||||
// Detect current Argo deployment type
|
||||
let current = detect_argo_deployment_type(&k8s_client, &desired_ns).await?;
|
||||
info!("Detected Argo deployment type: {:?}", current);
|
||||
helm_score.interpret(inventory, topology).await?;
|
||||
|
||||
// Decide control namespace and whether we must install
|
||||
let (control_ns, must_install) = match current.clone() {
|
||||
ArgoDeploymentType::NotInstalled => {
|
||||
info!(
|
||||
"Argo CD not installed. Will install via Helm into namespace '{}'.",
|
||||
desired_ns
|
||||
);
|
||||
(desired_ns.clone(), true)
|
||||
}
|
||||
ArgoDeploymentType::AvailableInDesiredNamespace(ns) => {
|
||||
info!(
|
||||
"Argo CD already installed by Harmony in '{}'. Skipping install.",
|
||||
ns
|
||||
);
|
||||
(ns, false)
|
||||
}
|
||||
ArgoDeploymentType::InstalledClusterWide(ns) => {
|
||||
info!(
|
||||
"Argo CD installed cluster-wide in namespace '{}'.",
|
||||
ns
|
||||
);
|
||||
(ns, false)
|
||||
}
|
||||
ArgoDeploymentType::InstalledNamespaceScoped(ns) => {
|
||||
// TODO we could support this use case by installing a new argo instance. But that
|
||||
// means handling a few cases that are out of scope for now :
|
||||
// - Wether argo operator is installed
|
||||
// - Managing CRD versions compatibility
|
||||
// - Potentially handling the various k8s flavors and setups we might encounter
|
||||
//
|
||||
// There is a possibility that the helm chart already handles most or even all of these use cases but they are out of scope for now.
|
||||
let msg = format!(
|
||||
"Argo CD found in '{}' but it is namespace-scoped and not supported for attachment yet.",
|
||||
ns
|
||||
);
|
||||
warn!("{}", msg);
|
||||
return Err(InterpretError::new(msg));
|
||||
}
|
||||
};
|
||||
|
||||
info!("ArgoCD will be installed : {must_install} . Current argocd status : {current:?} ");
|
||||
|
||||
if must_install {
|
||||
let helm_score = argo_helm_chart_score(&desired_ns, self.score.openshift, &domain);
|
||||
info!(
|
||||
"Installing Argo CD via Helm into namespace '{}' ...",
|
||||
desired_ns
|
||||
);
|
||||
helm_score.interpret(inventory, topology).await?;
|
||||
info!("Argo CD install complete in '{}'.", desired_ns);
|
||||
}
|
||||
|
||||
let yamls: Vec<serde_yaml::Value> = self
|
||||
.argo_apps
|
||||
.iter()
|
||||
.map(|a| a.to_yaml(Some(&control_ns)))
|
||||
.collect();
|
||||
info!(
|
||||
"Applying {} Argo application object(s) into control namespace '{}'.",
|
||||
yamls.len(),
|
||||
control_ns
|
||||
);
|
||||
k8s_client
|
||||
.apply_yaml_many(&yamls, Some(control_ns.as_str()))
|
||||
.apply_yaml_many(&self.argo_apps.iter().map(|a| a.to_yaml()).collect(), None)
|
||||
.await
|
||||
.map_err(|e| InterpretError::new(format!("Failed applying Argo CRs: {e}")))?;
|
||||
.unwrap();
|
||||
|
||||
Ok(Outcome::success_with_details(
|
||||
format!(
|
||||
"ArgoCD {} {}",
|
||||
self.argo_apps.len(),
|
||||
if self.argo_apps.len() == 1 {
|
||||
"application"
|
||||
} else {
|
||||
"applications"
|
||||
match self.argo_apps.len() {
|
||||
1 => "application",
|
||||
_ => "applications",
|
||||
}
|
||||
),
|
||||
vec![
|
||||
format!("control_namespace={}", control_ns),
|
||||
format!("argo ui: http://{}", domain),
|
||||
],
|
||||
vec![format!("argo application: http://{}", domain)],
|
||||
))
|
||||
}
|
||||
|
||||
@@ -158,7 +86,7 @@ impl<T: Topology + K8sclient + HelmCommand + Ingress> Interpret<T> for ArgoInter
|
||||
}
|
||||
|
||||
fn get_version(&self) -> Version {
|
||||
Version::from("0.1.0").unwrap()
|
||||
todo!()
|
||||
}
|
||||
|
||||
fn get_status(&self) -> InterpretStatus {
|
||||
@@ -166,7 +94,39 @@ impl<T: Topology + K8sclient + HelmCommand + Ingress> Interpret<T> for ArgoInter
|
||||
}
|
||||
|
||||
fn get_children(&self) -> Vec<Id> {
|
||||
vec![]
|
||||
todo!()
|
||||
}
|
||||
}
|
||||
|
||||
impl ArgoInterpret {
|
||||
pub async fn get_host_domain(
|
||||
&self,
|
||||
client: Arc<K8sClient>,
|
||||
openshift: bool,
|
