Compare commits

..

3 Commits

84 changed files with 893 additions and 3445 deletions

29
.gitignore vendored
View File

@@ -1,25 +1,4 @@
### General ###
private_repos/
### Harmony ###
harmony.log
### Helm ###
# Chart dependencies
**/charts/*.tgz
### Rust ###
# Generated by Cargo
# will have compiled files and executables
debug/
target/
# Remove Cargo.lock from gitignore if creating an executable, leave it for libraries
# More information here https://doc.rust-lang.org/cargo/guide/cargo-toml-vs-cargo-lock.html
Cargo.lock
# These are backup files generated by rustfmt
**/*.rs.bk
# MSVC Windows builds of rustc generate these, which store debugging information
*.pdb
target
private_repos
log/
*.tgz

213
Cargo.lock generated
View File

@@ -96,12 +96,6 @@ dependencies = [
"libc",
]
[[package]]
name = "ansi_term"
version = "0.10.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6b3568b48b7cefa6b8ce125f9bb4989e52fbcc29ebea88df04cc7c5f12f70455"
[[package]]
name = "anstream"
version = "0.6.19"
@@ -656,19 +650,6 @@ dependencies = [
"crossbeam-utils",
]
[[package]]
name = "console"
version = "0.16.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2e09ced7ebbccb63b4c65413d821f2e00ce54c5ca4514ddc6b3c892fdbcbc69d"
dependencies = [
"encode_unicode",
"libc",
"once_cell",
"unicode-width 0.2.0",
"windows-sys 0.60.2",
]
[[package]]
name = "const-oid"
version = "0.9.6"
@@ -1156,12 +1137,6 @@ dependencies = [
"serde",
]
[[package]]
name = "encode_unicode"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
[[package]]
name = "encoding_rs"
version = "0.8.35"
@@ -1265,18 +1240,6 @@ dependencies = [
name = "example"
version = "0.0.0"
[[package]]
name = "example-application-monitoring-with-tenant"
version = "0.1.0"
dependencies = [
"env_logger",
"harmony",
"harmony_cli",
"logging",
"tokio",
"url",
]
[[package]]
name = "example-cli"
version = "0.1.0"
@@ -1392,7 +1355,6 @@ dependencies = [
name = "example-rust"
version = "0.1.0"
dependencies = [
"base64 0.22.1",
"env_logger",
"harmony",
"harmony_cli",
@@ -1465,18 +1427,6 @@ version = "0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "28dea519a9695b9977216879a3ebfddf92f1c08c05d984f8996aecd6ecdc811d"
[[package]]
name = "filetime"
version = "0.2.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "35c0522e981e68cbfa8c3f978441a5f34b30b96e146b33cd3359176b50fe8586"
dependencies = [
"cfg-if",
"libc",
"libredox",
"windows-sys 0.59.0",
]
[[package]]
name = "flate2"
version = "1.1.2"
@@ -1776,8 +1726,6 @@ name = "harmony"
version = "0.1.0"
dependencies = [
"async-trait",
"base64 0.22.1",
"bollard",
"chrono",
"cidr",
"convert_case",
@@ -1794,32 +1742,27 @@ dependencies = [
"helm-wrapper-rs",
"hex",
"http 1.3.1",
"inquire",
"k3d-rs",
"k8s-openapi",
"kube",
"kube-derive",
"lazy_static",
"libredfish",
"log",
"non-blank-string-rs",
"once_cell",
"opnsense-config",
"opnsense-config-xml",
"pretty_assertions",
"rand 0.9.1",
"reqwest 0.11.27",
"russh",
"rust-ipmi",
"schemars 0.8.22",
"semver",
"serde",
"serde-value",
"serde_json",
"serde_with",
"serde_yaml",
"similar",
"strum 0.27.1",
"tar",
"temp-dir",
"temp-file",
"tempfile",
@@ -1835,15 +1778,10 @@ version = "0.1.0"
dependencies = [
"assert_cmd",
"clap",
"console",
"env_logger",
"harmony",
"harmony_tui",
"indicatif",
"indicatif-log-bridge",
"inquire",
"lazy_static",
"log",
"tokio",
]
@@ -1854,16 +1792,10 @@ dependencies = [
"bollard",
"cargo_metadata",
"clap",
"console",
"current_platform",
"env_logger",
"futures-util",
"harmony_cli",
"indicatif",
"indicatif-log-bridge",
"lazy_static",
"log",
"once_cell",
"serde_json",
"tokio",
]
@@ -2459,29 +2391,6 @@ dependencies = [
"serde",
]
[[package]]
name = "indicatif"
version = "0.18.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "70a646d946d06bedbbc4cac4c218acf4bbf2d87757a784857025f4d447e4e1cd"
dependencies = [
"console",
"portable-atomic",
"unicode-width 0.2.0",
"unit-prefix",
"web-time",
]
[[package]]
name = "indicatif-log-bridge"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "63703cf9069b85dbe6fe26e1c5230d013dee99d3559cd3d02ba39e099ef7ab02"
dependencies = [
"indicatif",
"log",
]
[[package]]
name = "indoc"
version = "2.0.6"
@@ -2689,7 +2598,6 @@ dependencies = [
"k8s-openapi",
"kube-client",
"kube-core",
"kube-derive",
"kube-runtime",
]
@@ -2743,27 +2651,12 @@ dependencies = [
"http 1.3.1",
"json-patch",
"k8s-openapi",
"schemars 0.8.22",
"serde",
"serde-value",
"serde_json",
"thiserror 2.0.12",
]
[[package]]
name = "kube-derive"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "079fc8c1c397538628309cfdee20696ebdcc26745f9fb17f89b78782205bd995"
dependencies = [
"darling",
"proc-macro2",
"quote",
"serde",
"serde_json",
"syn",
]
[[package]]
name = "kube-runtime"
version = "1.1.0"
@@ -2833,7 +2726,6 @@ checksum = "1580801010e535496706ba011c15f8532df6b42297d2e471fec38ceadd8c0638"
dependencies = [
"bitflags 2.9.1",
"libc",
"redox_syscall",
]
[[package]]
@@ -2879,15 +2771,6 @@ dependencies = [
"log",
]
[[package]]
name = "logging"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "461a8beca676e8ab1bd468c92e9b4436d6368e11e96ae038209e520cfe665e46"
dependencies = [
"ansi_term",
]
[[package]]
name = "lru"
version = "0.12.5"
@@ -4185,18 +4068,6 @@ dependencies = [
"windows-sys 0.59.0",
]
[[package]]
name = "schemars"
version = "0.8.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fbf2ae1b8bc8e02df939598064d22402220cd5bbcca1c76f7d6a310974d5615"
dependencies = [
"dyn-clone",
"schemars_derive",
"serde",
"serde_json",
]
[[package]]
name = "schemars"
version = "0.9.0"
@@ -4209,30 +4080,6 @@ dependencies = [
"serde_json",
]
[[package]]
name = "schemars"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "82d20c4491bc164fa2f6c5d44565947a52ad80b9505d8e36f8d54c27c739fcd0"
dependencies = [
"dyn-clone",
"ref-cast",
"serde",
"serde_json",
]
[[package]]
name = "schemars_derive"
version = "0.8.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32e265784ad618884abaea0600a9adf15393368d840e0222d101a072f3f7534d"
dependencies = [
"proc-macro2",
"quote",
"serde_derive_internals",
"syn",
]
[[package]]
name = "scopeguard"
version = "1.2.0"
@@ -4365,17 +4212,6 @@ dependencies = [
"syn",
]
[[package]]
name = "serde_derive_internals"
version = "0.29.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "18d26a20a969b9e3fdf2fc2d9f21eda6c40e2de84c9408bb5d3b05d499aae711"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.140"
@@ -4444,36 +4280,22 @@ dependencies = [
[[package]]
name = "serde_with"
version = "3.14.0"
version = "3.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f2c45cd61fefa9db6f254525d46e392b852e0e61d9a1fd36e5bd183450a556d5"
checksum = "bf65a400f8f66fb7b0552869ad70157166676db75ed8181f8104ea91cf9d0b42"
dependencies = [
"base64 0.22.1",
"chrono",
"hex",
"indexmap 1.9.3",
"indexmap 2.10.0",
"schemars 0.9.0",
"schemars 1.0.4",
"schemars",
"serde",
"serde_derive",
"serde_json",
"serde_with_macros",
"time",
]
[[package]]
name = "serde_with_macros"
version = "3.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "de90945e6565ce0d9a25098082ed4ee4002e047cb59892c318d66821e14bb30f"
dependencies = [
"darling",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_yaml"
version = "0.9.34+deprecated"
@@ -4846,17 +4668,6 @@ version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55937e1799185b12863d447f42597ed69d9928686b8d88a1df17376a097d8369"
[[package]]
name = "tar"
version = "0.4.44"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1d863878d212c87a19c1a610eb53bb01fe12951c0501cf5a0d65f724914a667a"
dependencies = [
"filetime",
"libc",
"xattr",
]
[[package]]
name = "temp-dir"
version = "0.1.16"
@@ -5314,12 +5125,6 @@ version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
[[package]]
name = "unit-prefix"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "323402cff2dd658f39ca17c789b502021b3f18707c91cdf22e3838e1b4023817"
[[package]]
name = "universal-hash"
version = "0.5.1"
@@ -5908,16 +5713,6 @@ dependencies = [
"tap",
]
[[package]]
name = "xattr"
version = "1.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "af3a19837351dc82ba89f8a125e22a3c475f05aba604acc023d62b2739ae2909"
dependencies = [
"libc",
"rustix 1.0.7",
]
[[package]]
name = "xml-rs"
version = "0.8.26"

View File

@@ -52,7 +52,3 @@ convert_case = "0.8"
chrono = "0.4"
similar = "2"
uuid = { version = "1.11", features = ["v4", "fast-rng", "macro-diagnostics"] }
pretty_assertions = "1.4.1"
bollard = "0.19.1"
base64 = "0.22.1"
tar = "0.4.44"

View File

@@ -1,6 +1,5 @@
# Harmony : Open-source infrastructure orchestration that treats your platform like first-class code
_By [NationTech](https://nationtech.io)_
# Harmony : Open-source infrastructure orchestration that treats your platform like first-class code.
*By [NationTech](https://nationtech.io)*
[![Build](https://git.nationtech.io/NationTech/harmony/actions/workflows/check.yml/badge.svg)](https://git.nationtech.io/nationtech/harmony)
[![License](https://img.shields.io/badge/license-AGPLv3-blue?style=flat-square)](LICENSE)
@@ -24,11 +23,11 @@ From a **developer laptop** to a **global production cluster**, a single **sourc
Infrastructure is essential, but it shouldnt be your core business. Harmony is built on three guiding principles that make modern platforms reliable, repeatable, and easy to reason about.
| Principle | What it means for you |
| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Infrastructure as Resilient Code** | Replace sprawling YAML and bash scripts with type-safe Rust. Test, refactor, and version your platform just like application code. |
| **Prove It Works — Before You Deploy** | Harmony uses the compiler to verify that your applications needs match the target environments capabilities at **compile-time**, eliminating an entire class of runtime outages. |
| **One Unified Model** | Software and infrastructure are a single system. Harmony models them together, enabling deep automation—from bare-metal servers to Kubernetes workloads—with zero context switching. |
| Principle | What it means for you |
|-----------|-----------------------|
| **Infrastructure as Resilient Code** | Replace sprawling YAML and bash scripts with type-safe Rust. Test, refactor, and version your platform just like application code. |
| **Prove It Works — Before You Deploy** | Harmony uses the compiler to verify that your applications needs match the target environments capabilities at **compile-time**, eliminating an entire class of runtime outages. |
| **One Unified Model** | Software and infrastructure are a single system. Harmony models them together, enabling deep automation—from bare-metal servers to Kubernetes workloads—with zero context switching. |
These principles surface as simple, ergonomic Rust APIs that let teams focus on their product while trusting the platform underneath.
@@ -64,20 +63,22 @@ async fn main() {
},
};
// 2. Enhance with extra scores (monitoring, CI/CD, …)
// 2. Pick where it should run
let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
Inventory::autoload(), // auto-detect hardware / kube-config
K8sAnywhereTopology::from_env(), // local k3d, CI, staging, prod…
)
.await
.unwrap();
// 3. Enhance with extra scores (monitoring, CI/CD, …)
let mut monitoring = MonitoringAlertingStackScore::new();
monitoring.namespace = Some(lamp_stack.config.namespace.clone());
// 3. Run your scores on the desired topology & inventory
harmony_cli::run(
Inventory::autoload(), // auto-detect hardware / kube-config
K8sAnywhereTopology::from_env(), // local k3d, CI, staging, prod…
vec![
Box::new(lamp_stack),
Box::new(monitoring)
],
None
).await.unwrap();
maestro.register_all(vec![Box::new(lamp_stack), Box::new(monitoring)]);
// 4. Launch an interactive CLI / TUI
harmony_cli::init(maestro, None).await.unwrap();
}
```
@@ -93,13 +94,13 @@ Harmony analyses the code, shows an execution plan in a TUI, and applies it once
## 3 · Core Concepts
| Term | One-liner |
| ---------------- | ---------------------------------------------------------------------------------------------------- |
| **Score<T>** | Declarative description of the desired state (e.g., `LAMPScore`). |
| **Interpret<T>** | Imperative logic that realises a `Score` on a specific environment. |
| **Topology** | An environment (local k3d, AWS, bare-metal) exposing verified _Capabilities_ (Kubernetes, DNS, …). |
| **Maestro** | Orchestrator that compiles Scores + Topology, ensuring all capabilities line up **at compile-time**. |
| **Inventory** | Optional catalogue of physical assets for bare-metal and edge deployments. |
| Term | One-liner |
|------|-----------|
| **Score<T>** | Declarative description of the desired state (e.g., `LAMPScore`). |
| **Interpret<T>** | Imperative logic that realises a `Score` on a specific environment. |
| **Topology** | An environment (local k3d, AWS, bare-metal) exposing verified *Capabilities* (Kubernetes, DNS, …). |
| **Maestro** | Orchestrator that compiles Scores + Topology, ensuring all capabilities line up **at compile-time**. |
| **Inventory** | Optional catalogue of physical assets for bare-metal and edge deployments. |
A visual overview is in the diagram below.
@@ -111,9 +112,9 @@ A visual overview is in the diagram below.
Prerequisites:
- Rust
- Docker (if you deploy locally)
- `kubectl` / `helm` for Kubernetes-based topologies
* Rust
* Docker (if you deploy locally)
* `kubectl` / `helm` for Kubernetes-based topologies
```bash
git clone https://git.nationtech.io/nationtech/harmony
@@ -125,15 +126,15 @@ cargo build --release # builds the CLI, TUI and libraries
## 5 · Learning More
- **Architectural Decision Records** dive into the rationale
- [ADR-001 · Why Rust](adr/001-rust.md)
- [ADR-003 · Infrastructure Abstractions](adr/003-infrastructure-abstractions.md)
- [ADR-006 · Secret Management](adr/006-secret-management.md)
* **Architectural Decision Records** dive into the rationale
- [ADR-001 · Why Rust](adr/001-rust.md)
- [ADR-003 · Infrastructure Abstractions](adr/003-infrastructure-abstractions.md)
- [ADR-006 · Secret Management](adr/006-secret-management.md)
- [ADR-011 · Multi-Tenant Cluster](adr/011-multi-tenant-cluster.md)
- **Extending Harmony** write new Scores / Interprets, add hardware like OPNsense firewalls, or embed Harmony in your own tooling (`/docs`).
* **Extending Harmony** write new Scores / Interprets, add hardware like OPNsense firewalls, or embed Harmony in your own tooling (`/docs`).
- **Community** discussions and roadmap live in [GitLab issues](https://git.nationtech.io/nationtech/harmony/-/issues). PRs, ideas, and feedback are welcome!
* **Community** discussions and roadmap live in [GitLab issues](https://git.nationtech.io/nationtech/harmony/-/issues). PRs, ideas, and feedback are welcome!
---
@@ -147,4 +148,4 @@ See [LICENSE](LICENSE) for the full text.
---
_Made with ❤️ & 🦀 by the NationTech and the Harmony community_
*Made with ❤️ & 🦀 by the NationTech and the Harmony community*

View File

@@ -1,14 +0,0 @@
[package]
name = "example-application-monitoring-with-tenant"
edition = "2024"
version.workspace = true
readme.workspace = true
license.workspace = true
[dependencies]
env_logger.workspace = true
harmony = { version = "0.1.0", path = "../../harmony" }
harmony_cli = { version = "0.1.0", path = "../../harmony_cli" }
logging = "0.1.0"
tokio.workspace = true
url.workspace = true

View File

@@ -1,61 +0,0 @@
use std::{path::PathBuf, sync::Arc};
use harmony::{
data::Id,
inventory::Inventory,
maestro::Maestro,
modules::{
application::{
ApplicationScore, RustWebFramework, RustWebapp,
features::{ContinuousDelivery, Monitoring},
},
monitoring::alert_channel::{
discord_alert_channel::DiscordWebhook, webhook_receiver::WebhookReceiver,
},
tenant::TenantScore,
},
topology::{K8sAnywhereTopology, Url, tenant::TenantConfig},
};
#[tokio::main]
async fn main() {
//TODO there is a bug where the application is deployed into the namespace matching the
//application name and the tenant is created in the namesapce matching the tenant name
//in order for the application to be deployed in the tenant namespace the application.name and
//the TenantConfig.name must match
let tenant = TenantScore {
config: TenantConfig {
id: Id::from_str("test-tenant-id"),
name: "example-monitoring".to_string(),
..Default::default()
},
};
let application = Arc::new(RustWebapp {
name: "example-monitoring".to_string(),
domain: Url::Url(url::Url::parse("https://rustapp.harmony.example.com").unwrap()),
project_root: PathBuf::from("./examples/rust/webapp"),
framework: Some(RustWebFramework::Leptos),
});
let webhook_receiver = WebhookReceiver {
name: "sample-webhook-receiver".to_string(),
url: Url::Url(url::Url::parse("https://webhook-doesnt-exist.com").unwrap()),
};
let app = ApplicationScore {
features: vec![Box::new(Monitoring {
alert_receiver: vec![Box::new(webhook_receiver)],
application: application.clone(),
})],
application,
};
harmony_cli::run(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(tenant), Box::new(app)],
None,
)
.await
.unwrap();
}

View File

@@ -1,21 +1,20 @@
use harmony::{
inventory::Inventory,
maestro::Maestro,
modules::dummy::{ErrorScore, PanicScore, SuccessScore},
topology::LocalhostTopology,
};
#[tokio::main]
async fn main() {
harmony_cli::run(
Inventory::autoload(),
LocalhostTopology::new(),
vec![
Box::new(SuccessScore {}),
Box::new(ErrorScore {}),
Box::new(PanicScore {}),
],
None,
)
.await
.unwrap();
let inventory = Inventory::autoload();
let topology = LocalhostTopology::new();
let mut maestro = Maestro::initialize(inventory, topology).await.unwrap();
maestro.register_all(vec![
Box::new(SuccessScore {}),
Box::new(ErrorScore {}),
Box::new(PanicScore {}),
]);
harmony_cli::init(maestro, None).await.unwrap();
}

View File

@@ -1,6 +1,7 @@
use harmony::{
data::Version,
inventory::Inventory,
maestro::Maestro,
modules::lamp::{LAMPConfig, LAMPScore},
topology::{K8sAnywhereTopology, Url},
};
@@ -42,13 +43,15 @@ async fn main() {
// K8sAnywhereTopology as it is the most automatic one that enables you to easily deploy
// locally, to development environment from a CI, to staging, and to production with settings
// that automatically adapt to each environment grade.
harmony_cli::run(
let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(lamp_stack)],
None,
)
.await
.unwrap();
maestro.register_all(vec![Box::new(lamp_stack)]);
// Here we bootstrap the CLI, this gives some nice features if you need them
harmony_cli::init(maestro, None).await.unwrap();
}
// That's it, end of the infra as code.

