ppetru/alo-cluster
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Refactor common modules.

Browse Source
This commit is contained in:
Petru
2025-10-24 15:34:31 +01:00
parent e5cd9bd98e
commit 53ef2f6293
17 changed files with 262 additions and 219 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
CLAUDE.md
View File

@@ -7,16 +7,22 @@ NixOS cluster configuration using flakes. Homelab infrastructure with Nomad/Cons
```
├── common/
│ ├── global/ # Applied to all hosts (backup, sops, users, etc.)
│ ├── compute-node.nix # Nomad client + Consul agent + NFS client
│ ├── cluster-node.nix # Nomad server + Consul server (for quorum members)
│ ├── minimal-node.nix # Base (ssh, user, boot, impermanence)
│ ├── cluster-member.nix # Consul + storage clients (NFS/CIFS/GlusterFS)
│ ├── nomad-worker.nix # Nomad client (runs jobs) + Docker + NFS deps
│ ├── nomad-server.nix # Enables Consul + Nomad server mode
│ ├── cluster-tools.nix # Just CLI tools (nomad, wander, damon)
│ ├── workstation-node.nix # Dev tools (wget, deploy-rs, docker, nix-ld)
│ ├── desktop-node.nix # Hyprland + GUI environment
│ ├── nfs-services-server.nix # NFS server + btrfs replication (zippy)
│ └── nfs-services-standby.nix # NFS standby + receive replication (c1, c2)
│ └── nfs-services-standby.nix # NFS standby + receive replication (c1)
├── hosts/
│ ├── c1/, c2/, c3/ # Cattle nodes (compute, quorum members)
│ ├── zippy/ # Primary storage + NFS server + stateful workloads
│ ├── c1/, c2/, c3/ # Cattle nodes (quorum + workers)
│ ├── zippy/ # Primary storage + NFS server + worker (not quorum)
│ ├── chilly/ # Home Assistant VM + cluster member (Consul only)
│ ├── sparky/ # Desktop + cluster member (Consul only)
│ ├── fractal/ # (Proxmox, will become NixOS storage node)
│ ├── sunny/ # (Standalone ethereum node, not in cluster)
│ └── chilly/ # (Home Assistant VM, not in cluster)
│ └── sunny/ # (Standalone ethereum node, not in cluster)
├── docs/
│ ├── CLUSTER_REVAMP.md # Master plan for architecture changes
│ ├── MIGRATION_TODO.md # Tracking checklist for migration
@@ -35,11 +41,32 @@ NixOS cluster configuration using flakes. Homelab infrastructure with Nomad/Cons
- `/data/shared` - CIFS from fractal (existing, unchanged)
### Hosts
- **c1, c2, c3**: Cattle nodes, run most workloads, Nomad/Consul quorum
- **zippy**: Primary NFS server, runs databases (affinity), replicates to c1 every 5min
- **c1, c2, c3**: Cattle nodes, run most workloads, Nomad/Consul quorum members
- **zippy**: Primary NFS server, runs workloads (affinity), NOT quorum, replicates to c1 every 5min
- **chilly**: Home Assistant VM, cluster member (Consul agent + CLI tools), no workloads
- **sparky**: Desktop/laptop, cluster member (Consul agent + CLI tools), no workloads
- **fractal**: Storage node (Proxmox/ZFS), will join quorum after GlusterFS removed
- **sunny**: Standalone ethereum staking node
- **chilly**: Home Assistant VM
- **sunny**: Standalone ethereum staking node (not in cluster)
## Config Architecture
**Modular role-based configs** (compose as needed):
- `minimal-node.nix` - Base for all systems (SSH, user, boot, impermanence)
- `cluster-member.nix` - Consul agent + shared storage mounts (no Nomad)
- `nomad-worker.nix` - Nomad client to run jobs (requires cluster-member)
- `nomad-server.nix` - Enables Consul + Nomad server mode (for quorum members)
- `cluster-tools.nix` - Just CLI tools (no services)
**Machine type configs** (via flake profile):
- `workstation-node.nix` - Dev tools (deploy-rs, docker, nix-ld, emulation)
- `desktop-node.nix` - Extends workstation + Hyprland/GUI
**Host composition examples**:
- c1/c2/c3: `cluster-member + nomad-worker + nomad-server` (quorum + runs jobs)
- zippy: `cluster-member + nomad-worker` (runs jobs, not quorum)
- chilly/sparky: `cluster-member + cluster-tools` (Consul + CLI only)
**Key insight**: Profiles (workstation/desktop) no longer imply cluster membership. Hosts explicitly declare roles via imports.