||||
) -> Result<String, InterpretError> {
|
||||
//This should be the job of the topology to determine if we are in
|
||||
//openshift, potentially we need on openshift topology the same way we create a
|
||||
//localhosttopology
|
||||
match openshift {
|
||||
true => {
|
||||
let gvk = GroupVersionKind {
|
||||
group: "operator.openshift.io".into(),
|
||||
version: "v1".into(),
|
||||
kind: "IngressController".into(),
|
||||
};
|
||||
let ic = client
|
||||
.get_resource_json_value("default", Some("openshift-ingress-operator"), &gvk)
|
||||
.await?;
|
||||
|
||||
match ic.data["status"]["domain"].as_str() {
|
||||
Some(domain) => return Ok(domain.to_string()),
|
||||
None => return Err(InterpretError::new("Could not find domain".to_string())),
|
||||
}
|
||||
}
|
||||
false => {
|
||||
todo!()
|
||||
}
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -2,7 +2,11 @@ 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::{
|
||||
@@ -14,7 +18,7 @@ use crate::{
|
||||
topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
|
||||
};
|
||||
use crate::{
|
||||
modules::prometheus::prometheus::PrometheusApplicationMonitoring,
|
||||
modules::prometheus::prometheus::PrometheusMonitoring,
|
||||
topology::oberservability::monitoring::AlertReceiver,
|
||||
};
|
||||
use async_trait::async_trait;
|
||||
@@ -22,6 +26,7 @@ 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;
|
||||
@@ -40,7 +45,8 @@ impl<
|
||||
+ TenantManager
|
||||
+ K8sclient
|
||||
+ MultiTargetTopology
|
||||
+ PrometheusApplicationMonitoring<CRDPrometheus>
|
||||
+ PrometheusMonitoring<CRDPrometheus>
|
||||
+ Grafana
|
||||
+ Ingress
|
||||
+ std::fmt::Debug,
|
||||
> ApplicationFeature<T> for Monitoring
|
||||
@@ -57,10 +63,20 @@ 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(),
|
||||
|
||||
@@ -10,11 +10,12 @@ use crate::{
|
||||
data::Version,
|
||||
inventory::Inventory,
|
||||
modules::application::{
|
||||
features::{ArgoApplication, ArgoHelmScore}, webapp::Webapp, ApplicationFeature, HelmPackage, InstallationError, InstallationOutcome, OCICompliant
|
||||
ApplicationFeature, HelmPackage, InstallationError, InstallationOutcome, OCICompliant,
|
||||
features::{ArgoApplication, ArgoHelmScore},
|
||||
},
|
||||
score::Score,
|
||||
topology::{
|
||||
ingress::Ingress, DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, Topology
|
||||
DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, Topology, ingress::Ingress,
|
||||
},
|
||||
};
|
||||
|
||||
@@ -46,11 +47,11 @@ use crate::{
|
||||
/// - ArgoCD to install/upgrade/rollback/inspect k8s resources
|
||||
/// - Kubernetes for runtime orchestration
|
||||
#[derive(Debug, Default, Clone)]
|
||||
pub struct PackagingDeployment<A: OCICompliant + HelmPackage + Webapp> {
|
||||
pub struct PackagingDeployment<A: OCICompliant + HelmPackage> {
|
||||
pub application: Arc<A>,
|
||||
}
|
||||
|
||||
impl<A: OCICompliant + HelmPackage + Webapp> PackagingDeployment<A> {
|
||||
impl<A: OCICompliant + HelmPackage> PackagingDeployment<A> {
|
||||
async fn deploy_to_local_k3d(
|
||||
&self,
|
||||
app_name: String,
|
||||
@@ -136,7 +137,7 @@ impl<A: OCICompliant + HelmPackage + Webapp> PackagingDeployment<A> {
|
||||
|
||||
#[async_trait]
|
||||
impl<
|
||||
A: OCICompliant + HelmPackage + Webapp + Clone + 'static,
|
||||
A: OCICompliant + HelmPackage + Clone + 'static,
|
||||
T: Topology + HelmCommand + MultiTargetTopology + K8sclient + Ingress + 'static,
|
||||
> ApplicationFeature<T> for PackagingDeployment<A>
|
||||
{
|
||||
@@ -145,15 +146,10 @@ impl<
|
||||
topology: &T,
|
||||
) -> Result<InstallationOutcome, InstallationError> {
|
||||
let image = self.application.image_name();
|
||||
|
||||
let domain = if topology.current_target() == DeploymentTarget::Production {
|
||||
self.application.dns()
|
||||
} else {
|
||||
topology
|
||||
let domain = topology
|
||||
.get_domain(&self.application.name())
|
||||
.await
|
||||
.map_err(|e| e.to_string())?
