Merge pull request 'feat: Initial setup for monitoring and alerting' (#48) from feat/monitor into master
All checks were successful
Run Check Script / check (push) Successful in 1m50s

Reviewed-on: https://git.nationtech.io/NationTech/harmony/pulls/48
Reviewed-by: johnride <jg@nationtech.io>
This commit is contained in:
wjro 2025-06-03 18:17:13 +00:00
commit 31e59937dc
9 changed files with 121 additions and 44 deletions

View File

@ -49,3 +49,4 @@ fqdn = { version = "0.4.6", features = [
"serde", "serde",
] } ] }
temp-dir = "0.1.14" temp-dir = "0.1.14"
dyn-clone = "1.0.19"

View File

@ -1,4 +1,4 @@
use std::{io::Error, process::Command, sync::Arc}; use std::{process::Command, sync::Arc};
use async_trait::async_trait; use async_trait::async_trait;
use inquire::Confirm; use inquire::Confirm;

View File

@ -3,6 +3,7 @@ mod host_binding;
mod http; mod http;
mod k8s_anywhere; mod k8s_anywhere;
mod localhost; mod localhost;
pub mod oberservability;
pub mod tenant; pub mod tenant;
pub use k8s_anywhere::*; pub use k8s_anywhere::*;
pub use localhost::*; pub use localhost::*;

View File

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

View File

@ -0,0 +1,31 @@
use async_trait::async_trait;
use std::fmt::Debug;
use url::Url;
use crate::interpret::InterpretError;
use crate::{interpret::Outcome, topology::Topology};
/// Represents an entity responsible for collecting and organizing observability data
/// from various telemetry sources
/// A `Monitor` abstracts the logic required to scrape, aggregate, and structure
/// monitoring data, enabling consistent processing regardless of the underlying data source.
#[async_trait]
pub trait Monitor<T: Topology>: Debug + Send + Sync {
async fn deploy_monitor(
&self,
topology: &T,
alert_receivers: Vec<AlertReceiver>,
) -> Result<Outcome, InterpretError>;
async fn delete_monitor(
&self,
topolgy: &T,
alert_receivers: Vec<AlertReceiver>,
) -> Result<Outcome, InterpretError>;
}
pub struct AlertReceiver {
pub receiver_id: String,
}

View File

@ -1,30 +1,25 @@
use std::str::FromStr; use std::str::FromStr;
use non_blank_string_rs::NonBlankString; use non_blank_string_rs::NonBlankString;
use url::Url;
use crate::modules::helm::chart::HelmChartScore; use crate::modules::helm::chart::HelmChartScore;
use super::{config::KubePrometheusConfig, monitoring_alerting::AlertChannel}; pub fn discord_alert_manager_score(
webhook_url: Url,
fn get_discord_alert_manager_score(config: &KubePrometheusConfig) -> Option<HelmChartScore> { namespace: String,
let (url, name) = config.alert_channel.iter().find_map(|channel| { name: String,
if let AlertChannel::Discord { webhook_url, name } = channel { ) -> HelmChartScore {
Some((webhook_url, name))
} else {
None
}
})?;
let values = format!( let values = format!(
r#" r#"
environment: environment:
- name: "DISCORD_WEBHOOK" - name: "DISCORD_WEBHOOK"
value: "{url}" value: "{webhook_url}"
"#, "#,
); );
Some(HelmChartScore { HelmChartScore {
namespace: Some(NonBlankString::from_str(&config.namespace).unwrap()), namespace: Some(NonBlankString::from_str(&namespace).unwrap()),
release_name: NonBlankString::from_str(&name).unwrap(), release_name: NonBlankString::from_str(&name).unwrap(),
chart_name: NonBlankString::from_str( chart_name: NonBlankString::from_str(
"oci://hub.nationtech.io/library/alertmanager-discord", "oci://hub.nationtech.io/library/alertmanager-discord",
@ -36,13 +31,5 @@ environment:
create_namespace: true, create_namespace: true,
install_only: true, install_only: true,
repository: None, repository: None,
})
}
pub fn discord_alert_manager_score(config: &KubePrometheusConfig) -> HelmChartScore {
if let Some(chart) = get_discord_alert_manager_score(config) {
chart
} else {
panic!("Expected discord alert manager helm chart");
} }
} }

View File

@ -0,0 +1,55 @@
use async_trait::async_trait;
use serde_json::Value;
use url::Url;
use crate::{
interpret::{InterpretError, Outcome},
topology::K8sAnywhereTopology,
};
#[derive(Debug, Clone)]
pub struct DiscordWebhookConfig {
pub webhook_url: Url,
pub name: String,
pub send_resolved_notifications: bool,
}
pub trait DiscordWebhookReceiver {
fn deploy_discord_webhook_receiver(
&self,
_notification_adapter_id: &str,
) -> Result<Outcome, InterpretError>;
fn delete_discord_webhook_receiver(
&self,
_notification_adapter_id: &str,
) -> Result<Outcome, InterpretError>;
}
// trait used to generate alert manager config values impl<T: Topology + AlertManagerConfig> Monitor for KubePrometheus
pub trait AlertManagerConfig<T> {
fn get_alert_manager_config(&self) -> Result<Value, InterpretError>;
}
#[async_trait]
impl<T: DiscordWebhookReceiver> AlertManagerConfig<T> for DiscordWebhookConfig {
fn get_alert_manager_config(&self) -> Result<Value, InterpretError> {
todo!()
}
}
#[async_trait]
impl DiscordWebhookReceiver for K8sAnywhereTopology {
fn deploy_discord_webhook_receiver(
&self,
_notification_adapter_id: &str,
) -> Result<Outcome, InterpretError> {
todo!()
}
fn delete_discord_webhook_receiver(
&self,
_notification_adapter_id: &str,
) -> Result<Outcome, InterpretError> {
todo!()
}
}

View File

@ -1,4 +1,5 @@
mod config; mod config;
mod discord_alert_manager; mod discord_alert_manager;
pub mod discord_webhook_sender;
mod kube_prometheus; mod kube_prometheus;
pub mod monitoring_alerting; pub mod monitoring_alerting;

View File

@ -96,28 +96,28 @@ impl MonitoringAlertingStackInterpret {
topology: &T, topology: &T,
config: &KubePrometheusConfig, config: &KubePrometheusConfig,
) -> Result<Outcome, InterpretError> { ) -> Result<Outcome, InterpretError> {
let mut outcomes = vec![]; //let mut outcomes = vec![];
for channel in &self.score.alert_channel { //for channel in &self.score.alert_channel {
let outcome = match channel { // let outcome = match channel {
AlertChannel::Discord { .. } => { // AlertChannel::Discord { .. } => {
discord_alert_manager_score(config) // discord_alert_manager_score(config)
.create_interpret() // .create_interpret()
.execute(inventory, topology) // .execute(inventory, topology)
.await // .await
} // }
AlertChannel::Slack { .. } => Ok(Outcome::success( // AlertChannel::Slack { .. } => Ok(Outcome::success(
"No extra configs for slack alerting".to_string(), // "No extra configs for slack alerting".to_string(),
)), // )),
AlertChannel::Smpt { .. } => { // AlertChannel::Smpt { .. } => {
todo!() // todo!()
} // }
}; // };
outcomes.push(outcome); // outcomes.push(outcome);
} //}
for result in outcomes { //for result in outcomes {
result?; // result?;
} //}
Ok(Outcome::success("All alert channels deployed".to_string())) Ok(Outcome::success("All alert channels deployed".to_string()))
} }