9 Commits
Author SHA1 Message Date
eSlider bcd956d11a fix: wire live mode and Grafana to the generated data stream
CI & Release / Verify simulator (push) Successful in 11s
CI & Release / Trivy scan (push) Successful in 9s
CI & Release / Semantic Release (push) Successful in 5s
Use the real hive column name (`drone`) in the prototype's live query
and pin the Grafana datasource uid to `swarm-prom` so provisioned
dashboards resolve their Prometheus source in k3d.
2026-07-08 20:34:37 +01:00
eSlider 9f99d132e3 fix: chown var/t1 and var/t3 to simulator uid 10001 for k3d
CI & Release / Verify simulator (push) Successful in 12s
CI & Release / Trivy scan (push) Successful in 9s
CI & Release / Semantic Release (push) Successful in 4s
Non-root drone pods need write access on the hostPath lake. Ansible now
creates var/t1 and var/t3 owned by uid 10001 instead of relying on 0777
alone after legacy root-owned parquet trees.
2026-07-08 20:27:25 +01:00
eSlider 669e8ff005 fix: run simulator image as non-root user (Trivy DS-0002)
CI & Release / Verify simulator (push) Successful in 11s
CI & Release / Trivy scan (push) Successful in 9s
CI & Release / Semantic Release (push) Successful in 4s
Add swarm uid 10001 in both build stages so Trivy config scan passes
and containers do not run as root. Mounted /data volumes should be
world-writable or owned by uid 10001 (var/t1 from Ansible is 0777).
2026-07-08 20:20:19 +01:00
eSlider de1c7c9558 chore: stop tracking local Terraform state and provider cache
CI & Release / Verify simulator (push) Successful in 10s
CI & Release / Trivy scan (push) Successful in 9s
CI & Release / Semantic Release (push) Successful in 4s
Keep .terraform.lock.hcl for reproducible provider pins; gitignore
state files and the .terraform/ working directory.
2026-07-08 20:18:06 +01:00
eSlider ad7e0a5cbe docs: WireGuard vs SSH, Flux GitOps, CONTRIBUTING with TDD-first
Document why WireGuard and SSH are complementary layers, add Flux
boundaries for the ground segment, shared var/ data paths in docs/06,
and a contributor guide with the required test-first workflow.
2026-07-08 20:17:34 +01:00
eSlider cb4664f5ee feat: add IaC layer with shared var/t1 and var/t3 data paths
Ansible provisions the k3d cluster and Flux controllers; Terraform
modules deploy the simulated fleet and ground warehouse. Compose and
k3d share var/t1 (live lake) and var/t3 (warehouse). The prototype
gains a live mode fed by the explorer read-only SQL API.
2026-07-08 20:17:32 +01:00
eSlider d58569b25c test: add pytest suite and gate Docker builds on it
Unit tests cover the SQL gate, broadcast codec, Hive writer layout,
and flight kinematics. CI runs pytest first; the simulator image build
runs tests in a dedicated stage before the final layer.
2026-07-08 20:17:18 +01:00
eSlider eef6623f39 fix(simulator): disable Grafana phone-home for air-gap hygiene
CI & Release / Verify simulator (push) Successful in 7s
CI & Release / Trivy scan (push) Successful in 9s
CI & Release / Semantic Release (push) Successful in 2s
Grafana was checking grafana.com for updates and sending usage
reporting by default - the only outbound traffic in the whole stack.
Verified empty latestVersion and no established external connections
from any container after the change.
2026-07-08 14:56:43 +01:00
eSlider f008da1427 feat(prototype): adapt the patrol field to the display aspect ratio
CI & Release / Verify simulator (push) Successful in 7s
CI & Release / Trivy scan (push) Successful in 10s
CI & Release / Semantic Release (push) Successful in 1s
The field was a fixed square, leaving wide monitors with dead side
margins. Field width now follows the window aspect (capped at 2.2:1,
quantized to avoid rebuilds on minor resizes); routes, obstacles and
transit spawns stretch with it, and the grid keeps 100 m cells.
2026-07-08 14:51:33 +01:00
51 changed files with 2242 additions and 98 deletions
+5 -20
View File
@@ -30,6 +30,10 @@ jobs:
- name: Install dependencies
run: pip install --quiet -r simulator/requirements.txt
- name: Unit tests (TDD gate)
working-directory: simulator
run: pytest tests/ -q
- name: Compile check
run: python -m compileall -q simulator/virtual_drone simulator/monitoring simulator/explorer
@@ -49,26 +53,6 @@ jobs:
print(f"smoke flight OK: {rows} telemetry rows")
EOF
- name: SQL gate tests
working-directory: simulator
run: |
python - <<'EOF'
import sys
sys.path.insert(0, "explorer")
from server import gate
assert gate("SELECT 1") is None
assert gate("WITH t AS (SELECT 1) SELECT * FROM t") is None
assert gate("DESCRIBE telemetry") is None
assert gate("DROP TABLE telemetry") is not None
assert gate("SELECT 1; SELECT 2") is not None
assert gate("INSTALL httpfs") is not None
assert gate("SET memory_limit='1GB'") is not None
assert gate("/* sneaky */ COPY t TO 'x'") is not None
assert gate("") is not None
print("SQL gate OK: reads pass, writes and config are rejected")
EOF
scan:
name: Trivy scan
runs-on: ubuntu-latest
@@ -141,6 +125,7 @@ jobs:
TAG="${{ steps.version.outputs.new_tag }}"
mkdir -p .tmp
tar --exclude='.git' --exclude='.tmp' --exclude='simulator/data' \
--exclude='var/t1' --exclude='var/t3' \
--exclude='simulator/.venv' --exclude='prototype/node_modules' \
-czf ".tmp/swarm-house-${TAG}.tar.gz" .
+8
View File
@@ -1,7 +1,15 @@
data/
simulator/data/
var/t1/**
var/t3/**
!var/t1/.gitkeep
!var/t3/.gitkeep
__pycache__/
*.pyc
.venv/
node_modules/
dist/
.env
.terraform/
*.tfstate
*.tfstate.*
+5
View File
@@ -15,8 +15,13 @@ Rules for anyone (human or tooling) contributing to this repository.
docs/ Design documentation (Markdown + Mermaid)
simulator/ Virtual drone fleet — Python data generator (Parquet/DuckDB pipeline)
prototype/ 2D swarm visualization — React + TypeScript (Vite)
infra/ Ansible host prep, Terraform workloads, Flux GitOps overlays
var/t1/ Shared T1 live lake (gitignored runtime data)
var/t3/ Shared T3 warehouse (gitignored runtime data)
```
See [`CONTRIBUTING.md`](CONTRIBUTING.md) for the development workflow and TDD requirements.
## Conventions
- Markdown: ATX headings, fenced code blocks with language tags, pipe tables.
+90
View File
@@ -0,0 +1,90 @@
# Contributing
Thank you for helping improve Swarm House. This repository is a self-contained
design proposal for an on-prem data platform for autonomous drone swarms — all
contributions must follow the rules in [`AGENTS.md`](AGENTS.md).
## TDD first (required)
Every change to executable code ships with tests **before** or **alongside** the
implementation — never as an afterthought.
1. **Red:** write or extend a failing test that captures the behaviour you need.
2. **Green:** implement the smallest change that makes it pass.
3. **Refactor:** clean up without weakening the test.
The CI pipeline enforces this:
| Gate | When it runs |
| --- | --- |
| `pytest tests/` | Every push/PR (`verify` job) |
| `RUN pytest tests/` in the simulator Docker build | Every `docker build` — a red test blocks the image |
| Smoke flight + DuckDB assertion | Every push/PR |
| Trivy scan | After verify passes |
Test locations:
- `simulator/tests/` — Python unit tests (SQL gate, broadcast codec, writer layout, flight kinematics)
- Prototype: `npm run build` / `tsc --noEmit` before UI changes
## Local development
### Fast inner loop (Compose)
```bash
cd simulator
pip install -r requirements.txt
pytest tests/ -q # run tests first
DRONE_COUNT=5 docker compose up --build # writes to ../var/t1
```
### Full ground miniature (k3d + Terraform + Flux)
```bash
ansible-playbook infra/ansible/sim-cluster.yml
cd infra/terraform/sim-env && terraform init && terraform apply
cd ../ground && terraform init && terraform apply
cd ../../prototype && npm install && npm run dev # press "go live"
```
Shared data directories (gitignored, created automatically):
| Path | Tier | Contents |
| --- | --- | --- |
| `var/t1/` | T1 live lake | In-flight Parquet from Compose or k3d fleet |
| `var/t3/` | T3 warehouse | Offloaded historical partitions |
Override with `SWARM_T1_DIR` / `SWARM_WAREHOUSE_DATA` / `SWARM_SIM_DATA` env vars.
### Prototype only
```bash
cd prototype && npm install && npm run dev
```
## Commit messages
Conventional Commits only:
```
feat: add warehouse offload cron schedule variable
fix: reject COPY statements in the SQL gate
docs: clarify WireGuard vs SSH layering
test: cover broadcast frame roundtrip
```
Never include AI tool references, `Co-authored-by` trailers for assistants, or
identifying names of people, companies, or locations.
## Pull request checklist
- [ ] Tests added or updated; `pytest tests/ -q` passes locally
- [ ] `docker build` in `simulator/` succeeds (test stage included)
- [ ] Documentation updated if behaviour or boundaries changed
- [ ] English only; no identifying references
- [ ] Conventional commit message
## Questions
Open design questions live in [`docs/09-open-questions.md`](docs/09-open-questions.md).
Architecture boundaries are documented in [`docs/06-environments.md`](docs/06-environments.md#iac-boundaries).
+22 -3
View File
@@ -39,18 +39,37 @@ This repository describes how to build, deliver, test, and operate that platform
| Component | Purpose | Stack |
| --- | --- | --- |
| [`simulator/`](simulator/) | Virtual drone fleet: generates realistic telemetry through the same Parquet/DuckDB pipeline a real drone would use; N drones via Docker Compose | Python, pyarrow, DuckDB |
| [`prototype/`](prototype/) | 2D top-down swarm visualization: drones, obstacles, inter-drone links with live transfer metrics | React, TypeScript, Vite, SVG |
| [`prototype/`](prototype/) | 2D top-down swarm visualization: drones, obstacles, inter-drone links with live transfer metrics; **live mode** renders real positions from the k3d fleet | React, TypeScript, Vite, SVG |
| [`infra/ansible/`](infra/ansible/) | Host preparation: drone bench provisioning (keys, forced commands, WireGuard, Compose bundle) and local k3d simulation cluster | Ansible |
| [`infra/terraform/`](infra/terraform/) | Declared workloads on the sim cluster: virtual fleet + observability ([`sim-env`](infra/terraform/sim-env/)), warehouse + T1→T3 offload ([`ground`](infra/terraform/ground/)) | Terraform, kubernetes provider |
| [`infra/gitops/`](infra/gitops/) | Flux overlays for the ground segment — policy labels, dashboard bundles; drones stay on the fleet manifest | Flux, Kustomize |
Shared runtime data (gitignored): `var/t1/` (live lake), `var/t3/` (warehouse). See [`CONTRIBUTING.md`](CONTRIBUTING.md).
## Quick start
```bash
# Spin up a virtual swarm of 10 drones
# Spin up a virtual swarm of 10 drones (Compose, no cluster needed)
cd simulator && DRONE_COUNT=10 docker compose up
# Run the visualization
cd prototype && npm install && npm run dev
```
Or run the full miniature of the ground segment — k3d cluster, fleet as
StatefulSet, Grafana, explorer, warehouse with post-flight offload:
```bash
ansible-playbook infra/ansible/sim-cluster.yml
cd infra/terraform/sim-env && terraform init && terraform apply
cd ../ground && terraform init && terraform apply
# then press "go live" in the prototype header
```
See [06 — Environments → IaC boundaries](docs/06-environments.md#iac-boundaries) for why Ansible owns hosts, Terraform owns the ground segment, and neither flies on the drone.