|
||||
};
|
||||
.map_err(|e| e.to_string())?;
|
||||
|
||||
// TODO Write CI/CD workflow files
|
||||
// we can autotedect the CI type using the remote url (default to github action for github
|
||||
@@ -198,7 +194,7 @@ impl<
|
||||
openshift: true,
|
||||
argo_apps: vec![ArgoApplication::from(CDApplicationConfig {
|
||||
// helm pull oci://hub.nationtech.io/harmony/harmony-example-rust-webapp-chart --version 0.1.0
|
||||
version: Version::from("0.2.1").unwrap(),
|
||||
version: Version::from("0.1.0").unwrap(),
|
||||
helm_chart_repo_url: "hub.nationtech.io/harmony".to_string(),
|
||||
helm_chart_name: format!("{}-chart", self.application.name()),
|
||||
values_overrides: None,
|
||||
|
||||
@@ -3,6 +3,7 @@ use std::sync::Arc;
|
||||
use crate::modules::application::{
|
||||
Application, ApplicationFeature, InstallationError, InstallationOutcome,
|
||||
};
|
||||
use crate::modules::monitoring::application_monitoring::application_monitoring_score::ApplicationMonitoringScore;
|
||||
use crate::modules::monitoring::application_monitoring::rhobs_application_monitoring_score::ApplicationRHOBMonitoringScore;
|
||||
|
||||
use crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::RHOBObservability;
|
||||
@@ -17,7 +18,7 @@ use crate::{
|
||||
topology::{HelmCommand, K8sclient, Topology, tenant::TenantManager},
|
||||
};
|
||||
use crate::{
|
||||
modules::prometheus::prometheus::PrometheusApplicationMonitoring,
|
||||
modules::prometheus::prometheus::PrometheusMonitoring,
|
||||
topology::oberservability::monitoring::AlertReceiver,
|
||||
};
|
||||
use async_trait::async_trait;
|
||||
@@ -41,7 +42,7 @@ impl<
|
||||
+ MultiTargetTopology
|
||||
+ Ingress
|
||||
+ std::fmt::Debug
|
||||
+ PrometheusApplicationMonitoring<RHOBObservability>,
|
||||
+ PrometheusMonitoring<RHOBObservability>,
|
||||
> ApplicationFeature<T> for Monitoring
|
||||
{
|
||||
async fn ensure_installed(
|
||||
|
||||
@@ -2,7 +2,6 @@ mod feature;
|
||||
pub mod features;
|
||||
pub mod oci;
|
||||
mod rust;
|
||||
mod webapp;
|
||||
use std::sync::Arc;
|
||||
|
||||
pub use feature::*;
|
||||
|
||||
@@ -16,7 +16,6 @@ use tar::{Builder, Header};
|
||||
use walkdir::WalkDir;
|
||||
|
||||
use crate::config::{REGISTRY_PROJECT, REGISTRY_URL};
|
||||
use crate::modules::application::webapp::Webapp;
|
||||
use crate::{score::Score, topology::Topology};
|
||||
|
||||
use super::{Application, ApplicationFeature, ApplicationInterpret, HelmPackage, OCICompliant};
|
||||
@@ -61,10 +60,6 @@ pub struct RustWebapp {
|
||||
pub project_root: PathBuf,
|
||||
pub service_port: u32,
|
||||
pub framework: Option<RustWebFramework>,
|
||||
/// Host name that will be used in production environment.
|
||||
///
|
||||
/// This is the place to put the public host name if this is a public facing webapp.
|
||||
pub dns: String,
|
||||
}
|
||||
|
||||
impl Application for RustWebapp {
|
||||
@@ -73,12 +68,6 @@ impl Application for RustWebapp {
|
||||
}
|
||||
}
|
||||
|
||||
impl Webapp for RustWebapp {
|
||||
fn dns(&self) -> String {
|
||||
self.dns.clone()
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl HelmPackage for RustWebapp {
|
||||
async fn build_push_helm_package(
|
||||
@@ -205,10 +194,10 @@ impl RustWebapp {
|
||||
Some(body_full(tar_data.into())),
|
||||
);
|
||||
|
||||
while let Some(msg) = image_build_stream.next().await {
|
||||
while let Some(mut msg) = image_build_stream.next().await {
|
||||
trace!("Got bollard msg {msg:?}");
|
||||
match msg {
|
||||
Ok(msg) => {
|
||||
Ok(mut msg) => {
|
||||
if let Some(progress) = msg.progress_detail {
|
||||
info!(
|
||||
"Build progress {}/{}",
|
||||
@@ -268,6 +257,7 @@ impl RustWebapp {
|
||||
".harmony_generated",
|
||||
"harmony",
|
||||
"node_modules",
|
||||
"Dockerfile.harmony",
|
||||
];
|
||||
let mut entries: Vec<_> = WalkDir::new(project_root)
|
||||
.into_iter()
|
||||
@@ -471,53 +461,52 @@ impl RustWebapp {
|
||||
|
||||
let (image_repo, image_tag) = image_url.rsplit_once(':').unwrap_or((image_url, "latest"));
|
||||
|
||||
let app_name = &self.name;
|
||||
let service_port = self.service_port;
|
||||
// Create Chart.yaml
|
||||
let chart_yaml = format!(
|
||||
r#"
|
||||
apiVersion: v2
|
||||
name: {chart_name}
|
||||
description: A Helm chart for the {app_name} web application.
|
||||
name: {}
|
||||
description: A Helm chart for the {} web application.
|
||||
type: application
|
||||
version: 0.2.1
|
||||
appVersion: "{image_tag}"
|
||||
version: 0.1.0
|
||||
appVersion: "{}"
|
||||
"#,
|
||||
chart_name, self.name, image_tag
|
||||
);
|
||||
fs::write(chart_dir.join("Chart.yaml"), chart_yaml)?;
|
||||
|
||||
// Create values.yaml
|
||||
let values_yaml = format!(
|
||||
r#"
|
||||
# Default values for {chart_name}.
|
||||
# Default values for {}.
|
||||
# This is a YAML-formatted file.
|
||||
# Declare variables to be passed into your templates.
|
||||
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: {image_repo}
|
||||
repository: {}
|
||||
pullPolicy: IfNotPresent
|
||||
# Overridden by the chart's appVersion
|
||||
tag: "{image_tag}"
|
||||
tag: "{}"
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: {service_port}
|
||||
port: {}
|
||||
|
||||
ingress:
