Merge pull request 'monitoringalerting' (#37) from monitoringalerting into master

Reviewed-on: https://git.nationtech.io/NationTech/harmony/pulls/37
Reviewed-by: johnride <jg@nationtech.io>

Cargo.lock

@@ -930,6 +930,15 @@ dependencies = [
  "zeroize",
 ]
 
+[[package]]
+name = "email_address"
+version = "0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e079f19b08ca6239f47f8ba8509c11cf3ea30095831f7fed61441475edd8c449"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "encoding_rs"
 version = "0.8.35"
@@ -1400,6 +1409,7 @@ dependencies = [
  "derive-new",
  "directories",
  "dockerfile_builder",
+ "email_address",
  "env_logger",
  "fqdn",
  "harmony_macros",

examples/lamp/src/main.rs

@@ -4,7 +4,9 @@ use harmony::{
     maestro::Maestro,
     modules::{
         lamp::{LAMPConfig, LAMPScore},
-        monitoring::monitoring_alerting::MonitoringAlertingStackScore,
+        monitoring::monitoring_alerting::{
+            AlertChannel, MonitoringAlertingStackScore, WebhookServiceType,
+        },
     },
     topology::{K8sAnywhereTopology, Url},
 };
@@ -43,8 +45,15 @@ async fn main() {
     .await
     .unwrap();
 
-    let monitoring_stack_score =
+    let url = url::Url::parse("https://discord.com/api/webhooks/dummy_channel/dummy_token")
-        MonitoringAlertingStackScore::new_with_ns(&lamp_stack.config.namespace);
+        .expect("invalid URL");
+
+    let mut monitoring_stack_score = MonitoringAlertingStackScore::new();
+    monitoring_stack_score.namespace = Some(lamp_stack.config.namespace.clone());
+    monitoring_stack_score.alert_channel = Some(AlertChannel::WebHookUrl {
+        url: url,
+        webhook_service_type: WebhookServiceType::Discord,
+    });
 
     maestro.register_all(vec![Box::new(lamp_stack), Box::new(monitoring_stack_score)]);
     // Here we bootstrap the CLI, this gives some nice features if you need them

harmony/Cargo.toml

@@ -39,6 +39,7 @@ lazy_static = "1.5.0"
 dockerfile_builder = "0.1.5"
 temp-file = "0.1.9"
 convert_case.workspace = true
+email_address = "0.2.9"
 fqdn = { version = "0.4.6", features = [
     "domain-label-cannot-start-or-end-with-hyphen",
     "domain-label-length-limited-to-63",

harmony/src/modules/monitoring/config.rs

@@ -0,0 +1,55 @@
+use email_address::EmailAddress;
+use serde::Serialize;
+use url::Url;
+
+use super::monitoring_alerting::WebhookServiceType;
+
+#[derive(Debug, Clone, Serialize)]
+pub struct KubePrometheusConfig {
+    pub namespace: String,
+    pub default_rules: bool,
+    pub windows_monitoring: bool,
+    pub alert_manager: bool,
+    pub node_exporter: bool,
+    pub prometheus: bool,
+    pub grafana: bool,
+    pub kubernetes_service_monitors: bool,
+    pub kubernetes_api_server: bool,
+    pub kubelet: bool,
+    pub kube_controller_manager: bool,
+    pub core_dns: bool,
+    pub kube_etcd: bool,
+    pub kube_scheduler: bool,
+    pub kube_proxy: bool,
+    pub kube_state_metrics: bool,
+    pub prometheus_operator: bool,
+    pub webhook_url: Option<Url>,
+    pub webhook_service_type: Option<WebhookServiceType>,
+    pub discord_alert_manager_release_name: String,
+}
+impl KubePrometheusConfig {
+    pub fn new() -> Self {
+        Self {
+            namespace: "monitoring".into(),
+            default_rules: true,
+            windows_monitoring: false,
+            alert_manager: true,
+            webhook_service_type: None,
+            webhook_url: None,
+            grafana: true,
+            node_exporter: false,
+            prometheus: true,
+            kubernetes_service_monitors: true,
+            kubernetes_api_server: false,
+            kubelet: false,
+            kube_controller_manager: false,
+            kube_etcd: false,
+            kube_proxy: false,
+            kube_state_metrics: true,
+            prometheus_operator: true,
+            core_dns: false,
+            kube_scheduler: false,
+            discord_alert_manager_release_name: "discord-alert-manager".into(),
+        }
+    }
+}