## Key Patterns

0
common/cluster-node.nix → common/cluster-member.nix
View File

0
common/nomad-client.nix → common/cluster-tools.nix
View File

10
common/compute-node.nix
View File

@@ -1,10 +0,0 @@
{ pkgs, ... }:
{
# Compute node: Cluster node with Nomad and GlusterFS server
# Used by: c1, c2, c3
imports = [
./cluster-node.nix
./glusterfs.nix
./nomad.nix
];
}

11
common/consul.nix
View File

@@ -1,13 +1,15 @@
{ pkgs, config, ... }:
{ pkgs, config, lib, ... }:
let
servers = [
"c1"
"c2"
"c3"
];
server_enabled = builtins.elem config.networking.hostName servers;
in
{
options.clusterRole.consulServer = lib.mkEnableOption "Consul server mode";
config = {
services.consul = {
enable = true;
webUi = true;
@@ -15,8 +17,8 @@ in
extraConfig = {
client_addr = "0.0.0.0";
datacenter = "alo";
server = server_enabled;
bootstrap_expect = if server_enabled then (builtins.length servers + 2) / 2 else null;
server = config.clusterRole.consulServer;
bootstrap_expect = if config.clusterRole.consulServer then (builtins.length servers + 2) / 2 else null;
retry_join = builtins.filter (elem: elem != config.networking.hostName) servers;
telemetry = {
prometheus_retention_time = "24h";
@@ -41,4 +43,5 @@ in
8302
];
};
};
}

9
common/nomad-server.nix Normal file
View File

@@ -0,0 +1,9 @@
{ ... }:
{
# Enable server mode for both Consul and Nomad
# Used by: c1, c2, c3 (quorum members)
clusterRole = {
consulServer = true;
nomadServer = true;
};
}

9
common/nomad-worker.nix Normal file
View File

@@ -0,0 +1,9 @@
{ ... }:
{
# Enable Nomad client to run workloads
# Includes: Nomad client, Docker plugin, host volumes, NFS mount dependencies
# Used by: c1, c2, c3, zippy (all nodes that run Nomad jobs)
imports = [
./nomad.nix
];
}

13
common/nomad.nix
View File

@@ -1,14 +1,16 @@
# inspiration: https://github.com/astro/skyflake/blob/main/nixos-modules/nomad.nix
{ pkgs, config, ... }:
{ pkgs, config, lib, ... }:
let
servers = [
"c1"
"c2"
"c3"
];
server_enabled = builtins.elem config.networking.hostName servers;
in
{
options.clusterRole.nomadServer = lib.mkEnableOption "Nomad server mode";
config = {
services.nomad = {
enable = true;
# true breaks at least CSI volumes
@@ -42,7 +44,7 @@ in
};
server = {
enabled = server_enabled;
enabled = config.clusterRole.nomadServer;
bootstrap_expect = (builtins.length servers + 2) / 2;
server_join.retry_join = servers;
};
@@ -161,7 +163,7 @@ in
networking.firewall = {
allowedTCPPorts =
if server_enabled then
if config.clusterRole.nomadServer then
[
4646
4647
@@ -169,6 +171,7 @@ in
]
else
[ 4646 ];
allowedUDPPorts = if server_enabled then [ 4648 ] else [ ];
allowedUDPPorts = if config.clusterRole.nomadServer then [ 4648 ] else [ ];
};
};
}

14
common/server-node.nix
View File

@@ -1,14 +0,0 @@
{ pkgs, ... }:
{
# Server profile: Cluster-enabled system for server deployments
# Extends cluster-node with server-specific configurations
# Future: Add bare NixOS services here (mysql, postgres, etc.) when migrating from Nomad
imports = [
./cluster-node.nix
];
# Server-specific configurations can be added here
# Example (for future use):
# services.mysql.enable = lib.mkDefault false;
# services.postgresql.enable = lib.mkDefault false;
}

4