|
||||
enabled: true
|
||||
tls: true
|
||||
# Annotations for cert-manager to handle SSL.
|
||||
annotations:
|
||||
# Add other annotations like nginx ingress class if needed
|
||||
# kubernetes.io/ingress.class: nginx
|
||||
hosts:
|
||||
- host: {domain}
|
||||
- host: {}
|
||||
paths:
|
||||
- path: /
|
||||
pathType: ImplementationSpecific
|
||||
"#,
|
||||
chart_name, image_repo, image_tag, self.service_port, domain,
|
||||
);
|
||||
fs::write(chart_dir.join("values.yaml"), values_yaml)?;
|
||||
|
||||
@@ -594,11 +583,7 @@ spec:
|
||||
);
|
||||
fs::write(templates_dir.join("deployment.yaml"), deployment_yaml)?;
|
||||
|
||||
let service_port = self.service_port;
|
||||
|
||||
// Create templates/ingress.yaml
|
||||
// TODO get issuer name and tls config from topology as it may be different from one
|
||||
// cluster to another, also from one version to another
|
||||
let ingress_yaml = format!(
|
||||
r#"
|
||||
{{{{- if $.Values.ingress.enabled -}}}}
|
||||
@@ -611,11 +596,13 @@ metadata:
|
||||
spec:
|
||||
{{{{- if $.Values.ingress.tls }}}}
|
||||
tls:
|
||||
- secretName: {{{{ include "chart.fullname" . }}}}-tls
|
||||
hosts:
|
||||
{{{{- range $.Values.ingress.hosts }}}}
|
||||
- {{{{ .host | quote }}}}
|
||||
{{{{- range $.Values.ingress.tls }}}}
|
||||
- hosts:
|
||||
{{{{- range .hosts }}}}
|
||||
- {{{{ . | quote }}}}
|
||||
{{{{- end }}}}
|
||||
secretName: {{{{ .secretName }}}}
|
||||
{{{{- end }}}}
|
||||
{{{{- end }}}}
|
||||
rules:
|
||||
{{{{- range $.Values.ingress.hosts }}}}
|
||||
@@ -629,11 +616,12 @@ spec:
|
||||
service:
|
||||
name: {{{{ include "chart.fullname" $ }}}}
|
||||
port:
|
||||
number: {{{{ $.Values.service.port | default {service_port} }}}}
|
||||
number: {{{{ $.Values.service.port | default {} }}}}
|
||||
{{{{- end }}}}
|
||||
{{{{- end }}}}
|
||||
{{{{- end }}}}
|
||||
"#,
|
||||
self.service_port
|
||||
);
|
||||
fs::write(templates_dir.join("ingress.yaml"), ingress_yaml)?;
|
||||
|
||||
|
||||
@@ -1,7 +0,0 @@
|
||||
use super::Application;
|
||||
use async_trait::async_trait;
|
||||
|
||||
#[async_trait]
|
||||
pub trait Webapp: Application {
|
||||
fn dns(&self) -> String;
|
||||
}
|
||||
@@ -1,203 +0,0 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use log::{debug, info};
|
||||
|
||||
use crate::{interpret::InterpretError, topology::k8s::K8sClient};
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq)]
|
||||
pub enum ArgoScope {
|
||||
ClusterWide(String),
|
||||
NamespaceScoped(String),
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug)]
|
||||
pub struct DiscoveredArgo {
|
||||
pub control_namespace: String,
|
||||
pub scope: ArgoScope,
|
||||
pub has_crds: bool,
|
||||
pub has_applicationset: bool,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug, PartialEq, Eq)]
|
||||
pub enum ArgoDeploymentType {
|
||||
NotInstalled,
|
||||
AvailableInDesiredNamespace(String),
|
||||
InstalledClusterWide(String),
|
||||
InstalledNamespaceScoped(String),
|
||||
}
|
||||
|
||||
pub async fn discover_argo_all(
|
||||
k8s: &Arc<K8sClient>,
|
||||
) -> Result<Vec<DiscoveredArgo>, InterpretError> {
|
||||
use log::{debug, info, trace, warn};
|
||||
|
||||
trace!("Starting Argo discovery");
|
||||
|
||||
// CRDs
|
||||
let mut has_crds = true;
|
||||
let required_crds = vec!["applications.argoproj.io", "appprojects.argoproj.io"];
|
||||
trace!("Checking required Argo CRDs: {:?}", required_crds);
|
||||
|
||||
for crd in required_crds {
|
||||
trace!("Verifying CRD presence: {crd}");
|
||||
let crd_exists = k8s.has_crd(crd).await.map_err(|e| {
|
||||
InterpretError::new(format!("Failed to verify existence of CRD {crd}: {e}"))
|
||||
})?;
|
||||
|
||||
debug!("CRD {crd} exists: {crd_exists}");
|
||||
if !crd_exists {
|
||||
info!(
|
||||
"Missing Argo CRD {crd}, looks like Argo CD is not installed (or partially installed)"
|
||||
);
|
||||
has_crds = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
trace!(
|
||||
"Listing namespaces with healthy Argo CD deployments using selector app.kubernetes.io/part-of=argocd"
|
||||
);
|
||||
let mut candidate_namespaces = k8s
|
||||
.list_namespaces_with_healthy_deployments("app.kubernetes.io/part-of=argocd")
|
||||
.await
|
||||
.map_err(|e| InterpretError::new(format!("List healthy argocd deployments: {e}")))?;
|
||||
trace!(
|
||||
"Listing namespaces with healthy Argo CD deployments using selector app.kubernetes.io/name=argo-cd"
|
||||
);
|
||||
candidate_namespaces.append(
|
||||
&mut k8s
|
||||
.list_namespaces_with_healthy_deployments("app.kubernetes.io/name=argo-cd")
|
||||
.await
|
||||
.map_err(|e| InterpretError::new(format!("List healthy argocd deployments: {e}")))?,
|
||||
);
|
||||
|
||||
debug!(
|
||||
"Discovered {} candidate namespace(s) for Argo CD: {:?}",
|
||||