harmony/src/modules/monitoring/discord_alert_manager.rs

@@ -0,0 +1,37 @@
+use std::str::FromStr;
+
+use non_blank_string_rs::NonBlankString;
+
+use crate::modules::helm::chart::HelmChartScore;
+
+use super::config::KubePrometheusConfig;
+
+pub fn discord_alert_manager_score(config: &KubePrometheusConfig) -> HelmChartScore {
+    let url = if let Some(url) = &config.webhook_url {
+        url.to_string()
+    } else {
+        "None".to_string()
+    };
+
+    let values = format!(
+        r#"    
+
+environment:
+  - name: "DISCORD_WEBHOOK"
+    value: "{url}"
+    "#,
+    );
+
+    HelmChartScore {
+        namespace: Some(NonBlankString::from_str(&config.namespace).unwrap()),
+        release_name: NonBlankString::from_str(&config.discord_alert_manager_release_name).unwrap(),
+        chart_name: NonBlankString::from_str("oci://hub.nationtech.io/nt/alertmanager-discord")
+            .unwrap(),
+        chart_version: None,
+        values_overrides: None,
+        values_yaml: Some(values.to_string()),
+        create_namespace: true,
+        install_only: true,
+        repository: None,
+    }
+}

harmony/src/modules/monitoring/kube_prometheus.rs

@@ -1,14 +1,67 @@
-use std::str::FromStr;
+use super::{config::KubePrometheusConfig, monitoring_alerting::WebhookServiceType};
-
 use non_blank_string_rs::NonBlankString;
+use std::{collections::HashMap, str::FromStr};
 
 use crate::modules::helm::chart::HelmChartScore;
 