View File

@@ -2,6 +2,7 @@ use std::collections::HashMap;
use harmony::{
inventory::Inventory,
maestro::Maestro,
modules::{
monitoring::{
alert_channel::discord_alert_channel::DiscordWebhook,
@@ -50,8 +51,8 @@ async fn main() {
let service_monitor_endpoint = ServiceMonitorEndpoint {
port: Some("80".to_string()),
path: Some("/metrics".to_string()),
scheme: Some(HTTPScheme::HTTP),
path: "/metrics".to_string(),
scheme: HTTPScheme::HTTP,
..Default::default()
};
@@ -73,13 +74,13 @@ async fn main() {
rules: vec![Box::new(additional_rules), Box::new(additional_rules2)],
service_monitors: vec![service_monitor],
};
harmony_cli::run(
let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(alerting_score)],
None,
)
.await
.unwrap();
maestro.register_all(vec![Box::new(alerting_score)]);
harmony_cli::init(maestro, None).await.unwrap();
}

View File

@@ -3,6 +3,7 @@ use std::collections::HashMap;
use harmony::{
data::Id,
inventory::Inventory,
maestro::Maestro,
modules::{
monitoring::{
alert_channel::discord_alert_channel::DiscordWebhook,
@@ -53,8 +54,8 @@ async fn main() {
let service_monitor_endpoint = ServiceMonitorEndpoint {
port: Some("80".to_string()),
path: Some("/metrics".to_string()),
scheme: Some(HTTPScheme::HTTP),
path: "/metrics".to_string(),
scheme: HTTPScheme::HTTP,
..Default::default()
};
@@ -77,13 +78,13 @@ async fn main() {
rules: vec![Box::new(additional_rules)],
service_monitors: vec![service_monitor],
};
harmony_cli::run(
let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(tenant), Box::new(alerting_score)],
None,
)
.await
.unwrap();
maestro.register_all(vec![Box::new(tenant), Box::new(alerting_score)]);
harmony_cli::init(maestro, None).await.unwrap();
}

View File

@@ -10,7 +10,7 @@ use harmony::{
inventory::Inventory,
maestro::Maestro,
modules::{
http::StaticFilesHttpScore,
http::HttpScore,
ipxe::IpxeScore,
okd::{
bootstrap_dhcp::OKDBootstrapDhcpScore,
@@ -126,7 +126,7 @@ async fn main() {
harmony::modules::okd::load_balancer::OKDLoadBalancerScore::new(&topology);
let tftp_score = TftpScore::new(Url::LocalFolder("./data/watchguard/tftpboot".to_string()));
let http_score = StaticFilesHttpScore::new(Url::LocalFolder(
let http_score = HttpScore::new(Url::LocalFolder(
"./data/watchguard/pxe-http-files".to_string(),
));
let ipxe_score = IpxeScore::new();

View File

@@ -1,18 +1,19 @@
use harmony::{
inventory::Inventory, modules::monitoring::ntfy::ntfy::NtfyScore, topology::K8sAnywhereTopology,
inventory::Inventory, maestro::Maestro, modules::monitoring::ntfy::ntfy::NtfyScore,
topology::K8sAnywhereTopology,
};
#[tokio::main]
async fn main() {
harmony_cli::run(
let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(NtfyScore {
namespace: "monitoring".to_string(),
host: "localhost".to_string(),
})],
None,
)
.await
.unwrap();
maestro.register_all(vec![Box::new(NtfyScore {
namespace: "monitoring".to_string(),
})]);
harmony_cli::init(maestro, None).await.unwrap();
}

View File

@@ -11,7 +11,7 @@ use harmony::{
maestro::Maestro,
modules::{
dummy::{ErrorScore, PanicScore, SuccessScore},
http::StaticFilesHttpScore,
http::HttpScore,
okd::{dhcp::OKDDhcpScore, dns::OKDDnsScore, load_balancer::OKDLoadBalancerScore},
opnsense::OPNsenseShellCommandScore,
tftp::TftpScore,
@@ -81,7 +81,7 @@ async fn main() {
let load_balancer_score = OKDLoadBalancerScore::new(&topology);
let tftp_score = TftpScore::new(Url::LocalFolder("./data/watchguard/tftpboot".to_string()));
let http_score = StaticFilesHttpScore::new(Url::LocalFolder(
let http_score = HttpScore::new(Url::LocalFolder(
"./data/watchguard/pxe-http-files".to_string(),
));
let mut maestro = Maestro::initialize(inventory, topology).await.unwrap();

View File

@@ -1,3 +0,0 @@
Dockerfile.harmony
.harmony_generated
harmony

View File

@@ -12,4 +12,3 @@ tokio = { workspace = true }
log = { workspace = true }
env_logger = { workspace = true }
url = { workspace = true }
base64.workspace = true

View File

@@ -2,13 +2,18 @@ use std::{path::PathBuf, sync::Arc};
use harmony::{
inventory::Inventory,
maestro::Maestro,
modules::{
application::{
ApplicationScore, RustWebFramework, RustWebapp,
features::{ContinuousDelivery, Monitoring},
features::{ContinuousDelivery, PrometheusMonitoring},
},
monitoring::alert_channel::{
discord_alert_channel::DiscordWebhook, webhook_receiver::WebhookReceiver,
monitoring::{
alert_channel::discord_alert_channel::DiscordWebhook,
alert_rule::prometheus_alert_rule::AlertManagerRuleGroup,
},
prometheus::alerts::k8s::{
pod::pod_in_failed_state, pvc::high_pvc_fill_rate_over_two_days,
},
},
topology::{K8sAnywhereTopology, Url},
@@ -16,43 +21,42 @@ use harmony::{
#[tokio::main]
async fn main() {
env_logger::init();
let application = Arc::new(RustWebapp {
name: "harmony-example-rust-webapp".to_string(),
domain: Url::Url(url::Url::parse("https://rustapp.harmony.example.com").unwrap()),
project_root: PathBuf::from("./webapp"), // Relative from 'harmony-path' param
project_root: PathBuf::from("./examples/rust/webapp"),
framework: Some(RustWebFramework::Leptos),
});
let discord_receiver = DiscordWebhook {
name: "test-discord".to_string(),
url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
};
let webhook_receiver = WebhookReceiver {
name: "sample-webhook-receiver".to_string(),
url: Url::Url(url::Url::parse("https://webhook-doesnt-exist.com").unwrap()),
};
let pod_failed = pod_in_failed_state();
let pod_failed_2 = pod_in_failed_state();
let pod_failed_3 = pod_in_failed_state();
let additional_rules = AlertManagerRuleGroup::new("pod-alerts", vec![pod_failed]);
let additional_rules_2 = AlertManagerRuleGroup::new("pod-alerts-2", vec![pod_failed_2, pod_failed_3]);
let app = ApplicationScore {
features: vec![
Box::new(ContinuousDelivery {
//Box::new(ContinuousDelivery {
// application: application.clone(),
//}),
Box::new(PrometheusMonitoring {
application: application.clone(),
alert_receivers: vec![Box::new(DiscordWebhook {
name: "dummy-discord".to_string(),
url: Url::Url(url::Url::parse("https://discord.doesnt.exist.com").unwrap()),
})],
alert_rules: vec![Box::new(additional_rules), Box::new(additional_rules_2)],
}),
Box::new(Monitoring {
application: application.clone(),
alert_receiver: vec![Box::new(discord_receiver), Box::new(webhook_receiver)],
}),
// TODO add backups, multisite ha, etc
// TODO add monitoring, backups, multisite ha, etc
],
application,
};
harmony_cli::run(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(app)],
None,
)
.await
.unwrap();
let topology = K8sAnywhereTopology::from_env();
let mut maestro = Maestro::initialize(Inventory::autoload(), topology)
.await
.unwrap();
maestro.register_all(vec![Box::new(app)]);
harmony_cli::init(maestro, None).await.unwrap();
}

View File

@@ -0,0 +1,16 @@
FROM rust:bookworm as builder
RUN apt-get update && apt-get install -y --no-install-recommends clang wget && wget https://github.com/cargo-bins/cargo-binstall/releases/latest/download/cargo-binstall-x86_64-unknown-linux-musl.tgz && tar -xvf cargo-binstall-x86_64-unknown-linux-musl.tgz && cp cargo-binstall /usr/local/cargo/bin && rm cargo-binstall-x86_64-unknown-linux-musl.tgz cargo-binstall && apt-get clean && rm -rf /var/lib/apt/lists/*
RUN cargo binstall cargo-leptos -y
RUN rustup target add wasm32-unknown-unknown
WORKDIR /app
COPY . .
RUN cargo leptos build --release -vv
FROM debian:bookworm-slim
RUN groupadd -r appgroup && useradd -r -s /bin/false -g appgroup appuser
ENV LEPTOS_SITE_ADDR=0.0.0.0:3000
EXPOSE 3000/tcp
WORKDIR /home/appuser
COPY --from=builder /app/target/site/pkg /home/appuser/pkg
COPY --from=builder /app/target/release/harmony-example-rust-webapp /home/appuser/harmony-example-rust-webapp
USER appuser
CMD /home/appuser/harmony-example-rust-webapp

View File

@@ -1,6 +1,7 @@
use harmony::{
data::Id,
inventory::Inventory,
maestro::Maestro,
modules::tenant::TenantScore,
topology::{K8sAnywhereTopology, tenant::TenantConfig},
};
@@ -15,14 +16,15 @@ async fn main() {
},
};
harmony_cli::run(
let mut maestro = Maestro::<K8sAnywhereTopology>::initialize(
Inventory::autoload(),
K8sAnywhereTopology::from_env(),
vec![Box::new(tenant)],
None,
)
.await
.unwrap();
maestro.register_all(vec![Box::new(tenant)]);
harmony_cli::init(maestro, None).await.unwrap();
}
// TODO write tests

View File

@@ -27,11 +27,12 @@ harmony_macros = { path = "../harmony_macros" }
harmony_types = { path = "../harmony_types" }
uuid.workspace = true
url.workspace = true
kube = { workspace = true, features = ["derive"] }
kube.workspace = true
k8s-openapi.workspace = true
serde_yaml.workspace = true
http.workspace = true
serde-value.workspace = true
inquire.workspace = true
helm-wrapper-rs = "0.4.0"
non-blank-string-rs = "1.0.4"
k3d-rs = { path = "../k3d" }
@@ -43,12 +44,12 @@ convert_case.workspace = true
email_address = "0.2.9"
chrono.workspace = true
fqdn = { version = "0.4.6", features = [
"domain-label-cannot-start-or-end-with-hyphen",
"domain-label-length-limited-to-63",
"domain-name-without-special-chars",
"domain-name-length-limited-to-255",
"punycode",
"serde",
"domain-label-cannot-start-or-end-with-hyphen",
"domain-label-length-limited-to-63",
"domain-name-without-special-chars",
"domain-name-length-limited-to-255",
"punycode",
"serde",
] }
temp-dir = "0.1.14"
dyn-clone = "1.0.19"
@@ -57,13 +58,3 @@ futures-util = "0.3.31"
tokio-util = "0.7.15"
strum = { version = "0.27.1", features = ["derive"] }
tempfile = "3.20.0"
serde_with = "3.14.0"
schemars = "0.8.22"
kube-derive = "1.1.0"
bollard.workspace = true
tar.workspace = true
base64.workspace = true
once_cell = "1.21.3"
[dev-dependencies]
pretty_assertions.workspace = true

View File

@@ -1,63 +0,0 @@
use log::debug;
use once_cell::sync::Lazy;
use tokio::sync::broadcast;
use super::interpret::{InterpretError, Outcome};
#[derive(Debug, Clone)]
pub enum HarmonyEvent {
HarmonyStarted,
PrepareTopologyStarted {
topology: String,
},
TopologyPrepared {
topology: String,
outcome: Outcome,
},
InterpretExecutionStarted {
topology: String,
interpret: String,
message: String,
},
InterpretExecutionFinished {
topology: String,
interpret: String,
outcome: Result<Outcome, InterpretError>,
},
}
static HARMONY_EVENT_BUS: Lazy<broadcast::Sender<HarmonyEvent>> = Lazy::new(|| {
// TODO: Adjust channel capacity
let (tx, _rx) = broadcast::channel(100);
tx
});
pub fn instrument(event: HarmonyEvent) -> Result<(), &'static str> {
match HARMONY_EVENT_BUS.send(event) {
Ok(_) => Ok(()),
Err(_) => Err("send error: no subscribers"),
}
}
pub async fn subscribe<F, Fut>(name: &str, mut handler: F)
where
F: FnMut(HarmonyEvent) -> Fut + Send + 'static,
Fut: Future<Output = bool> + Send,
{
let mut rx = HARMONY_EVENT_BUS.subscribe();
debug!("[{name}] Service started. Listening for events...");
loop {
match rx.recv().await {
Ok(event) => {
if !handler(event).await {
debug!("[{name}] Handler requested exit.");
break;
}
}
Err(broadcast::error::RecvError::Lagged(n)) => {
debug!("[{name}] Lagged behind by {n} messages.");
}
Err(_) => break,
}
}
}

View File

@@ -1,8 +1,6 @@
use std::sync::{Arc, Mutex, RwLock};
use log::{debug, warn};
use crate::instrumentation::{self, HarmonyEvent};
use log::{info, warn};
use super::{
interpret::{InterpretError, InterpretStatus, Outcome},
@@ -42,18 +40,13 @@ impl<T: Topology> Maestro<T> {
/// Ensures the associated Topology is ready for operations.
/// Delegates the readiness check and potential setup actions to the Topology.
pub async fn prepare_topology(&self) -> Result<Outcome, InterpretError> {
instrumentation::instrument(HarmonyEvent::PrepareTopologyStarted {
topology: self.topology.name().to_string(),
})
.unwrap();
info!("Ensuring topology '{}' is ready...", self.topology.name());
let outcome = self.topology.ensure_ready().await?;
instrumentation::instrument(HarmonyEvent::TopologyPrepared {
topology: self.topology.name().to_string(),
outcome: outcome.clone(),
})
.unwrap();
info!(
"Topology '{}' readiness check complete: {}",
self.topology.name(),
outcome.status
);
self.topology_preparation_result
.lock()
@@ -87,11 +80,11 @@ impl<T: Topology> Maestro<T> {
self.topology.name(),
);
}
debug!("Running score {score:?}");
info!("Running score {score:?}");
let interpret = score.create_interpret();
debug!("Launching interpret {interpret:?}");
info!("Launching interpret {interpret:?}");
let result = interpret.execute(&self.inventory, &self.topology).await;
debug!("Got result {result:?}");
info!("Got result {result:?}");
result
}

View File

@@ -3,7 +3,6 @@ pub mod data;
pub mod executors;
pub mod filter;
pub mod hardware;
pub mod instrumentation;
pub mod interpret;
pub mod inventory;
pub mod maestro;

View File

@@ -17,7 +17,7 @@ use kube::{
runtime::wait::await_condition,
};
use log::{debug, error, trace};
use serde::{Serialize, de::DeserializeOwned};
use serde::de::DeserializeOwned;
use similar::{DiffableStr, TextDiff};
#[derive(new, Clone)]
@@ -25,15 +25,6 @@ pub struct K8sClient {
client: Client,
}
impl Serialize for K8sClient {
fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
todo!()
}
}
impl std::fmt::Debug for K8sClient {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
// This is a poor man's debug implementation for now as kube::Client does not provide much
@@ -269,33 +260,17 @@ impl K8sClient {
) -> Result<(), Error> {
let obj: DynamicObject = serde_yaml::from_value(yaml.clone()).expect("TODO do not unwrap");
let name = obj.metadata.name.as_ref().expect("YAML must have a name");
let namespace = obj
.metadata
.namespace
.as_ref()
.expect("YAML must have a namespace");
let api_version = yaml
.get("apiVersion")
.expect("couldn't get apiVersion from YAML")
.as_str()
.expect("couldn't get apiVersion as str");
let kind = yaml
.get("kind")
.expect("couldn't get kind from YAML")
.as_str()
.expect("couldn't get kind as str");
let split: Vec<&str> = api_version.splitn(2, "/").collect();
let g = split[0];
let v = split[1];
let gvk = GroupVersionKind::gvk(g, v, kind);
let api_resource = ApiResource::from_gvk(&gvk);
let namespace = match ns {
Some(n) => n,
None => obj
.metadata
.namespace
.as_ref()
.expect("YAML must have a namespace"),
};
// 4. Define the API resource type using the GVK from the object.
// The plural name 'applications' is taken from your CRD definition.
error!("This only supports argocd application harcoded, very rrrong");
let gvk = GroupVersionKind::gvk("argoproj.io", "v1alpha1", "Application");
let api_resource = ApiResource::from_gvk_with_plural(&gvk, "applications");
// 5. Create a dynamic API client for this resource type.
let api: Api<DynamicObject> =

View File

@@ -1,39 +1,30 @@
use std::{process::Command, sync::Arc};
use async_trait::async_trait;
use inquire::Confirm;
use log::{debug, info, warn};
use serde::Serialize;
use tokio::sync::OnceCell;
use crate::{
executors::ExecutorError,
interpret::{InterpretError, InterpretStatus, Outcome},
interpret::{InterpretError, Outcome},
inventory::Inventory,
modules::{
k3d::K3DInstallationScore,
monitoring::kube_prometheus::crd::{
crd_alertmanager_config::CRDPrometheus,
prometheus_operator::prometheus_operator_helm_chart_score,
},
prometheus::{
k8s_prometheus_alerting_score::K8sPrometheusCRDAlertingScore,
prometheus::PrometheusApplicationMonitoring,
},
},
score::Score,
maestro::Maestro,
modules::k3d::K3DInstallationScore,
topology::LocalhostTopology,
};
use super::{
DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, Topology,
k8s::K8sClient,
oberservability::monitoring::AlertReceiver,
tenant::{TenantConfig, TenantManager, k8s::K8sTenantManager},
};
#[derive(Clone, Debug)]
struct K8sState {
client: Arc<K8sClient>,
source: K8sSource,
_source: K8sSource,
message: String,
}
@@ -67,32 +58,8 @@ impl K8sclient for K8sAnywhereTopology {
}
}
#[async_trait]
impl PrometheusApplicationMonitoring<CRDPrometheus> for K8sAnywhereTopology {
async fn install_prometheus(
&self,
sender: &CRDPrometheus,
inventory: &Inventory,
receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
) -> Result<Outcome, InterpretError> {
let po_result = self.ensure_prometheus_operator(sender).await?;
if po_result.status == InterpretStatus::NOOP {
debug!("Skipping Prometheus CR installation due to missing operator.");
return Ok(Outcome::noop());
}
self.get_k8s_prometheus_application_score(sender.clone(), receivers)
.await
.create_interpret()
.execute(inventory, self)
.await?;
Ok(Outcome::success(format!("No action, working on cluster ")))
}
}
impl Serialize for K8sAnywhereTopology {
fn serialize<S>(&self, _serializer: S) -> Result<S::Ok, S::Error>
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
@@ -117,19 +84,6 @@ impl K8sAnywhereTopology {
}
}
async fn get_k8s_prometheus_application_score(
&self,
sender: CRDPrometheus,
receivers: Option<Vec<Box<dyn AlertReceiver<CRDPrometheus>>>>,
) -> K8sPrometheusCRDAlertingScore {
K8sPrometheusCRDAlertingScore {
sender,
receivers: receivers.unwrap_or_else(Vec::new),
service_monitors: vec![],
prometheus_rules: vec![],
}
}
fn is_helm_available(&self) -> Result<(), String> {
let version_result = Command::new("helm")
.arg("version")
@@ -140,8 +94,9 @@ impl K8sAnywhereTopology {
return Err("Failed to run 'helm -version'".to_string());
}
// Print the version output
let version_output = String::from_utf8_lossy(&version_result.stdout);
debug!("Helm version: {}", version_output.trim());
println!("Helm version: {}", version_output.trim());
Ok(())
}
@@ -159,10 +114,9 @@ impl K8sAnywhereTopology {
}
async fn try_install_k3d(&self) -> Result<(), InterpretError> {
self.get_k3d_installation_score()
.create_interpret()
.execute(&Inventory::empty(), self)
.await?;
let maestro = Maestro::initialize(Inventory::autoload(), LocalhostTopology::new()).await?;
let k3d_score = self.get_k3d_installation_score();
maestro.interpret(Box::new(k3d_score)).await?;
Ok(())
}
@@ -172,7 +126,7 @@ impl K8sAnywhereTopology {
// TODO this deserves some refactoring, it is becoming a bit hard to figure out
// be careful when making modifications here
if k8s_anywhere_config.use_local_k3d {
debug!("Using local k3d cluster because of use_local_k3d set to true");
info!("Using local k3d cluster because of use_local_k3d set to true");
} else {
if let Some(kubeconfig) = &k8s_anywhere_config.kubeconfig {
debug!("Loading kubeconfig {kubeconfig}");
@@ -180,7 +134,7 @@ impl K8sAnywhereTopology {
Some(client) => {
return Ok(Some(K8sState {
client: Arc::new(client),
source: K8sSource::Kubeconfig,
_source: K8sSource::Kubeconfig,
message: format!("Loaded k8s client from kubeconfig {kubeconfig}"),
}));
}
@@ -204,13 +158,22 @@ impl K8sAnywhereTopology {
}
if !k8s_anywhere_config.autoinstall {
warn!(
"Installation cancelled, K8sAnywhere could not initialize a valid Kubernetes client"
);
return Ok(None);
debug!("Autoinstall confirmation prompt");
let confirmation = Confirm::new( "Harmony autoinstallation is not activated, do you wish to launch autoinstallation? : ")
.with_default(false)
.prompt()
.expect("Unexpected prompt error");
debug!("Autoinstall confirmation {confirmation}");
if !confirmation {
warn!(
"Installation cancelled, K8sAnywhere could not initialize a valid Kubernetes client"
);
return Ok(None);
}
}
debug!("Starting K8sAnywhere installation");
info!("Starting K8sAnywhere installation");
self.try_install_k3d().await?;
let k3d_score = self.get_k3d_installation_score();
// I feel like having to rely on the k3d_rs crate here is a smell
@@ -222,8 +185,8 @@ impl K8sAnywhereTopology {
let state = match k3d.get_client().await {
Ok(client) => K8sState {
client: Arc::new(K8sClient::new(client)),
source: K8sSource::LocalK3d,
message: "K8s client ready".to_string(),
_source: K8sSource::LocalK3d,
message: "Successfully installed K3D cluster and acquired client".to_string(),
},
Err(_) => todo!(),
};
@@ -238,7 +201,6 @@ impl K8sAnywhereTopology {
self.tenant_manager
.get_or_try_init(async || -> Result<K8sTenantManager, String> {
// TOOD: checker si K8s ou K3d/s tenant manager (ref. issue https://git.nationtech.io/NationTech/harmony/issues/94)
let k8s_client = self.k8s_client().await?;
Ok(K8sTenantManager::new(k8s_client))
})
@@ -255,48 +217,6 @@ impl K8sAnywhereTopology {
)),
}
}
async fn ensure_prometheus_operator(
&self,
sender: &CRDPrometheus,
) -> Result<Outcome, InterpretError> {
let status = Command::new("sh")
.args(["-c", "kubectl get crd -A | grep -i prometheuses"])
.status()
.map_err(|e| InterpretError::new(format!("could not connect to cluster: {}", e)))?;
if !status.success() {
if let Some(Some(k8s_state)) = self.k8s_state.get() {
match k8s_state.source {
K8sSource::LocalK3d => {
debug!("installing prometheus operator");
let op_score =
prometheus_operator_helm_chart_score(sender.namespace.clone());
op_score
.create_interpret()
.execute(&Inventory::empty(), self)
.await?;
return Ok(Outcome::success(
"installed prometheus operator".to_string(),
));
}
K8sSource::Kubeconfig => {
debug!("unable to install prometheus operator, contact cluster admin");
return Ok(Outcome::noop());
}
}
} else {
warn!("Unable to detect k8s_state. Skipping Prometheus Operator install.");
return Ok(Outcome::noop());
}
}
debug!("Prometheus operator is already present, skipping install");
Ok(Outcome::success(
"prometheus operator present in cluster".to_string(),
))
}
}
#[derive(Clone, Debug)]
@@ -317,7 +237,7 @@ pub struct K8sAnywhereConfig {
///
/// When enabled, autoinstall will setup a K3D cluster on the localhost. https://k3d.io/stable/
///
/// Default: true
/// Default: false
pub autoinstall: bool,
/// Whether to use local k3d cluster.
@@ -336,7 +256,7 @@ impl K8sAnywhereConfig {
use_system_kubeconfig: std::env::var("HARMONY_USE_SYSTEM_KUBECONFIG")
.map_or_else(|_| false, |v| v.parse().ok().unwrap_or(false)),
autoinstall: std::env::var("HARMONY_AUTOINSTALL")
.map_or_else(|_| true, |v| v.parse().ok().unwrap_or(false)),
.map_or_else(|_| false, |v| v.parse().ok().unwrap_or(false)),
// TODO harmony_profile should be managed at a more core level than this
harmony_profile: std::env::var("HARMONY_PROFILE").map_or_else(
|_| "dev".to_string(),