candidate_namespaces.len(),
|
||||
candidate_namespaces
|
||||
);
|
||||
|
||||
let mut found = Vec::new();
|
||||
for ns in candidate_namespaces {
|
||||
trace!("Evaluating namespace '{ns}' for Argo CD instance");
|
||||
|
||||
// Require the application-controller to be healthy (sanity check)
|
||||
trace!(
|
||||
"Checking healthy deployment with label app.kubernetes.io/name=argocd-application-controller in namespace '{ns}'"
|
||||
);
|
||||
let controller_ok = k8s
|
||||
.has_healthy_deployment_with_label(
|
||||
&ns,
|
||||
"app.kubernetes.io/name=argocd-application-controller",
|
||||
)
|
||||
.await
|
||||
.unwrap_or_else(|e| {
|
||||
warn!(
|
||||
"Error while checking application-controller health in namespace '{ns}': {e}"
|
||||
);
|
||||
false
|
||||
}) || k8s
|
||||
.has_healthy_deployment_with_label(
|
||||
&ns,
|
||||
"app.kubernetes.io/component=controller",
|
||||
)
|
||||
.await
|
||||
.unwrap_or_else(|e| {
|
||||
warn!(
|
||||
"Error while checking application-controller health in namespace '{ns}': {e}"
|
||||
);
|
||||
false
|
||||
});
|
||||
debug!("Namespace '{ns}': application-controller healthy = {controller_ok}");
|
||||
|
||||
if !controller_ok {
|
||||
trace!("Skipping namespace '{ns}' because application-controller is not healthy");
|
||||
continue;
|
||||
}
|
||||
|
||||
trace!("Determining Argo CD scope for namespace '{ns}' (cluster-wide vs namespace-scoped)");
|
||||
let scope = match k8s.is_argocd_cluster_wide(&ns).await {
|
||||
Ok(true) => {
|
||||
debug!("Namespace '{ns}' identified as cluster-wide Argo CD control plane");
|
||||
ArgoScope::ClusterWide(ns.to_string())
|
||||
}
|
||||
Ok(false) => {
|
||||
debug!("Namespace '{ns}' identified as namespace-scoped Argo CD control plane");
|
||||
ArgoScope::NamespaceScoped(ns.to_string())
|
||||
}
|
||||
Err(e) => {
|
||||
warn!(
|
||||
"Failed to determine Argo CD scope for namespace '{ns}': {e}. Assuming namespace-scoped."
|
||||
);
|
||||
ArgoScope::NamespaceScoped(ns.to_string())
|
||||
}
|
||||
};
|
||||
|
||||
trace!("Checking optional ApplicationSet CRD (applicationsets.argoproj.io)");
|
||||
let has_applicationset = match k8s.has_crd("applicationsets.argoproj.io").await {
|
||||
Ok(v) => {
|
||||
debug!("applicationsets.argoproj.io present: {v}");
|
||||
v
|
||||
}
|
||||
Err(e) => {
|
||||
warn!("Failed to check applicationsets.argoproj.io CRD: {e}. Assuming absent.");
|
||||
false
|
||||
}
|
||||
};
|
||||
|
||||
let argo = DiscoveredArgo {
|
||||
control_namespace: ns.clone(),
|
||||
scope,
|
||||
has_crds,
|
||||
has_applicationset,
|
||||
};
|
||||
|
||||
debug!("Discovered Argo instance in '{ns}': {argo:?}");
|
||||
found.push(argo);
|
||||
}
|
||||
|
||||
if found.is_empty() {
|
||||
info!("No Argo CD installations discovered");
|
||||
} else {
|
||||
info!(
|
||||
"Argo CD discovery complete: {} instance(s) found",
|
||||
found.len()
|
||||
);
|
||||
}
|
||||
|
||||
Ok(found)
|
||||
}
|
||||
|
||||
pub async fn detect_argo_deployment_type(
|
||||
k8s: &Arc<K8sClient>,
|
||||
desired_namespace: &str,
|
||||
) -> Result<ArgoDeploymentType, InterpretError> {
|
||||
let discovered = discover_argo_all(k8s).await?;
|
||||
debug!("Discovered argo instances {discovered:?}");
|
||||
|
||||
if discovered.is_empty() {
|
||||
return Ok(ArgoDeploymentType::NotInstalled);
|
||||
}
|
||||
|
||||
if let Some(d) = discovered
|
||||
.iter()
|
||||
.find(|d| d.control_namespace == desired_namespace)
|
||||
{
|
||||
return Ok(ArgoDeploymentType::AvailableInDesiredNamespace(
|
||||
d.control_namespace.clone(),
|
||||
));
|
||||
}
|
||||
|
||||
if let Some(d) = discovered
|
||||
.iter()
|
||||
.find(|d| matches!(d.scope, ArgoScope::ClusterWide(_)))
|
||||
{
|
||||
return Ok(ArgoDeploymentType::InstalledClusterWide(
|
||||
d.control_namespace.clone(),
|
||||
));
|
||||
}
|
||||
|
||||
Ok(ArgoDeploymentType::InstalledNamespaceScoped(
|
||||
discovered[0].control_namespace.clone(),
|
||||
))
|
||||
}
|
||||
@@ -90,12 +90,12 @@ impl<T: Topology> Interpret<T> for DiscoverInventoryAgentInterpret {
|
||||
// refactoring to do it now
|
||||
let harmony_inventory_agent::hwinfo::PhysicalHost {
|
||||
storage_drives,
|
||||
storage_controller: _,
|
||||
storage_controller,
|
||||
memory_modules,
|
||||
cpus,
|
||||
chipset: _,
|
||||
chipset,
|
||||
network_interfaces,
|
||||
management_interface: _,
|
||||
management_interface,
|
||||
host_uuid,
|
||||
} = host;
|
||||
|
||||
|
||||
@@ -17,4 +17,3 @@ pub mod prometheus;
|
||||
pub mod storage;
|
||||
pub mod tenant;
|
||||
pub mod tftp;
|
||||
pub mod argocd;
|
||||
|
||||
@@ -3,7 +3,8 @@ use std::collections::BTreeMap;
|
||||
|
||||
use async_trait::async_trait;
|
||||
use k8s_openapi::api::core::v1::Secret;
|
||||
use kube::api::ObjectMeta;
|
||||
use kube::Resource;
|
||||