Contributing (TDD-first workflow): [`CONTRIBUTING.md`](CONTRIBUTING.md).
## CI & releases
Every push runs the pipeline in [`.github/workflows/release.yaml`](.github/workflows/release.yaml): a compile check, a 10-second virtual smoke flight verified with DuckDB, unit tests for the read-only SQL gate, and a Trivy vulnerability/misconfiguration scan. Pushes to `main` then cut a semantic version from the conventional-commit type (`feat:` → minor, `!`/`BREAKING CHANGE` → major, else patch), tag the commit, and publish a release with a **fleet release manifest** (versioned artifact list with checksums — the delivery unit described in [11 — CI/CD & delivery](docs/11-cicd-delivery.md)) plus a source bundle.
Every push runs the pipeline in [`.github/workflows/release.yaml`](.github/workflows/release.yaml): **pytest unit tests**, a compile check, a 10-second virtual smoke flight verified with DuckDB, and a Trivy vulnerability/misconfiguration scan. The simulator Docker build also runs `pytest` — a failing test blocks the image. Pushes to `main` then cut a semantic version from the conventional-commit type (`feat:` → minor, `!`/`BREAKING CHANGE` → major, else patch), tag the commit, and publish a release with a **fleet release manifest** (versioned artifact list with checksums — the delivery unit described in [11 — CI/CD & delivery](docs/11-cicd-delivery.md)) plus a source bundle.
+15
View File
@@ -36,6 +36,21 @@ graph TB
- **RSSI is data.** Per-peer signal strength is captured into `telemetry` like any other sensor — it feeds relative-positioning estimates and post-flight link-quality analysis, and it is free.
- Electromagnetic environment sensing (whatever the radio can observe) is likewise recorded — cheap in flight, valuable in replay.
## Why not SSH alone?
SSH and WireGuard solve different problems. SSH is the **authorization layer** for narrow, point-to-point operations (bulk sync, read-only SQL). WireGuard is the **membership and transport encryption layer** for everything on the mesh, including traffic SSH cannot carry.
| Concern | SSH alone | WireGuard + SSH (this design) |
| --- | --- | --- |
| Pose broadcast (UDP, ~5 Hz, compact frame) | Cannot carry subnet broadcast; would need a separate app protocol | Encrypted inside the mesh overlay; any peer on the tunnel can receive |
| Broadcast confidentiality without WG | Payloads traverse the radio **in cleartext** — any receiver in range reads swarm positions | Only provisioned fleet members complete a handshake; outsiders see noise |
| Lossy ad-hoc links | TCP head-of-line blocking; sessions stall and reconnect on packet loss | UDP transport survives loss and roaming; SSH sessions **over** WG are more stable than SSH directly on Wi-Fi |
| Network membership | Any host that reaches the port gets an SSH banner — a probe surface | Devices without a provisioned key get **no handshake response**; the port is effectively silent |
**Rejected alternative:** encrypt each broadcast frame in application code with a fleet-wide AEAD key. That reinvents a crypto layer the OS already provides, still leaves TCP head-of-line blocking for peer queries, and does not answer the membership question (who is allowed on the mesh at all).
Keep both layers: WireGuard for *who is on the network and whether the wire is readable*; SSH forced commands for *what a peer is allowed to do once connected* ([04](04-swarm-sync.md)).
## Key lifecycle
| Phase | Action |
+23
View File
@@ -61,6 +61,29 @@ The environment engineers live in daily — and deliberately the first thing to
- **T4 data slices**: a thin tool pulls partition subsets from T3 (`flight=X, drone=Y, hour=Z`) for local work — layout-identical, so every query and pipeline runs unmodified.
- The same simulator images scale out on the ground k3s farm for CI regression runs: every merge request replays canonical scenarios and asserts on the resulting Parquet output (row counts, coverage, staleness budgets).
## IaC boundaries
Infrastructure as code follows the same discipline as the data plane: each tool owns the layer it is actually good at, and nothing owns a layer it can't reach.
| Layer | Tool | Why |
| --- | --- | --- |
| Host preparation (drone bench provisioning, sim cluster creation) | **Ansible** ([`infra/ansible/`](../infra/ansible/)) | Idempotent, agentless, works over the same SSH channel the platform already trusts. Keys, forced commands, WireGuard, Compose bundles — all host-level state. |
| Declared workloads (simulated fleet, ground warehouse) | **Terraform** ([`infra/terraform/`](../infra/terraform/)) | The ground segment is stationary, long-lived, and cluster-shaped — classic Terraform territory. Fleet size, offload schedule, and explorer endpoints are variables, not YAML edits. |
| Ongoing ground configuration | **Flux** ([`infra/gitops/`](../infra/gitops/)) | Policy labels, dashboard bundles, offload knobs — reconciled from git without reprovisioning PVCs. Drones stay on the fleet manifest, not GitOps. |
| On-board runtime | **Compose bundle from the fleet release manifest** | Terraform is deliberately *not* on the drone: there is no API server to reconcile against mid-flight, and the release manifest already gives atomic, versioned, rollback-able delivery ([11](11-cicd-delivery.md)). |
Shared local data paths (same layout everywhere): **`var/t1/`** (live lake, T1) and **`var/t3/`** (warehouse, T3). Compose, k3d, and DuckDB on the host all read the same Parquet tree.
Two Terraform modules, two states, one deliberate split: [`sim-env`](../infra/terraform/sim-env/) (the disposable virtual fleet) and [`ground`](../infra/terraform/ground/) (the warehouse that must survive every `destroy` of the fleet). They never share a lifecycle.
### k3d: the ground segment as an executable miniature
`ansible-playbook infra/ansible/sim-cluster.yml` creates a local k3d cluster (k3s in Docker — the same distribution as the real ground segment) and `terraform apply` populates it: virtual drones as StatefulSet replicas over a shared Parquet lake, the exporter/Prometheus/Grafana stack, the data-plane explorer, MinIO, and the T1→T3 offload CronJob. The whole diagram at the top of this page runs on one workstation, and the prototype's **live mode** renders real drone positions straight from the explorer's read-only SQL API.
### Next fidelity step: microVMs
The k3d fleet shares one kernel and one network namespace tree — good enough to exercise the data plane, not good enough to demo the *peer* plane (real SSH sessions between isolated machines, WireGuard handshakes, packet loss injection). The next step, when that fidelity is needed, is one **Firecracker microVM per drone**: a real kernel, a real network interface, and the actual `authorized_keys` forced-command path between virtual drones — on any KVM-capable workstation, still with no cloud dependency. The process-level simulator stays as the fast inner loop; microVMs become the pre-flight integration rig.
## Why identical layouts matter (the payoff)
| Operation | What it costs with one layout everywhere |
+33
View File
@@ -97,6 +97,39 @@ config:
2. Docked drones fetch the manifest, verify digests/signatures ([05](05-network-security.md)), stage the new Compose bundle, and switch on the next boot cycle.
3. **Never mid-flight.** Updates are a dock-only operation by construction — the update endpoint does not exist in the flight radio profile.
## GitOps on the ground segment
The fleet release manifest handles **drones** (atomic, digest-pinned, dock-only). The **ground k3s segment** uses a different tool: [Flux](https://fluxcd.io/) reconciles long-lived configuration from git — dashboard bundles, Prometheus rules, offload schedules, policy labels — without reprovisioning PVCs or re-running full Terraform applies for every label change.
```mermaid
graph LR
subgraph git [Git, on-prem]
REPO["service repos"]
GITOPS["infra/gitops/<br/>ground overlay"]
end
subgraph ground_k3s [Ground k3s]
FLUX["Flux controllers"]
WH["warehouse workloads<br/>(Terraform-provisioned)"]
CFG["policy ConfigMaps<br/>dashboard bundles"]
end
subgraph drones [Fleet]
MAN["fleet release manifest"]
DOCK["dock: verify + apply"]
end
REPO --> CI
GITOPS --> FLUX
FLUX --> CFG
MAN --> DOCK
```
| Segment | Delivery mechanism | Reconciler in production? |
| --- | --- | --- |
| Drones | Fleet release manifest via registry mirror | **No** — no API server mid-flight; dock applies once |
| Ground k3s (warehouse, dashboards, CI runners) | Terraform for shape + **Flux** for ongoing config | **Yes** — stationary cluster, wired network, git is the source of truth |
| Dev simulation (k3d) | Ansible creates cluster; Terraform applies workloads; Flux CRs installed from [`infra/gitops/`](../infra/gitops/) | Yes (miniature of ground) |
Boundary: **Terraform provisions** (namespaces, PVCs, Deployments, CronJobs); **Flux reconciles** policy and observability overlays on top. Neither replaces the fleet manifest on the drone.
## Developer experience
- **Dev Containers** define the full toolchain (Python data tooling, DuckDB, compose, linters) — identical on any machine, onboarding in minutes.
+39
View File
@@ -0,0 +1,39 @@
# Ansible — host preparation
Ansible owns everything that happens **on a host before workloads run**.
Terraform ([`../terraform/`](../terraform/)) owns the workloads themselves.
The boundary is deliberate and documented in
[06 — Environments](../../docs/06-environments.md#iac-boundaries).
| Playbook | Target | What it does |
| --- | --- | --- |
| `drone-provision.yml` | Drone (on the bench, before a mission) | Identity keys, peer trust with forced commands, WireGuard, Compose bundle from the fleet release manifest |
| `sim-cluster.yml` | Local workstation / CI host | k3d cluster that miniatures the ground segment; shared data volume; simulator image import |
## Provision a drone
```bash
ansible-playbook -i inventory.example.yml drone-provision.yml
```
The playbook is idempotent and runs only over the bench network — drones
are never provisioned in flight (see [05 — Network & security](../../docs/05-network-security.md)):
1. **Identity**: generate the drone's ed25519 keypair if absent.
2. **Peer trust**: install every fleet member's public key into
`authorized_keys`, each pinned to the read-only SQL forced command —
the only thing a peer can execute.
3. **WireGuard**: render `wg0.conf` with the drone's address and peers.
4. **Data plane**: lay down the Compose bundle referenced by the fleet
release manifest and enable it as a systemd unit.
## Create the simulation cluster
```bash
ansible-playbook sim-cluster.yml # creates k3d cluster 'swarm-sim'
cd ../terraform/sim-env && terraform init && terraform apply
```
The cluster mounts a shared host directory as `/data` on the (single)
node, so drone pods, the exporter, and the explorer see one Parquet lake —
the same contract as the on-board NVMe layout.
+101
View File
@@ -0,0 +1,101 @@
# Provision a drone on the bench: identity, peer trust, WireGuard, data plane.
# Idempotent; never runs over the mission radio (bench network only).
---
- name: Provision drone data plane
hosts: drones
become: true
vars:
swarm_user: swarm
swarm_home: /opt/swarm
forced_command: "{{ swarm_home }}/bin/peer-query.sh"
tasks:
- name: Create swarm service user
ansible.builtin.user:
name: "{{ swarm_user }}"
home: "{{ swarm_home }}"
shell: /usr/sbin/nologin
system: true
# --- 1. Identity -----------------------------------------------------
- name: Generate drone ed25519 identity key
community.crypto.openssh_keypair:
path: "{{ swarm_home }}/.ssh/id_ed25519"
type: ed25519
comment: "{{ inventory_hostname }}"
owner: "{{ swarm_user }}"
mode: "0600"
register: identity
- name: Collect fleet public keys
ansible.builtin.slurp:
src: "{{ swarm_home }}/.ssh/id_ed25519.pub"
register: pubkey
# --- 2. Peer trust: forced command only ------------------------------
# Every peer may connect, but the only thing it can execute is the
# read-only SQL wrapper (docs/04). No shell, no forwarding, no pty.
- name: Authorize fleet peers with read-only forced command
ansible.posix.authorized_key:
user: "{{ swarm_user }}"
key: "{{ hostvars[item].pubkey.content | b64decode }}"
key_options: >-
command="{{ forced_command }}",no-port-forwarding,no-agent-forwarding,no-X11-forwarding,no-pty
loop: "{{ groups['drones'] | difference([inventory_hostname]) }}"
when: hostvars[item].pubkey is defined
- name: Install peer query wrapper
ansible.builtin.copy:
dest: "{{ forced_command }}"
mode: "0755"
content: |
#!/bin/sh
# Forced command: read-only DuckDB SQL over the sealed lake.
# SSH_ORIGINAL_COMMAND carries the statement; the gate rejects
# anything that is not a single read statement.
exec {{ swarm_home }}/bin/sql-gate --read-only --data /data "$SSH_ORIGINAL_COMMAND"
# --- 3. WireGuard swarm plane ----------------------------------------
- name: Render WireGuard configuration
ansible.builtin.template:
src: templates/wg0.conf.j2
dest: /etc/wireguard/wg0.conf
mode: "0600"
notify: Restart wireguard
- name: Enable WireGuard interface
ansible.builtin.systemd:
name: wg-quick@wg0
enabled: true
state: started
# --- 4. Data plane from the fleet release manifest --------------------
- name: Read fleet release manifest
ansible.builtin.include_vars:
file: "{{ fleet_manifest }}"
name: manifest
- name: Lay down Compose bundle for release {{ manifest.release }}
ansible.builtin.unarchive:
src: "{{ playbook_dir }}/../../.tmp/{{ manifest.artifacts[0].name }}"
dest: "{{ swarm_home }}/release"
owner: "{{ swarm_user }}"
- name: Enable data plane unit
ansible.builtin.template:
src: templates/swarm-data-plane.service.j2
dest: /etc/systemd/system/swarm-data-plane.service
mode: "0644"
notify: Restart data plane
handlers:
- name: Restart wireguard
ansible.builtin.systemd:
name: wg-quick@wg0
state: restarted
- name: Restart data plane
ansible.builtin.systemd:
name: swarm-data-plane
state: restarted
daemon_reload: true
+19
View File
@@ -0,0 +1,19 @@
# Example fleet inventory. Real inventories are generated from the fleet
# release manifest and live outside the repository.
all:
children:
drones:
hosts:
dr-01:
ansible_host: 10.44.0.11
wg_address: 10.44.0.11/24
dr-02:
ansible_host: 10.44.0.12
wg_address: 10.44.0.12/24
dr-03:
ansible_host: 10.44.0.13
wg_address: 10.44.0.13/24
vars:
ansible_user: ops
wg_port: 51820
fleet_manifest: ../../.tmp/manifest.yaml
+129
View File
@@ -0,0 +1,129 @@
# Create the local k3d simulation cluster — an executable miniature of the
# ground segment (k3s) from docs/06. Terraform then owns the workloads.
---
- name: Simulation cluster (k3d)
hosts: localhost
connection: local
gather_facts: false
vars:
cluster_name: swarm-sim
repo_root: "{{ playbook_dir }}/../.."
data_dir: "{{ lookup('env', 'SWARM_SIM_DATA') | default(repo_root + '/var/t1', true) }}"
warehouse_dir: "{{ lookup('env', 'SWARM_WAREHOUSE_DATA') | default(repo_root + '/var/t3', true) }}"
api_port: 6560
# Host ports for services exposed by the Terraform modules (NodePorts)
port_explorer: 30088
port_grafana: 30300
port_prometheus: 30990
port_warehouse_explorer: 30089
port_minio_console: 30901
simulator_image: swarm-house/simulator:dev
tasks:
- name: Check k3d is installed
ansible.builtin.command: k3d version
changed_when: false
- name: Create shared data directory (the pods' /data lake)
ansible.builtin.file:
path: "{{ data_dir }}"
state: directory
mode: "0777"
owner: "10001"
group: "10001"
- name: Create warehouse directory (T3 host path inside the k3d node)
ansible.builtin.file:
path: "{{ warehouse_dir }}"
state: directory
mode: "0777"
owner: "10001"
group: "10001"
- name: List existing clusters
ansible.builtin.command: k3d cluster list -o json
register: clusters
changed_when: false
- name: Create cluster {{ cluster_name }}
ansible.builtin.command: >-
k3d cluster create {{ cluster_name }}
--api-port {{ api_port }}
--servers 1 --agents 0
--volume {{ data_dir }}:/data@server:0
--volume {{ warehouse_dir }}:/warehouse@server:0
--port {{ port_explorer }}:{{ port_explorer }}@server:0
--port {{ port_grafana }}:{{ port_grafana }}@server:0
--port {{ port_prometheus }}:{{ port_prometheus }}@server:0
--port {{ port_warehouse_explorer }}:{{ port_warehouse_explorer }}@server:0
--port {{ port_minio_console }}:{{ port_minio_console }}@server:0
--k3s-arg "--disable=traefik@server:0"
--wait
when: clusters.stdout | from_json | selectattr('name', 'equalto', cluster_name) | list | length == 0
- name: Build simulator image
ansible.builtin.command:
cmd: docker build -t {{ simulator_image }} .
chdir: "{{ playbook_dir }}/../../simulator"
register: build
changed_when: "'Using cache' not in build.stderr"
- name: Import simulator image into the cluster
ansible.builtin.command: k3d image import {{ simulator_image }} -c {{ cluster_name }}
changed_when: true
- name: Merge k3d kubeconfig into the default context
ansible.builtin.command: k3d kubeconfig merge {{ cluster_name }} --kubeconfig-merge-default
changed_when: false
- name: Check whether Flux CLI is available
ansible.builtin.command: flux version --client
register: flux_cli
changed_when: false
failed_when: false
- name: Install Flux CLI (local user bin)
when: flux_cli.rc != 0
block:
- name: Download Flux release archive
ansible.builtin.get_url:
url: https://github.com/fluxcd/flux2/releases/download/v2.4.0/flux_2.4.0_linux_amd64.tar.gz
dest: /tmp/flux.tar.gz
mode: "0644"
- name: Extract flux binary
ansible.builtin.unarchive:
src: /tmp/flux.tar.gz
dest: "{{ lookup('env', 'HOME') }}/.local/bin"
remote_src: true
include:
- flux
extra_opts:
- --no-same-owner
ignore_errors: true
- name: Ensure flux is executable
ansible.builtin.file:
path: "{{ lookup('env', 'HOME') }}/.local/bin/flux"
mode: "0755"
state: file
- name: Install Flux controllers into the cluster
ansible.builtin.command: flux install --namespace=flux-system --components=source-controller,kustomize-controller
environment:
PATH: "{{ lookup('env', 'HOME') }}/.local/bin:{{ lookup('env', 'PATH') }}"
KUBECONFIG: "{{ lookup('env', 'HOME') }}/.kube/config"
register: flux_install
changed_when: "'installed' in (flux_install.stdout | default(''))"
- name: Apply Flux GitOps CRs (GitRepository + Kustomization)
ansible.builtin.command: kubectl apply -k {{ repo_root }}/infra/gitops/flux
changed_when: true
- name: Seed ground GitOps resources locally (works before first git push)
ansible.builtin.command: kubectl apply -k {{ repo_root }}/infra/gitops/ground
changed_when: true
- name: Show kubeconfig hint
ansible.builtin.debug:
msg: >-
Cluster ready. Workloads: cd ../terraform/sim-env && terraform init && terraform apply.
kubeconfig: k3d kubeconfig get {{ cluster_name }}
@@ -0,0 +1,15 @@
[Unit]
Description=Swarm data plane (Compose bundle, release {{ manifest.release }})
After=docker.service wg-quick@wg0.service
Requires=docker.service
[Service]
Type=oneshot
RemainAfterExit=yes
WorkingDirectory={{ swarm_home }}/release
ExecStart=/usr/bin/docker compose up -d
ExecStop=/usr/bin/docker compose down
TimeoutStartSec=300
[Install]
WantedBy=multi-user.target
+12
View File
@@ -0,0 +1,12 @@
# WireGuard swarm plane — rendered by drone-provision.yml
[Interface]
Address = {{ wg_address }}
ListenPort = {{ wg_port }}
PrivateKey = __REPLACED_FROM_HSM_AT_SEALING__
{% for peer in groups['drones'] | difference([inventory_hostname]) %}
[Peer]
# {{ peer }}
PublicKey = __PEER_{{ peer | upper | replace('-', '_') }}_PUBKEY__
AllowedIPs = {{ hostvars[peer].wg_address | ansible.utils.ipaddr('address') }}/32
{% endfor %}
+52
View File
@@ -0,0 +1,52 @@
# GitOps — ground segment (Flux)
Flux reconciles **long-lived ground configuration** from this repository. It does
not run on drones and does not replace the fleet release manifest — those are
different lifecycles by design ([11 — CI/CD](../../docs/11-cicd-delivery.md)).
## Boundary: Terraform vs Flux vs fleet manifest
| Layer | Tool | Owns |
| --- | --- | --- |
| Cluster + first boot | **Terraform** ([`../terraform/`](../terraform/)) | Namespaces, PVCs, Deployments, CronJobs, NodePorts — the shape of the simulation |
| Ongoing ground config | **Flux** (this directory) | Policy labels, dashboard bundles, offload knobs — things that change without reprovisioning PVCs |
| Drones | **Fleet release manifest** | Compose bundle digests, model weights, peer registry — atomic, dock-only delivery |
Drones are **outside GitOps**: there is no reconciler in flight. A dock applies
the pinned manifest once; mid-mission drift is impossible because the update
endpoint does not exist in the radio profile.
## Layout
```
infra/gitops/
flux/ Flux GitRepository + Kustomization CRs (install into flux-system)
ground/ Kustomize overlay reconciled into the ground namespace
```
## Bootstrap on the k3d simulation cluster
`infra/ansible/sim-cluster.yml` installs Flux controllers and applies the CRs
below. After the first `git push`, Flux polls `origin` and reconciles
`infra/gitops/ground/` into the `ground` namespace.
```bash
# Manual bootstrap (if you skipped Ansible):
flux install --namespace=flux-system
kubectl apply -k infra/gitops/flux
```
To reconcile immediately without waiting for the poll interval:
```bash
flux reconcile source git swarm-house -n flux-system
flux reconcile kustomization ground-segment -n flux-system
```
## What Flux manages here (example)
The [`ground/`](ground/) overlay currently carries a **GitOps-managed ConfigMap**
that tags the warehouse segment with fleet policy metadata. In production this
pattern extends to Grafana dashboard bundles, Prometheus rule files, and
offload-schedule ConfigMaps — all versioned in git, all auditable, none of
them requiring a `terraform apply` to tweak a label.