-pub fn kube_prometheus_score(ns: &str) -> HelmChartScore {
+pub fn kube_prometheus_helm_chart_score(config: &KubePrometheusConfig) -> HelmChartScore {
     //TODO this should be make into a rule with default formatting that can be easily passed as a vec
     //to the overrides or something leaving the user to deal with formatting here seems bad
-    let values = r#"
+    let default_rules = config.default_rules.to_string();
+    let windows_monitoring = config.windows_monitoring.to_string();
+    let alert_manager = config.alert_manager.to_string();
+    let webhook_service_type = if let Some(service) = &config.webhook_service_type {
+        match service {
+            WebhookServiceType::Discord  => "Discord".to_string(),
+            WebhookServiceType::Slack  => "Slack".to_string(),
+        }
+    } else {
+        "None".to_string()
+    };
+    let grafana = config.grafana.to_string();
+    let kubernetes_service_monitors = config.kubernetes_service_monitors.to_string();
+    let kubernetes_api_server = config.kubernetes_api_server.to_string();
+    let kubelet = config.kubelet.to_string();
+    let kube_controller_manager = config.kube_controller_manager.to_string();
+    let core_dns = config.core_dns.to_string();
+    let kube_etcd = config.kube_etcd.to_string();
+    let kube_scheduler = config.kube_scheduler.to_string();
+    let kube_proxy = config.kube_proxy.to_string();
+    let kube_state_metrics = config.kube_state_metrics.to_string();
+    let node_exporter = config.node_exporter.to_string();
+    let prometheus_operator = config.prometheus_operator.to_string();
+    let prometheus = config.prometheus.to_string();
+    let discord_alert_manager_release_name = config.discord_alert_manager_release_name.to_string();
+    let values = format!(
+        r#"
 additionalPrometheusRulesMap:
+  pods-status-alerts:
+    groups:
+      - name: pods
+        rules:
+          - alert: "[CRIT] POD not healthy"
+            expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{{phase=~"Pending|Unknown|Failed"}})[15m:1m]) > 0
+            for: 0m
+            labels:
+              severity: critical
+            annotations:
+              title: "[CRIT] POD not healthy : {{ $labels.pod }}"
+              description: |
+               A POD is in a non-ready state!
+               - **Pod**: {{ $labels.pod }}
+               - **Namespace**: {{ $labels.namespace }}
+          - alert: "[CRIT] POD crash looping"
+            expr: increase(kube_pod_container_status_restarts_total[5m]) > 3
+            for: 0m
+            labels:
+              severity: critical
+            annotations:
+              title: "[CRIT] POD crash looping : {{ $labels.pod }}"
+              description: |
+               A POD is drowning in a crash loop!
+               - **Pod**: {{ $labels.pod }}
+               - **Namespace**: {{ $labels.namespace }}
+               - **Instance**: {{ $labels.instance }}
   pvc-alerts:
     groups:
       - name: pvc-alerts
@@ -31,13 +84,99 @@ additionalPrometheusRulesMap:
             annotations:
               description: The PVC {{ $labels.persistentvolumeclaim }} in namespace {{ $labels.namespace }} is predicted to fill over 95% in less than 2 days.
               title: PVC {{ $labels.persistentvolumeclaim }} in namespace {{ $labels.namespace }} will fill over 95% in less than 2 days
-"#;
+defaultRules:
+  create: {default_rules}
+  rules:
+    alertmanager: true
+    etcd: true
+    configReloaders: true
+    general: true
+    k8sContainerCpuUsageSecondsTotal: true
+    k8sContainerMemoryCache: true
+    k8sContainerMemoryRss: true
+    k8sContainerMemorySwap: true
+    k8sContainerResource: true
+    k8sContainerMemoryWorkingSetBytes: true
+    k8sPodOwner: true
+    kubeApiserverAvailability: true
+    kubeApiserverBurnrate: true
+    kubeApiserverHistogram: true
+    kubeApiserverSlos: true
+    kubeControllerManager: true
+    kubelet: true
+    kubeProxy: true
+    kubePrometheusGeneral: true
+    kubePrometheusNodeRecording: true
+    kubernetesApps: true
+    kubernetesResources: true
+    kubernetesStorage: true
+    kubernetesSystem: true
+    kubeSchedulerAlerting: true
+    kubeSchedulerRecording: true
+    kubeStateMetrics: true
+    network: true
+    node: true
+    nodeExporterAlerting: true
+    nodeExporterRecording: true
+    prometheus: true
+    prometheusOperator: true
+    windows: true
+windowsMonitoring:
+  enabled: {windows_monitoring}
+alertmanager:
+  enabled: {alert_manager}
+  config: 
+    route:
+      group_by: ['job']
+      group_wait: 30s
+      group_interval: 5m
+      repeat_interval: 12h
+      receiver: '{webhook_service_type}'
+      routes:
+      - receiver: 'null'
+        matchers:
+          - alertname="Watchdog"
+        continue: false
+    receivers:
+    - name: 'null'
+    - name: '{webhook_service_type}'
+      webhook_configs:
+      - url: 'http://{discord_alert_manager_release_name}-alertmanager-discord:9094'
+        send_resolved: true
+grafana:
+  enabled: {grafana}
+kubernetesServiceMonitors:
+  enabled: {kubernetes_service_monitors}
+kubeApiServer:
+  enabled: {kubernetes_api_server}
+kubelet:
+  enabled: {kubelet}
+kubeControllerManager:
+  enabled: {kube_controller_manager}
+coreDns:
+  enabled: {core_dns}
+kubeEtcd:
+  enabled: {kube_etcd}
+kubeScheduler:
+  enabled: {kube_scheduler}
+kubeProxy:
+  enabled: {kube_proxy}
+kubeStateMetrics:
+  enabled: {kube_state_metrics}
+nodeExporter:
+  enabled: {node_exporter}
+prometheusOperator:
+  enabled: {prometheus_operator}
+prometheus:
+  enabled: {prometheus}
+"#,
+    );
+
     HelmChartScore {
-        namespace: Some(NonBlankString::from_str(ns).unwrap()),
+        namespace: Some(NonBlankString::from_str(&config.namespace).unwrap()),
         release_name: NonBlankString::from_str("kube-prometheus").unwrap(),
         chart_name: NonBlankString::from_str(
-            "oci://ghcr.io/prometheus-community/charts/kube-prometheus-stack", //use kube prometheus chart which includes grafana, prometheus, alert
+            "oci://ghcr.io/prometheus-community/charts/kube-prometheus-stack",
-                                                                               //manager, etc
         )
         .unwrap(),
         chart_version: None,

harmony/src/modules/monitoring/mod.rs

@@ -1,2 +1,4 @@
 mod kube_prometheus;
 pub mod monitoring_alerting;
+mod discord_alert_manager;
+mod config;

harmony/src/modules/monitoring/monitoring_alerting.rs

@@ -1,47 +1,179 @@
+use async_trait::async_trait;
+use email_address::EmailAddress;
+
+use log::info;
 use serde::Serialize;
+use url::Url;
 
 use crate::{
-    interpret::Interpret,
+    data::{Id, Version},
-    modules::helm::chart::HelmChartScore,
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
     score::Score,
     topology::{HelmCommand, Topology},
 };
 
-use super::kube_prometheus::kube_prometheus_score;
+use super::{
+    config::KubePrometheusConfig, discord_alert_manager::discord_alert_manager_score,
+    kube_prometheus::kube_prometheus_helm_chart_score,
+};
+
+#[derive(Debug, Clone, Serialize)]
+pub enum AlertChannel {
+    WebHookUrl {
+        url: Url,
+        webhook_service_type: WebhookServiceType,
+    },
+    //TODO test and implement in helm chart
+    //currently does not work
+    Smpt {
+        email_address: EmailAddress,
+        service_name: String,
+    },
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub enum WebhookServiceType {
+    Discord,
+    //TODO test slack notifications
+    Slack,
+}
 