use kube::api::{DynamicObject, ObjectMeta};
|
||||
use log::debug;
|
||||
use serde::Serialize;
|
||||
use serde_json::json;
|
||||
@@ -13,6 +14,8 @@ 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::{
|
||||
@@ -32,10 +35,8 @@ pub struct DiscordWebhook {
|
||||
pub url: Url,
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl AlertReceiver<RHOBObservability> for DiscordWebhook {
|
||||
async fn install(&self, sender: &RHOBObservability) -> Result<Outcome, InterpretError> {
|
||||
let ns = sender.namespace.clone();
|
||||
impl DiscordWebhook {
|
||||
fn get_receiver_config(&self) -> AlertManagerReceiver {
|
||||
let secret_name = format!("{}-secret", self.name.clone());
|
||||
let webhook_key = format!("{}", self.url.clone());
|
||||
|
||||
@@ -52,26 +53,74 @@ impl AlertReceiver<RHOBObservability> for DiscordWebhook {
|
||||
..Default::default()
|
||||
};
|
||||
|
||||
let _ = sender.client.apply(&secret, Some(&ns)).await;
|
||||
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 spec = crate::modules::monitoring::kube_prometheus::crd::rhob_alertmanager_config::AlertmanagerConfigSpec {
|
||||
data: json!({
|
||||
"route": {
|
||||
"receiver": self.name,
|
||||
},
|
||||
"receivers": [
|
||||
{
|
||||
"name": self.name,
|
||||
"discordConfigs": [
|
||||
{
|
||||
"apiURL": {
|
||||
"name": secret_name,
|
||||
"key": "webhook-url",
|
||||
},
|
||||
"title": "{{ template \"discord.default.title\" . }}",
|
||||
"message": "{{ template \"discord.default.message\" . }}"
|
||||
}
|
||||
]
|
||||
}
|
||||
config.receiver_config
|
||||
]
|
||||
}),
|
||||
};
|
||||
@@ -122,6 +171,9 @@ 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());
|
||||
@@ -200,6 +252,9 @@ 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
|
||||
}
|
||||
@@ -226,6 +281,9 @@ 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
|
||||
}
|
||||
|
||||
@@ -19,7 +19,7 @@ use crate::{
|
||||
},
|
||||
prometheus::prometheus::{Prometheus, PrometheusReceiver},
|
||||
},
|
||||
topology::oberservability::monitoring::AlertReceiver,
|
||||
topology::oberservability::monitoring::{AlertManagerReceiver, AlertReceiver},
|
||||
};
|
||||
use harmony_types::net::Url;
|
||||
|
||||
@@ -31,6 +31,9 @@ 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!({
|
||||
@@ -97,6 +100,9 @@ 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!({
|
||||
@@ -158,6 +164,9 @@ 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
|
||||
}
|
||||
@@ -184,6 +193,9 @@ 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
|
||||
}
|
||||
|
||||
@@ -1,21 +1,23 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use async_trait::async_trait;
|
||||
use log::debug;
|
||||
use serde::Serialize;
|
||||
|
||||
use crate::{
|
||||
data::Version,
|
||||
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
|
||||
inventory::Inventory,
|
||||
interpret::Interpret,
|
||||
modules::{
|
||||
application::Application,
|
||||
monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
|
||||
prometheus::prometheus::PrometheusApplicationMonitoring,
|
||||
monitoring::{
|
||||
grafana::grafana::Grafana, kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
|
||||
},
|
||||
prometheus::prometheus::PrometheusMonitoring,
|
||||
},
|
||||
score::Score,
|
||||
topology::{PreparationOutcome, Topology, oberservability::monitoring::AlertReceiver},
|
||||
topology::{
|
||||
K8sclient, Topology,
|
||||
oberservability::monitoring::{AlertReceiver, AlertingInterpret, ScrapeTarget},
|
||||
},
|
||||
};
|
||||
use harmony_types::id::Id;
|
||||
|
||||
#[derive(Debug, Clone, Serialize)]
|
||||
pub struct ApplicationMonitoringScore {
|
||||
@@ -24,12 +26,16 @@ pub struct ApplicationMonitoringScore {
|
||||
pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
|
||||
}
|
||||
|
||||
impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
|
||||
impl<T: Topology + PrometheusMonitoring<CRDPrometheus> + K8sclient + Grafana> Score<T>
|
||||
for ApplicationMonitoringScore
|
||||
{
|
||||
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
|
||||
Box::new(ApplicationMonitoringInterpret {
|
||||
score: self.clone(),
|
||||
debug!("creating alerting interpret");
|
||||
Box::new(AlertingInterpret {
|
||||
sender: self.sender.clone(),
|
||||
receivers: self.receivers.clone(),
|
||||
rules: vec![],
|
||||
scrape_targets: None,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -40,55 +46,3 @@ impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
#[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!()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -12,7 +12,7 @@ use crate::{
|
||||
monitoring::kube_prometheus::crd::{
|
||||
crd_alertmanager_config::CRDPrometheus, rhob_alertmanager_config::RHOBObservability,
|
||||
},
|
||||
prometheus::prometheus::PrometheusApplicationMonitoring,