common/workstation-node.nix
View File

@@ -1,9 +1,9 @@
{ pkgs, inputs, ... }:
{
# Workstation profile: Development workstation configuration
# Extends server-node with development tools and emulation
# Adds development tools and emulation on top of minimal-node
imports = [
./server-node.nix
./minimal-node.nix
./unattended-encryption.nix
];

2
flake.nix
View File

@@ -140,7 +140,7 @@
c2 = mkHost "x86_64-linux" "server" [ ./hosts/c2 ];
c3 = mkHost "x86_64-linux" "server" [ ./hosts/c3 ];
alo-cloud-1 = mkHost "aarch64-linux" "cloud" [ ./hosts/alo-cloud-1 ];
zippy = mkHost "x86_64-linux" "workstation" [
zippy = mkHost "x86_64-linux" "minimal" [
ethereum-nix.nixosModules.default
./hosts/zippy
];

5
hosts/c1/default.nix
View File

@@ -3,7 +3,10 @@
imports = [
../../common/encrypted-btrfs-layout.nix
../../common/global
../../common/compute-node.nix
../../common/cluster-member.nix # Consul + storage clients
../../common/nomad-worker.nix # Nomad client (runs jobs)
../../common/nomad-server.nix # Consul + Nomad server mode
../../common/glusterfs.nix # GlusterFS server (temp during migration)
../../common/nfs-services-standby.nix # NFS standby for /data/services
# To promote to NFS server (during failover):
# 1. Follow procedure in docs/NFS_FAILOVER.md

5
hosts/c2/default.nix
View File

@@ -3,7 +3,10 @@
imports = [
../../common/encrypted-btrfs-layout.nix
../../common/global
../../common/compute-node.nix
../../common/cluster-member.nix # Consul + storage clients
../../common/nomad-worker.nix # Nomad client (runs jobs)
../../common/nomad-server.nix # Consul + Nomad server mode
../../common/glusterfs.nix # GlusterFS server (temp during migration)
./hardware.nix
];

5
hosts/c3/default.nix
View File

@@ -3,7 +3,10 @@
imports = [
../../common/encrypted-btrfs-layout.nix
../../common/global
../../common/compute-node.nix
../../common/cluster-member.nix # Consul + storage clients
../../common/nomad-worker.nix # Nomad client (runs jobs)
../../common/nomad-server.nix # Consul + Nomad server mode
../../common/glusterfs.nix # GlusterFS server (temp during migration)
../../common/binary-cache-server.nix
./hardware.nix
];

2
hosts/chilly/default.nix
View File

@@ -8,6 +8,8 @@
imports = [
../../common/encrypted-btrfs-layout.nix
../../common/global
../../common/cluster-member.nix # Consul + storage clients
../../common/cluster-tools.nix # Nomad CLI (no service)
./hardware.nix
];

2
hosts/sparky/default.nix
View File

@@ -3,6 +3,8 @@
imports = [
../../common/encrypted-btrfs-layout.nix
../../common/global
../../common/cluster-member.nix # Consul + storage clients
../../common/cluster-tools.nix # Nomad CLI (no service)
./hardware.nix
];

5
hosts/zippy/default.nix
View File

@@ -3,7 +3,10 @@
imports = [
../../common/encrypted-btrfs-layout.nix
../../common/global
../../common/compute-node.nix
../../common/cluster-member.nix # Consul + storage clients
../../common/nomad-worker.nix # Nomad client (runs jobs)
# NOTE: zippy is NOT a server - no nomad-server.nix import
../../common/glusterfs.nix # GlusterFS server (temp during migration)
# ../../common/ethereum.nix
../../common/nfs-services-server.nix # NFS server for /data/services
# To move NFS server role to another host: