Explorer and exporter were scanning the full Parquet lake every 1–5s (~2000 files, 200MB+), driving ~2.2 CPU cores. Limit metrics to the last N flights, cache DuckDB views and the partition tree, slow live polls to 2s, and keep drones alive after seal to stop restart churn. Add node-exporter, scan-duration metrics, and a Swarm Platform Grafana dashboard for node CPU/memory and scan health.
148 lines
5.2 KiB
Python
148 lines
5.2 KiB
Python
"""Prometheus exporter over the simulator's Parquet output.
|
|
|
|
Periodically scans DATA_DIR with DuckDB and exposes fleet statistics as
|
|
/metrics. Scans only the most recent flight partitions by default so CPU
|
|
stays bounded as the lake grows across pod restarts.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import sys
|
|
import threading
|
|
import time
|
|
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
|
from pathlib import Path
|
|
|
|
import duckdb
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parent))
|
|
from lake import flight_window, iter_parquet_files, parquet_reader # noqa: E402
|
|
|
|
DATA_DIR = Path(os.environ.get("DATA_DIR", "./data"))
|
|
PORT = int(os.environ.get("EXPORTER_PORT", "9105"))
|
|
SCAN_INTERVAL_S = float(os.environ.get("SCAN_INTERVAL_S", "15"))
|
|
|
|
_lock = threading.Lock()
|
|
_payload = "# swarm exporter starting\n"
|
|
_last_scan_s = 0.0
|
|
|
|
|
|
def _q(con: duckdb.DuckDBPyConnection, sql: str) -> list[tuple]:
|
|
try:
|
|
return con.sql(sql).fetchall()
|
|
except duckdb.Error:
|
|
return []
|
|
|
|
|
|
def collect() -> str:
|
|
global _last_scan_s
|
|
started = time.monotonic()
|
|
con = duckdb.connect()
|
|
lines: list[str] = []
|
|
|
|
def metric(name: str, help_text: str, mtype: str, rows: list[str]) -> None:
|
|
lines.append(f"# HELP {name} {help_text}")
|
|
lines.append(f"# TYPE {name} {mtype}")
|
|
lines.extend(rows)
|
|
|
|
for ds, name in (
|
|
("telemetry", "swarm_rows_total"),
|
|
("detections", "swarm_detections_total"),
|
|
("state", "swarm_state_frames_total"),
|
|
):
|
|
reader = parquet_reader(DATA_DIR, ds)
|
|
if ds == "telemetry":
|
|
metric(
|
|
name, f"Rows in dataset={ds} (recent {flight_window()} flights)", "gauge",
|
|
[f'{name}{{drone="{d}",sensor="{s}"}} {n}'
|
|
for d, s, n in _q(con, f"SELECT drone, sensor, count(*) FROM read_parquet({reader}) GROUP BY 1,2")],
|
|
)
|
|
elif ds == "detections":
|
|
metric(
|
|
name, "Detection events per drone and class", "gauge",
|
|
[f'{name}{{drone="{d}",cls="{c}"}} {n}'
|
|
for d, c, n in _q(con, f"SELECT drone, cls, count(*) FROM read_parquet({reader}) GROUP BY 1,2")],
|
|
)
|
|
else:
|
|
metric(
|
|
name, "Pose broadcast frames per drone and direction", "gauge",
|
|
[f'{name}{{drone="{d}",direction="{dr}"}} {n}'
|
|
for d, dr, n in _q(con, f"SELECT drone, direction, count(*) FROM read_parquet({reader}) GROUP BY 1,2")],
|
|
)
|
|
|
|
telem = parquet_reader(DATA_DIR, "telemetry")
|
|
metric(
|
|
"swarm_battery_pct", "Latest battery level per drone", "gauge",
|
|
[f'swarm_battery_pct{{drone="{d}"}} {v}'
|
|
for d, v in _q(con, f"""
|
|
SELECT drone, arg_max(level_pct, ts_ns)
|
|
FROM read_parquet({telem})
|
|
WHERE sensor='battery' GROUP BY drone""")],
|
|
)
|
|
metric(
|
|
"swarm_rssi_dbm", "Latest RSSI per drone-peer link", "gauge",
|
|
[f'swarm_rssi_dbm{{drone="{d}",peer="{p}"}} {v}'
|
|
for d, p, v in _q(con, f"""
|
|
SELECT drone, peer_id, arg_max(rssi_dbm, ts_ns)
|
|
FROM read_parquet({telem})
|
|
WHERE sensor='rssi' GROUP BY drone, peer_id""")],
|
|
)
|
|
|
|
files = iter_parquet_files(DATA_DIR)
|
|
metric(
|
|
"swarm_parquet_bytes", "Bytes on disk per dataset (recent flights)", "gauge",
|
|
[f'swarm_parquet_bytes{{dataset="{ds}"}} {sum(f.stat().st_size for f in files if f"dataset={ds}" in str(f))}'
|
|
for ds in ("telemetry", "detections", "state")],
|
|
)
|
|
metric("swarm_parquet_files", "Parquet files scanned (recent flights)", "gauge",
|
|
[f"swarm_parquet_files {len(files)}"])
|
|
metric("swarm_metric_flight_window", "Flight partitions included per dataset", "gauge",
|
|
[f"swarm_metric_flight_window {flight_window()}"])
|
|
|
|
_last_scan_s = time.monotonic() - started
|
|
metric("swarm_exporter_scan_duration_seconds", "Wall time of the last metrics scan", "gauge",
|
|
[f"swarm_exporter_scan_duration_seconds {_last_scan_s:.4f}"])
|
|
con.close()
|
|
return "\n".join(lines) + "\n"
|
|
|
|
|
|
def scanner() -> None:
|
|
global _payload
|
|
while True:
|
|
started = time.monotonic()
|
|
try:
|
|
payload = collect()
|
|
except Exception as exc:
|
|
payload = f"# collect error: {exc}\n"
|
|
with _lock:
|
|
_payload = payload
|
|
time.sleep(max(1.0, SCAN_INTERVAL_S - (time.monotonic() - started)))
|
|
|
|
|
|
class Handler(BaseHTTPRequestHandler):
|
|
def do_GET(self) -> None: # noqa: N802 — http.server API
|
|
if self.path != "/metrics":
|
|
self.send_response(404)
|
|
self.end_headers()
|
|
return
|
|
with _lock:
|
|
body = _payload.encode()
|
|
self.send_response(200)
|
|
self.send_header("Content-Type", "text/plain; version=0.0.4")
|
|
self.send_header("Content-Length", str(len(body)))
|
|
self.end_headers()
|
|
self.wfile.write(body)
|
|
|
|
def log_message(self, *_args: object) -> None:
|
|
pass
|
|
|
|
|
|
if __name__ == "__main__":
|
|
threading.Thread(target=scanner, daemon=True).start()
|
|
print(
|
|
f"swarm exporter on :{PORT}/metrics, scanning last {flight_window()} flights "
|
|
f"every {SCAN_INTERVAL_S}s under {DATA_DIR}"
|
|
)
|
|
ThreadingHTTPServer(("", PORT), Handler).serve_forever()
|