|
||||
prometheus::prometheus::PrometheusMonitoring,
|
||||
},
|
||||
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 + PrometheusApplicationMonitoring<RHOBObservability>> Score<T>
|
||||
impl<T: Topology + PrometheusMonitoring<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 + PrometheusApplicationMonitoring<RHOBObservability>> Interpret<T>
|
||||
impl<T: Topology + PrometheusMonitoring<RHOBObservability>> Interpret<T>
|
||||
for ApplicationRHOBMonitoringInterpret
|
||||
{
|
||||
async fn execute(
|
||||
|
||||
17
harmony/src/modules/monitoring/grafana/grafana.rs
Normal file
17
harmony/src/modules/monitoring/grafana/grafana.rs
Normal file
@@ -0,0 +1,17 @@
|
||||
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>;
|
||||
}
|
||||
@@ -1,27 +1,28 @@
|
||||
use harmony_macros::hurl;
|
||||
use non_blank_string_rs::NonBlankString;
|
||||
use std::str::FromStr;
|
||||
use std::{collections::HashMap, str::FromStr};
|
||||
|
||||
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();
|
||||
use crate::modules::helm::chart::{HelmChartScore, HelmRepository};
|
||||
|
||||
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").unwrap(),
|
||||
chart_name: NonBlankString::from_str("oci://ghcr.io/grafana/helm-charts/grafana").unwrap(),
|
||||
release_name: NonBlankString::from_str("grafana-operator").unwrap(),
|
||||
chart_name: NonBlankString::from_str("grafana/grafana-operator").unwrap(),
|
||||
chart_version: None,
|
||||
values_overrides: None,
|
||||
values_yaml: Some(values.to_string()),
|
||||
values_overrides: Some(values_overrides),
|
||||
values_yaml: None,
|
||||
create_namespace: true,
|
||||
install_only: true,
|
||||
repository: None,
|
||||
repository: Some(HelmRepository::new(
|
||||
"grafana".to_string(),
|
||||
hurl!("https://grafana.github.io/helm-charts"),
|
||||
true,
|
||||
)),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1 +1,2 @@
|
||||
pub mod grafana;
|
||||
pub mod helm;
|
||||
|
||||
@@ -1,12 +1,25 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use async_trait::async_trait;
|
||||
use kube::CustomResource;
|
||||
use schemars::JsonSchema;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use crate::topology::{
|
||||
k8s::K8sClient,
|
||||
oberservability::monitoring::{AlertReceiver, AlertSender},
|
||||
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,
|
||||
k8s::K8sClient,
|
||||
oberservability::monitoring::{AlertReceiver, AlertSender, ScrapeTarget},
|
||||
},
|
||||
};
|
||||
|
||||
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
|
||||
@@ -26,6 +39,7 @@ pub struct AlertmanagerConfigSpec {
|
||||
pub struct CRDPrometheus {
|
||||
pub namespace: String,
|
||||
pub client: Arc<K8sClient>,
|
||||
pub service_monitor: Vec<ServiceMonitor>,
|
||||
}
|
||||
|
||||
impl AlertSender for CRDPrometheus {
|
||||
@@ -40,6 +54,12 @@ 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
|
||||
@@ -48,3 +68,24 @@ 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(())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -103,9 +103,34 @@ 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,
|
||||
|
||||
pub json: String,
|
||||
#[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>,
|
||||
}
|
||||
|
||||
// ------------------------------------------------------------------------------------------------
|
||||
@@ -126,20 +151,79 @@ 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,
|
||||
pub database: Option<String>,
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub json_data: Option<BTreeMap<String, String>>,
|
||||
pub database: Option<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)]
|
||||
|
||||
@@ -1,8 +1,12 @@
|
||||
use std::collections::BTreeMap;
|
||||
|
||||
use kube::CustomResource;
|
||||
use schemars::JsonSchema;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use crate::modules::monitoring::kube_prometheus::crd::rhob_prometheuses::LabelSelector;
|
||||
use crate::modules::monitoring::kube_prometheus::crd::rhob_prometheuses::{
|
||||
LabelSelector, PrometheusSpec,
|
||||
};
|
||||
|
||||
/// MonitoringStack CRD for monitoring.rhobs/v1alpha1
|
||||
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
|
||||
|
||||
139
harmony/src/modules/monitoring/okd/cluster_monitoring.rs
Normal file
139
harmony/src/modules/monitoring/okd/cluster_monitoring.rs
Normal file
@@ -0,0 +1,139 @@
|
||||
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!()
|
||||
}
|
||||
}
|
||||
90
harmony/src/modules/monitoring/okd/config.rs
Normal file
90
harmony/src/modules/monitoring/okd/config.rs
Normal file
@@ -0,0 +1,90 @@
|
||||
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
|
||||
)))
|
||||
}
|
||||
}
|
||||
@@ -1,16 +1,13 @@
|
||||
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, k8s::K8sClient},
|
||||