View File

@@ -11,7 +11,7 @@ use crate::{
};
#[async_trait]
pub trait AlertSender: Send + Sync + std::fmt::Debug {
pub trait AlertSender: Any + Send + Sync + std::fmt::Debug {
fn name(&self) -> String;
}
@@ -64,9 +64,7 @@ impl<S: AlertSender + Installable<T>, T: Topology> Interpret<T> for AlertingInte
#[async_trait]
pub trait AlertReceiver<S: AlertSender>: std::fmt::Debug + Send + Sync {
async fn install(&self, sender: &S) -> Result<Outcome, InterpretError>;
fn name(&self) -> String;
fn clone_box(&self) -> Box<dyn AlertReceiver<S>>;
fn as_any(&self) -> &dyn Any;
}
#[async_trait]
@@ -76,6 +74,6 @@ pub trait AlertRule<S: AlertSender>: std::fmt::Debug + Send + Sync {
}
#[async_trait]
pub trait ScrapeTarget<S: AlertSender> {
pub trait ScrapeTarger<S: AlertSender> {
async fn install(&self, sender: &S) -> Result<(), InterpretError>;
}

View File

@@ -231,13 +231,8 @@ impl K8sTenantManager {
{
"to": [
{
//TODO this ip is from the docker network that k3d is running on
//since k3d does not deploy kube-api-server as a pod it needs to ahve the ip
//address opened up
//need to find a way to automatically detect the ip address from the docker
//network
"ipBlock": {
"cidr": "172.24.0.0/16",
"cidr": "172.23.0.0/16",
}
}
]

View File

@@ -1,11 +1,13 @@
use std::{backtrace, collections::HashMap};
use k8s_openapi::{Metadata, NamespaceResourceScope, Resource};
use log::debug;
use serde::Serialize;
use serde_with::skip_serializing_none;
use serde_yaml::Value;
use url::Url;
use crate::modules::application::features::CDApplicationConfig;
#[skip_serializing_none]
#[derive(Clone, Debug, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct Helm {
@@ -25,18 +27,13 @@ pub struct Helm {
pub namespace: Option<String>,
}
#[skip_serializing_none]
#[derive(Clone, Debug, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct Source {
// Using string for this because URL enforces a URL scheme at the beginning but Helm, ArgoCD, etc do not, and it can be counterproductive,
// as the only way I've found to get OCI working isn't by using oci:// but rather no scheme at all
#[serde(rename = "repoURL")]
pub repo_url: String,
pub repo_url: Url,
pub target_revision: Option<String>,
pub chart: String,
pub helm: Helm,
pub path: String,
}
#[derive(Clone, Debug, Serialize)]
@@ -70,7 +67,6 @@ pub struct SyncPolicy {
pub retry: Retry,
}
#[skip_serializing_none]
#[derive(Clone, Debug, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct ArgoApplication {
@@ -89,7 +85,7 @@ impl Default for ArgoApplication {
namespace: Default::default(),
project: Default::default(),
source: Source {
repo_url: "http://asdf".to_string(),
repo_url: Url::parse("http://asdf").expect("Couldn't parse to URL"),
target_revision: None,
chart: "".to_string(),
helm: Helm {
@@ -108,7 +104,6 @@ impl Default for ArgoApplication {
api_versions: vec![],
namespace: None,
},
path: "".to_string(),
},
sync_policy: SyncPolicy {
automated: Automated {
@@ -138,10 +133,10 @@ impl From<CDApplicationConfig> for ArgoApplication {
namespace: Some(value.namespace),
project: "default".to_string(),
source: Source {
repo_url: value.helm_chart_repo_url,
target_revision: Some(value.version.to_string()),
chart: value.helm_chart_name.clone(),
path: value.helm_chart_name,
repo_url: Url::parse(value.helm_chart_repo_url.to_string().as_str())
.expect("couldn't convert to URL"),
target_revision: None,
chart: value.helm_chart_name,
helm: Helm {
pass_credentials: None,
parameters: vec![],
@@ -150,7 +145,7 @@ impl From<CDApplicationConfig> for ArgoApplication {
value_files: vec![],
ignore_missing_value_files: None,
values: None,
values_object: value.values_overrides,
values_object: Some(value.values_overrides),
skip_crds: None,
skip_schema_validation: None,
version: None,
@@ -218,7 +213,7 @@ spec:
let mut yaml_value: Value =
serde_yaml::from_str(yaml_str.as_str()).expect("couldn't parse string to YAML");
let spec = yaml_value
let mut spec = yaml_value
.get_mut("spec")
.expect("couldn't get spec from yaml")
.as_mapping_mut()
@@ -257,7 +252,7 @@ spec:
#[cfg(test)]
mod tests {
use pretty_assertions::assert_eq;
use url::Url;
use crate::modules::application::features::{
ArgoApplication, Automated, Backoff, Helm, Retry, Source, SyncPolicy,
@@ -270,7 +265,7 @@ mod tests {
namespace: Some("test-ns".to_string()),
project: "test-project".to_string(),
source: Source {
repo_url: "http://test".to_string(),
repo_url: Url::parse("http://test").unwrap(),
target_revision: None,
chart: "test-chart".to_string(),
helm: Helm {
@@ -289,7 +284,6 @@ mod tests {
api_versions: vec![],
namespace: None,
},
path: "".to_string(),
},
sync_policy: SyncPolicy {
automated: Automated {
@@ -321,15 +315,24 @@ spec:
server: https://kubernetes.default.svc
namespace: test-ns
source:
repoURL: http://test
repoUrl: http://test/
targetRevision: null
chart: test-chart
helm:
passCredentials: null
parameters: []
fileParameters: []
releaseName: test-release-neame
valueFiles: []
ignoreMissingValueFiles: null
values: null
valuesObject: null
skipCrds: null
skipSchemaValidation: null
version: null
kubeVersion: null
apiVersions: []
path: ''
namespace: null
syncPolicy:
automated:
prune: false

View File

@@ -1,7 +1,7 @@
use std::{io::Write, process::Command, sync::Arc};
use async_trait::async_trait;
use log::{debug, error};
use log::{error, info};
use serde_yaml::Value;
use tempfile::NamedTempFile;
@@ -9,12 +9,15 @@ use crate::{
config::HARMONY_DATA_DIR,
data::Version,
inventory::Inventory,
modules::application::{
Application, ApplicationFeature, HelmPackage, OCICompliant,
features::{ArgoApplication, ArgoHelmScore},
modules::{
application::{
Application, ApplicationFeature, HelmPackage, OCICompliant,
features::{ArgoApplication, ArgoHelmScore},
},
helm::chart::HelmChartScore,
},
score::Score,
topology::{DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, Topology},
topology::{DeploymentTarget, HelmCommand, K8sclient, MultiTargetTopology, Topology, Url},
};
/// ContinuousDelivery in Harmony provides this functionality :
@@ -63,7 +66,7 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
error!("TODO hardcoded k3d bin path is wrong");
let k3d_bin_path = (*HARMONY_DATA_DIR).join("k3d").join("k3d");
// --- 1. Import the container image into the k3d cluster ---
debug!(
info!(
"Importing image '{}' into k3d cluster 'harmony'",
image_name
);
@@ -80,7 +83,7 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
}
// --- 2. Get the kubeconfig for the k3d cluster and write it to a temp file ---
debug!("Retrieving kubeconfig for k3d cluster 'harmony'");
info!("Retrieving kubeconfig for k3d cluster 'harmony'");
let kubeconfig_output = Command::new(&k3d_bin_path)
.args(["kubeconfig", "get", "harmony"])
.output()
@@ -101,7 +104,7 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
let kubeconfig_path = temp_kubeconfig.path().to_str().unwrap();
// --- 3. Install or upgrade the Helm chart in the cluster ---
debug!(
info!(
"Deploying Helm chart '{}' to namespace '{}'",
chart_url, app_name
);
@@ -131,7 +134,7 @@ impl<A: OCICompliant + HelmPackage> ContinuousDelivery<A> {
));
}
debug!("Successfully deployed '{}' to local k3d cluster.", app_name);
info!("Successfully deployed '{}' to local k3d cluster.", app_name);
Ok(())
}
}
@@ -145,19 +148,23 @@ impl<
async fn ensure_installed(&self, topology: &T) -> Result<(), String> {
let image = self.application.image_name();
// TODO
error!(
"TODO reverse helm chart packaging and docker image build. I put helm package first for faster iterations"
);
// TODO Write CI/CD workflow files
// we can autotedect the CI type using the remote url (default to github action for github
// url, etc..)
// Or ask for it when unknown
let helm_chart = self.application.build_push_helm_package(&image).await?;
debug!("Pushed new helm chart {helm_chart}");
info!("Pushed new helm chart {helm_chart}");
error!("TODO Make building image configurable/skippable if image already exists (prompt)");
let image = self.application.build_push_oci_image().await?;
debug!("Pushed new docker image {image}");
info!("Pushed new docker image {image}");
debug!("Installing ContinuousDelivery feature");
info!("Installing ContinuousDelivery feature");
// TODO this is a temporary hack for demo purposes, the deployment target should be driven
// by the topology only and we should not have to know how to perform tasks like this for
// which the topology should be responsible.
@@ -177,17 +184,17 @@ impl<
.await?;
}
target => {
debug!("Deploying to target {target:?}");
info!("Deploying to target {target:?}");
let score = ArgoHelmScore {
namespace: "harmonydemo-staging".to_string(),
openshift: false,
openshift: true,
domain: "argo.harmonydemo.apps.st.mcd".to_string(),
argo_apps: vec![ArgoApplication::from(CDApplicationConfig {
// helm pull oci://hub.nationtech.io/harmony/harmony-example-rust-webapp-chart --version 0.1.0
// helm pull oci://hub.nationtech.io/harmony/harmony-example-rust-webapp-chart/harmony-example-rust-webapp-chart --version 0.1.0
version: Version::from("0.1.0").unwrap(),
helm_chart_repo_url: "hub.nationtech.io/harmony".to_string(),
helm_chart_repo_url: Url::Url(url::Url::parse("oci://hub.nationtech.io/harmony/harmony-example-rust-webapp-chart/harmony-example-rust-webapp-chart").unwrap()),
helm_chart_name: "harmony-example-rust-webapp-chart".to_string(),
values_overrides: None,
values_overrides: Value::Null,
name: "harmony-demo-rust-webapp".to_string(),
namespace: "harmonydemo-staging".to_string(),
})],
@@ -199,7 +206,14 @@ impl<
.unwrap();
}
};
Ok(())
todo!("1. Create ArgoCD score that installs argo using helm chart, see if Taha's already done it
- [X] Package app (docker image, helm chart)
- [X] Push to registry
- [X] Push only if staging or prod
- [X] Deploy to local k3d when target is local
- [ ] Poke Argo
- [ ] Ensure app is up")
}
fn name(&self) -> String {
"ContinuousDelivery".to_string()
@@ -210,9 +224,9 @@ impl<
/// more CD systems
pub struct CDApplicationConfig {
pub version: Version,
pub helm_chart_repo_url: String,
pub helm_chart_repo_url: Url,
pub helm_chart_name: String,
pub values_overrides: Option<Value>,
pub values_overrides: Value,
pub name: String,
pub namespace: String,
}

View File

@@ -1,5 +1,5 @@
use async_trait::async_trait;
use log::error;
use k8s_openapi::Resource;
use non_blank_string_rs::NonBlankString;
use serde::Serialize;
use std::str::FromStr;
@@ -50,7 +50,6 @@ impl<T: Topology + K8sclient + HelmCommand> Interpret<T> for ArgoInterpret {
inventory: &Inventory,
topology: &T,
) -> Result<Outcome, InterpretError> {
error!("Uncomment below, only disabled for debugging");
self.score
.create_interpret()
.execute(inventory, topology)
@@ -646,7 +645,7 @@ server:
# Argo CD server ingress configuration
ingress:
# -- Enable an ingress resource for the Argo CD server
enabled: true
enabled: false
# -- Specific implementation for ingress controller. One of `generic`, `aws` or `gke`
## Additional configuration might be required in related configuration sections
controller: generic

View File

@@ -1,99 +1,47 @@
use std::sync::Arc;
use crate::modules::application::{Application, ApplicationFeature};
use crate::modules::monitoring::application_monitoring::application_monitoring_score::ApplicationMonitoringScore;
use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus;
use async_trait::async_trait;
use log::info;
use crate::{
inventory::Inventory,
modules::monitoring::{
alert_channel::webhook_receiver::WebhookReceiver, ntfy::ntfy::NtfyScore,
modules::{
application::{Application, ApplicationFeature},
monitoring::{
application_monitoring::k8s_application_monitoring_score::ApplicationPrometheusMonitoringScore,
kube_prometheus::types::{NamespaceSelector, ServiceMonitor}, prometheus::prometheus::Prometheus,
},
},
score::Score,
topology::{HelmCommand, K8sclient, Topology, Url, tenant::TenantManager},
topology::{oberservability::monitoring::{AlertReceiver, AlertRule, AlertSender}, tenant::TenantManager, HelmCommand, K8sclient, Topology},
};
use crate::{
modules::prometheus::prometheus::PrometheusApplicationMonitoring,
topology::oberservability::monitoring::AlertReceiver,
};
use async_trait::async_trait;
use base64::{Engine as _, engine::general_purpose};
use log::{debug, info};
#[derive(Debug, Clone)]
pub struct Monitoring {
pub struct PrometheusMonitoring {
pub application: Arc<dyn Application>,
pub alert_receiver: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
pub alert_receivers: Vec<Box<dyn AlertReceiver<Prometheus>>>,
pub alert_rules: Vec<Box<dyn AlertRule<Prometheus>>>,
}
#[async_trait]
impl<
T: Topology
+ HelmCommand
+ 'static
+ TenantManager
+ K8sclient
+ std::fmt::Debug
+ PrometheusApplicationMonitoring<CRDPrometheus>,
> ApplicationFeature<T> for Monitoring
{
impl<T: Topology + HelmCommand + 'static + TenantManager> ApplicationFeature<T> for PrometheusMonitoring {
async fn ensure_installed(&self, topology: &T) -> Result<(), String> {
info!("Ensuring monitoring is available for application");
let namespace = topology
.get_tenant_config()
.await
.map(|ns| ns.name.clone())
.unwrap_or_else(|| self.application.name());
let mut alerting_score = ApplicationMonitoringScore {
sender: CRDPrometheus {
namespace: namespace.clone(),
client: topology.k8s_client().await.unwrap(),
},
application: self.application.clone(),
receivers: self.alert_receiver.clone(),
};
let ntfy = NtfyScore {
namespace: namespace.clone(),
host: "localhost".to_string(),
};
ntfy.create_interpret()
.execute(&Inventory::empty(), topology)
.await
.expect("couldn't create interpret for ntfy");
let ntfy_default_auth_username = "harmony";
let ntfy_default_auth_password = "harmony";
let ntfy_default_auth_header = format!(
"Basic {}",
general_purpose::STANDARD.encode(format!(
"{ntfy_default_auth_username}:{ntfy_default_auth_password}"
))
);
debug!("ntfy_default_auth_header: {ntfy_default_auth_header}");
let ntfy_default_auth_param = general_purpose::STANDARD
.encode(ntfy_default_auth_header)
.replace("=", "");
debug!("ntfy_default_auth_param: {ntfy_default_auth_param}");
let ntfy_receiver = WebhookReceiver {
name: "ntfy-webhook".to_string(),
url: Url::Url(
url::Url::parse(
format!(
"http://ntfy.{}.svc.cluster.local/rust-web-app?auth={ntfy_default_auth_param}",
namespace.clone()
)
.as_str(),
)
.unwrap(),
),
let ns = self.application.name();
let mut service_monitor = ServiceMonitor::default();
service_monitor.name = ns.clone();
service_monitor.namespace = ns.clone();
service_monitor.namespace_selector = Some(NamespaceSelector {
any: true,
match_names: vec![ns.clone()],
});
let alerting_score = ApplicationPrometheusMonitoringScore {
namespace: ns,
receivers: self.alert_receivers.clone(),
rules: self.alert_rules.clone(),
service_monitors: vec![service_monitor],
};
alerting_score.receivers.push(Box::new(ntfy_receiver));
alerting_score
.create_interpret()
.execute(&Inventory::empty(), topology)

View File

@@ -5,12 +5,11 @@ mod rust;
use std::sync::Arc;
pub use feature::*;
use log::debug;
use log::info;
pub use oci::*;
pub use rust::*;
use async_trait::async_trait;
use serde::Serialize;
use crate::{
data::{Id, Version},
@@ -37,7 +36,7 @@ impl<A: Application, T: Topology + std::fmt::Debug> Interpret<T> for Application
topology: &T,
) -> Result<Outcome, InterpretError> {
let app_name = self.application.name();
debug!(
info!(
"Preparing {} features [{}] for application {app_name}",
self.features.len(),
self.features
@@ -47,7 +46,7 @@ impl<A: Application, T: Topology + std::fmt::Debug> Interpret<T> for Application
.join(", ")
);
for feature in self.features.iter() {
debug!(
info!(
"Installing feature {} for application {app_name}",
feature.name()
);
@@ -60,7 +59,9 @@ impl<A: Application, T: Topology + std::fmt::Debug> Interpret<T> for Application
}
};
}
Ok(Outcome::success("successfully created app".to_string()))
todo!(
"Do I need to do anything more than this here?? I feel like the Application trait itself should expose something like ensure_ready but its becoming redundant. We'll see as this evolves."
)
}
fn get_name(&self) -> InterpretName {
@@ -79,12 +80,3 @@ impl<A: Application, T: Topology + std::fmt::Debug> Interpret<T> for Application
todo!()
}
}
impl Serialize for dyn Application {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
todo!()
}
}