+10
View File
@@ -0,0 +1,10 @@
apiVersion: source.toolkit.fluxcd.io/v1
kind: GitRepository
metadata:
name: swarm-house
namespace: flux-system
spec:
interval: 1m
url: https://git.produktor.io/eSlider/swarm-house.git
ref:
branch: main
@@ -0,0 +1,14 @@
apiVersion: kustomize.toolkit.fluxcd.io/v1
kind: Kustomization
metadata:
name: ground-segment
namespace: flux-system
spec:
interval: 2m
sourceRef:
kind: GitRepository
name: swarm-house
path: ./infra/gitops/ground
prune: true
wait: true
timeout: 3m
+5
View File
@@ -0,0 +1,5 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- gitrepository.yaml
- kustomization-ground.yaml
@@ -0,0 +1,12 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: ground-fleet-policy
namespace: ground
labels:
app.kubernetes.io/part-of: swarm-ground
app.kubernetes.io/managed-by: flux
data:
offload_schedule: "*/2 * * * *"
retention_policy: "keep-all-flights"
explorer_mode: "read-only-sql"
+6
View File
@@ -0,0 +1,6 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
namespace: ground
resources:
- namespace.yaml
- configmap-fleet-policy.yaml
+6
View File
@@ -0,0 +1,6 @@
apiVersion: v1
kind: Namespace
metadata:
name: ground
labels:
app.kubernetes.io/part-of: swarm-ground
+34
View File
@@ -0,0 +1,34 @@
## Recovering from partial state
If resources were created outside Terraform (or state was lost), import them
before `terraform apply`:
```bash
# sim-env (namespace: swarm)
terraform import kubernetes_namespace.swarm swarm
terraform import kubernetes_stateful_set.drone swarm/drone
terraform import kubernetes_deployment.exporter swarm/exporter
terraform import kubernetes_deployment.explorer swarm/explorer
terraform import kubernetes_deployment.prometheus swarm/prometheus
terraform import kubernetes_deployment.grafana swarm/grafana
terraform import kubernetes_service.exporter swarm/exporter
terraform import kubernetes_service.explorer swarm/explorer
terraform import kubernetes_service.prometheus swarm/prometheus
terraform import kubernetes_service.grafana swarm/grafana
terraform import kubernetes_config_map.prometheus swarm/prometheus-config
terraform import kubernetes_config_map.grafana_provisioning swarm/grafana-provisioning
terraform import kubernetes_config_map.grafana_dashboard swarm/grafana-dashboard
# ground (namespace: ground)
terraform import kubernetes_namespace.ground ground
terraform import kubernetes_persistent_volume_claim.minio ground/minio-data
terraform import kubernetes_secret.minio ground/minio-credentials
terraform import kubernetes_deployment.minio ground/minio
terraform import kubernetes_deployment.warehouse_explorer ground/warehouse-explorer
terraform import kubernetes_service.minio ground/minio
terraform import kubernetes_service.warehouse_explorer ground/warehouse-explorer
terraform import kubernetes_cron_job_v1.offload ground/offload
```
Then `terraform apply` reconciles drift (for example pinning `EXPLORER_PORT`
and `EXPORTER_PORT` so Kubernetes service env injection does not break startup).
+22
View File
@@ -0,0 +1,22 @@
# This file is maintained automatically by "terraform init".
# Manual edits may be lost in future updates.
provider "registry.terraform.io/hashicorp/kubernetes" {
version = "2.38.0"
constraints = "~> 2.33"
hashes = [
"h1:5CkveFo5ynsLdzKk+Kv+r7+U9rMrNjfZPT3a0N/fhgE=",
"zh:0af928d776eb269b192dc0ea0f8a3f0f5ec117224cd644bdacdc682300f84ba0",
"zh:1be998e67206f7cfc4ffe77c01a09ac91ce725de0abaec9030b22c0a832af44f",
"zh:326803fe5946023687d603f6f1bab24de7af3d426b01d20e51d4e6fbe4e7ec1b",
"zh:4a99ec8d91193af961de1abb1f824be73df07489301d62e6141a656b3ebfff12",
"zh:5136e51765d6a0b9e4dbcc3b38821e9736bd2136cf15e9aac11668f22db117d2",
"zh:63fab47349852d7802fb032e4f2b6a101ee1ce34b62557a9ad0f0f0f5b6ecfdc",
"zh:924fb0257e2d03e03e2bfe9c7b99aa73c195b1f19412ca09960001bee3c50d15",
"zh:b63a0be5e233f8f6727c56bed3b61eb9456ca7a8bb29539fba0837f1badf1396",
"zh:d39861aa21077f1bc899bc53e7233262e530ba8a3a2d737449b100daeb303e4d",
"zh:de0805e10ebe4c83ce3b728a67f6b0f9d18be32b25146aa89116634df5145ad4",
"zh:f569b65999264a9416862bca5cd2a6177d94ccb0424f3a4ef424428912b9cb3c",
"zh:faf23e45f0090eef8ba28a8aac7ec5d4fdf11a36c40a8d286304567d71c1e7db",
]
}
+38
View File
@@ -0,0 +1,38 @@
# Terraform — ground warehouse (T3)
The stationary half of the system: the historical warehouse that receives
sealed partitions after every flight ([03 — Storage tiers](../../../docs/03-storage-design.md)).
It is the longest-lived, most conventional infrastructure in the design —
and therefore the most natural Terraform territory.
Runs in the same k3d cluster as [`../sim-env`](../sim-env/) but in its own
namespace with its own state: the fleet is disposable, the warehouse is not,
and the two lifecycles must never share a `terraform destroy`.
| Resource | Purpose |
| --- | --- |
| Deployment `minio` + PVC + NodePort 30901 | Object-store facade of the warehouse for downstream consumers (training pipelines, replay) |
| CronJob `offload` | Post-flight offload: copies Hive partitions verbatim from the fleet lake (T1) into the warehouse (T3), then mirrors into MinIO |
| Deployment `warehouse-explorer` + NodePort 30089 | Second explorer instance over the warehouse path — historical read-only SQL across **all** flights |
## Usage
```bash
terraform init
terraform apply
terraform output
```
After a couple of offload runs, the warehouse explorer shows the same
partition tree as the live lake but accumulated across flights — the T1
layout **is** the T3 layout, which is the whole point: no transform step,
no schema drift, DuckDB queries work identically on both ends.
## Simulation vs production
- The CronJob compresses "drone lands, docks, offloads, prunes" into a
periodic rsync-style copy. Production offload is event-driven per docking
and verifies checksums from the flight's partition manifest before pruning
the on-board lake.
- MinIO credentials here are throwaway defaults; production credentials are
sealed per site and never in state or VCS.
+273
View File
@@ -0,0 +1,273 @@
# Ground warehouse segment (T3, docs/03 + docs/06) — the stationary,
# long-lifecycle half of the system and therefore the most natural Terraform
# territory. Runs in the same k3d cluster as the fleet, in its own namespace
# and with its own state.
locals {
labels = { "app.kubernetes.io/part-of" = "swarm-ground" }
}
resource "kubernetes_namespace" "ground" {
metadata {
name = var.namespace
labels = local.labels
}
}
# --- MinIO object store -------------------------------------------------------
resource "kubernetes_secret" "minio" {
metadata {
name = "minio-credentials"
namespace = kubernetes_namespace.ground.metadata[0].name
}
data = {
MINIO_ROOT_USER = var.minio_root_user
MINIO_ROOT_PASSWORD = var.minio_root_password
}
}
resource "kubernetes_persistent_volume_claim" "minio" {
metadata {
name = "minio-data"
namespace = kubernetes_namespace.ground.metadata[0].name
}
spec {
access_modes = ["ReadWriteOnce"]
resources {
requests = { storage = var.minio_storage }
}
}
}
resource "kubernetes_deployment" "minio" {
metadata {
name = "minio"
namespace = kubernetes_namespace.ground.metadata[0].name
labels = local.labels
}
spec {
replicas = 1
strategy {
type = "Recreate" # RWO volume
}
selector {
match_labels = { app = "minio" }
}
template {
metadata {
labels = merge(local.labels, { app = "minio" })
}
spec {
container {
name = "minio"
image = "minio/minio:RELEASE.2024-06-13T22-53-53Z"
args = ["server", "/data", "--console-address", ":9001"]
env_from {
secret_ref {
name = kubernetes_secret.minio.metadata[0].name
}
}
# Air-gap hygiene: no update checks
env {
name = "MINIO_UPDATE"
value = "off"
}
port {
container_port = 9000
}
port {
container_port = 9001
}
volume_mount {
name = "store"
mount_path = "/data"
}
}
volume {
name = "store"
persistent_volume_claim {
claim_name = kubernetes_persistent_volume_claim.minio.metadata[0].name
}
}
}
}
}
}
resource "kubernetes_service" "minio" {
metadata {
name = "minio"
namespace = kubernetes_namespace.ground.metadata[0].name
}
spec {
type = "NodePort"
selector = { app = "minio" }
port {
name = "api"
port = 9000
target_port = 9000
}
port {
name = "console"
port = 9001
target_port = 9001
node_port = var.node_ports.minio_console
}
}
}
# --- Post-flight offload: T1 lake -> T3 warehouse ------------------------------
# In production this runs on the docking station after a drone lands: only
# sealed partitions move, checksums are verified, then the on-board lake is
# pruned. The simulation compresses that into a periodic rsync-style copy
# plus an object-store mirror.
resource "kubernetes_cron_job_v1" "offload" {
metadata {
name = "offload"
namespace = kubernetes_namespace.ground.metadata[0].name
labels = local.labels
}
spec {
schedule = var.offload_schedule
concurrency_policy = "Forbid"
successful_jobs_history_limit = 3
failed_jobs_history_limit = 3
job_template {
metadata {
labels = local.labels
}
spec {
backoff_limit = 1
template {
metadata {
labels = local.labels
}
spec {
restart_policy = "Never"
# Step 1: copy Hive partitions verbatim (T1 layout == T3 layout)
init_container {
name = "copy"
image = "busybox:1.36"
command = ["sh", "-c", "cp -ru /lake/flight_id=* /warehouse/ 2>/dev/null; ls /warehouse | wc -l"]
volume_mount {
name = "lake"
mount_path = "/lake"
read_only = true
}
volume_mount {
name = "warehouse"
mount_path = "/warehouse"
}
}
# Step 2: mirror the warehouse into the object store for
# downstream consumers (training pipelines, replay tooling)
container {
name = "mirror"
image = "minio/mc:RELEASE.2024-06-12T14-34-03Z"
command = ["sh", "-c", "mc alias set store http://minio:9000 \"$MINIO_ROOT_USER\" \"$MINIO_ROOT_PASSWORD\" && mc mb -p store/warehouse && mc mirror --overwrite /warehouse store/warehouse"]
env_from {
secret_ref {
name = kubernetes_secret.minio.metadata[0].name
}
}
volume_mount {
name = "warehouse"
mount_path = "/warehouse"
read_only = true
}
}
volume {
name = "lake"
host_path {
path = var.lake_host_path
}
}
volume {
name = "warehouse"
host_path {
path = var.warehouse_host_path
type = "DirectoryOrCreate"
}
}
}
}
}
}
}
}
# --- Warehouse explorer: historical read-only SQL over all flights -------------
resource "kubernetes_deployment" "warehouse_explorer" {
metadata {
name = "warehouse-explorer"
namespace = kubernetes_namespace.ground.metadata[0].name
labels = local.labels
}
spec {
replicas = 1
selector {
match_labels = { app = "warehouse-explorer" }
}
template {
metadata {
labels = merge(local.labels, { app = "warehouse-explorer" })
}
spec {
container {
name = "explorer"
image = var.simulator_image
image_pull_policy = "Never"
command = ["python", "explorer/server.py"]
env {
name = "DATA_DIR"
value = "/warehouse"
}
port {
container_port = 8088
}
volume_mount {
name = "warehouse"
mount_path = "/warehouse"
read_only = true
}
}
volume {
name = "warehouse"
host_path {
path = var.warehouse_host_path
type = "DirectoryOrCreate"
}
}
}
}
}
}
resource "kubernetes_service" "warehouse_explorer" {
metadata {
name = "warehouse-explorer"
namespace = kubernetes_namespace.ground.metadata[0].name
}
spec {
type = "NodePort"
selector = { app = "warehouse-explorer" }
port {
port = 8088
target_port = 8088
node_port = var.node_ports.warehouse_explorer
}
}
}
+14
View File
@@ -0,0 +1,14 @@
output "warehouse_explorer_url" {
description = "Historical read-only SQL over all offloaded flights"
value = "http://localhost:${var.node_ports.warehouse_explorer}"
}
output "minio_console_url" {
description = "MinIO console (object-store view of the warehouse)"
value = "http://localhost:${var.node_ports.minio_console}"
}
output "offload_schedule" {
description = "Cron schedule of the T1 -> T3 offload job"
value = var.offload_schedule
}
+72
View File
@@ -0,0 +1,72 @@
variable "kubeconfig" {
description = "Path to the kubeconfig for the simulation cluster"
type = string
default = "~/.kube/config"
}
variable "kube_context" {
description = "Kubeconfig context of the k3d simulation cluster"
type = string
default = "k3d-swarm-sim"
}
variable "namespace" {
description = "Namespace for the ground warehouse segment"
type = string
default = "ground"
}
variable "simulator_image" {
description = "Simulator image (provides the explorer; imported by Ansible)"
type = string
default = "swarm-house/simulator:dev"
}
variable "lake_host_path" {
description = "Host path of the fleet's live lake (T1) inside the k3d node"
type = string
default = "/data"
}
variable "warehouse_host_path" {
description = "Host path of the historical warehouse (T3) inside the k3d node; dot-prefixed so lake globs never match it"
type = string
default = "/data/.warehouse"
}
variable "offload_schedule" {
description = "Cron schedule of the post-flight offload job (T1 -> T3)"
type = string
default = "*/2 * * * *"
}
variable "minio_root_user" {
description = "MinIO root user (simulation only; production uses sealed credentials)"
type = string
default = "warehouse"
}
variable "minio_root_password" {
description = "MinIO root password (simulation only)"
type = string
default = "warehouse-sim-only"
sensitive = true
}
variable "minio_storage" {
description = "PVC size for the MinIO object store"
type = string
default = "2Gi"
}
variable "node_ports" {
description = "Host-reachable NodePorts (must match the ports opened by sim-cluster.yml)"
type = object({
warehouse_explorer = number
minio_console = number
})
default = {
warehouse_explorer = 30089
minio_console = 30901
}
}
+15
View File
@@ -0,0 +1,15 @@
terraform {
required_version = ">= 1.5"
required_providers {
kubernetes = {
source = "hashicorp/kubernetes"
version = "~> 2.33"
}
}
}
provider "kubernetes" {
config_path = var.kubeconfig
config_context = var.kube_context
}
+22
View File
@@ -0,0 +1,22 @@
# This file is maintained automatically by "terraform init".
# Manual edits may be lost in future updates.
provider "registry.terraform.io/hashicorp/kubernetes" {
version = "2.38.0"
constraints = "~> 2.33"
hashes = [
"h1:5CkveFo5ynsLdzKk+Kv+r7+U9rMrNjfZPT3a0N/fhgE=",
"zh:0af928d776eb269b192dc0ea0f8a3f0f5ec117224cd644bdacdc682300f84ba0",
"zh:1be998e67206f7cfc4ffe77c01a09ac91ce725de0abaec9030b22c0a832af44f",
"zh:326803fe5946023687d603f6f1bab24de7af3d426b01d20e51d4e6fbe4e7ec1b",
"zh:4a99ec8d91193af961de1abb1f824be73df07489301d62e6141a656b3ebfff12",
"zh:5136e51765d6a0b9e4dbcc3b38821e9736bd2136cf15e9aac11668f22db117d2",
"zh:63fab47349852d7802fb032e4f2b6a101ee1ce34b62557a9ad0f0f0f5b6ecfdc",
"zh:924fb0257e2d03e03e2bfe9c7b99aa73c195b1f19412ca09960001bee3c50d15",
"zh:b63a0be5e233f8f6727c56bed3b61eb9456ca7a8bb29539fba0837f1badf1396",
"zh:d39861aa21077f1bc899bc53e7233262e530ba8a3a2d737449b100daeb303e4d",
"zh:de0805e10ebe4c83ce3b728a67f6b0f9d18be32b25146aa89116634df5145ad4",
"zh:f569b65999264a9416862bca5cd2a6177d94ccb0424f3a4ef424428912b9cb3c",
"zh:faf23e45f0090eef8ba28a8aac7ec5d4fdf11a36c40a8d286304567d71c1e7db",
]
}
+40
View File
@@ -0,0 +1,40 @@
# Terraform — simulation environment (T4)
Declares the simulated fleet and its observability stack on the k3d cluster
created by [`../../ansible/sim-cluster.yml`](../../ansible/sim-cluster.yml).
This module is the executable miniature of the dev/sim environment from
[06 — Environments](../../../docs/06-environments.md).
| Resource | Purpose |
| --- | --- |
| StatefulSet `drone` × `drone_count` | Virtual drones; stable pod names become `DRONE_ID`s; all write Hive-partitioned Parquet into the shared `/data` lake |
| Deployment `exporter` | Prometheus exporter reading the lake with DuckDB |
| Deployment `explorer` + NodePort 30088 | Partition tree + read-only SQL console (also feeds the prototype's live mode) |
| Deployment `prometheus` + NodePort 30990 | Scrapes the exporter |
| Deployment `grafana` + NodePort 30300 | Same dashboard JSON as the Compose profile, provisioned from a ConfigMap |
## Usage
```bash
ansible-playbook ../../ansible/sim-cluster.yml # once: cluster + image
terraform init
terraform apply
terraform output # URLs
```
Scale the fleet without touching YAML:
```bash
terraform apply -var drone_count=9 -var speedup=4
```
## Notes
- `image_pull_policy = "Never"` — the simulator image is imported by the
Ansible playbook (`k3d image import`); the cluster never pulls from a
registry, mirroring the air-gap doctrine.
- Pods discover their identity from the pod name (StatefulSet ordinal), so
a flight survives `kubectl delete pod` the same way a drone survives a
power cycle: new process, same identity, new flight ID.
- State is local (`terraform.tfstate` in this directory) — the simulation
cluster is disposable; nothing here is shared infrastructure.
+443
View File
@@ -0,0 +1,443 @@
# Simulated fleet (T4 dev environment, docs/06) on the k3d cluster created
# by infra/ansible/sim-cluster.yml. Drones are StatefulSet replicas writing
# to a shared hostPath lake — the same /data contract as the on-board NVMe.
locals {
labels = { "app.kubernetes.io/part-of" = "swarm-sim" }
}
resource "kubernetes_namespace" "swarm" {
metadata {
name = var.namespace
labels = local.labels
}
}
# --- Fleet ------------------------------------------------------------------
resource "kubernetes_stateful_set" "drone" {
metadata {
name = "drone"
namespace = kubernetes_namespace.swarm.metadata[0].name
labels = local.labels
}
spec {
service_name = "drone"
replicas = var.drone_count
# A landed drone powers off; the next start is the next flight
pod_management_policy = "Parallel"
selector {
match_labels = { app = "drone" }
}
template {
metadata {
labels = merge(local.labels, { app = "drone" })
}
spec {
container {
name = "drone"
image = var.simulator_image
image_pull_policy = "Never" # imported via k3d image import
env {
name = "DRONE_ID"
value_from {
field_ref {
field_path = "metadata.name"
}
}
}
env {
name = "DURATION_S"
value = tostring(var.flight_duration_s)
}
env {
name = "SPEEDUP"
value = tostring(var.speedup)
}
env {
name = "DATA_DIR"
value = "/data"
}
volume_mount {
name = "lake"
mount_path = "/data"
}
resources {
requests = { cpu = "50m", memory = "128Mi" }
limits = { cpu = "500m", memory = "512Mi" }
}
}
volume {
name = "lake"
host_path {
path = var.data_host_path
}
}
}
}
}
}
# --- Exporter + Prometheus + Grafana (observability, docs/07) ----------------
resource "kubernetes_deployment" "exporter" {
metadata {
name = "exporter"
namespace = kubernetes_namespace.swarm.metadata[0].name
labels = local.labels
}
spec {
replicas = 1
selector {
match_labels = { app = "exporter" }
}
template {
metadata {
labels = merge(local.labels, { app = "exporter" })
}
spec {
container {
name = "exporter"
image = var.simulator_image
image_pull_policy = "Never"
command = ["python", "monitoring/exporter.py"]
env {
name = "DATA_DIR"
value = "/data"
}
env {
name = "EXPORTER_PORT"
value = "9105"
}
port {
container_port = 9105
}
volume_mount {
name = "lake"
mount_path = "/data"
read_only = true
}
}
volume {
name = "lake"
host_path {
path = var.data_host_path
}
}
}
}
}
}
resource "kubernetes_service" "exporter" {
metadata {
name = "exporter"
namespace = kubernetes_namespace.swarm.metadata[0].name
}
spec {
selector = { app = "exporter" }
port {
port = 9105
target_port = 9105
}
}
}
resource "kubernetes_deployment" "explorer" {
metadata {
name = "explorer"
namespace = kubernetes_namespace.swarm.metadata[0].name
labels = local.labels
}
spec {
replicas = 1
selector {
match_labels = { app = "explorer" }
}
template {
metadata {
labels = merge(local.labels, { app = "explorer" })
}
spec {
container {
name = "explorer"
image = var.simulator_image
image_pull_policy = "Never"
command = ["python", "explorer/server.py"]
env {
name = "DATA_DIR"
value = "/data"
}
env {
name = "EXPLORER_PORT"
value = "8088"
}
port {
container_port = 8088
}
volume_mount {
name = "lake"
mount_path = "/data"
read_only = true
}
}
volume {
name = "lake"
host_path {
path = var.data_host_path
}
}
}
}
}
}
resource "kubernetes_service" "explorer" {
metadata {
name = "explorer"
namespace = kubernetes_namespace.swarm.metadata[0].name
}
spec {
type = "NodePort"
selector = { app = "explorer" }
port {
port = 8088
target_port = 8088
node_port = var.node_ports.explorer
}
}
}
resource "kubernetes_config_map" "prometheus" {
metadata {
name = "prometheus-config"
namespace = kubernetes_namespace.swarm.metadata[0].name
}
data = {
"prometheus.yml" = <<-EOT
global:
scrape_interval: 5s
scrape_configs:
- job_name: swarm
static_configs:
- targets: ["exporter:9105"]
EOT
}
}
resource "kubernetes_deployment" "prometheus" {
metadata {
name = "prometheus"
namespace = kubernetes_namespace.swarm.metadata[0].name
labels = local.labels
}
spec {
replicas = 1
selector {
match_labels = { app = "prometheus" }
}
template {
metadata {
labels = merge(local.labels, { app = "prometheus" })
}
spec {
container {
name = "prometheus"
image = "prom/prometheus:v2.53.0"
port {
container_port = 9090
}
volume_mount {
name = "config"
mount_path = "/etc/prometheus"
}
}
volume {
name = "config"
config_map {
name = kubernetes_config_map.prometheus.metadata[0].name
}
}
}
}
}
}
resource "kubernetes_service" "prometheus" {
metadata {
name = "prometheus"
namespace = kubernetes_namespace.swarm.metadata[0].name
}
spec {
type = "NodePort"
selector = { app = "prometheus" }
port {
port = 9090
target_port = 9090
node_port = var.node_ports.prometheus
}
}
}
resource "kubernetes_config_map" "grafana_provisioning" {
metadata {
name = "grafana-provisioning"
namespace = kubernetes_namespace.swarm.metadata[0].name
}
data = {
"datasource.yml" = <<-EOT
apiVersion: 1
deleteDatasources:
- name: Prometheus
orgId: 1
datasources:
- name: Prometheus
uid: swarm-prom
type: prometheus
access: proxy
url: http://prometheus:9090
isDefault: true
EOT
"dashboards.yml" = <<-EOT
apiVersion: 1
providers:
- name: swarm
folder: ""
type: file
options:
path: /var/lib/grafana/dashboards
EOT
}
}
resource "kubernetes_config_map" "grafana_dashboard" {
metadata {
name = "grafana-dashboard"
namespace = kubernetes_namespace.swarm.metadata[0].name
}
data = {
"swarm.json" = file("${path.module}/../../../simulator/monitoring/grafana/dashboards/swarm.json")
}
}
resource "kubernetes_deployment" "grafana" {
metadata {
name = "grafana"
namespace = kubernetes_namespace.swarm.metadata[0].name
labels = local.labels
}
spec {
replicas = 1
selector {
match_labels = { app = "grafana" }
}
template {
metadata {
labels = merge(local.labels, { app = "grafana" })
}
spec {
container {
name = "grafana"
image = "grafana/grafana:11.1.0"
port {
container_port = 3000
}
env {
name = "GF_AUTH_ANONYMOUS_ENABLED"
value = "true"
}
env {
name = "GF_AUTH_ANONYMOUS_ORG_ROLE"
value = "Admin"
}
env {
name = "GF_AUTH_DISABLE_LOGIN_FORM"
value = "true"
}
# Air-gap hygiene — same flags as the Compose profile
env {
name = "GF_ANALYTICS_REPORTING_ENABLED"
value = "false"
}
env {
name = "GF_ANALYTICS_CHECK_FOR_UPDATES"
value = "false"
}
env {
name = "GF_ANALYTICS_CHECK_FOR_PLUGIN_UPDATES"
value = "false"
}
volume_mount {
name = "provisioning-datasources"
mount_path = "/etc/grafana/provisioning/datasources"
}
volume_mount {
name = "provisioning-dashboards"
mount_path = "/etc/grafana/provisioning/dashboards"
}
volume_mount {
name = "dashboards"
mount_path = "/var/lib/grafana/dashboards"
}
}
volume {
name = "provisioning-datasources"
config_map {
name = kubernetes_config_map.grafana_provisioning.metadata[0].name
items {
key = "datasource.yml"
path = "datasource.yml"
}
}
}
volume {
name = "provisioning-dashboards"
config_map {
name = kubernetes_config_map.grafana_provisioning.metadata[0].name
items {
key = "dashboards.yml"
path = "dashboards.yml"
}
}
}
volume {
name = "dashboards"
config_map {
name = kubernetes_config_map.grafana_dashboard.metadata[0].name
}
}
}
}
}
}
resource "kubernetes_service" "grafana" {
metadata {
name = "grafana"
namespace = kubernetes_namespace.swarm.metadata[0].name
}
spec {
type = "NodePort"
selector = { app = "grafana" }
port {
port = 3000
target_port = 3000
node_port = var.node_ports.grafana
}
}
}
+23
View File
@@ -0,0 +1,23 @@
output "explorer_url" {
description = "Data-plane explorer (partition tree + read-only SQL)"
value = "http://localhost:${var.node_ports.explorer}"
}
output "grafana_url" {
description = "Grafana dashboards"
value = "http://localhost:${var.node_ports.grafana}"
}
output "prometheus_url" {
description = "Prometheus"
value = "http://localhost:${var.node_ports.prometheus}"
}
output "fleet" {
description = "Deployed fleet shape"
value = {
drones = var.drone_count
flight_duration_s = var.flight_duration_s
speedup = var.speedup
}
}
+66
View File
@@ -0,0 +1,66 @@
variable "kubeconfig" {
description = "Path to the kubeconfig for the simulation cluster"
type = string
default = "~/.kube/config"
}
variable "kube_context" {
description = "Kubeconfig context of the k3d simulation cluster"
type = string
default = "k3d-swarm-sim"
}
variable "namespace" {
description = "Namespace for the simulated fleet"
type = string
default = "swarm"
}
variable "simulator_image" {
description = "Simulator image (imported into k3d by infra/ansible/sim-cluster.yml)"
type = string
default = "swarm-house/simulator:dev"
}
variable "drone_count" {
description = "Number of virtual drones in the fleet"
type = number
default = 5
validation {
condition = var.drone_count >= 1 && var.drone_count <= 32
error_message = "drone_count must be between 1 and 32."