topology::{K8sclient, Topology},
|
||||
};
|
||||
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)]
|
||||
@@ -37,10 +34,9 @@ impl<T: Topology + K8sclient> Interpret<T> for OpenshiftUserWorkloadMonitoringIn
|
||||
topology: &T,
|
||||
) -> Result<Outcome, InterpretError> {
|
||||
let client = topology.k8s_client().await.unwrap();
|
||||
self.update_cluster_monitoring_config_cm(&client).await?;
|
||||
self.update_user_workload_monitoring_config_cm(&client)
|
||||
.await?;
|
||||
self.verify_user_workload(&client).await?;
|
||||
Config::create_cluster_monitoring_config_cm(&client).await?;
|
||||
Config::create_user_workload_monitoring_config_cm(&client).await?;
|
||||
Config::verify_user_workload(&client).await?;
|
||||
Ok(Outcome::success(
|
||||
"successfully enabled user-workload-monitoring".to_string(),
|
||||
))
|
||||
@@ -62,88 +58,3 @@ 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
|
||||
)))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1 +1,14 @@
|
||||
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()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -114,7 +114,7 @@ impl Prometheus {
|
||||
};
|
||||
|
||||
if let Some(ns) = namespace.as_deref() {
|
||||
grafana_helm_chart_score(ns)
|
||||
grafana_helm_chart_score(ns, false)
|
||||
.interpret(inventory, topology)
|
||||
.await
|
||||
} else {
|
||||
|
||||
@@ -73,4 +73,8 @@ impl ScrapeTarget<CRDPrometheus> for Server {
|
||||
self.name.clone()
|
||||
)))
|
||||
}
|
||||
|
||||
fn clone_box(&self) -> Box<dyn ScrapeTarget<CRDPrometheus>> {
|
||||
Box::new(self.clone())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -12,7 +12,8 @@ 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,
|
||||
GrafanaDatasourceSpec, GrafanaSpec,
|
||||
GrafanaDatasourceJsonData, GrafanaDatasourceSpec, GrafanaSecretKeyRef, GrafanaSpec,
|
||||
GrafanaValueFrom, GrafanaValueSource,
|
||||
};
|
||||
use crate::modules::monitoring::kube_prometheus::crd::crd_prometheus_rules::{
|
||||
PrometheusRule, PrometheusRuleSpec, RuleGroup,
|
||||
@@ -39,7 +40,7 @@ use crate::{
|
||||
};
|
||||
use harmony_types::id::Id;
|
||||
|
||||
use super::prometheus::PrometheusApplicationMonitoring;
|
||||
use super::prometheus::PrometheusMonitoring;
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
pub struct K8sPrometheusCRDAlertingScore {
|
||||
@@ -49,7 +50,7 @@ pub struct K8sPrometheusCRDAlertingScore {
|
||||
pub prometheus_rules: Vec<RuleGroup>,
|
||||
}
|
||||
|
||||
impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
|
||||
impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus>> Score<T>
|
||||
for K8sPrometheusCRDAlertingScore
|
||||
{
|
||||
fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
|
||||
@@ -75,7 +76,7 @@ pub struct K8sPrometheusCRDAlertingInterpret {
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
|
||||
impl<T: Topology + K8sclient + PrometheusMonitoring<CRDPrometheus>> Interpret<T>
|
||||
for K8sPrometheusCRDAlertingInterpret
|
||||
{
|
||||
async fn execute(
|
||||
@@ -466,10 +467,13 @@ 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 {
|
||||
@@ -495,7 +499,11 @@ 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,
|
||||
},
|
||||
};
|
||||
|
||||
@@ -516,7 +524,9 @@ impl K8sPrometheusCRDAlertingInterpret {
|
||||
spec: GrafanaDashboardSpec {
|
||||
resync_period: Some("30s".to_string()),
|
||||
instance_selector: labels.clone(),
|
||||
json,
|
||||
json: Some(json),
|
||||
grafana_com: None,
|
||||
datasources: None,
|
||||
},
|
||||
};
|
||||
|
||||
|
||||
@@ -9,11 +9,17 @@ use crate::{
|
||||
};
|
||||
|
||||
#[async_trait]
|
||||
pub trait PrometheusApplicationMonitoring<S: AlertSender> {
|
||||
pub trait PrometheusMonitoring<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>;
|
||||
}
|
||||
|
||||
@@ -38,7 +38,7 @@ use crate::{
|
||||
};
|
||||
use harmony_types::id::Id;
|
||||
|
||||
use super::prometheus::PrometheusApplicationMonitoring;
|
||||
use super::prometheus::PrometheusMonitoring;
|
||||
|
||||
#[derive(Clone, Debug, Serialize)]
|
||||
pub struct RHOBAlertingScore {
|
||||
@@ -48,8 +48,8 @@ pub struct RHOBAlertingScore {
|
||||
pub prometheus_rules: Vec<RuleGroup>,
|
||||
}
|
||||
|
||||
impl<T: Topology + K8sclient + Ingress + PrometheusApplicationMonitoring<RHOBObservability>>
|
||||
Score<T> for RHOBAlertingScore
|
||||
impl<T: Topology + K8sclient + Ingress + PrometheusMonitoring<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 + PrometheusApplicationMonitoring<RHOBObservability>>
|
||||
Interpret<T> for RHOBAlertingInterpret
|
||||
impl<T: Topology + K8sclient + Ingress + PrometheusMonitoring<RHOBObservability>> Interpret<T>
|
||||
for RHOBAlertingInterpret
|
||||
{
|
||||
async fn execute(
|
||||
&self,
|
||||
|
||||
Reference in New Issue
Block a user