View File

@@ -4,15 +4,11 @@ use std::process;
use std::sync::Arc;
use async_trait::async_trait;
use bollard::query_parameters::PushImageOptionsBuilder;
use bollard::{Docker, body_full};
use dockerfile_builder::Dockerfile;
use dockerfile_builder::instruction::{CMD, COPY, ENV, EXPOSE, FROM, RUN, USER, WORKDIR};
use dockerfile_builder::instruction_builder::CopyBuilder;
use futures_util::StreamExt;
use log::{debug, error, log_enabled};
use log::{debug, error, info};
use serde::Serialize;
use tar::Archive;
use crate::config::{REGISTRY_PROJECT, REGISTRY_URL};
use crate::{
@@ -73,19 +69,19 @@ impl Application for RustWebapp {
#[async_trait]
impl HelmPackage for RustWebapp {
async fn build_push_helm_package(&self, image_url: &str) -> Result<String, String> {
debug!("Starting Helm chart build and push for '{}'", self.name);
info!("Starting Helm chart build and push for '{}'", self.name);
// 1. Create the Helm chart files on disk.
let chart_dir = self
.create_helm_chart_files(image_url)
.map_err(|e| format!("Failed to create Helm chart files: {}", e))?;
debug!("Successfully created Helm chart files in {:?}", chart_dir);
info!("Successfully created Helm chart files in {:?}", chart_dir);
// 2. Package the chart into a .tgz archive.
let packaged_chart_path = self
.package_helm_chart(&chart_dir)
.map_err(|e| format!("Failed to package Helm chart: {}", e))?;
debug!(
info!(
"Successfully packaged Helm chart: {}",
packaged_chart_path.to_string_lossy()
);
@@ -94,7 +90,7 @@ impl HelmPackage for RustWebapp {
let oci_chart_url = self
.push_helm_chart(&packaged_chart_path)
.map_err(|e| format!("Failed to push Helm chart: {}", e))?;
debug!("Successfully pushed Helm chart to: {}", oci_chart_url);
info!("Successfully pushed Helm chart to: {}", oci_chart_url);
Ok(oci_chart_url)
}
@@ -107,22 +103,24 @@ impl OCICompliant for RustWebapp {
async fn build_push_oci_image(&self) -> Result<String, String> {
// This function orchestrates the build and push process.
// It's async to match the trait definition, though the underlying docker commands are blocking.
debug!("Starting OCI image build and push for '{}'", self.name);
info!("Starting OCI image build and push for '{}'", self.name);
// 1. Build the image by calling the synchronous helper function.
let image_tag = self.image_name();
self.build_docker_image(&image_tag)
.await
// 1. Build the local image by calling the synchronous helper function.
let local_image_name = self.local_image_name();
self.build_docker_image(&local_image_name)
.map_err(|e| format!("Failed to build Docker image: {}", e))?;
debug!("Successfully built Docker image: {}", image_tag);
info!(
"Successfully built local Docker image: {}",
local_image_name
);
let remote_image_name = self.image_name();
// 2. Push the image to the registry.
self.push_docker_image(&image_tag)
.await
self.push_docker_image(&local_image_name, &remote_image_name)
.map_err(|e| format!("Failed to push Docker image: {}", e))?;
debug!("Successfully pushed Docker image to: {}", image_tag);
info!("Successfully pushed Docker image to: {}", remote_image_name);
Ok(image_tag)
Ok(remote_image_name)
}
fn local_image_name(&self) -> String {
@@ -155,74 +153,68 @@ impl RustWebapp {
}
/// Builds the Docker image using the generated Dockerfile.
pub async fn build_docker_image(
pub fn build_docker_image(
&self,
image_name: &str,
) -> Result<String, Box<dyn std::error::Error>> {
debug!("Generating Dockerfile for '{}'", self.name);
let _dockerfile_path = self.build_dockerfile()?;
info!("Generating Dockerfile for '{}'", self.name);
let dockerfile_path = self.build_dockerfile()?;
let docker = Docker::connect_with_socket_defaults().unwrap();
let quiet = !log_enabled!(log::Level::Debug);
let build_image_options = bollard::query_parameters::BuildImageOptionsBuilder::default()
.dockerfile("Dockerfile.harmony")
.t(image_name)
.q(quiet)
.version(bollard::query_parameters::BuilderVersion::BuilderV1)
.platform("linux/x86_64");
let mut temp_tar_builder = tar::Builder::new(Vec::new());
let _ = temp_tar_builder
.append_dir_all("", self.project_root.clone())
.unwrap();
let archive = temp_tar_builder
.into_inner()
.expect("couldn't finish creating tar");
let archived_files = Archive::new(archive.as_slice())
.entries()
.unwrap()
.map(|entry| entry.unwrap().path().unwrap().into_owned())
.collect::<Vec<_>>();
debug!("files in docker tar: {:#?}", archived_files);
let mut image_build_stream = docker.build_image(
build_image_options.build(),
None,
Some(body_full(archive.into())),
info!(
"Building Docker image with file {} from root {}",
dockerfile_path.to_string_lossy(),
self.project_root.to_string_lossy()
);
let output = process::Command::new("docker")
.args([
"build",
"--file",
dockerfile_path.to_str().unwrap(),
"-t",
&image_name,
self.project_root.to_str().unwrap(),
])
.spawn()?
.wait_with_output()?;
while let Some(msg) = image_build_stream.next().await {
println!("Message: {msg:?}");
}
self.check_output(&output, "Failed to build Docker image")?;
Ok(image_name.to_string())
}
/// Tags and pushes a Docker image to the configured remote registry.
async fn push_docker_image(
fn push_docker_image(
&self,
image_tag: &str,
image_name: &str,
full_tag: &str,
) -> Result<String, Box<dyn std::error::Error>> {
debug!("Pushing docker image {image_tag}");
info!("Pushing docker image {full_tag}");
let docker = Docker::connect_with_socket_defaults().unwrap();
// let push_options = PushImageOptionsBuilder::new().tag(tag);
let mut push_image_stream = docker.push_image(
image_tag,
Some(PushImageOptionsBuilder::new().build()),
None,
// Tag the image for the remote registry.
let output = process::Command::new("docker")
.args(["tag", image_name, &full_tag])
.spawn()?
.wait_with_output()?;
self.check_output(&output, "Tagging docker image failed")?;
debug!(
"docker tag output: stdout: {}, stderr: {}",
String::from_utf8_lossy(&output.stdout),
String::from_utf8_lossy(&output.stderr)
);
while let Some(msg) = push_image_stream.next().await {
println!("Message: {msg:?}");
}
// Push the image.
let output = process::Command::new("docker")
.args(["push", &full_tag])
.spawn()?
.wait_with_output()?;
self.check_output(&output, "Pushing docker image failed")?;
debug!(
"docker push output: stdout: {}, stderr: {}",
String::from_utf8_lossy(&output.stdout),
String::from_utf8_lossy(&output.stderr)
);
Ok(image_tag.to_string())
Ok(full_tag.to_string())
}
/// Checks the output of a process command for success.
@@ -357,11 +349,7 @@ impl RustWebapp {
image_url: &str,
) -> Result<PathBuf, Box<dyn std::error::Error>> {
let chart_name = format!("{}-chart", self.name);
let chart_dir = self
.project_root
.join(".harmony_generated")
.join("helm")
.join(&chart_name);
let chart_dir = self.project_root.join("helm").join(&chart_name);
let templates_dir = chart_dir.join("templates");
fs::create_dir_all(&templates_dir)?;
@@ -428,7 +416,7 @@ ingress:
Expand the name of the chart.
*/}}
{{- define "chart.name" -}}
{{- default .Chart.Name $.Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
@@ -436,7 +424,7 @@ Create a default fully qualified app name.
We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
*/}}
{{- define "chart.fullname" -}}
{{- $name := default .Chart.Name $.Values.nameOverride }}
{{- $name := default .Chart.Name .Values.nameOverride }}
{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
{{- end }}
"#;
@@ -449,12 +437,12 @@ kind: Service
metadata:
name: {{ include "chart.fullname" . }}
spec:
type: {{ $.Values.service.type }}
type: {{ .Values.service.type }}
ports:
- name: main
port: {{ $.Values.service.port | default 3000 }}
targetPort: {{ $.Values.service.port | default 3000 }}
- port: {{ .Values.service.port }}
targetPort: 3000
protocol: TCP
name: http
selector:
app: {{ include "chart.name" . }}
"#;
@@ -467,7 +455,7 @@ kind: Deployment
metadata:
name: {{ include "chart.fullname" . }}
spec:
replicas: {{ $.Values.replicaCount }}
replicas: {{ .Values.replicaCount }}
selector:
matchLabels:
app: {{ include "chart.name" . }}
@@ -478,28 +466,28 @@ spec:
spec:
containers:
- name: {{ .Chart.Name }}
image: "{{ $.Values.image.repository }}:{{ $.Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ $.Values.image.pullPolicy }}
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
ports:
- name: main
containerPort: {{ $.Values.service.port | default 3000 }}
- name: http
containerPort: 3000
protocol: TCP
"#;
fs::write(templates_dir.join("deployment.yaml"), deployment_yaml)?;
// Create templates/ingress.yaml
let ingress_yaml = r#"
{{- if $.Values.ingress.enabled -}}
{{- if .Values.ingress.enabled -}}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: {{ include "chart.fullname" . }}
annotations:
{{- toYaml $.Values.ingress.annotations | nindent 4 }}
{{- toYaml .Values.ingress.annotations | nindent 4 }}
spec:
{{- if $.Values.ingress.tls }}
{{- if .Values.ingress.tls }}
tls:
{{- range $.Values.ingress.tls }}
{{- range .Values.ingress.tls }}
- hosts:
{{- range .hosts }}
- {{ . | quote }}
@@ -508,7 +496,7 @@ spec:
{{- end }}
{{- end }}
rules:
{{- range $.Values.ingress.hosts }}
{{- range .Values.ingress.hosts }}
- host: {{ .host | quote }}
http:
paths:
@@ -519,7 +507,7 @@ spec:
service:
name: {{ include "chart.fullname" $ }}
port:
number: {{ $.Values.service.port | default 3000 }}
number: 3000
{{- end }}
{{- end }}
{{- end }}
@@ -535,18 +523,14 @@ spec:
chart_dir: &PathBuf,
) -> Result<PathBuf, Box<dyn std::error::Error>> {
let chart_dirname = chart_dir.file_name().expect("Should find a chart dirname");
debug!(
info!(
"Launching `helm package {}` cli with CWD {}",
chart_dirname.to_string_lossy(),
&self
.project_root
.join(".harmony_generated")
.join("helm")
.to_string_lossy()
&self.project_root.join("helm").to_string_lossy()
);
let output = process::Command::new("helm")
.args(["package", chart_dirname.to_str().unwrap()])
.current_dir(&self.project_root.join(".harmony_generated").join("helm")) // Run package from the parent dir
.current_dir(&self.project_root.join("helm")) // Run package from the parent dir
.output()?;
self.check_output(&output, "Failed to package Helm chart")?;
@@ -563,11 +547,7 @@ spec:
}
// The output from helm is relative, so we join it with the execution directory.
Ok(self
.project_root
.join(".harmony_generated")
.join("helm")
.join(tgz_name))
Ok(self.project_root.join("helm").join(tgz_name))
}
/// Pushes a packaged Helm chart to an OCI registry.
@@ -580,7 +560,7 @@ spec:
let oci_push_url = format!("oci://{}/{}", *REGISTRY_URL, *REGISTRY_PROJECT);
let oci_pull_url = format!("{oci_push_url}/{}-chart", self.name);
debug!(
info!(
"Pushing Helm chart {} to {}",
packaged_chart_path.to_string_lossy(),
oci_push_url

View File

@@ -220,7 +220,6 @@ impl<T: Topology + HelmCommand> Interpret<T> for HelmChartInterpret {
yaml_path,
Some(&helm_options),
);
let status = match res {
Ok(status) => status,
Err(err) => return Err(InterpretError::new(err.to_string())),

View File

@@ -10,25 +10,14 @@ use crate::{
topology::{HttpServer, Topology, Url},
};
/// Configure an HTTP server that is provided by the Topology
///
/// This Score will let you easily specify a file path to be served by the HTTP server
///
/// For example, if you have a folder of assets at `/var/www/assets` simply do :
///
/// ```rust,ignore
/// StaticFilesHttpScore {
/// files_to_serve: url!("file:///var/www/assets"),
/// }
/// ```
#[derive(Debug, new, Clone, Serialize)]
pub struct StaticFilesHttpScore {
pub struct HttpScore {
files_to_serve: Url,
}
impl<T: Topology + HttpServer> Score<T> for StaticFilesHttpScore {
impl<T: Topology + HttpServer> Score<T> for HttpScore {
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
Box::new(StaticFilesHttpInterpret::new(self.clone()))
Box::new(HttpInterpret::new(self.clone()))
}
fn name(&self) -> String {
@@ -37,12 +26,12 @@ impl<T: Topology + HttpServer> Score<T> for StaticFilesHttpScore {
}
#[derive(Debug, new, Clone)]
pub struct StaticFilesHttpInterpret {
score: StaticFilesHttpScore,
pub struct HttpInterpret {
score: HttpScore,
}
#[async_trait]
impl<T: Topology + HttpServer> Interpret<T> for StaticFilesHttpInterpret {
impl<T: Topology + HttpServer> Interpret<T> for HttpInterpret {
async fn execute(
&self,
_inventory: &Inventory,

View File

@@ -1,13 +1,12 @@
use std::path::PathBuf;
use async_trait::async_trait;
use log::{debug, info};
use log::info;
use serde::Serialize;
use crate::{
config::HARMONY_DATA_DIR,
data::{Id, Version},
instrumentation::{self, HarmonyEvent},
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
score::Score,
@@ -51,38 +50,22 @@ impl<T: Topology> Interpret<T> for K3dInstallationInterpret {
async fn execute(
&self,
_inventory: &Inventory,
topology: &T,
_topology: &T,
) -> Result<Outcome, InterpretError> {
instrumentation::instrument(HarmonyEvent::InterpretExecutionStarted {
topology: topology.name().into(),
interpret: "k3d-installation".into(),
message: "installing k3d...".into(),
})
.unwrap();
let k3d = k3d_rs::K3d::new(
self.score.installation_path.clone(),
Some(self.score.cluster_name.clone()),
);
let outcome = match k3d.ensure_installed().await {
match k3d.ensure_installed().await {
Ok(_client) => {
let msg = format!("k3d cluster '{}' installed ", self.score.cluster_name);
debug!("{msg}");
let msg = format!("k3d cluster {} is installed ", self.score.cluster_name);
info!("{msg}");
Ok(Outcome::success(msg))
}
Err(msg) => Err(InterpretError::new(format!(
"failed to ensure k3d is installed : {msg}"
"K3dInstallationInterpret failed to ensure k3d is installed : {msg}"
))),
};
instrumentation::instrument(HarmonyEvent::InterpretExecutionFinished {
topology: topology.name().into(),
interpret: "k3d-installation".into(),
outcome: outcome.clone(),
})
.unwrap();
outcome
}
}
fn get_name(&self) -> InterpretName {
InterpretName::K3dInstallation

View File

@@ -1,16 +1,9 @@
use std::any::Any;
use std::collections::BTreeMap;
use async_trait::async_trait;
use k8s_openapi::api::core::v1::Secret;
use kube::api::ObjectMeta;
use serde::Serialize;
use serde_json::json;
use serde_yaml::{Mapping, Value};
use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::{
AlertmanagerConfig, AlertmanagerConfigSpec, CRDPrometheus,
};
use crate::{
interpret::{InterpretError, Outcome},
modules::monitoring::{
@@ -20,7 +13,10 @@ use crate::{
},
prometheus::prometheus::{Prometheus, PrometheusReceiver},
},
topology::{Url, oberservability::monitoring::AlertReceiver},
topology::{
Url,
oberservability::monitoring::{AlertReceiver, AlertSender},
},
};
#[derive(Debug, Clone, Serialize)]
@@ -29,98 +25,14 @@ pub struct DiscordWebhook {
pub url: Url,
}
#[async_trait]
impl AlertReceiver<CRDPrometheus> for DiscordWebhook {
async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
let ns = sender.namespace.clone();
let secret_name = format!("{}-secret", self.name.clone());
let webhook_key = format!("{}", self.url.clone());
let mut string_data = BTreeMap::new();
string_data.insert("webhook-url".to_string(), webhook_key.clone());
let secret = Secret {
metadata: kube::core::ObjectMeta {
name: Some(secret_name.clone()),
..Default::default()
},
string_data: Some(string_data),
type_: Some("Opaque".to_string()),
..Default::default()
};
let _ = sender.client.apply(&secret, Some(&ns)).await;
let spec = 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\" . }}"
}
]
}
]
}),
};
let alertmanager_configs = AlertmanagerConfig {
metadata: ObjectMeta {
name: Some(self.name.clone()),
labels: Some(std::collections::BTreeMap::from([(
"alertmanagerConfig".to_string(),
"enabled".to_string(),
)])),
namespace: Some(ns),
..Default::default()
},
spec,
};
sender
.client
.apply(&alertmanager_configs, Some(&sender.namespace))
.await?;
Ok(Outcome::success(format!(
"installed crd-alertmanagerconfigs for {}",
self.name
)))
}
fn name(&self) -> String {
"discord-webhook".to_string()
}
fn clone_box(&self) -> Box<dyn AlertReceiver<CRDPrometheus>> {
Box::new(self.clone())
}
fn as_any(&self) -> &dyn Any {
self
}
}
#[async_trait]
impl AlertReceiver<Prometheus> for DiscordWebhook {
async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
sender.install_receiver(self).await
}
fn name(&self) -> String {
"discord-webhook".to_string()
}
fn clone_box(&self) -> Box<dyn AlertReceiver<Prometheus>> {
Box::new(self.clone())
}
fn as_any(&self) -> &dyn Any {
self
}
}
#[async_trait]
@@ -141,12 +53,6 @@ impl AlertReceiver<KubePrometheus> for DiscordWebhook {
fn clone_box(&self) -> Box<dyn AlertReceiver<KubePrometheus>> {
Box::new(self.clone())
}
fn name(&self) -> String {
"discord-webhook".to_string()
}
fn as_any(&self) -> &dyn Any {
self
}
}
#[async_trait]

View File

@@ -1,19 +1,11 @@
use std::any::Any;
use async_trait::async_trait;
use kube::api::ObjectMeta;
use log::debug;
use serde::Serialize;
use serde_json::json;
use serde_yaml::{Mapping, Value};
use crate::{
interpret::{InterpretError, Outcome},
modules::monitoring::{
kube_prometheus::{
crd::crd_alertmanager_config::{
AlertmanagerConfig, AlertmanagerConfigSpec, CRDPrometheus,
},
prometheus::{KubePrometheus, KubePrometheusReceiver},
types::{AlertChannelConfig, AlertManagerChannelConfig},
},
@@ -28,81 +20,14 @@ pub struct WebhookReceiver {
pub url: Url,
}
#[async_trait]
impl AlertReceiver<CRDPrometheus> for WebhookReceiver {
async fn install(&self, sender: &CRDPrometheus) -> Result<Outcome, InterpretError> {
let spec = AlertmanagerConfigSpec {
data: json!({
"route": {
"receiver": self.name,
},
"receivers": [
{
"name": self.name,
"webhookConfigs": [
{
"url": self.url,
}
]
}
]
}),
};
let alertmanager_configs = AlertmanagerConfig {
metadata: ObjectMeta {
name: Some(self.name.clone()),
labels: Some(std::collections::BTreeMap::from([(
"alertmanagerConfig".to_string(),
"enabled".to_string(),
)])),
namespace: Some(sender.namespace.clone()),
..Default::default()
},
spec,
};
debug!(
"alert manager configs: \n{:#?}",
alertmanager_configs.clone()
);
sender
.client
.apply(&alertmanager_configs, Some(&sender.namespace))
.await?;
Ok(Outcome::success(format!(
"installed crd-alertmanagerconfigs for {}",
self.name
)))
}
fn name(&self) -> String {
"webhook-receiver".to_string()
}
fn clone_box(&self) -> Box<dyn AlertReceiver<CRDPrometheus>> {
Box::new(self.clone())
}
fn as_any(&self) -> &dyn Any {
self
}
}
#[async_trait]
impl AlertReceiver<Prometheus> for WebhookReceiver {
async fn install(&self, sender: &Prometheus) -> Result<Outcome, InterpretError> {
sender.install_receiver(self).await
}
fn name(&self) -> String {
"webhook-receiver".to_string()
}
fn clone_box(&self) -> Box<dyn AlertReceiver<Prometheus>> {
Box::new(self.clone())
}
fn as_any(&self) -> &dyn Any {
self
}
}
#[async_trait]
@@ -119,15 +44,9 @@ impl AlertReceiver<KubePrometheus> for WebhookReceiver {
async fn install(&self, sender: &KubePrometheus) -> Result<Outcome, InterpretError> {
sender.install_receiver(self).await
}
fn name(&self) -> String {
"webhook-receiver".to_string()
}
fn clone_box(&self) -> Box<dyn AlertReceiver<KubePrometheus>> {
Box::new(self.clone())
}
fn as_any(&self) -> &dyn Any {
self
}
}
#[async_trait]

View File

@@ -1,78 +0,0 @@
use std::sync::Arc;
use async_trait::async_trait;
use serde::Serialize;
use crate::{
data::{Id, Version},
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
modules::{
application::Application,
monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus,
prometheus::prometheus::PrometheusApplicationMonitoring,
},
score::Score,
topology::{Topology, oberservability::monitoring::AlertReceiver},
};
#[derive(Debug, Clone, Serialize)]
pub struct ApplicationMonitoringScore {
pub sender: CRDPrometheus,
pub application: Arc<dyn Application>,
pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
}
impl<T: Topology + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
for ApplicationMonitoringScore
{
fn create_interpret(&self) -> Box<dyn Interpret<T>> {
Box::new(ApplicationMonitoringInterpret {
score: self.clone(),
})
}
fn name(&self) -> String {
"ApplicationMonitoringScore".to_string()
}
}
#[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> {
topology
.install_prometheus(
&self.score.sender,
inventory,
Some(self.score.receivers.clone()),
)
.await
}
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!()
}
}

View File

@@ -0,0 +1,45 @@
use std::sync::{Arc, Mutex};
use log::debug;
use serde::Serialize;
use crate::{
modules::monitoring::{
kube_prometheus::types::ServiceMonitor,
prometheus::{prometheus::Prometheus, prometheus_config::HelmPrometheusConfig},
},
score::Score,
topology::{
oberservability::monitoring::{AlertReceiver, AlertRule, AlertingInterpret}, tenant::TenantManager, HelmCommand, K8sclient, Topology
},
};
#[derive(Clone, Debug, Serialize)]
pub struct ApplicationPrometheusMonitoringScore {
pub namespace: String,
pub receivers: Vec<Box<dyn AlertReceiver<Prometheus>>>,
pub rules: Vec<Box<dyn AlertRule<Prometheus>>>,
pub service_monitors: Vec<ServiceMonitor>,
}
impl<T: Topology + HelmCommand + TenantManager> Score<T> for ApplicationPrometheusMonitoringScore {
fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
let config = Arc::new(Mutex::new(HelmPrometheusConfig::new()));
config
.try_lock()
.expect("couldn't lock config")
.additional_service_monitors = self.service_monitors.clone();
let ns = self.namespace.clone();
config.try_lock().expect("couldn't lock config").namespace = Some(ns.clone());
debug!("set namespace to {}", ns);
Box::new(AlertingInterpret {
sender: Prometheus { config },
receivers: self.receivers.clone(),
rules: self.rules.clone(),
})
}
fn name(&self) -> String {
"ApplicationPrometheusMonitoringScore".to_string()
}
}

View File

@@ -1 +1 @@
pub mod application_monitoring_score;
pub mod k8s_application_monitoring_score;

View File

@@ -1,6 +1,5 @@
use non_blank_string_rs::NonBlankString;
use std::str::FromStr;
use non_blank_string_rs::NonBlankString;
use crate::modules::helm::chart::HelmChartScore;
pub fn grafana_helm_chart_score(ns: &str) -> HelmChartScore {
@@ -8,10 +7,46 @@ pub fn grafana_helm_chart_score(ns: &str) -> HelmChartScore {
r#"
rbac:
namespaced: true
sidecar:
dashboards:
enabled: true
"#
datasources:
datasources.yaml:
apiVersion: 1
datasources:
- name: Prometheus
type: prometheus
access: proxy
url: http://prometheus-server.{ns}.svc.cluster.local
isDefault: true
dashboardProviders:
dashboardproviders.yaml:
apiVersion: 1
providers:
- name: 'default'
orgId: 1
folder: ''
type: file
disableDeletion: false
updateIntervalSeconds: 10
allowUiUpdates: true
editable: true
options:
path: /var/lib/grafana/dashboards/default
dashboards:
default:
compute-usage:
url: https://grafana.com/api/dashboards/315/revisions/1/download
pod-health:
url: https://grafana.com/api/dashboards/15758/revisions/1/download
namespace-resources:
url: https://grafana.com/api/dashboards/9809/revisions/1/download
namespace-resources-vs-quotas:
url: https://grafana.com/api/dashboards/17044/revisions/1/download
persistent-volume-usage:
url: https://grafana.com/api/dashboards/7685/revisions/1/download
"#,
ns = ns
);
HelmChartScore {
@@ -20,9 +55,10 @@ sidecar:
chart_name: NonBlankString::from_str("oci://ghcr.io/grafana/helm-charts/grafana").unwrap(),
chart_version: None,
values_overrides: None,
values_yaml: Some(values.to_string()),
values_yaml: Some(values),
create_namespace: true,
install_only: true,
install_only: false,
repository: None,
}
}

View File

@@ -1,50 +0,0 @@
use std::sync::Arc;
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use crate::topology::{
k8s::K8sClient,
oberservability::monitoring::{AlertReceiver, AlertSender},
};
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "monitoring.coreos.com",
version = "v1alpha1",
kind = "AlertmanagerConfig",
plural = "alertmanagerconfigs",
namespaced
)]
pub struct AlertmanagerConfigSpec {
#[serde(flatten)]
pub data: serde_json::Value,
}
#[derive(Debug, Clone, Serialize)]
pub struct CRDPrometheus {
pub namespace: String,
pub client: Arc<K8sClient>,
}
impl AlertSender for CRDPrometheus {
fn name(&self) -> String {
"CRDAlertManager".to_string()
}
}
impl Clone for Box<dyn AlertReceiver<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
S: serde::Serializer,
{
todo!()
}
}

View File

@@ -1,53 +0,0 @@
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use std::collections::BTreeMap;
use super::crd_prometheuses::LabelSelector;
/// Rust CRD for `Alertmanager` from Prometheus Operator
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "monitoring.coreos.com",
version = "v1",
kind = "Alertmanager",
plural = "alertmanagers",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct AlertmanagerSpec {
/// Number of replicas for HA
pub replicas: i32,
/// Selectors for AlertmanagerConfig CRDs
#[serde(default, skip_serializing_if = "Option::is_none")]
pub alertmanager_config_selector: Option<LabelSelector>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub alertmanager_config_namespace_selector: Option<LabelSelector>,
/// Optional pod template metadata (annotations, labels)
#[serde(default, skip_serializing_if = "Option::is_none")]
pub pod_metadata: Option<LabelSelector>,
/// Optional topology spread settings
#[serde(default, skip_serializing_if = "Option::is_none")]
pub version: Option<String>,
}
impl Default for AlertmanagerSpec {
fn default() -> Self {
AlertmanagerSpec {
replicas: 1,
// Match all AlertmanagerConfigs in the same namespace
alertmanager_config_namespace_selector: None,
// Empty selector matches all AlertmanagerConfigs in that namespace
alertmanager_config_selector: Some(LabelSelector::default()),
pod_metadata: None,
version: None,
}
}
}

View File

@@ -1,30 +0,0 @@
use std::collections::BTreeMap;
use crate::modules::{
monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule,
prometheus::alerts::k8s::{
deployment::alert_deployment_unavailable,
pod::{alert_container_restarting, alert_pod_not_ready, pod_failed},
pvc::high_pvc_fill_rate_over_two_days,
service::alert_service_down,
},
};
use super::crd_prometheus_rules::Rule;
pub fn build_default_application_rules() -> Vec<Rule> {
let pod_failed: Rule = pod_failed().into();
let container_restarting: Rule = alert_container_restarting().into();
let pod_not_ready: Rule = alert_pod_not_ready().into();
let service_down: Rule = alert_service_down().into();
let deployment_unavailable: Rule = alert_deployment_unavailable().into();
let high_pvc_fill_rate: Rule = high_pvc_fill_rate_over_two_days().into();
vec![
pod_failed,
container_restarting,
pod_not_ready,
service_down,
deployment_unavailable,
high_pvc_fill_rate,
]
}

View File

@@ -1,153 +0,0 @@
use std::collections::BTreeMap;
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use super::crd_prometheuses::LabelSelector;
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "grafana.integreatly.org",
version = "v1beta1",
kind = "Grafana",
plural = "grafanas",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaSpec {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub config: Option<GrafanaConfig>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub admin_user: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub admin_password: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub ingress: Option<GrafanaIngress>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub persistence: Option<GrafanaPersistence>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub resources: Option<ResourceRequirements>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaConfig {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub log: Option<GrafanaLogConfig>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub security: Option<GrafanaSecurityConfig>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaLogConfig {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub mode: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub level: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaSecurityConfig {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub admin_user: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub admin_password: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaIngress {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub enabled: Option<bool>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub hosts: Option<Vec<String>>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaPersistence {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub enabled: Option<bool>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub storage_class_name: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub size: Option<String>,
}
// ------------------------------------------------------------------------------------------------
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "grafana.integreatly.org",
version = "v1beta1",
kind = "GrafanaDashboard",
plural = "grafanadashboards",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaDashboardSpec {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub resync_period: Option<String>,
pub instance_selector: LabelSelector,
pub json: String,
}
// ------------------------------------------------------------------------------------------------
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "grafana.integreatly.org",
version = "v1beta1",
kind = "GrafanaDatasource",
plural = "grafanadatasources",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct GrafanaDatasourceSpec {
pub instance_selector: LabelSelector,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub allow_cross_namespace_import: Option<bool>,
pub datasource: GrafanaDatasourceConfig,
}
#[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 name: String,
pub r#type: String,
pub url: String,
}
// ------------------------------------------------------------------------------------------------
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
#[serde(rename_all = "camelCase")]
pub struct ResourceRequirements {
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub limits: BTreeMap<String, String>,
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub requests: BTreeMap<String, String>,
}

View File

@@ -1,59 +0,0 @@
use std::collections::BTreeMap;
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
use super::crd_default_rules::build_default_application_rules;
#[derive(CustomResource, Debug, Serialize, Deserialize, Clone, JsonSchema)]
#[kube(
group = "monitoring.coreos.com",
version = "v1",
kind = "PrometheusRule",
plural = "prometheusrules",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct PrometheusRuleSpec {
pub groups: Vec<RuleGroup>,
}
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
pub struct RuleGroup {
pub name: String,
pub rules: Vec<Rule>,
}
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct Rule {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub alert: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub expr: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub for_: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub labels: Option<std::collections::BTreeMap<String, String>>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub annotations: Option<std::collections::BTreeMap<String, String>>,
}
impl From<PrometheusAlertRule> for Rule {
fn from(value: PrometheusAlertRule) -> Self {
Rule {
alert: Some(value.alert),
expr: Some(value.expr),
for_: value.r#for,
labels: Some(value.labels.into_iter().collect::<BTreeMap<_, _>>()),
annotations: Some(value.annotations.into_iter().collect::<BTreeMap<_, _>>()),
}
}
}

View File

@@ -1,118 +0,0 @@
use std::collections::BTreeMap;
use kube::CustomResource;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use crate::modules::monitoring::kube_prometheus::types::Operator;
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "monitoring.coreos.com",
version = "v1",
kind = "Prometheus",
plural = "prometheuses",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct PrometheusSpec {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub alerting: Option<PrometheusSpecAlerting>,
pub service_account_name: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub service_monitor_namespace_selector: Option<LabelSelector>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub service_monitor_selector: Option<LabelSelector>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub service_discovery_role: Option<String>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub pod_monitor_selector: Option<LabelSelector>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub rule_selector: Option<LabelSelector>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub rule_namespace_selector: Option<LabelSelector>,
}
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
#[serde(rename_all = "camelCase")]
pub struct NamespaceSelector {
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub match_names: Vec<String>,
}
/// Contains alerting configuration, specifically Alertmanager endpoints.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
pub struct PrometheusSpecAlerting {
#[serde(skip_serializing_if = "Option::is_none")]
pub alertmanagers: Option<Vec<AlertmanagerEndpoints>>,
}
/// Represents an Alertmanager endpoint configuration used by Prometheus.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
pub struct AlertmanagerEndpoints {
/// Name of the Alertmanager Service.
#[serde(skip_serializing_if = "Option::is_none")]
pub name: Option<String>,
/// Namespace of the Alertmanager Service.
#[serde(skip_serializing_if = "Option::is_none")]
pub namespace: Option<String>,
/// Port to access on the Alertmanager Service (e.g. "web").
#[serde(skip_serializing_if = "Option::is_none")]
pub port: Option<String>,
/// Scheme to use for connecting (e.g. "http").
#[serde(skip_serializing_if = "Option::is_none")]
pub scheme: Option<String>,
// Other fields like `tls_config`, `path_prefix`, etc., can be added if needed.
}
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
#[serde(rename_all = "camelCase")]
pub struct LabelSelector {
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub match_labels: BTreeMap<String, String>,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub match_expressions: Vec<LabelSelectorRequirement>,
}
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct LabelSelectorRequirement {
pub key: String,
pub operator: Operator,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub values: Vec<String>,
}
impl Default for PrometheusSpec {
fn default() -> Self {
PrometheusSpec {
alerting: None,
service_account_name: "prometheus".into(),
// null means "only my namespace"
service_monitor_namespace_selector: None,
// empty selector means match all ServiceMonitors in that namespace
service_monitor_selector: Some(LabelSelector::default()),
service_discovery_role: Some("Endpoints".into()),
pod_monitor_selector: None,
rule_selector: None,
rule_namespace_selector: Some(LabelSelector::default()),
}
}
}

View File

@@ -1,203 +0,0 @@
pub fn build_default_dashboard(namespace: &str) -> String {
let dashboard = format!(
r#"{{
"annotations": {{
"list": []
}},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"id": null,
"iteration": 171105,
"panels": [
{{
"datasource": "$datasource",
"fieldConfig": {{
"defaults": {{
"unit": "short"
}},
"overrides": []
}},
"gridPos": {{
"h": 6,
"w": 6,
"x": 0,
"y": 0
}},
"id": 1,
"options": {{
"reduceOptions": {{
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}}
}},
"pluginVersion": "9.0.0",
"targets": [
{{
"expr": "sum(kube_pod_status_phase{{namespace=\"{namespace}\", phase=\"Running\"}})",
"legendFormat": "",
"refId": "A"
}}
],
"title": "Pods in Namespace",
"type": "stat"
}},
{{
"datasource": "$datasource",
"fieldConfig": {{
"defaults": {{
"unit": "short"
}},
"overrides": []
}},
"gridPos": {{
"h": 6,
"w": 6,
"x": 6,
"y": 0
}},
"id": 2,
"options": {{
"reduceOptions": {{
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}}
}},
"pluginVersion": "9.0.0",
"targets": [
{{
"expr": "sum(kube_pod_status_phase{{phase=\"Failed\", namespace=\"{namespace}\"}})",
"legendFormat": "",
"refId": "A"
}}
],
"title": "Pods in Failed State",
"type": "stat"
}},
{{
"datasource": "$datasource",
"fieldConfig": {{
"defaults": {{
"unit": "percentunit"
}},
"overrides": []
}},
"gridPos": {{
"h": 6,
"w": 12,
"x": 0,
"y": 6
}},
"id": 3,
"options": {{
"reduceOptions": {{
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}}
}},
"pluginVersion": "9.0.0",
"targets": [
{{
"expr": "sum(kube_deployment_status_replicas_available{{namespace=\"{namespace}\"}}) / sum(kube_deployment_spec_replicas{{namespace=\"{namespace}\"}})",
"legendFormat": "",
"refId": "A"
}}
],
"title": "Deployment Health (Available / Desired)",
"type": "stat"
}},
{{
"datasource": "$datasource",
"fieldConfig": {{
"defaults": {{
"unit": "short"
}},
"overrides": []
}},
"gridPos": {{
"h": 6,
"w": 12,
"x": 0,
"y": 12
}},
"id": 4,
"options": {{
"reduceOptions": {{
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}}
}},
"pluginVersion": "9.0.0",
"targets": [
{{
"expr": "sum by(pod) (rate(kube_pod_container_status_restarts_total{{namespace=\"{namespace}\"}}[5m]))",
"legendFormat": "{{{{pod}}}}",
"refId": "A"
}}
],
"title": "Container Restarts (per pod)",
"type": "timeseries"
}},
{{
"datasource": "$datasource",
"fieldConfig": {{
"defaults": {{
"unit": "short"
}},
"overrides": []
}},
"gridPos": {{
"h": 6,
"w": 12,
"x": 0,
"y": 18
}},
"id": 5,
"options": {{
"reduceOptions": {{
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}}
}},
"pluginVersion": "9.0.0",
"targets": [
{{
"expr": "sum(ALERTS{{alertstate=\"firing\", namespace=\"{namespace}\"}}) or vector(0)",
"legendFormat": "",
"refId": "A"
}}
],
"title": "Firing Alerts in Namespace",
"type": "stat"
}}
],
"schemaVersion": 36,
"templating": {{
"list": [
{{
"name": "datasource",
"type": "datasource",
"pluginId": "prometheus",
"label": "Prometheus",
"query": "prometheus",
"refresh": 1,
"hide": 0,
"current": {{
"selected": true,
"text": "Prometheus",
"value": "Prometheus"
}}
}}
]
}},
"title": "Tenant Namespace Overview",
"version": 1
}}"#
);
dashboard
}

View File

@@ -1,20 +0,0 @@
use std::str::FromStr;
use non_blank_string_rs::NonBlankString;
use crate::modules::helm::chart::HelmChartScore;
pub fn grafana_operator_helm_chart_score(ns: String) -> HelmChartScore {
HelmChartScore {
namespace: Some(NonBlankString::from_str(&ns).unwrap()),
release_name: NonBlankString::from_str("grafana_operator").unwrap(),
chart_name: NonBlankString::from_str("oci://ghcr.io/grafana/helm-charts/grafana-operator")
.unwrap(),
chart_version: None,
values_overrides: None,
values_yaml: None,
create_namespace: true,
install_only: true,
repository: None,
}
}

View File

@@ -1,11 +0,0 @@
pub mod crd_alertmanager_config;
pub mod crd_alertmanagers;
pub mod crd_default_rules;
pub mod crd_grafana;
pub mod crd_prometheus_rules;
pub mod crd_prometheuses;
pub mod grafana_default_dashboard;
pub mod grafana_operator;
pub mod prometheus_operator;
pub mod role;
pub mod service_monitor;

View File

@@ -1,22 +0,0 @@
use std::str::FromStr;
use non_blank_string_rs::NonBlankString;
use crate::modules::helm::chart::HelmChartScore;
pub fn prometheus_operator_helm_chart_score(ns: String) -> HelmChartScore {
HelmChartScore {
namespace: Some(NonBlankString::from_str(&ns).unwrap()),
release_name: NonBlankString::from_str("prometheus-operator").unwrap(),
chart_name: NonBlankString::from_str(
"oci://hub.nationtech.io/harmony/nt-prometheus-operator",
)
.unwrap(),
chart_version: None,
values_overrides: None,
values_yaml: None,
create_namespace: true,
install_only: true,
repository: None,
}
}

View File

@@ -1,62 +0,0 @@
use k8s_openapi::api::{
core::v1::ServiceAccount,
rbac::v1::{PolicyRule, Role, RoleBinding, RoleRef, Subject},
};
use kube::api::ObjectMeta;
pub fn build_prom_role(role_name: String, namespace: String) -> Role {
Role {
metadata: ObjectMeta {
name: Some(role_name),
namespace: Some(namespace),
..Default::default()
},
rules: Some(vec![PolicyRule {
api_groups: Some(vec!["".into()]), // core API group
resources: Some(vec!["services".into(), "endpoints".into(), "pods".into()]),
verbs: vec!["get".into(), "list".into(), "watch".into()],
..Default::default()
}]),
}
}
pub fn build_prom_rolebinding(
role_name: String,
namespace: String,
service_account_name: String,
) -> RoleBinding {
RoleBinding {
metadata: ObjectMeta {
name: Some(format!("{}-rolebinding", role_name)),
namespace: Some(namespace.clone()),
..Default::default()
},
role_ref: RoleRef {
api_group: "rbac.authorization.k8s.io".into(),
kind: "Role".into(),
name: role_name,
},
subjects: Some(vec![Subject {
kind: "ServiceAccount".into(),
name: service_account_name,
namespace: Some(namespace.clone()),
..Default::default()
}]),
}
}
pub fn build_prom_service_account(
service_account_name: String,
namespace: String,
) -> ServiceAccount {
ServiceAccount {
automount_service_account_token: None,
image_pull_secrets: None,
metadata: ObjectMeta {
name: Some(service_account_name),
namespace: Some(namespace),
..Default::default()
},
secrets: None,
}
}

View File

@@ -1,89 +0,0 @@
use std::collections::{BTreeMap, HashMap};
use kube::{CustomResource, Resource, api::ObjectMeta};
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use crate::interpret::InterpretError;
use crate::modules::monitoring::kube_prometheus::types::{
HTTPScheme, MatchExpression, NamespaceSelector, Operator, Selector,
ServiceMonitor as KubeServiceMonitor, ServiceMonitorEndpoint,
};
/// This is the top-level struct for the ServiceMonitor Custom Resource.
/// The `#[derive(CustomResource)]` macro handles all the boilerplate for you,
/// including the `impl Resource`.
#[derive(CustomResource, Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[kube(
group = "monitoring.coreos.com",
version = "v1",
kind = "ServiceMonitor",
plural = "servicemonitors",
namespaced
)]
#[serde(rename_all = "camelCase")]
pub struct ServiceMonitorSpec {
/// A label selector to select services to monitor.
pub selector: Selector,
/// A list of endpoints on the selected services to be monitored.
pub endpoints: Vec<ServiceMonitorEndpoint>,
/// Selector to select which namespaces the Kubernetes Endpoints objects
/// are discovered from.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub namespace_selector: Option<NamespaceSelector>,
/// The label to use to retrieve the job name from.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub job_label: Option<String>,
/// Pod-based target labels to transfer from the Kubernetes Pod onto the target.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub pod_target_labels: Vec<String>,
/// TargetLabels transfers labels on the Kubernetes Service object to the target.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub target_labels: Vec<String>,
}
impl Default for ServiceMonitorSpec {
fn default() -> Self {
let mut labels = HashMap::new();
Self {
selector: Selector {
match_labels: { labels },
match_expressions: vec![MatchExpression {
key: "app.kubernetes.io/name".into(),
operator: Operator::Exists,
values: vec![],
}],
},
endpoints: vec![ServiceMonitorEndpoint {
port: Some("http".to_string()),
path: Some("/metrics".into()),
interval: Some("30s".into()),
scheme: Some(HTTPScheme::HTTP),
..Default::default()
}],
namespace_selector: None, // only the same namespace
job_label: Some("app".into()),
pod_target_labels: vec![],
target_labels: vec![],
}
}
}
impl From<KubeServiceMonitor> for ServiceMonitorSpec {
fn from(value: KubeServiceMonitor) -> Self {
Self {
selector: value.selector,
endpoints: value.endpoints,
namespace_selector: value.namespace_selector,
job_label: value.job_label,
pod_target_labels: value.pod_target_labels,
target_labels: value.target_labels,
}
}
}

View File

@@ -35,18 +35,18 @@ impl KubePrometheusConfig {
windows_monitoring: false,
alert_manager: true,
grafana: true,
node_exporter: true,
node_exporter: false,
prometheus: true,
kubernetes_service_monitors: true,
kubernetes_api_server: true,
kubernetes_api_server: false,
kubelet: true,
kube_controller_manager: true,
kube_etcd: true,
kube_proxy: true,
kube_controller_manager: false,
kube_etcd: false,
kube_proxy: false,
kube_state_metrics: true,
prometheus_operator: true,
core_dns: true,
kube_scheduler: true,
core_dns: false,
kube_scheduler: false,
alert_receiver_configs: vec![],
alert_rules: vec![],
additional_service_monitors: vec![],