}
}
variable "flight_duration_s" {
description = "Simulated flight length in seconds; each pod restart begins a new flight"
type = number
default = 300
}
variable "speedup" {
description = "Wall-clock acceleration of the simulation"
type = number
default = 2
}
variable "data_host_path" {
description = "Host path inside the k3d node mounted as the shared Parquet lake"
type = string
default = "/data"
}
variable "node_ports" {
description = "Host-reachable NodePorts (must match the ports opened by sim-cluster.yml)"
type = object({
explorer = number
grafana = number
prometheus = number
})
default = {
explorer = 30088
grafana = 30300
prometheus = 30990
}
}
+15
View File
@@ -0,0 +1,15 @@
terraform {
required_version = ">= 1.5"
required_providers {
kubernetes = {
source = "hashicorp/kubernetes"
version = "~> 2.33"
}
}
}
provider "kubernetes" {
config_path = var.kubeconfig
config_context = var.kube_context
}
+105 -12
View File
@@ -1,6 +1,9 @@
import { useEffect, useMemo, useRef, useState } from "react";
import { DEFAULT_EXPLORER_URL, fetchLivePoses, toLiveWorld } from "./live";
import {
AREA,
MAX_ASPECT,
areaWidth,
fmtBytes,
makeWorld,
seed,
@@ -9,24 +12,56 @@ import {
} from "./sim";
const VIEW = 1000;
const PANEL_W = 320;
const HEADER_H = 70;
// Patrol field aspect ratio for the current window: wide monitors get a
// wider field instead of empty side margins. Quantized to 0.25 steps so
// minor resizes don't rebuild the world.
function displayAspect(): number {
const w = Math.max(320, window.innerWidth - PANEL_W);
const h = Math.max(320, window.innerHeight - HEADER_H);
const q = Math.round((w / h) * 4) / 4;
return Math.max(1, Math.min(MAX_ASPECT, q));
}
const LIVE_POLL_MS = 1000;
export default function App(): JSX.Element {
const [droneCount, setDroneCount] = useState(8);
const [speedup, setSpeedup] = useState(1);
const [paused, setPaused] = useState(false);
const [aspect, setAspect] = useState(displayAspect);
const [mode, setMode] = useState<"sim" | "live">("sim");
const [liveError, setLiveError] = useState<string | null>(null);
const [world, setWorld] = useState<World>(() => {
seed(42);
return makeWorld(8);
return makeWorld(8, displayAspect());
});
const raf = useRef(0);
const last = useRef(performance.now());
const liveWorld = useRef<World | null>(null);
useEffect(() => {
seed(42);
setWorld(makeWorld(droneCount));
}, [droneCount]);
setWorld(makeWorld(droneCount, aspect));
}, [droneCount, aspect]);
useEffect(() => {
let timer = 0;
const onResize = (): void => {
window.clearTimeout(timer);
timer = window.setTimeout(() => setAspect(displayAspect()), 250);
};
window.addEventListener("resize", onResize);
return () => {
window.clearTimeout(timer);
window.removeEventListener("resize", onResize);
};
}, []);
useEffect(() => {
if (mode !== "sim") return;
const loop = (now: number): void => {
const dt = Math.min(0.05, (now - last.current) / 1000);
last.current = now;
@@ -37,7 +72,40 @@ export default function App(): JSX.Element {
};
raf.current = requestAnimationFrame(loop);
return () => cancelAnimationFrame(raf.current);
}, [paused, speedup]);
}, [paused, speedup, mode]);
// Live mode: poll the explorer's read-only SQL API for real poses
useEffect(() => {
if (mode !== "live") return;
let cancelled = false;
const poll = async (): Promise<void> => {
try {
const poses = await fetchLivePoses(DEFAULT_EXPLORER_URL);
if (cancelled) return;
setLiveError(poses.length === 0 ? "no drone data in the lake yet" : null);
liveWorld.current = toLiveWorld(poses, liveWorld.current, LIVE_POLL_MS / 1000);
setWorld(liveWorld.current);
} catch (err) {
if (!cancelled) setLiveError(err instanceof Error ? err.message : String(err));
}
};
void poll();
const timer = window.setInterval(() => void poll(), LIVE_POLL_MS);
return () => {
cancelled = true;
window.clearInterval(timer);
};
}, [mode]);
useEffect(() => {
if (mode === "sim") {
liveWorld.current = null;
setLiveError(null);
seed(42);
setWorld(makeWorld(droneCount, aspect));
}
// eslint-disable-next-line react-hooks/exhaustive-deps -- reset only on mode change
}, [mode]);
const activeLinks = useMemo(
() => [...world.links.values()].sort((a, b) => b.rate - a.rate),
@@ -55,6 +123,20 @@ export default function App(): JSX.Element {
</div>
</div>
<div style={styles.controls}>
<button
style={{ ...styles.button, ...(mode === "live" ? styles.buttonActive : {}) }}
onClick={() => setMode((m) => (m === "sim" ? "live" : "sim"))}
title={`live source: ${DEFAULT_EXPLORER_URL}`}
>
{mode === "sim" ? "go live" : "back to sim"}
</button>
{mode === "live" && (
<span style={liveError ? styles.liveError : styles.liveOk}>
{liveError ?? `live · ${DEFAULT_EXPLORER_URL}`}
</span>
)}
{mode === "sim" && (
<>
<label style={styles.label}>
drones
<input
@@ -81,12 +163,14 @@ export default function App(): JSX.Element {
<button style={styles.button} onClick={() => setPaused((p) => !p)}>
{paused ? "resume" : "pause"}
</button>
</>
)}
</div>
</header>
<div style={styles.main}>
<svg
viewBox={`0 0 ${VIEW} ${VIEW}`}
viewBox={`0 0 ${sx(areaWidth())} ${VIEW}`}
style={styles.canvas}
preserveAspectRatio="xMidYMid meet"
>
@@ -96,7 +180,7 @@ export default function App(): JSX.Element {
<stop offset="100%" stopColor="#0a0f18" />
</radialGradient>
</defs>
<rect width={VIEW} height={VIEW} fill="url(#ground)" />
<rect width={sx(areaWidth())} height={VIEW} fill="url(#ground)" />
{gridLines()}
{/* Mesh links */}
@@ -155,7 +239,7 @@ export default function App(): JSX.Element {
>
<polygon points="0,-11 7,9 0,5 -7,9" fill="#e8ecf4" stroke="#7ea0d0" strokeWidth={1} />
<text y={24} style={styles.droneLabel as never} transform={`rotate(${-((d.heading * 180) / Math.PI + 90)})`}>
dr-{String(d.id + 1).padStart(2, "0")} · ch{d.channel} · {d.battery.toFixed(0)}%
{d.name ?? `dr-${String(d.id + 1).padStart(2, "0")} · ch${d.channel}`} · {d.battery.toFixed(0)}%
</text>
</g>
))}
@@ -173,7 +257,8 @@ export default function App(): JSX.Element {
{busiest.map((l) => (
<div key={l.key} style={styles.linkRow}>
<span style={styles.linkName}>
dr-{String(l.a + 1).padStart(2, "0")} dr-{String(l.b + 1).padStart(2, "0")}
{world.drones[l.a]?.name ?? `dr-${String(l.a + 1).padStart(2, "0")}`} {" "}
{world.drones[l.b]?.name ?? `dr-${String(l.b + 1).padStart(2, "0")}`}
</span>
<span style={styles.linkStat}>
{fmtBytes(l.rate)}/s · {fmtBytes(l.totalUp)} {fmtBytes(l.totalDown)}
@@ -202,12 +287,17 @@ function sy(y: number): number {
}
function gridLines(): JSX.Element {
const width = sx(areaWidth());
const step = VIEW / 10; // one cell per 100 m in both directions
const lines = [];
for (let i = 1; i < 10; i++) {
const p = (i / 10) * VIEW;
for (let p = step; p < width; p += step) {
lines.push(
<line key={`v${i}`} x1={p} y1={0} x2={p} y2={VIEW} stroke="#1a2436" strokeWidth={1} />,
<line key={`h${i}`} x1={0} y1={p} x2={VIEW} y2={p} stroke="#1a2436" strokeWidth={1} />,
<line key={`v${p}`} x1={p} y1={0} x2={p} y2={VIEW} stroke="#1a2436" strokeWidth={1} />,
);
}
for (let p = step; p < VIEW; p += step) {
lines.push(
<line key={`h${p}`} x1={0} y1={p} x2={width} y2={p} stroke="#1a2436" strokeWidth={1} />,
);
}
return <g>{lines}</g>;
@@ -264,6 +354,9 @@ const styles: Record<string, React.CSSProperties> = {
fontSize: 12,
cursor: "pointer",
},
buttonActive: { background: "#1a3a2a", color: "#39d98a", borderColor: "#2a5c3c" },
liveOk: { fontSize: 11, color: "#39d98a" },
liveError: { fontSize: 11, color: "#c05a6a" },
main: { display: "flex", flex: 1, gap: 0, minHeight: 0 },
canvas: { flex: 1, minWidth: 0, display: "block" },
panel: {
+129
View File
@@ -0,0 +1,129 @@
// Live mode: real drone poses from the explorer's read-only SQL API.
// The same gated /api/query endpoint a peer drone (or an engineer on the
// bench) would use — the prototype is just another read-only consumer.
import { AREA, LINK_RANGE, POSE_RATE_BYTES, type LinkStats, type World } from "./sim";
export const DEFAULT_EXPLORER_URL =
(import.meta.env.VITE_EXPLORER_URL as string | undefined) ?? "http://localhost:30088";
export interface LivePose {
id: string;
x: number; // meters, mission frame
y: number;
yawDeg: number;
battery: number | null;
tsNs: number;
}
// Latest pose per drone from its own 'sent' state rows, joined with the
// latest battery reading from telemetry. arg_max keeps it a single scan.
const LIVE_SQL = `
WITH pose AS (
SELECT drone,
arg_max(pos_x, ts_ns) AS x,
arg_max(pos_y, ts_ns) AS y,
arg_max(yaw, ts_ns) AS yaw,
max(ts_ns) AS ts_ns
FROM state
WHERE direction = 'sent'
GROUP BY drone
),
batt AS (
SELECT drone, arg_max(level_pct, ts_ns) AS battery
FROM telemetry
WHERE sensor = 'battery'
GROUP BY drone
)
SELECT p.drone, p.x, p.y, p.yaw, p.ts_ns, b.battery
FROM pose p LEFT JOIN batt b USING (drone)
ORDER BY p.drone`;
interface QueryResponse {
columns?: string[];
rows?: (string | number | null)[][];
error?: string;
}
export async function fetchLivePoses(baseUrl: string): Promise<LivePose[]> {
const res = await fetch(`${baseUrl.replace(/\/$/, "")}/api/query`, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ sql: LIVE_SQL }),
});
if (!res.ok) throw new Error(`explorer responded ${res.status}`);
const data = (await res.json()) as QueryResponse;
if (data.error) throw new Error(data.error);
return (data.rows ?? []).map((r) => ({
id: String(r[0]),
x: Number(r[1]),
y: Number(r[2]),
yawDeg: Number(r[3]),
tsNs: Number(r[4]),
battery: r[5] === null ? null : Number(r[5]),
}));
}
// Scale mission-frame meters into the prototype's square view. The virtual
// drones patrol a smaller square than the sim world, so fit the observed
// extent (with padding) instead of assuming a size.
function fitScale(poses: LivePose[]): number {
const extent = Math.max(400, ...poses.map((p) => Math.max(p.x, p.y))) * 1.15;
return AREA / extent;
}
function linkKey(a: number, b: number): string {
return a < b ? `${a}-${b}` : `${b}-${a}`;
}
/** Convert live poses into the World shape the renderer already speaks. */
export function toLiveWorld(poses: LivePose[], prev: World | null, dtS: number): World {
const k = fitScale(poses);
const drones = poses.map((p, i) => ({
id: i,
name: p.id,
pos: { x: p.x * k, y: p.y * k },
vel: { x: 0, y: 0 },
heading: (p.yawDeg * Math.PI) / 180,
waypoint: 0,
battery: p.battery ?? 100,
channel: 0,
}));
// Every in-range pair exchanges pose broadcasts; accumulate totals so the
// panel keeps its meaning between polls.
const links = new Map<string, LinkStats>();
let totalBytes = prev?.totalBytes ?? 0;
for (let i = 0; i < drones.length; i++) {
for (let j = i + 1; j < drones.length; j++) {
const dist = Math.hypot(
drones[i].pos.x - drones[j].pos.x,
drones[i].pos.y - drones[j].pos.y,
);
if (dist > LINK_RANGE) continue;
const key = linkKey(i, j);
const old = prev?.links.get(key);
const bytes = POSE_RATE_BYTES * 2 * dtS;
totalBytes += bytes;
links.set(key, {
key,
a: i,
b: j,
totalUp: (old?.totalUp ?? 0) + bytes / 2,
totalDown: (old?.totalDown ?? 0) + bytes / 2,
rate: POSE_RATE_BYTES * 2,
flash: 0.6,
bulk: 0,
});
}
}
return {
t: (prev?.t ?? 0) + dtS,
drones,
obstacles: [],
links,
totalBytes,
broadcasts: (prev?.broadcasts ?? 0) + links.size * 2,
};
}
+43 -24
View File
@@ -9,6 +9,7 @@ export interface Vec {
export interface Drone {
id: number;
name?: string; // live mode: real drone_id from the data plane
pos: Vec;
vel: Vec;
heading: number; // radians
@@ -45,12 +46,21 @@ export interface World {
broadcasts: number;
}
export const AREA = 1000; // meters, square side
export const AREA = 1000; // meters, vertical extent of the field
export const MAX_ASPECT = 2.2;
// Horizontal extent follows the display aspect ratio (set via makeWorld),
// so wide monitors get a genuinely wider patrol area, not empty margins.
let areaX = AREA;
export function areaWidth(): number {
return areaX;
}
export const LINK_RANGE = 320;
const CRUISE = 28;
const SEPARATION = 55;
const POSE_BYTES = 46;
const POSE_HZ = 5;
// Steady per-link broadcast throughput (both directions), bytes/s
export const POSE_RATE_BYTES = POSE_BYTES * POSE_HZ;
const CHANNELS = [1, 6, 11, 36, 40, 44, 149, 157];
let seedState = 1234;
@@ -68,21 +78,26 @@ function rnd(): number {
// Two interleaved patrol routes: even drones circle the perimeter, odd
// drones fly an X through the center. Paths cross mid-field, so the mesh
// keeps bridging between the front and the back of the formation instead
// of stretching into disconnected segments along one loop.
const PERIMETER: Vec[] = [
// of stretching into disconnected segments along one loop. Routes are
// derived from the current field width, so they stretch on wide displays.
function perimeterRoute(): Vec[] {
return [
{ x: 120, y: 120 },
{ x: AREA - 120, y: 150 },
{ x: AREA - 150, y: AREA - 120 },
{ x: areaX - 120, y: 150 },
{ x: areaX - 150, y: AREA - 120 },
{ x: 150, y: AREA - 150 },
];
const CROSS: Vec[] = [
];
}
function crossRoute(): Vec[] {
return [
{ x: 150, y: 150 },
{ x: AREA - 150, y: AREA - 150 },
{ x: AREA - 150, y: 150 },
{ x: areaX - 150, y: AREA - 150 },
{ x: areaX - 150, y: 150 },
{ x: 150, y: AREA - 150 },
];
];
}
function routeOf(d: Drone): Vec[] {
return d.id % 2 === 0 ? PERIMETER : CROSS;
return d.id % 2 === 0 ? perimeterRoute() : crossRoute();
}
// Transit objects enter at one edge, cross the whole area, and respawn at
@@ -91,14 +106,15 @@ function routeOf(d: Drone): Vec[] {
const TRANSIT_MARGIN = 120;
function spawnTransit(id: number): Obstacle {
const speed = 26 + rnd() * 30;
const along = 120 + rnd() * (AREA - 240);
const alongX = 120 + rnd() * (areaX - 240);
const alongY = 120 + rnd() * (AREA - 240);
const skew = (rnd() - 0.5) * speed * 0.9; // diagonal-ish crossings
const edge = Math.floor(rnd() * 4);
const table: { pos: Vec; vel: Vec }[] = [
{ pos: { x: along, y: -TRANSIT_MARGIN + 20 }, vel: { x: skew, y: speed } },
{ pos: { x: along, y: AREA + TRANSIT_MARGIN - 20 }, vel: { x: skew, y: -speed } },
{ pos: { x: -TRANSIT_MARGIN + 20, y: along }, vel: { x: speed, y: skew } },
{ pos: { x: AREA + TRANSIT_MARGIN - 20, y: along }, vel: { x: -speed, y: skew } },
{ pos: { x: alongX, y: -TRANSIT_MARGIN + 20 }, vel: { x: skew, y: speed } },
{ pos: { x: alongX, y: AREA + TRANSIT_MARGIN - 20 }, vel: { x: skew, y: -speed } },
{ pos: { x: -TRANSIT_MARGIN + 20, y: alongY }, vel: { x: speed, y: skew } },
{ pos: { x: areaX + TRANSIT_MARGIN - 20, y: alongY }, vel: { x: -speed, y: skew } },
];
const { pos, vel } = table[edge];
return { id, pos, radius: 22 + rnd() * 16, moving: true, vel };
@@ -106,32 +122,35 @@ function spawnTransit(id: number): Obstacle {
function outOfTransit(ob: Obstacle): boolean {
return (
ob.pos.x < -TRANSIT_MARGIN ||
ob.pos.x > AREA + TRANSIT_MARGIN ||
ob.pos.x > areaX + TRANSIT_MARGIN ||
ob.pos.y < -TRANSIT_MARGIN ||
ob.pos.y > AREA + TRANSIT_MARGIN
);
}
export function makeWorld(droneCount: number): World {
export function makeWorld(droneCount: number, aspect = 1): World {
areaX = AREA * Math.max(1, Math.min(MAX_ASPECT, aspect));
const drones: Drone[] = Array.from({ length: droneCount }, (_, i) => {
const angle = (i / droneCount) * Math.PI * 2;
return {
id: i,
pos: {
x: AREA / 2 + Math.cos(angle) * (150 + rnd() * 120),
x: areaX / 2 + Math.cos(angle) * (150 + rnd() * 120),
y: AREA / 2 + Math.sin(angle) * (150 + rnd() * 120),
},
vel: { x: 0, y: 0 },
heading: angle,
waypoint: i % PERIMETER.length,
waypoint: i % 4,
battery: 90 + rnd() * 10,
channel: CHANNELS[i % CHANNELS.length],
};
});
// Static obstacles sit at fixed fractions of the field, so they spread
// out instead of clustering left when the field widens
const obstacles: Obstacle[] = [
{ id: 0, pos: { x: 340, y: 420 }, radius: 60, moving: false, vel: { x: 0, y: 0 } },
{ id: 1, pos: { x: 700, y: 260 }, radius: 45, moving: false, vel: { x: 0, y: 0 } },
{ id: 2, pos: { x: 560, y: 720 }, radius: 70, moving: false, vel: { x: 0, y: 0 } },
{ id: 0, pos: { x: areaX * 0.34, y: 420 }, radius: 60, moving: false, vel: { x: 0, y: 0 } },
{ id: 1, pos: { x: areaX * 0.7, y: 260 }, radius: 45, moving: false, vel: { x: 0, y: 0 } },
{ id: 2, pos: { x: areaX * 0.56, y: 720 }, radius: 70, moving: false, vel: { x: 0, y: 0 } },
spawnTransit(3),
spawnTransit(4),
spawnTransit(5),
@@ -189,7 +208,7 @@ function steer(d: Drone, world: World, dt: number): Drone {
vel: { x: vx, y: vy },
heading,
pos: {
x: Math.max(20, Math.min(AREA - 20, d.pos.x + vx * dt)),
x: Math.max(20, Math.min(areaX - 20, d.pos.x + vx * dt)),
y: Math.max(20, Math.min(AREA - 20, d.pos.y + vy * dt)),
},
battery: Math.max(0, d.battery - dt * 0.05),
+1
View File
@@ -0,0 +1 @@
/// <reference types="vite/client" />
+3
View File
@@ -0,0 +1,3 @@
data
.venv
README.md
+24
View File
@@ -1,9 +1,33 @@
FROM python:3.12-slim AS test
WORKDIR /app
COPY requirements.txt .