 #[derive(Debug, Clone, Serialize)]
 pub struct MonitoringAlertingStackScore {
-    // TODO Support other components in our monitoring/alerting stack instead of a single helm
+    pub alert_channel: Option<AlertChannel>,
-    // chart
+    pub namespace: Option<String>,
-    pub monitoring_stack: HelmChartScore,
-    pub namespace: String,
 }
 
 impl MonitoringAlertingStackScore {
-    pub fn new_with_ns(ns: &str) -> Self {
+    pub fn new() -> Self {
         Self {
-            monitoring_stack: kube_prometheus_score(ns),
+            alert_channel: None,
-            namespace: ns.to_string(),
+            namespace: None,
+        }
+    }
+    fn set_alert_channel(&self, config: &mut KubePrometheusConfig) {
+        if let Some(alert_channel) = &self.alert_channel {
+            match alert_channel {
+                AlertChannel::WebHookUrl {
+                    url,
+                    webhook_service_type,
+                } => {
+                    config.webhook_url = Some(url.clone());
+                    config.webhook_service_type = Some(webhook_service_type.clone());
+                }
+                AlertChannel::Smpt {
+                    //TODO setup smpt alerts 
+                    email_address,
+                    service_name,
+                } => {
+                    todo!()
                 }
             }
-}
-
-impl Default for MonitoringAlertingStackScore {
-    fn default() -> Self {
-        let ns = "monitoring";
-        Self {
-            monitoring_stack: kube_prometheus_score(ns),
-            namespace: ns.to_string(),
         }
     }
 }
 
 impl<T: Topology + HelmCommand> Score<T> for MonitoringAlertingStackScore {
     fn create_interpret(&self) -> Box<dyn Interpret<T>> {
-        self.monitoring_stack.create_interpret()
+        Box::new(MonitoringAlertingStackInterpret {
+            score: self.clone(),
+        })
     }
-
     fn name(&self) -> String {
         format!("MonitoringAlertingStackScore")
     }
 }
+
+#[derive(Debug, Clone, Serialize)]
+struct MonitoringAlertingStackInterpret {
+    score: MonitoringAlertingStackScore,
+}
+
+impl MonitoringAlertingStackInterpret {
+    async fn build_kube_prometheus_helm_chart_config(&self) -> KubePrometheusConfig {
+        let mut config = KubePrometheusConfig::new();
+        self.score.set_alert_channel(&mut config);
+        if let Some(ns) = &self.score.namespace {
+            config.namespace = ns.clone();
+        }
+        config
+    }
+
+    async fn deploy_kube_prometheus_helm_chart_score<T: Topology + HelmCommand>(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+        config: &KubePrometheusConfig,
+    ) -> Result<Outcome, InterpretError> {
+        let helm_chart = kube_prometheus_helm_chart_score(config);
+        helm_chart
+            .create_interpret()
+            .execute(inventory, topology)
+            .await
+    }
+
+    async fn deploy_alert_channel_service<T: Topology + HelmCommand>(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+        config: &KubePrometheusConfig,
+    ) -> Result<Outcome, InterpretError> {
+        match &self.score.alert_channel {
+            Some(AlertChannel::WebHookUrl {
+                webhook_service_type,
+                ..
+            }) => match webhook_service_type {
+                WebhookServiceType::Discord => {
+                    discord_alert_manager_score(config)
+                        .create_interpret()
+                        .execute(inventory, topology)
+                        .await
+                }
+                WebhookServiceType::Slack => Ok(Outcome::success(
+                    "No extra configs for slack alerting".to_string(),
+                )),
+            },
+            Some(AlertChannel::Smpt { .. }) => {
+                todo!()
+            }
+            None => Ok(Outcome::success("No alert channel configured".to_string())),
+        }
+    }
+}
+
+#[async_trait]
+impl<T: Topology + HelmCommand> Interpret<T> for MonitoringAlertingStackInterpret {
+    async fn execute(
+        &self,
+        inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let config = self.build_kube_prometheus_helm_chart_config().await;
+        info!("Built kube prometheus config");
+        info!("Installing kube prometheus chart");
+        self.deploy_kube_prometheus_helm_chart_score(inventory, topology, &config)
+            .await?;
+        info!("Installing alert channel service");
+        self.deploy_alert_channel_service(inventory, topology, &config).await?;
+        Ok(Outcome::success(format!(
+            "succesfully deployed monitoring and alerting stack"
+        )))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        todo!()
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}