View File

@@ -12,8 +12,8 @@ use crate::modules::{
helm::chart::HelmChartScore,
monitoring::kube_prometheus::types::{
AlertGroup, AlertManager, AlertManagerAdditionalPromRules, AlertManagerConfig,
AlertManagerConfigSelector, AlertManagerRoute, AlertManagerSpec, AlertManagerValues,
ConfigReloader, Limits, PrometheusConfig, Requests, Resources,
AlertManagerRoute, AlertManagerSpec, AlertManagerValues, ConfigReloader, Limits,
PrometheusConfig, Requests, Resources,
},
};
@@ -70,12 +70,12 @@ pub fn kube_prometheus_helm_chart_score(
r#"
global:
rbac:
create: true
create: false
prometheus:
enabled: {prometheus}
prometheusSpec:
resources:
requests:
requests:
cpu: 100m
memory: 500Mi
limits:
@@ -121,7 +121,7 @@ defaultRules:
windowsMonitoring:
enabled: {windows_monitoring}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -130,13 +130,13 @@ windowsMonitoring:
grafana:
enabled: {grafana}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
cpu: 200m
memory: 250Mi
initChownData:
initChownData:
resources:
requests:
cpu: 10m
@@ -157,7 +157,7 @@ kubernetesServiceMonitors:
kubeApiServer:
enabled: {kubernetes_api_server}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -166,7 +166,7 @@ kubeApiServer:
kubelet:
enabled: {kubelet}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -175,7 +175,7 @@ kubelet:
kubeControllerManager:
enabled: {kube_controller_manager}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -184,7 +184,7 @@ kubeControllerManager:
coreDns:
enabled: {core_dns}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -193,7 +193,7 @@ coreDns:
kubeEtcd:
enabled: {kube_etcd}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -202,7 +202,7 @@ kubeEtcd:
kubeScheduler:
enabled: {kube_scheduler}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -211,7 +211,7 @@ kubeScheduler:
kubeProxy:
enabled: {kube_proxy}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -221,7 +221,7 @@ kubeStateMetrics:
enabled: {kube_state_metrics}
kube-state-metrics:
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -230,7 +230,7 @@ kube-state-metrics:
nodeExporter:
enabled: {node_exporter}
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -238,16 +238,16 @@ nodeExporter:
memory: 250Mi
prometheus-node-exporter:
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
cpu: 200m
memory: 250Mi
prometheusOperator:
enabled: true
enabled: false
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -255,7 +255,7 @@ prometheusOperator:
memory: 200Mi
prometheusConfigReloader:
resources:
requests:
requests:
cpu: 100m
memory: 150Mi
limits:
@@ -267,7 +267,7 @@ prometheusOperator:
limits:
cpu: 10m
memory: 100Mi
requests:
requests:
cpu: 10m
memory: 100Mi
patch:
@@ -275,7 +275,7 @@ prometheusOperator:
limits:
cpu: 10m
memory: 100Mi
requests:
requests:
cpu: 10m
memory: 100Mi
"#,
@@ -332,11 +332,6 @@ prometheusOperator:
.push(receiver.channel_receiver.clone());
}
let mut labels = BTreeMap::new();
labels.insert("alertmanagerConfig".to_string(), "enabled".to_string());
let alert_manager_config_selector = AlertManagerConfigSelector {
match_labels: labels,
};
let alert_manager_values = AlertManagerValues {
alertmanager: AlertManager {
enabled: config.alert_manager,
@@ -352,8 +347,6 @@ prometheusOperator:
cpu: "100m".to_string(),
},
},
alert_manager_config_selector,
replicas: 2,
},
init_config_reloader: ConfigReloader {
resources: Resources {

View File

@@ -28,7 +28,7 @@ impl<T: Topology + HelmCommand + TenantManager> Score<T> for HelmPrometheusAlert
.expect("couldn't lock config")
.additional_service_monitors = self.service_monitors.clone();
Box::new(AlertingInterpret {
sender: KubePrometheus { config },
sender: KubePrometheus::new(),
receivers: self.receivers.clone(),
rules: self.rules.clone(),
})

View File

@@ -1,4 +1,3 @@
pub mod crd;
pub mod helm;
pub mod helm_prometheus_alert_score;
pub mod prometheus;

View File

@@ -1,8 +1,7 @@
use std::collections::{BTreeMap, HashMap};
use async_trait::async_trait;
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use serde::Serialize;
use serde_yaml::{Mapping, Sequence, Value};
use crate::modules::monitoring::alert_rule::prometheus_alert_rule::AlertManagerRuleGroup;
@@ -56,14 +55,6 @@ pub struct AlertManagerChannelConfig {
#[serde(rename_all = "camelCase")]
pub struct AlertManagerSpec {
pub(crate) resources: Resources,
pub replicas: u32,
pub alert_manager_config_selector: AlertManagerConfigSelector,
}
#[derive(Debug, Clone, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct AlertManagerConfigSelector {
pub match_labels: BTreeMap<String, String>,
}
#[derive(Debug, Clone, Serialize)]
@@ -95,7 +86,7 @@ pub struct AlertGroup {
pub groups: Vec<AlertManagerRuleGroup>,
}
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[derive(Debug, Clone, Serialize)]
pub enum HTTPScheme {
#[serde(rename = "http")]
HTTP,
@@ -103,7 +94,7 @@ pub enum HTTPScheme {
HTTPS,
}
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
#[derive(Debug, Clone, Serialize)]
pub enum Operator {
In,
NotIn,
@@ -148,87 +139,80 @@ pub struct ServiceMonitorTLSConfig {
pub server_name: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
#[derive(Debug, Clone, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct ServiceMonitorEndpoint {
/// Name of the service port this endpoint refers to.
// ## Name of the endpoint's service port
// ## Mutually exclusive with targetPort
pub port: Option<String>,
/// Interval at which metrics should be scraped.
#[serde(default, skip_serializing_if = "Option::is_none")]
// ## Name or number of the endpoint's target port
// ## Mutually exclusive with port
pub target_port: Option<String>,
// ## File containing bearer token to be used when scraping targets
// ##
pub bearer_token_file: Option<String>,
// ## Interval at which metrics should be scraped
// ##
pub interval: Option<String>,
/// The HTTP path to scrape for metrics.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub path: Option<String>,
// ## HTTP path to scrape for metrics
// ##
pub path: String,
/// HTTP scheme to use for scraping.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub scheme: Option<HTTPScheme>,
// ## HTTP scheme to use for scraping
// ##
pub scheme: HTTPScheme,
/// Relabelings to apply to samples before scraping.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub relabelings: Vec<RelabelConfig>,
// ## TLS configuration to use when scraping the endpoint
// ##
pub tls_config: Option<ServiceMonitorTLSConfig>,
/// MetricRelabelings to apply to samples after scraping, but before ingestion.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub metric_relabelings: Vec<RelabelConfig>,
// ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
// ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
// ##
// # - action: keep
// # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
// # sourceLabels: [__name__]
pub metric_relabelings: Vec<Mapping>,
// ## RelabelConfigs to apply to samples before scraping
// ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api-reference/api.md#relabelconfig
// ##
// # - sourceLabels: [__meta_kubernetes_pod_node_name]
// # separator: ;
// # regex: ^(.*)$
// # targetLabel: nodename
// # replacement: $1
// # action: replace
pub relabelings: Vec<Mapping>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[serde(rename_all = "camelCase")]
pub struct RelabelConfig {
/// The action to perform based on the regex matching.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub action: Option<String>,
/// A list of labels from which to extract values.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub source_labels: Vec<String>,
/// Separator to be used when concatenating source_labels.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub separator: Option<String>,
/// The label to which the resulting value is written.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub target_label: Option<String>,
/// A regular expression to match against the concatenated source label values.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub regex: Option<String>,
/// The replacement value to use.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub replacement: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema)]
#[derive(Debug, Clone, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct MatchExpression {
pub key: String,
pub operator: Operator, // "In", "NotIn", "Exists", "DoesNotExist"
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub operator: Operator,
pub values: Vec<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
#[derive(Debug, Clone, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct Selector {
/// A map of key-value pairs to match.
#[serde(default, skip_serializing_if = "HashMap::is_empty")]
// # label selector for services
pub match_labels: HashMap<String, String>,
/// A list of label selector requirements.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub match_expressions: Vec<MatchExpression>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
#[derive(Debug, Clone, Serialize)]
#[serde(rename_all = "camelCase")]
pub struct ServiceMonitor {
pub name: String,
pub namespace: String,
// # Additional labels to set used for the ServiceMonitorSelector. Together with standard labels from the chart
pub additional_labels: Option<HashMap<String, String>>,
@@ -268,15 +252,10 @@ pub struct ServiceMonitor {
pub fallback_scrape_protocol: Option<String>,
}
#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
#[derive(Debug, Serialize, Clone)]
#[serde(rename_all = "camelCase")]
pub struct NamespaceSelector {
/// Select all namespaces.
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
pub any: bool,
/// List of namespace names to select from.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub match_names: Vec<String>,
}
@@ -284,6 +263,7 @@ impl Default for ServiceMonitor {
fn default() -> Self {
Self {
name: Default::default(),
namespace: Default::default(),
additional_labels: Default::default(),
job_label: Default::default(),
target_labels: Default::default(),
@@ -298,3 +278,19 @@ impl Default for ServiceMonitor {
}
}
}
impl Default for ServiceMonitorEndpoint {
fn default() -> Self {
Self {
port: Some("80".to_string()),
target_port: Default::default(),
bearer_token_file: Default::default(),
interval: Default::default(),
path: "/metrics".to_string(),
scheme: HTTPScheme::HTTP,
tls_config: Default::default(),
metric_relabelings: Default::default(),
relabelings: Default::default(),
}
}
}

View File

@@ -3,7 +3,7 @@ use std::str::FromStr;
use crate::modules::helm::chart::{HelmChartScore, HelmRepository};
pub fn ntfy_helm_chart_score(namespace: String, host: String) -> HelmChartScore {
pub fn ntfy_helm_chart_score(namespace: String) -> HelmChartScore {
let values = format!(
r#"
replicaCount: 1
@@ -28,12 +28,12 @@ service:
port: 80
ingress:
enabled: true
enabled: false
# annotations:
# kubernetes.io/ingress.class: nginx
# kubernetes.io/tls-acme: "true"
hosts:
- host: {host}
- host: ntfy.host.com
paths:
- path: /
pathType: ImplementationSpecific
@@ -58,7 +58,6 @@ config:
# web-root: "disable"
enable-signup: false
enable-login: "true"
enable-metrics: "true"
persistence:
enabled: true

View File

@@ -17,7 +17,6 @@ use crate::{
#[derive(Debug, Clone, Serialize)]
pub struct NtfyScore {
pub namespace: String,
pub host: String,
}
impl<T: Topology + HelmCommand + K8sclient> Score<T> for NtfyScore {
@@ -127,7 +126,7 @@ impl<T: Topology + HelmCommand + K8sclient> Interpret<T> for NtfyInterpret {
inventory: &Inventory,
topology: &T,
) -> Result<Outcome, InterpretError> {
ntfy_helm_chart_score(self.score.namespace.clone(), self.score.host.clone())
ntfy_helm_chart_score(self.score.namespace.clone())
.create_interpret()
.execute(inventory, topology)
.await?;

View File

@@ -1 +1,2 @@
pub mod prometheus_helm;
pub mod types;

View File

@@ -1,37 +1,145 @@
use std::collections::BTreeMap;
use std::str::FromStr;
use std::sync::{Arc, Mutex};
use log::debug;
use non_blank_string_rs::NonBlankString;
use serde_yaml::{Mapping, Value};
use crate::modules::{
helm::chart::HelmChartScore, monitoring::prometheus::prometheus_config::PrometheusConfig,
use crate::modules::helm::chart::HelmChartScore;
use crate::modules::monitoring::kube_prometheus::types::{
AlertGroup, AlertManager, AlertManagerConfig, AlertManagerRoute, AlertManagerSpec,
ConfigReloader, Limits, Requests, Resources,
};
use crate::modules::monitoring::prometheus::helm::types::{
AlertFile, EnabledConfig, KsmRbacConfig, KubeStateMetricsConfig, LabelSelector, Monitor,
Prometheus, PrometheusHelmValues, RbacConfig, ServerConfig, ServerRbacConfig,
};
use crate::modules::monitoring::prometheus::prometheus_config::HelmPrometheusConfig;
pub fn prometheus_helm_chart_score(config: Arc<Mutex<PrometheusConfig>>) -> HelmChartScore {
pub fn prometheus_helm_chart_score(config: Arc<Mutex<HelmPrometheusConfig>>) -> HelmChartScore {
let config = config.lock().unwrap();
let ns = config.namespace.clone().unwrap();
let values = format!(
r#"
rbac:
create: true
kube-state-metrics:
enabled: false
nodeExporter:
enabled: false
alertmanager:
enabled: false
pushgateway:
enabled: false
server:
serviceAccount:
create: false
rbac:
create: true
fullnameOverride: prometheus-{ns}
"#
let rbac_config = RbacConfig { create: false };
let ksm_config = KubeStateMetricsConfig {
enabled: true,
rbac: KsmRbacConfig {
use_cluster_role: false,
},
prometheus: Prometheus {
monitor: Monitor { enabled: true },
},
};
let mut selector_labels = BTreeMap::new();
selector_labels.insert("kubernetes.io/metadata.name".to_string(), ns.clone());
let mut kube_state_metrics_labels = BTreeMap::new();
kube_state_metrics_labels.insert(
"app.kubernetes.io/name".to_string(),
"kube-state-metrics".to_string(),
);
let selector = LabelSelector {
match_labels: selector_labels,
};
let server_config = ServerConfig {
namespaces: vec![ns.clone()],
use_existing_cluster_role_name: false,
};
let mut null_receiver = Mapping::new();
null_receiver.insert(
Value::String("receiver".to_string()),
Value::String("default-receiver".to_string()),
);
null_receiver.insert(
Value::String("matchers".to_string()),
Value::Sequence(vec![Value::String("alertname!=Watchdog".to_string())]),
);
null_receiver.insert(Value::String("continue".to_string()), Value::Bool(true));
let mut alert_manager_channel_config = AlertManagerConfig {
global: Mapping::new(),
route: AlertManagerRoute {
routes: vec![Value::Mapping(null_receiver)],
},
receivers: vec![serde_yaml::from_str("name: 'default-receiver'").unwrap()],
};
for receiver in config.alert_receiver_configs.iter() {
if let Some(global) = receiver.channel_global_config.clone() {
alert_manager_channel_config
.global
.insert(global.0, global.1);
}
alert_manager_channel_config
.route
.routes
.push(receiver.channel_route.clone());
alert_manager_channel_config
.receivers
.push(receiver.channel_receiver.clone());
}
let alert_manager_values = AlertManager {
enabled: config.alert_manager,
config: alert_manager_channel_config,
alertmanager_spec: AlertManagerSpec {
resources: Resources {
limits: Limits {
memory: "100Mi".to_string(),
cpu: "100m".to_string(),
},
requests: Requests {
memory: "100Mi".to_string(),
cpu: "100m".to_string(),
},
},
},
init_config_reloader: ConfigReloader {
resources: Resources {
limits: Limits {
memory: "100Mi".to_string(),
cpu: "100m".to_string(),
},
requests: Requests {
memory: "100Mi".to_string(),
cpu: "100m".to_string(),
},
},
},
};
let mut result: BTreeMap<String, AlertFile> = BTreeMap::new();
for rule in config.alert_rules.clone().iter() {
for (name, group) in &rule.rules {
result
.entry("alerting_rules.yml".to_string())
.and_modify(|e| e.groups.extend(group.groups.clone()))
.or_insert(AlertFile {
groups: group.groups.clone(),
});
}
}
let final_values = PrometheusHelmValues {
rbac: rbac_config,
kube_state_metrics: ksm_config,
server: server_config,
alertmanager: alert_manager_values,
server_files: result,
additional_service_monitors: config.additional_service_monitors.clone(),
prometheus_node_exporter: EnabledConfig { enabled: false },
prometheus_pushgateway: EnabledConfig { enabled: false },
};
let values_yaml =
serde_yaml::to_string(&final_values).expect("Failed to serialize final Helm values");
debug!("full values.yaml: \n{}", values_yaml);
HelmChartScore {
namespace: Some(NonBlankString::from_str(&config.namespace.clone().unwrap()).unwrap()),
namespace: Some(NonBlankString::from_str(&ns).unwrap()),
release_name: NonBlankString::from_str("prometheus").unwrap(),
chart_name: NonBlankString::from_str(
"oci://ghcr.io/prometheus-community/charts/prometheus",
@@ -39,7 +147,7 @@ fullnameOverride: prometheus-{ns}
.unwrap(),
chart_version: None,
values_overrides: None,
values_yaml: Some(values.to_string()),
values_yaml: Some(values_yaml),
create_namespace: true,
install_only: true,
repository: None,

View File

@@ -0,0 +1,94 @@
use std::collections::BTreeMap;
use serde::Serialize;
use crate::modules::monitoring::{alert_rule::prometheus_alert_rule::AlertManagerRuleGroup, kube_prometheus::types::{
AlertGroup, AlertManager, AlertManagerAdditionalPromRules, AlertManagerValues, ServiceMonitor
}};
#[derive(Debug, Clone, Serialize)]
pub struct RuleFilesConfig {
#[serde(rename = "ruleFiles")]
pub files: BTreeMap<String, AlertGroup>,
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct PrometheusHelmValues {
pub rbac: RbacConfig,
#[serde(rename = "kube-state-metrics")]
pub kube_state_metrics: KubeStateMetricsConfig,
pub server: ServerConfig,
pub alertmanager: AlertManager, // You already have this
#[serde(rename = "serverFiles")]
pub server_files: BTreeMap<String, AlertFile>, // You already have this
pub additional_service_monitors: Vec<ServiceMonitor>, // You already have this
#[serde(rename = "prometheus-node-exporter")]
pub prometheus_node_exporter: EnabledConfig,
#[serde(rename = "prometheus-pushgateway")]
pub prometheus_pushgateway: EnabledConfig,
}
#[derive(Serialize, Debug, Clone)]
pub struct AlertFile {
pub groups: Vec<AlertManagerRuleGroup>,
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct RbacConfig {
pub create: bool,
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct KubeStateMetricsConfig {
pub enabled: bool,
pub rbac: KsmRbacConfig,
pub prometheus: Prometheus,
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct Prometheus {
pub monitor: Monitor
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct Monitor{
pub enabled: bool
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct KsmRbacConfig {
pub use_cluster_role: bool,
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct ServerConfig {
pub namespaces: Vec<String>,
pub use_existing_cluster_role_name: bool,
}
#[derive(Serialize, Debug)]
#[serde(rename_all = "camelCase")]
pub struct ServerRbacConfig {
pub create: bool,
pub use_cluster_role: bool,
pub namespaced: bool,
}
#[derive(Serialize, Debug, Clone)]
#[serde(rename_all = "camelCase")]
pub struct LabelSelector {
#[serde(rename = "matchLabels")]
pub match_labels: BTreeMap<String, String>,
}
#[derive(Serialize, Debug)]
pub struct EnabledConfig {
pub enabled: bool,
}

View File

@@ -14,7 +14,7 @@ use crate::{
},
score::Score,
topology::{
HelmCommand, Topology,
HelmCommand, K8sclient, Topology,
installable::Installable,
oberservability::monitoring::{AlertReceiver, AlertRule, AlertSender},
tenant::TenantManager,
@@ -22,12 +22,12 @@ use crate::{
};
use super::{
helm::prometheus_helm::prometheus_helm_chart_score, prometheus_config::PrometheusConfig,
helm::prometheus_helm::prometheus_helm_chart_score, prometheus_config::HelmPrometheusConfig,
};
#[derive(Debug)]
pub struct Prometheus {
pub config: Arc<Mutex<PrometheusConfig>>,
pub config: Arc<Mutex<HelmPrometheusConfig>>,
}
#[async_trait]
@@ -40,18 +40,17 @@ impl AlertSender for Prometheus {
impl Prometheus {
pub fn new() -> Self {
Self {
config: Arc::new(Mutex::new(PrometheusConfig::new())),
config: Arc::new(Mutex::new(HelmPrometheusConfig::new())),
}
}
pub async fn configure_with_topology<T: TenantManager>(&self, topology: &T) {
let ns = topology
.get_tenant_config()
.await
.map(|cfg| cfg.name.clone())
.unwrap_or_else(|| "monitoring".to_string());
if let Some(cfg) = topology.get_tenant_config().await {
debug!("Overriding namespace with tenant config: {}", cfg.name);
self.config.lock().unwrap().namespace = Some(cfg.name.clone());
} else {
debug!("No tenant config found; keeping existing namespace.");
}
error!("This must be refactored, see comments in pr #74");
debug!("NS: {}", ns);
self.config.lock().unwrap().namespace = Some(ns);
}
pub async fn install_receiver(

View File

@@ -3,9 +3,8 @@ use crate::modules::monitoring::kube_prometheus::types::{
};
#[derive(Debug)]
pub struct PrometheusConfig {
pub struct HelmPrometheusConfig {
pub namespace: Option<String>,
pub default_rules: bool,
pub alert_manager: bool,
pub node_exporter: bool,
pub kube_state_metrics: bool,
@@ -16,11 +15,10 @@ pub struct PrometheusConfig {
pub additional_service_monitors: Vec<ServiceMonitor>,
}
impl PrometheusConfig {
impl HelmPrometheusConfig {
pub fn new() -> Self {
Self {
namespace: None,
default_rules: true,
alert_manager: true,
node_exporter: false,
kube_state_metrics: false,

View File

@@ -1,23 +0,0 @@
use std::collections::HashMap;
use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
pub fn alert_deployment_unavailable() -> PrometheusAlertRule {
PrometheusAlertRule {
alert: "DeploymentUnavailable".into(),
expr: "kube_deployment_status_replicas_unavailable > 0".into(),
r#for: Some("2m".into()),
labels: HashMap::from([("severity".into(), "warning".into())]),
annotations: HashMap::from([
(
"summary".into(),
"Deployment has unavailable replicas".into(),
),
(
"description".into(),
"A deployment in this namespace has unavailable replicas for over 2 minutes."
.into(),
),
]),
}
}