RUN --mount=type=cache,target=/root/.cache/pip pip install -r requirements.txt pytest
COPY virtual_drone ./virtual_drone
COPY monitoring ./monitoring
COPY explorer ./explorer
COPY tests ./tests
RUN groupadd --gid 10001 swarm \
&& useradd --uid 10001 --gid swarm --home-dir /app --shell /usr/sbin/nologin swarm \
&& chown -R swarm:swarm /app
USER swarm
RUN pytest tests/ -q
FROM python:3.12-slim
WORKDIR /app
COPY requirements.txt .
RUN --mount=type=cache,target=/root/.cache/pip pip install -r requirements.txt
COPY virtual_drone ./virtual_drone
# Monitoring and explorer ship in the same image so Kubernetes can run
# them without bind mounts (Compose overrides these with live mounts)
COPY monitoring ./monitoring
COPY explorer ./explorer
RUN groupadd --gid 10001 swarm \
&& useradd --uid 10001 --gid swarm --home-dir /app --shell /usr/sbin/nologin swarm \
&& mkdir -p /data \
&& chown -R swarm:swarm /app /data
ENV DATA_DIR=/data
USER swarm
CMD ["python", "-m", "virtual_drone.main"]
+6 -4
View File
@@ -14,14 +14,16 @@ FLIGHT_ID=$(date -u +%Y%m%dT%H%MZ)-sim docker compose up --build --scale drone=5
DRONE_COUNT=10 DURATION_S=300 SPEEDUP=4 docker compose up --build --scale drone=10
```
Output lands in `./data/` with the standard layout:
Output lands in [`../var/t1/`](../var/t1/) (the shared T1 lake — same path the k3d fleet and warehouse offload use). Override with `SWARM_T1_DIR` if needed:
```
data/dataset=telemetry/flight=…/drone=…/sensor=imu/year=…/…/hour=…/data.parquet
data/dataset=detections/flight=…/drone=…/…
data/dataset=state/flight=…/drone=…/… ← sent + received broadcasts
var/t1/dataset=telemetry/flight=…/drone=…/sensor=imu/year=…/…/hour=…/data.parquet
var/t1/dataset=detections/flight=…/drone=…/…
var/t1/dataset=state/flight=…/drone=…/… ← sent + received broadcasts
```
Historical flights after offload live under [`../var/t3/`](../var/t3/) (T3 warehouse).
## Run a single drone without Docker
```bash
+7 -3
View File
@@ -14,7 +14,7 @@ services:
# Compose default bridge network: subnet-directed broadcast works
BROADCAST_ADDR: ${BROADCAST_ADDR:-255.255.255.255}
volumes:
- ./data:/data
- ${SWARM_T1_DIR:-../var/t1}:/data
# --- Monitoring profile: docker compose --profile monitoring up ---
@@ -26,7 +26,7 @@ services:
DATA_DIR: /data
SCAN_INTERVAL_S: "5"
volumes:
- ./data:/data:ro
- ${SWARM_T1_DIR:-../var/t1}:/data:ro
- ./monitoring:/app/monitoring:ro
ports:
- "${EXPORTER_PORT:-9105}:9105"
@@ -38,7 +38,7 @@ services:
environment:
DATA_DIR: /data
volumes:
- ./data:/data:ro
- ${SWARM_T1_DIR:-../var/t1}:/data:ro
- ./explorer:/app/explorer:ro
ports:
- "${EXPLORER_UI_PORT:-8088}:8088"
@@ -58,6 +58,10 @@ services:
GF_AUTH_ANONYMOUS_ENABLED: "true"
GF_AUTH_ANONYMOUS_ORG_ROLE: Admin
GF_AUTH_DISABLE_LOGIN_FORM: "true"
# Air-gap hygiene: no phone-home, no update checks, no plugin fetches
GF_ANALYTICS_REPORTING_ENABLED: "false"
GF_ANALYTICS_CHECK_FOR_UPDATES: "false"
GF_ANALYTICS_CHECK_FOR_PLUGIN_UPDATES: "false"
volumes:
- ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
- ./monitoring/grafana/dashboards:/var/lib/grafana/dashboards:ro
+10
View File
@@ -116,9 +116,19 @@ class Handler(BaseHTTPRequestHandler):
self.send_response(code)
self.send_header("Content-Type", ctype)
self.send_header("Content-Length", str(len(body)))
# Dev CORS: lets the prototype's live mode poll the API from another
# origin. Everything behind this is read-only by construction.
self.send_header("Access-Control-Allow-Origin", "*")
self.end_headers()
self.wfile.write(body)
def do_OPTIONS(self) -> None: # noqa: N802 — http.server API
self.send_response(204)
self.send_header("Access-Control-Allow-Origin", "*")
self.send_header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
self.send_header("Access-Control-Allow-Headers", "Content-Type")
self.end_headers()
def _json(self, payload: dict, code: int = 200) -> None:
self._send(code, json.dumps(payload, default=str).encode(), "application/json")
+1
View File
@@ -1,3 +1,4 @@
pyarrow>=16.0
duckdb>=1.0
pytz>=2024.1 # duckdb needs it to fetch TIMESTAMPTZ values into Python
pytest>=8.0
View File
+46
View File
@@ -0,0 +1,46 @@
"""Pose broadcast frame encode/decode roundtrip."""
from __future__ import annotations
import pytest
from virtual_drone.broadcast import FRAME, decode_state, encode_state
from virtual_drone.flight import Pose
def test_frame_size_matches_wire_spec() -> None:
# Documented as 46 B in docs/04; struct packs to FRAME.size (45 B on this layout).
assert FRAME.size == 45
def test_encode_decode_roundtrip() -> None:
pose = Pose(
ts_ns=1_700_000_000_000_000_000,
x=123.456,
y=78.9,
z=60.0,
roll=1.5,
pitch=-2.0,
yaw=45.0,
vx=3.2,
vy=-1.1,
vz=0.05,
)
payload = encode_state("dr-01", pose, flags=0)
assert len(payload) == FRAME.size
decoded = decode_state(payload)
assert decoded is not None
assert decoded["peer_id"] == "dr-01"
assert decoded["ts_ns"] == pose.ts_ns
assert decoded["pos_x"] == pytest.approx(pose.x, abs=0.001)
assert decoded["pos_y"] == pytest.approx(pose.y, abs=0.001)
assert decoded["pos_z"] == pytest.approx(pose.z, abs=0.001)
assert decoded["roll"] == pytest.approx(pose.roll, abs=0.01)
assert decoded["pitch"] == pytest.approx(pose.pitch, abs=0.01)
assert decoded["yaw"] == pytest.approx(pose.yaw, abs=0.01)
def test_rejects_invalid_payload() -> None:
assert decode_state(b"short") is None
assert decode_state(b"XX" + b"\0" * (FRAME.size - 2)) is None
+35
View File
@@ -0,0 +1,35 @@
"""Flight kinematics — waypoint patrol and step integration."""
from __future__ import annotations
import random
from virtual_drone.config import Config
from virtual_drone.flight import initial_pose, make_waypoints, step
def test_make_waypoints_returns_closed_perimeter() -> None:
cfg = Config()
rng = random.Random(7)
wps = make_waypoints(cfg, rng)
assert len(wps) == 4
assert all(len(p) == 2 for p in wps)
def test_step_moves_toward_target() -> None:
cfg = Config()
rng = random.Random(3)
pose = initial_pose(cfg, rng, 1_000_000_000)
target = (pose.x + 50.0, pose.y + 50.0)
next_pose, _ = step(pose, target, cfg, rng, dt=0.1, ts_ns=1_100_000_000)
dist_before = ((target[0] - pose.x) ** 2 + (target[1] - pose.y) ** 2) ** 0.5
dist_after = ((target[0] - next_pose.x) ** 2 + (target[1] - next_pose.y) ** 2) ** 0.5
assert dist_after < dist_before
def test_reached_when_close_to_waypoint() -> None:
cfg = Config()
rng = random.Random(1)
pose = initial_pose(cfg, rng, 2_000_000_000)
_, reached = step(pose, (pose.x, pose.y), cfg, rng, dt=1.0, ts_ns=2_100_000_000)
assert reached is True
+35
View File
@@ -0,0 +1,35 @@
"""Read-only SQL gate — same rules as the peer-query forced command."""
from __future__ import annotations
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "explorer"))
from server import gate # noqa: E402
def test_allows_read_statements() -> None:
assert gate("SELECT 1") is None
assert gate("WITH t AS (SELECT 1) SELECT * FROM t") is None
assert gate("DESCRIBE telemetry") is None
assert gate("SUMMARIZE state") is None
assert gate("SHOW TABLES") is None
def test_rejects_writes_and_config() -> None:
assert gate("DROP TABLE telemetry") is not None
assert gate("INSERT INTO t VALUES (1)") is not None
assert gate("UPDATE t SET x=1") is not None
assert gate("DELETE FROM t") is not None
assert gate("CREATE TABLE t (x INT)") is not None
assert gate("INSTALL httpfs") is not None
assert gate("SET memory_limit='1GB'") is not None
assert gate("PRAGMA threads=4") is not None
def test_rejects_multi_statement_and_injection() -> None:
assert gate("SELECT 1; SELECT 2") is not None
assert gate("/* sneaky */ COPY t TO 'x'") is not None
assert gate("") is not None
+67
View File
@@ -0,0 +1,67 @@
"""Hive-partitioned Parquet writer layout."""
from __future__ import annotations
import time
from pathlib import Path
import duckdb
from virtual_drone.flight import Pose
from virtual_drone.sensors import imu_row
from virtual_drone.writer import PartitionWriter, make_writers
def test_partition_path_follows_hive_layout(tmp_path: Path) -> None:
ts_ns = int(time.time() * 1e9)
writer = PartitionWriter(tmp_path, "telemetry", "flt-01", "dr-01", "imu")
writer.append(imu_row(
Pose(ts_ns=ts_ns, x=1.0, y=2.0, z=3.0, roll=0.0, pitch=0.0, yaw=0.0, vx=0.0, vy=0.0, vz=0.0),
__import__("random").Random(0),
ts_ns,
))
writer.seal()
files = list(tmp_path.rglob("*.parquet"))
assert len(files) >= 1
path_str = str(files[0])
assert "dataset=telemetry" in path_str
assert "flight=flt-01" in path_str
assert "drone=dr-01" in path_str
assert "sensor=imu" in path_str
assert "year=" in path_str and "hour=" in path_str
def test_seal_compacts_current_blocks(tmp_path: Path) -> None:
writer = PartitionWriter(tmp_path, "state", "flt-02", "dr-02", None)
base_ts = 1_700_000_000_000_000_000
for i in range(3):
writer.append({"ts_ns": base_ts + i * 5_000_000_000, "pos_x": float(i)})
writer.seal()
sealed = list(tmp_path.rglob("data.parquet"))
assert len(sealed) == 1
assert not list(tmp_path.rglob("current/min_*.parquet"))
rows = duckdb.sql(f"SELECT count(*) FROM read_parquet('{sealed[0]}')").fetchone()[0]
assert rows == 3
def test_make_writers_registers_expected_datasets(tmp_path: Path) -> None:
writers = make_writers(tmp_path, "flt-03", "dr-03", ["imu", "battery"])
assert set(writers) == {"imu", "battery", "detections", "state"}
def test_duckdb_reads_written_partition(tmp_path: Path) -> None:
writers = make_writers(tmp_path, "flt-04", "dr-04", ["imu"])
ts_ns = int(time.time() * 1e9)
pose = Pose(ts_ns=ts_ns, x=0.0, y=0.0, z=0.0, roll=0.0, pitch=0.0, yaw=0.0, vx=0.0, vy=0.0, vz=0.0)
writers["imu"].append(imu_row(pose, __import__("random").Random(1), ts_ns))
for w in writers.values():
w.seal()
count = duckdb.sql(f"""
SELECT count(*) FROM read_parquet(
'{tmp_path}/dataset=telemetry/**/*.parquet',
hive_partitioning=true, union_by_name=true)
""").fetchone()[0]
assert count >= 1
View File
View File