View File

@@ -1,37 +0,0 @@
use std::collections::HashMap;
use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
pub fn alert_high_memory_usage() -> PrometheusAlertRule {
PrometheusAlertRule {
alert: "HighMemoryUsage".into(),
expr: "container_memory_working_set_bytes{container!=\"\",namespace!=\"\"} > 500000000"
.into(),
r#for: Some("2m".into()),
labels: HashMap::from([("severity".into(), "warning".into())]),
annotations: HashMap::from([
("summary".into(), "Pod is using high memory".into()),
(
"description".into(),
"A pod is consuming more than 500Mi of memory.".into(),
),
]),
}
}
pub fn alert_high_cpu_usage() -> PrometheusAlertRule {
PrometheusAlertRule {
alert: "HighCPUUsage".into(),
expr: "rate(container_cpu_usage_seconds_total{container!=\"\",namespace!=\"\"}[1m]) > 0.9"
.into(),
r#for: Some("1m".into()),
labels: HashMap::from([("severity".into(), "warning".into())]),
annotations: HashMap::from([
("summary".into(), "Pod is using high CPU".into()),
(
"description".into(),
"A pod is using more than 90% of a core over 1 minute.".into(),
),
]),
}
}

View File

@@ -1,5 +1,2 @@
pub mod deployment;
pub mod memory_usage;
pub mod pod;
pub mod pvc;
pub mod service;
pub mod pod;

View File

@@ -1,55 +1,38 @@
use std::collections::HashMap;
use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
pub fn pod_failed() -> PrometheusAlertRule {
PrometheusAlertRule {
alert: "PodFailed".into(),
expr: "kube_pod_status_phase{phase=\"Failed\"} > 2".into(),
r#for: Some("2m".into()),
labels: HashMap::from([("severity".into(), "critical".into())]),
annotations: HashMap::from([
("summary".into(), "A pod has failed".into()),
(
"description".into(),
"One or more pods are in Failed phase.".into(),
),
]),
}
pub fn pod_in_failed_state() -> PrometheusAlertRule {
PrometheusAlertRule::new(
"PodInFailedState",
// This expression checks for any pod where the status phase is 'Failed' and the value is 1 (true).
"kube_pod_status_phase{phase=\"Failed\"} == 1",
)
.for_duration("1m") // Fire if the pod is in this state for 1 minute.
.label("severity", "critical") // A failed pod is a critical issue.
.annotation(
"summary",
"Pod {{ $labels.pod }} in namespace {{ $labels.namespace }} has failed.",
)
.annotation(
"description",
"The pod {{ $labels.pod }} in namespace {{ $labels.namespace }} has entered the 'Failed' state. This is a terminal error and the pod will not be automatically restarted. Please check the pod logs to diagnose the issue.",
)
}
pub fn alert_container_restarting() -> PrometheusAlertRule {
PrometheusAlertRule {
alert: "ContainerRestarting".into(),
expr: "increase(kube_pod_container_status_restarts_total[5m]) > 3".into(),
r#for: Some("5m".into()),
labels: HashMap::from([("severity".into(), "warning".into())]),
annotations: HashMap::from([
(
"summary".into(),
"Container is restarting frequently".into(),
),
(
"description".into(),
"A container in this namespace has restarted more than 3 times in 5 minutes."
.into(),
),
]),
}
}
pub fn alert_pod_not_ready() -> PrometheusAlertRule {
PrometheusAlertRule {
alert: "PodNotReady".into(),
expr: "kube_pod_status_ready{condition=\"true\"} == 0".into(),
r#for: Some("2m".into()),
labels: HashMap::from([("severity".into(), "warning".into())]),
annotations: HashMap::from([
("summary".into(), "Pod is not ready".into()),
(
"description".into(),
"A pod in the namespace is not reporting Ready status.".into(),
),
]),
}
pub fn pod_restarting_frequently() -> PrometheusAlertRule {
PrometheusAlertRule::new(
"PodRestartingFrequently",
// This expression calculates the increase in the restart count over the last 30 minutes.
// Alert if a container has restarted more than 5 times.
"increase(kube_pod_container_status_restarts_total[30m]) > 5",
)
.for_duration("15m") // The condition must persist for 15 minutes to avoid alerts for minor flaps.
.label("severity", "critical") // A crash-looping pod is effectively down.
.annotation(
"summary",
"Container {{ $labels.container }} in pod {{ $labels.pod }} is restarting frequently.",
)
.annotation(
"description",
"The container '{{ $labels.container }}' in pod '{{ $labels.pod }}' (namespace '{{ $labels.namespace }}') has restarted more than 5 times in the last 30 minutes. The pod is likely in a CrashLoopBackOff state.",
)
}

View File

@@ -1,19 +0,0 @@
use std::collections::HashMap;
use crate::modules::monitoring::alert_rule::prometheus_alert_rule::PrometheusAlertRule;
pub fn alert_service_down() -> PrometheusAlertRule {
PrometheusAlertRule {
alert: "ServiceDown".into(),
expr: "up == 0".into(),
r#for: Some("1m".into()),
labels: HashMap::from([("severity".into(), "critical".into())]),
annotations: HashMap::from([
("summary".into(), "Service is down".into()),
(
"description".into(),
"A target service in the namespace is not responding to Prometheus scrapes.".into(),
),
]),
}
}

View File

@@ -1,569 +0,0 @@
use std::fs;
use std::{collections::BTreeMap, sync::Arc};
use tempfile::tempdir;
use async_trait::async_trait;
use kube::api::ObjectMeta;
use log::{debug, info};
use serde::Serialize;
use std::process::Command;
use crate::modules::monitoring::kube_prometheus::crd::crd_alertmanager_config::CRDPrometheus;
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,
};
use crate::modules::monitoring::kube_prometheus::crd::crd_prometheus_rules::{
PrometheusRule, PrometheusRuleSpec, RuleGroup,
};
use crate::modules::monitoring::kube_prometheus::crd::grafana_default_dashboard::build_default_dashboard;
use crate::modules::monitoring::kube_prometheus::crd::service_monitor::{
ServiceMonitor, ServiceMonitorSpec,
};
use crate::topology::oberservability::monitoring::AlertReceiver;
use crate::topology::{K8sclient, Topology, k8s::K8sClient};
use crate::{
data::{Id, Version},
interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
inventory::Inventory,
modules::monitoring::kube_prometheus::crd::{
crd_alertmanagers::{Alertmanager, AlertmanagerSpec},
crd_prometheuses::{
AlertmanagerEndpoints, LabelSelector, Prometheus, PrometheusSpec,
PrometheusSpecAlerting,
},
role::{build_prom_role, build_prom_rolebinding, build_prom_service_account},
},
score::Score,
};
use super::prometheus::PrometheusApplicationMonitoring;
#[derive(Clone, Debug, Serialize)]
pub struct K8sPrometheusCRDAlertingScore {
pub sender: CRDPrometheus,
pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
pub service_monitors: Vec<ServiceMonitor>,
pub prometheus_rules: Vec<RuleGroup>,
}
impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Score<T>
for K8sPrometheusCRDAlertingScore
{
fn create_interpret(&self) -> Box<dyn crate::interpret::Interpret<T>> {
Box::new(K8sPrometheusCRDAlertingInterpret {
sender: self.sender.clone(),
receivers: self.receivers.clone(),
service_monitors: self.service_monitors.clone(),
prometheus_rules: self.prometheus_rules.clone(),
})
}
fn name(&self) -> String {
"CRDApplicationAlertingScore".into()
}
}
#[derive(Clone, Debug)]
pub struct K8sPrometheusCRDAlertingInterpret {
pub sender: CRDPrometheus,
pub receivers: Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
pub service_monitors: Vec<ServiceMonitor>,
pub prometheus_rules: Vec<RuleGroup>,
}
#[async_trait]
impl<T: Topology + K8sclient + PrometheusApplicationMonitoring<CRDPrometheus>> Interpret<T>
for K8sPrometheusCRDAlertingInterpret
{
async fn execute(
&self,
_inventory: &Inventory,
topology: &T,
) -> Result<Outcome, InterpretError> {
let client = topology.k8s_client().await.unwrap();
self.ensure_grafana_operator().await?;
self.install_prometheus(&client).await?;
self.install_alert_manager(&client).await?;
self.install_client_kube_metrics().await?;
self.install_grafana(&client).await?;
self.install_receivers(&self.sender, &self.receivers)
.await?;
self.install_rules(&self.prometheus_rules, &client).await?;
self.install_monitors(self.service_monitors.clone(), &client)
.await?;
Ok(Outcome::success(format!(
"deployed application monitoring composants"
)))
}
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!()
}
}
impl K8sPrometheusCRDAlertingInterpret {
async fn crd_exists(&self, crd: &str) -> bool {
let status = Command::new("sh")
.args(["-c", "kubectl get crd -A | grep -i", crd])
.status()
.map_err(|e| InterpretError::new(format!("could not connect to cluster: {}", e)))
.unwrap();
status.success()
}
async fn install_chart(
&self,
chart_path: String,
chart_name: String,
) -> Result<(), InterpretError> {
let temp_dir =
tempdir().map_err(|e| InterpretError::new(format!("Tempdir error: {}", e)))?;
let temp_path = temp_dir.path().to_path_buf();
debug!("Using temp directory: {}", temp_path.display());
let chart = format!("{}/{}", chart_path, chart_name);
let pull_output = Command::new("helm")
.args(["pull", &chart, "--destination", temp_path.to_str().unwrap()])
.output()
.map_err(|e| InterpretError::new(format!("Helm pull error: {}", e)))?;
if !pull_output.status.success() {
return Err(InterpretError::new(format!(
"Helm pull failed: {}",
String::from_utf8_lossy(&pull_output.stderr)
)));
}
let tgz_path = fs::read_dir(&temp_path)
.unwrap()
.filter_map(|entry| {
let entry = entry.ok()?;
let path = entry.path();
if path.extension()? == "tgz" {
Some(path)
} else {
None
}
})
.next()
.ok_or_else(|| InterpretError::new("Could not find pulled Helm chart".into()))?;
debug!("Installing chart from: {}", tgz_path.display());
let install_output = Command::new("helm")
.args([
"install",
&chart_name,
tgz_path.to_str().unwrap(),
"--namespace",
&self.sender.namespace.clone(),
"--create-namespace",
"--wait",
"--atomic",
])
.output()
.map_err(|e| InterpretError::new(format!("Helm install error: {}", e)))?;
if !install_output.status.success() {
return Err(InterpretError::new(format!(
"Helm install failed: {}",
String::from_utf8_lossy(&install_output.stderr)
)));
}
debug!(
"Installed chart {}/{} in namespace: {}",
&chart_path,
&chart_name,
self.sender.namespace.clone()
);
Ok(())
}
async fn ensure_grafana_operator(&self) -> Result<Outcome, InterpretError> {
if self.crd_exists("grafanas.grafana.integreatly.org").await {
debug!("grafana CRDs already exist — skipping install.");
return Ok(Outcome::success("Grafana CRDs already exist".to_string()));
}
let _ = Command::new("helm")
.args([
"repo",
"add",
"grafana-operator",
"https://grafana.github.io/helm-charts",
])
.output()
.unwrap();
let _ = Command::new("helm")
.args(["repo", "update"])
.output()
.unwrap();
let output = Command::new("helm")
.args([
"install",
"grafana-operator",
"grafana-operator/grafana-operator",
"--namespace",
&self.sender.namespace.clone(),
"--create-namespace",
"--set",
"namespaceScope=true",
])
.output()
.unwrap();
if !output.status.success() {
return Err(InterpretError::new(format!(
"helm install failed:\nstdout: {}\nstderr: {}",
String::from_utf8_lossy(&output.stdout),
String::from_utf8_lossy(&output.stderr)
)));
}
Ok(Outcome::success(format!(
"installed grafana operator in ns {}",
self.sender.namespace.clone()
)))
}
async fn install_prometheus(&self, client: &Arc<K8sClient>) -> Result<Outcome, InterpretError> {
debug!(
"installing crd-prometheuses in namespace {}",
self.sender.namespace.clone()
);
debug!("building role/rolebinding/serviceaccount for crd-prometheus");
let rolename = format!("{}-prom", self.sender.namespace.clone());
let sa_name = format!("{}-prom-sa", self.sender.namespace.clone());
let role = build_prom_role(rolename.clone(), self.sender.namespace.clone());
let rolebinding = build_prom_rolebinding(
rolename.clone(),
self.sender.namespace.clone(),
sa_name.clone(),
);
let sa = build_prom_service_account(sa_name.clone(), self.sender.namespace.clone());
let prom_spec = PrometheusSpec {
alerting: Some(PrometheusSpecAlerting {
alertmanagers: Some(vec![AlertmanagerEndpoints {
name: Some("alertmanager-operated".into()),
namespace: Some(self.sender.namespace.clone()),
port: Some("web".into()),
scheme: Some("http".into()),
}]),
}),
service_account_name: sa_name.clone(),
service_monitor_namespace_selector: Some(LabelSelector {
match_labels: BTreeMap::from([(
"kubernetes.io/metadata.name".to_string(),
self.sender.namespace.clone(),
)]),
match_expressions: vec![],
}),
service_monitor_selector: Some(LabelSelector {
match_labels: BTreeMap::from([("client".to_string(), "prometheus".to_string())]),
..Default::default()
}),
service_discovery_role: Some("Endpoints".into()),
pod_monitor_selector: Some(LabelSelector {
match_labels: BTreeMap::from([("client".to_string(), "prometheus".to_string())]),
..Default::default()
}),
rule_selector: Some(LabelSelector {
match_labels: BTreeMap::from([("role".to_string(), "prometheus-rule".to_string())]),
..Default::default()
}),
rule_namespace_selector: Some(LabelSelector {
match_labels: BTreeMap::from([(
"kubernetes.io/metadata.name".to_string(),
self.sender.namespace.clone(),
)]),
match_expressions: vec![],
}),
};
let prom = Prometheus {
metadata: ObjectMeta {
name: Some(self.sender.namespace.clone()),
labels: Some(std::collections::BTreeMap::from([
("alertmanagerConfig".to_string(), "enabled".to_string()),
("client".to_string(), "prometheus".to_string()),
])),
namespace: Some(self.sender.namespace.clone()),
..Default::default()
},
spec: prom_spec,
};
client
.apply(&role, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
info!(
"installed prometheus role: {:#?} in ns {:#?}",
role.metadata.name.unwrap(),
role.metadata.namespace.unwrap()
);
client
.apply(&rolebinding, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
info!(
"installed prometheus rolebinding: {:#?} in ns {:#?}",
rolebinding.metadata.name.unwrap(),
rolebinding.metadata.namespace.unwrap()
);
client
.apply(&sa, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
info!(
"installed prometheus service account: {:#?} in ns {:#?}",
sa.metadata.name.unwrap(),
sa.metadata.namespace.unwrap()
);
client
.apply(&prom, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
info!(
"installed prometheus: {:#?} in ns {:#?}",
&prom.metadata.name.clone().unwrap(),
&prom.metadata.namespace.clone().unwrap()
);
Ok(Outcome::success(format!(
"successfully deployed crd-prometheus {:#?}",
prom
)))
}
async fn install_alert_manager(
&self,
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let am = Alertmanager {
metadata: ObjectMeta {
name: Some(self.sender.namespace.clone()),
labels: Some(std::collections::BTreeMap::from([(
"alertmanagerConfig".to_string(),
"enabled".to_string(),
)])),
namespace: Some(self.sender.namespace.clone()),
..Default::default()
},
spec: AlertmanagerSpec::default(),
};
client
.apply(&am, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
Ok(Outcome::success(format!(
"successfully deployed service monitor {:#?}",
am.metadata.name
)))
}
async fn install_monitors(
&self,
mut monitors: Vec<ServiceMonitor>,
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let default_service_monitor = ServiceMonitor {
metadata: ObjectMeta {
name: Some(self.sender.namespace.clone()),
labels: Some(std::collections::BTreeMap::from([
("alertmanagerConfig".to_string(), "enabled".to_string()),
("client".to_string(), "prometheus".to_string()),
(
"app.kubernetes.io/name".to_string(),
"kube-state-metrics".to_string(),
),
])),
namespace: Some(self.sender.namespace.clone()),
..Default::default()
},
spec: ServiceMonitorSpec::default(),
};
monitors.push(default_service_monitor);
for monitor in monitors.iter() {
client
.apply(monitor, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
}
Ok(Outcome::success(
"succesfully deployed service monitors".to_string(),
))
}
async fn install_rules(
&self,
rules: &Vec<RuleGroup>,
client: &Arc<K8sClient>,
) -> Result<Outcome, InterpretError> {
let mut prom_rule_spec = PrometheusRuleSpec {
groups: rules.clone(),
};
let default_rules_group = RuleGroup {
name: format!("default-rules"),
rules: build_default_application_rules(),
};
prom_rule_spec.groups.push(default_rules_group);
let prom_rules = PrometheusRule {
metadata: ObjectMeta {
name: Some(self.sender.namespace.clone()),
labels: Some(std::collections::BTreeMap::from([
("alertmanagerConfig".to_string(), "enabled".to_string()),
("role".to_string(), "prometheus-rule".to_string()),
])),
namespace: Some(self.sender.namespace.clone()),
..Default::default()
},
spec: prom_rule_spec,
};
client
.apply(&prom_rules, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
Ok(Outcome::success(format!(
"successfully deployed rules {:#?}",
prom_rules.metadata.name
)))
}
async fn install_client_kube_metrics(&self) -> Result<Outcome, InterpretError> {
self.install_chart(
"oci://hub.nationtech.io/harmony".to_string(),
"nt-kube-metrics".to_string(),
)
.await?;
Ok(Outcome::success(format!(
"Installed client kube metrics in ns {}",
&self.sender.namespace.clone()
)))
}
async fn install_grafana(&self, client: &Arc<K8sClient>) -> Result<Outcome, InterpretError> {
let mut label = BTreeMap::new();
label.insert("dashboards".to_string(), "grafana".to_string());
let labels = LabelSelector {
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 = build_default_dashboard(&namespace);
let graf_data_source = GrafanaDatasource {
metadata: ObjectMeta {
name: Some(format!(
"grafana-datasource-{}",
self.sender.namespace.clone()
)),
namespace: Some(self.sender.namespace.clone()),
..Default::default()
},
spec: GrafanaDatasourceSpec {
instance_selector: labels.clone(),
allow_cross_namespace_import: Some(false),
datasource: GrafanaDatasourceConfig {
access: "proxy".to_string(),
database: Some("prometheus".to_string()),
json_data: Some(json_data),
//this is fragile
name: format!("prometheus-{}-0", self.sender.namespace.clone()),
r#type: "prometheus".to_string(),
url: format!(
"http://prometheus-operated.{}.svc.cluster.local:9090",
self.sender.namespace.clone()
),
},
},
};
client
.apply(&graf_data_source, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
let graf_dashboard = GrafanaDashboard {
metadata: ObjectMeta {
name: Some(format!(
"grafana-dashboard-{}",
self.sender.namespace.clone()
)),
namespace: Some(self.sender.namespace.clone()),
..Default::default()
},
spec: GrafanaDashboardSpec {
resync_period: Some("30s".to_string()),
instance_selector: labels.clone(),
json,
},
};
client
.apply(&graf_dashboard, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
let grafana = Grafana {
metadata: ObjectMeta {
name: Some(format!("grafana-{}", self.sender.namespace.clone())),
namespace: Some(self.sender.namespace.clone()),
labels: Some(label.clone()),
..Default::default()
},
spec: GrafanaSpec {
config: None,
admin_user: None,
admin_password: None,
ingress: None,
persistence: None,
resources: None,
},
};
client
.apply(&grafana, Some(&self.sender.namespace.clone()))
.await
.map_err(|e| InterpretError::new(e.to_string()))?;
Ok(Outcome::success(format!(
"successfully deployed grafana instance {:#?}",
grafana.metadata.name
)))
}
async fn install_receivers(
&self,
sender: &CRDPrometheus,
receivers: &Vec<Box<dyn AlertReceiver<CRDPrometheus>>>,
) -> Result<Outcome, InterpretError> {
for receiver in receivers.iter() {
receiver.install(sender).await.map_err(|err| {
InterpretError::new(format!("failed to install receiver: {}", err))
})?;
}
Ok(Outcome::success("successfully deployed receivers".into()))
}
}

View File

@@ -1,3 +1 @@
pub mod alerts;
pub mod k8s_prometheus_alerting_score;
pub mod prometheus;

View File

@@ -1,17 +0,0 @@
use async_trait::async_trait;
use crate::{
interpret::{InterpretError, Outcome},
inventory::Inventory,
topology::oberservability::monitoring::{AlertReceiver, AlertSender},
};
#[async_trait]
pub trait PrometheusApplicationMonitoring<S: AlertSender> {
async fn install_prometheus(
&self,
sender: &S,
inventory: &Inventory,
receivers: Option<Vec<Box<dyn AlertReceiver<S>>>>,
) -> Result<Outcome, InterpretError>;
}

View File

@@ -13,11 +13,6 @@ harmony_tui = { path = "../harmony_tui", optional = true }
inquire.workspace = true
tokio.workspace = true
env_logger.workspace = true
console = "0.16.0"
indicatif = "0.18.0"
lazy_static = "1.5.0"
log.workspace = true
indicatif-log-bridge = "0.2.3"
[features]

View File

@@ -1,116 +0,0 @@
use harmony::instrumentation::{self, HarmonyEvent};
use indicatif::{MultiProgress, ProgressBar};
use indicatif_log_bridge::LogWrapper;
use std::{
collections::{HashMap, hash_map},
sync::{Arc, Mutex},
};
use crate::progress;
pub fn init() -> tokio::task::JoinHandle<()> {
configure_logger();
let handle = tokio::spawn(handle_events());
loop {
if instrumentation::instrument(HarmonyEvent::HarmonyStarted).is_ok() {
break;
}
}
handle
}
fn configure_logger() {
let logger =
env_logger::Builder::from_env(env_logger::Env::default().default_filter_or("info")).build();
let level = logger.filter();
let multi = MultiProgress::new();
LogWrapper::new(multi.clone(), logger).try_init().unwrap();
log::set_max_level(level);
}
async fn handle_events() {
instrumentation::subscribe("Harmony CLI Logger", {
let sections: Arc<Mutex<HashMap<String, MultiProgress>>> =
Arc::new(Mutex::new(HashMap::new()));
let progress_bars: Arc<Mutex<HashMap<String, ProgressBar>>> =
Arc::new(Mutex::new(HashMap::new()));
move |event| {
let sections_clone = Arc::clone(&sections);
let progress_bars_clone = Arc::clone(&progress_bars);
async move {
let mut sections = sections_clone.lock().unwrap();
let mut progress_bars = progress_bars_clone.lock().unwrap();
match event {
HarmonyEvent::HarmonyStarted => {}
HarmonyEvent::PrepareTopologyStarted { topology: name } => {
let section = progress::new_section(format!(
"{} Preparing environment: {name}...",
crate::theme::EMOJI_TOPOLOGY,
));
(*sections).insert(name, section);
}
HarmonyEvent::TopologyPrepared {
topology: name,
outcome,
} => {
let section = (*sections).get(&name).unwrap();
let progress = progress::add_spinner(section, "".into());
match outcome.status {
harmony::interpret::InterpretStatus::SUCCESS => {
progress::success(section, Some(progress), outcome.message);
}
harmony::interpret::InterpretStatus::FAILURE => {
progress::error(section, Some(progress), outcome.message);
}
harmony::interpret::InterpretStatus::RUNNING => todo!(),
harmony::interpret::InterpretStatus::QUEUED => todo!(),
harmony::interpret::InterpretStatus::BLOCKED => todo!(),
harmony::interpret::InterpretStatus::NOOP => {
progress::skip(section, Some(progress), outcome.message);
}
}
}
HarmonyEvent::InterpretExecutionStarted {
interpret: name,
topology,
message,
} => {
let section = (*sections).get(&topology).unwrap();
let progress_bar = progress::add_spinner(section, message);
(*progress_bars).insert(name, progress_bar);
}
HarmonyEvent::InterpretExecutionFinished {
topology,
interpret: name,
outcome,
} => {
let section = (*sections).get(&topology).unwrap();
let progress_bar = (*progress_bars).get(&name).cloned();
let _ = section.clear();
match outcome {
Ok(outcome) => {
progress::success(section, progress_bar, outcome.message);
}
Err(err) => {
progress::error(section, progress_bar, err.to_string());
}
}
(*progress_bars).remove(&name);
}
}
true
}
}
})
.await;
}

View File

@@ -1,14 +1,8 @@
use clap::Parser;
use clap::builder::ArgPredicate;
use harmony::inventory::Inventory;
use harmony::maestro::Maestro;
use harmony;
use harmony::{score::Score, topology::Topology};
use inquire::Confirm;
use log::debug;
pub mod cli_logger; // FIXME: Don't make me pub
pub mod progress;
pub mod theme;
#[cfg(feature = "tui")]
use harmony_tui;
@@ -86,24 +80,7 @@ fn list_scores_with_index<T: Topology>(scores_vec: &Vec<Box<dyn Score<T>>>) -> S
return display_str;
}
pub async fn run<T: Topology + Send + Sync + 'static>(
inventory: Inventory,
topology: T,
scores: Vec<Box<dyn Score<T>>>,
args_struct: Option<Args>,
) -> Result<(), Box<dyn std::error::Error>> {
let cli_logger_handle = cli_logger::init();
let mut maestro = Maestro::initialize(inventory, topology).await.unwrap();
maestro.register_all(scores);
let result = init(maestro, args_struct).await;
let _ = tokio::try_join!(cli_logger_handle);
result
}
async fn init<T: Topology + Send + Sync + 'static>(
pub async fn init<T: Topology + Send + Sync + 'static>(
maestro: harmony::maestro::Maestro<T>,
args_struct: Option<Args>,
) -> Result<(), Box<dyn std::error::Error>> {
@@ -157,7 +134,7 @@ async fn init<T: Topology + Send + Sync + 'static>(
// Run filtered scores
for s in scores_vec {
debug!("Running: {}", s.name());
println!("Running: {}", s.name());
maestro.interpret(s).await?;
}

View File

@@ -1,50 +0,0 @@
use std::time::Duration;
use indicatif::{MultiProgress, ProgressBar};
pub fn new_section(title: String) -> MultiProgress {
let multi_progress = MultiProgress::new();
let _ = multi_progress.println(title);
multi_progress
}
pub fn add_spinner(multi_progress: &MultiProgress, message: String) -> ProgressBar {
let progress = multi_progress.add(ProgressBar::new_spinner());
progress.set_style(crate::theme::SPINNER_STYLE.clone());
progress.set_message(message);
progress.enable_steady_tick(Duration::from_millis(100));
progress
}
pub fn success(multi_progress: &MultiProgress, progress: Option<ProgressBar>, message: String) {
if let Some(progress) = progress {
multi_progress.remove(&progress)
}
let progress = multi_progress.add(ProgressBar::new_spinner());
progress.set_style(crate::theme::SUCCESS_SPINNER_STYLE.clone());
progress.finish_with_message(message);
}
pub fn error(multi_progress: &MultiProgress, progress: Option<ProgressBar>, message: String) {
if let Some(progress) = progress {
multi_progress.remove(&progress)
}
let progress = multi_progress.add(ProgressBar::new_spinner());
progress.set_style(crate::theme::ERROR_SPINNER_STYLE.clone());
progress.finish_with_message(message);
}
pub fn skip(multi_progress: &MultiProgress, progress: Option<ProgressBar>, message: String) {
if let Some(progress) = progress {
multi_progress.remove(&progress)
}
let progress = multi_progress.add(ProgressBar::new_spinner());
progress.set_style(crate::theme::SKIP_SPINNER_STYLE.clone());
progress.finish_with_message(message);
}

View File

@@ -1,26 +0,0 @@
use console::Emoji;
use indicatif::ProgressStyle;
use lazy_static::lazy_static;
pub static EMOJI_HARMONY: Emoji<'_, '_> = Emoji("🎼", "");
pub static EMOJI_SUCCESS: Emoji<'_, '_> = Emoji("", "");
pub static EMOJI_SKIP: Emoji<'_, '_> = Emoji("⏭️", "");
pub static EMOJI_ERROR: Emoji<'_, '_> = Emoji("⚠️", "");
pub static EMOJI_DEPLOY: Emoji<'_, '_> = Emoji("🚀", "");
pub static EMOJI_TOPOLOGY: Emoji<'_, '_> = Emoji("📦", "");
lazy_static! {
pub static ref SPINNER_STYLE: ProgressStyle = ProgressStyle::default_spinner()
.template(" {spinner:.green} {msg}")
.unwrap()
.tick_strings(&["", "", "", "", "", "", "", "", "", ""]);
pub static ref SUCCESS_SPINNER_STYLE: ProgressStyle = SPINNER_STYLE
.clone()
.tick_strings(&[format!("{}", EMOJI_SUCCESS).as_str()]);
pub static ref SKIP_SPINNER_STYLE: ProgressStyle = SPINNER_STYLE
.clone()
.tick_strings(&[format!("{}", EMOJI_SKIP).as_str()]);
pub static ref ERROR_SPINNER_STYLE: ProgressStyle = SPINNER_STYLE
.clone()
.tick_strings(&[format!("{}", EMOJI_ERROR).as_str()]);
}

View File

@@ -15,9 +15,3 @@ current_platform = "0.2.0"
futures-util = "0.3.31"
serde_json = "1.0.140"
cargo_metadata = "0.20.0"
indicatif = "0.18.0"
console = "0.16.0"
lazy_static = "1.5.0"
once_cell = "1.21.3"
harmony_cli = { path = "../harmony_cli" }
indicatif-log-bridge = "0.2.3"

View File

@@ -1,112 +0,0 @@
use indicatif::{MultiProgress, ProgressBar};
use indicatif_log_bridge::LogWrapper;
use log::error;
use std::{
collections::HashMap,
sync::{Arc, Mutex},
};
use crate::instrumentation::{self, HarmonyComposerEvent};
pub fn init() -> tokio::task::JoinHandle<()> {
configure_logger();
let handle = tokio::spawn(handle_events());
loop {
if instrumentation::instrument(HarmonyComposerEvent::HarmonyComposerStarted).is_ok() {
break;
}
}
handle
}
fn configure_logger() {
let logger =
env_logger::Builder::from_env(env_logger::Env::default().default_filter_or("info")).build();
let level = logger.filter();
let multi = MultiProgress::new();
LogWrapper::new(multi.clone(), logger).try_init().unwrap();
log::set_max_level(level);
}
pub async fn handle_events() {
const PROGRESS_SETUP: &str = "project-initialization";
const PROGRESS_DEPLOYMENT: &str = "deployment";
instrumentation::subscribe("Harmony Composer Logger", {
let progresses: Arc<Mutex<HashMap<String, MultiProgress>>> =
Arc::new(Mutex::new(HashMap::new()));
let compilation_progress = Arc::new(Mutex::new(None::<ProgressBar>));
move |event| {
let progresses_clone = Arc::clone(&progresses);
let compilation_progress_clone = Arc::clone(&compilation_progress);
async move {
let mut progresses_guard = progresses_clone.lock().unwrap();
let mut compilation_progress_guard = compilation_progress_clone.lock().unwrap();
match event {
HarmonyComposerEvent::HarmonyComposerStarted => {}
HarmonyComposerEvent::ProjectInitializationStarted => {
let multi_progress = harmony_cli::progress::new_section(format!(
"{} Initializing Harmony project...",
harmony_cli::theme::EMOJI_HARMONY,
));
(*progresses_guard).insert(PROGRESS_SETUP.to_string(), multi_progress);
}
HarmonyComposerEvent::ProjectInitialized => println!("\n"),
HarmonyComposerEvent::ProjectCompilationStarted { details } => {
let initialization_progress =
(*progresses_guard).get(PROGRESS_SETUP).unwrap();
let _ = initialization_progress.clear();
let progress =
harmony_cli::progress::add_spinner(initialization_progress, details);
*compilation_progress_guard = Some(progress);
}
HarmonyComposerEvent::ProjectCompiled => {
let initialization_progress =
(*progresses_guard).get(PROGRESS_SETUP).unwrap();
harmony_cli::progress::success(
initialization_progress,
(*compilation_progress_guard).take(),
"project compiled".to_string(),
);
}
HarmonyComposerEvent::ProjectCompilationFailed { details } => {
let initialization_progress =
(*progresses_guard).get(PROGRESS_SETUP).unwrap();
harmony_cli::progress::error(
initialization_progress,
(*compilation_progress_guard).take(),
"failed to compile project".to_string(),
);
error!("{details}");
}
HarmonyComposerEvent::DeploymentStarted { target } => {
let multi_progress = harmony_cli::progress::new_section(format!(
"{} Starting deployment to {target}...\n\n",
harmony_cli::theme::EMOJI_DEPLOY
));
(*progresses_guard).insert(PROGRESS_DEPLOYMENT.to_string(), multi_progress);
}
HarmonyComposerEvent::DeploymentCompleted { details } => println!("\n"),
HarmonyComposerEvent::Shutdown => {
for (_, progresses) in (*progresses_guard).iter() {
progresses.clear().unwrap();
}
return false;
}
}
true
}
}
})
.await
}

View File

@@ -1,53 +0,0 @@
use log::debug;
use once_cell::sync::Lazy;
use tokio::sync::broadcast;
#[derive(Debug, Clone)]
pub enum HarmonyComposerEvent {
HarmonyComposerStarted,
ProjectInitializationStarted,
ProjectInitialized,
ProjectCompilationStarted { details: String },
ProjectCompiled,
ProjectCompilationFailed { details: String },
DeploymentStarted { target: String },
DeploymentCompleted { details: String },
Shutdown,
}
static HARMONY_COMPOSER_EVENT_BUS: Lazy<broadcast::Sender<HarmonyComposerEvent>> =
Lazy::new(|| {
// TODO: Adjust channel capacity
let (tx, _rx) = broadcast::channel(16);
tx
});
pub fn instrument(event: HarmonyComposerEvent) -> Result<(), &'static str> {
match HARMONY_COMPOSER_EVENT_BUS.send(event) {
Ok(_) => Ok(()),
Err(_) => Err("send error: no subscribers"),
}
}
pub async fn subscribe<F, Fut>(name: &str, mut handler: F)
where
F: FnMut(HarmonyComposerEvent) -> Fut + Send + 'static,
Fut: Future<Output = bool> + Send,
{
let mut rx = HARMONY_COMPOSER_EVENT_BUS.subscribe();
debug!("[{name}] Service started. Listening for events...");
loop {
match rx.recv().await {
Ok(event) => {
if !handler(event).await {
debug!("[{name}] Handler requested exit.");
break;
}
}
Err(broadcast::error::RecvError::Lagged(n)) => {
debug!("[{name}] Lagged behind by {n} messages.");
}
Err(_) => break,
}
}
}

View File

@@ -7,16 +7,12 @@ use bollard::secret::HostConfig;
use cargo_metadata::{Artifact, Message, MetadataCommand};
use clap::{Args, Parser, Subcommand};
use futures_util::StreamExt;
use instrumentation::HarmonyComposerEvent;
use log::{debug, info, log_enabled};
use log::info;
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use std::process::{Command, Stdio};
use tokio::fs;
mod harmony_composer_logger;
mod instrumentation;
#[derive(Parser)]
#[command(version, about, long_about = None, flatten_help = true, propagate_version = true)]
struct GlobalArgs {
@@ -70,15 +66,13 @@ struct AllArgs {
#[tokio::main]
async fn main() {
let hc_logger_handle = harmony_composer_logger::init();
env_logger::init();
let cli_args = GlobalArgs::parse();
let harmony_path = Path::new(&cli_args.harmony_path)
.try_exists()
.expect("couldn't check if path exists");
instrumentation::instrument(HarmonyComposerEvent::ProjectInitializationStarted).unwrap();
let harmony_bin_path: PathBuf = match harmony_path {
true => {
compile_harmony(
@@ -91,8 +85,6 @@ async fn main() {
false => todo!("implement autodetect code"),
};
instrumentation::instrument(HarmonyComposerEvent::ProjectInitialized).unwrap();
match cli_args.command {
Some(command) => match command {
Commands::Check(args) => {
@@ -106,9 +98,7 @@ async fn main() {
.expect("couldn't check if path exists")
{
true => (),
false => todo!(
"path {check_script_str} not found. Other paths currently unsupported."
),
false => todo!("implement couldn't find path logic"),
};
let check_output = Command::new(check_script)
@@ -124,31 +114,19 @@ async fn main() {
}
Commands::Deploy(args) => {
let deploy = if args.staging {
instrumentation::instrument(HarmonyComposerEvent::DeploymentStarted {
target: "staging".to_string(),
})
.unwrap();
todo!("implement staging deployment")
} else if args.prod {
instrumentation::instrument(HarmonyComposerEvent::DeploymentStarted {
target: "prod".to_string(),
})
.unwrap();
todo!("implement prod deployment")
} else {
instrumentation::instrument(HarmonyComposerEvent::DeploymentStarted {
target: "dev".to_string(),
})
.unwrap();
Command::new(harmony_bin_path).arg("-y").arg("-a").spawn()
}
.expect("failed to run harmony deploy");
let deploy_output = deploy.wait_with_output().unwrap();
instrumentation::instrument(HarmonyComposerEvent::DeploymentCompleted {
details: String::from_utf8(deploy_output.stdout).unwrap(),
})
.unwrap();
println!(
"deploy output: {}",
String::from_utf8(deploy_output.stdout).expect("couldn't parse from utf8")
);
}
Commands::All(_args) => todo!(
"take all previous match arms and turn them into separate functions, and call them all one after the other"
@@ -157,10 +135,6 @@ async fn main() {
},
None => todo!("run interactively, ask for info on CLI"),
}
instrumentation::instrument(HarmonyComposerEvent::Shutdown).unwrap();
let _ = tokio::try_join!(hc_logger_handle);
}
#[derive(Clone, Debug, clap::ValueEnum)]
@@ -181,7 +155,6 @@ async fn compile_harmony(
let cargo_exists = Command::new("which")
.arg("cargo")
.stdout(Stdio::null())
.status()
.expect("couldn't get `which cargo` status")
.success();
@@ -190,32 +163,17 @@ async fn compile_harmony(
Some(m) => m,
None => {
if cargo_exists {
CompileMethod::LocalCargo
return compile_cargo(platform, harmony_location).await;
} else {
CompileMethod::Docker
return compile_docker(platform, harmony_location).await;
}
}
};
let path = match method {
CompileMethod::LocalCargo => {
instrumentation::instrument(HarmonyComposerEvent::ProjectCompilationStarted {
details: "compiling project with cargo".to_string(),
})
.unwrap();
compile_cargo(platform, harmony_location).await
}
CompileMethod::Docker => {
instrumentation::instrument(HarmonyComposerEvent::ProjectCompilationStarted {
details: "compiling project with docker".to_string(),
})
.unwrap();
compile_docker(platform, harmony_location).await
}
match method {
CompileMethod::LocalCargo => return compile_cargo(platform, harmony_location).await,
CompileMethod::Docker => return compile_docker(platform, harmony_location).await,
};
instrumentation::instrument(HarmonyComposerEvent::ProjectCompiled).unwrap();
path
}
// TODO: make sure this works with cargo workspaces
@@ -225,12 +183,6 @@ async fn compile_cargo(platform: String, harmony_location: String) -> PathBuf {
.exec()
.unwrap();
let stderr = if log_enabled!(log::Level::Debug) {
Stdio::inherit()
} else {
Stdio::piped()
};
let mut cargo_build = Command::new("cargo")
.current_dir(&harmony_location)
.args(vec![
@@ -240,7 +192,6 @@ async fn compile_cargo(platform: String, harmony_location: String) -> PathBuf {
"--message-format=json-render-diagnostics",
])
.stdout(Stdio::piped())
.stderr(stderr)
.spawn()
.expect("run cargo command failed");
@@ -256,20 +207,18 @@ async fn compile_cargo(platform: String, harmony_location: String) -> PathBuf {
.expect("failed to get root package")
.manifest_path
{
debug!("{:?}", artifact);
println!("{:?}", artifact);
artifacts.push(artifact);
}
}
Message::BuildScriptExecuted(_script) => (),
Message::BuildFinished(finished) => {
debug!("{:?}", finished);
println!("{:?}", finished);
}
_ => (), // Unknown message
}
}
cargo_build.wait().expect("run cargo command failed");
let bin = artifacts
.last()
.expect("no binaries built")
@@ -285,8 +234,7 @@ async fn compile_cargo(platform: String, harmony_location: String) -> PathBuf {
bin_out = PathBuf::from(format!("{}/harmony", harmony_location));
let _copy_res = fs::copy(&bin, &bin_out).await;
}
bin_out
return bin_out;
}
async fn compile_docker(platform: String, harmony_location: String) -> PathBuf {

View File

@@ -2,7 +2,7 @@ mod downloadable_asset;
use downloadable_asset::*;
use kube::Client;
use log::{debug, warn};
use log::{debug, info, warn};
use std::path::PathBuf;
const K3D_BIN_FILE_NAME: &str = "k3d";
@@ -90,7 +90,7 @@ impl K3d {
let latest_release = self.get_latest_release_tag().await.unwrap();
let release_binary = self.get_binary_for_current_platform(latest_release).await;
debug!("Foudn K3d binary to install : {release_binary:#?}");
info!("Foudn K3d binary to install : {release_binary:#?}");
release_binary.download_to_path(self.base_dir.clone()).await
}
@@ -175,7 +175,7 @@ impl K3d {
Err(_) => return Err("Could not get cluster_name, cannot initialize".to_string()),
};
debug!("Initializing k3d cluster '{}'", cluster_name);
info!("Initializing k3d cluster '{}'", cluster_name);
self.create_cluster(cluster_name)?;
self.create_kubernetes_client().await
@@ -205,7 +205,7 @@ impl K3d {
/// - `Err(String)` - Error message if any step failed
pub async fn ensure_installed(&self) -> Result<Client, String> {
if !self.is_installed() {
debug!("K3d is not installed, downloading latest release");
info!("K3d is not installed, downloading latest release");
self.download_latest_release()
.await
.map_err(|e| format!("Failed to download k3d: {}", e))?;
@@ -216,13 +216,13 @@ impl K3d {
}
if !self.is_cluster_initialized() {
debug!("Cluster is not initialized, initializing now");
info!("Cluster is not initialized, initializing now");
return self.initialize_cluster().await;
}
self.start_cluster().await?;
debug!("K3d and cluster are already properly set up");
info!("K3d and cluster are already properly set up");
self.create_kubernetes_client().await
}
@@ -325,12 +325,12 @@ impl K3d {
return Err(format!("Failed to create cluster: {}", stderr));
}
debug!("Successfully created k3d cluster '{}'", cluster_name);
info!("Successfully created k3d cluster '{}'", cluster_name);
Ok(())
}
async fn create_kubernetes_client(&self) -> Result<Client, String> {
// TODO: Connect the client to the right k3d cluster (see https://git.nationtech.io/NationTech/harmony/issues/92)
warn!("TODO this method is way too dumb, it should make sure that the client is connected to the k3d cluster actually represented by this instance, not just any default client");
Client::try_default()
.await
.map_err(|e| format!("Failed to create Kubernetes client: {}", e))
@@ -352,7 +352,7 @@ impl K3d {
return Err(format!("Failed to start cluster: {}", stderr));
}
debug!("Successfully started k3d cluster '{}'", cluster_name);
info!("Successfully started k3d cluster '{}'", cluster_name);
Ok(())
}
}

View File

@@ -22,4 +22,4 @@ tokio-util = { version = "0.7.13", features = [ "codec" ] }
tokio-stream = "0.1.17"
[dev-dependencies]
pretty_assertions.workspace = true
pretty_assertions = "1.4.1"