first commit

q1-deploy-monitor/health-check.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python3
+"""
+Lightweight uptime/health monitor.
+
+Polls the target app's /health endpoint every CHECK_INTERVAL seconds,
+logs status + response time, and writes the latest result to a JSON
+file (status.json) that can be consumed by other tools or dashboards.
+
+Usage:
+    python health-check.py --url https://your-app.ghaymah.systems
+    python health-check.py --url https://your-app.ghaymah.systems --interval 30
+"""
+
+import argparse
+import json
+import logging
+import time
+import urllib.request
+import urllib.error
+from datetime import datetime, timezone
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] %(message)s",
+    handlers=[
+        logging.FileHandler("monitor.log"),
+        logging.StreamHandler(),
+    ],
+)
+log = logging.getLogger("monitor")
+
+STATUS_FILE = "status.json"
+FAILURE_THRESHOLD = 3  # consecutive failures before raising an "ALERT"
+
+
+def check_health(url: str, timeout: float = 5.0):
+    start = time.perf_counter()
+    try:
+        with urllib.request.urlopen(url, timeout=timeout) as resp:
+            elapsed_ms = round((time.perf_counter() - start) * 1000, 2)
+            body = json.loads(resp.read().decode())
+            return {
+                "ok": resp.status == 200,
+                "http_status": resp.status,
+                "response_time_ms": elapsed_ms,
+                "body": body,
+            }
+    except urllib.error.HTTPError as e:
+        elapsed_ms = round((time.perf_counter() - start) * 1000, 2)
+        return {"ok": False, "http_status": e.code, "response_time_ms": elapsed_ms, "error": str(e)}
+    except Exception as e:  # DNS errors, timeouts, connection refused, etc.
+        elapsed_ms = round((time.perf_counter() - start) * 1000, 2)
+        return {"ok": False, "http_status": None, "response_time_ms": elapsed_ms, "error": str(e)}
+
+
+def write_status(result: dict, consecutive_failures: int):
+    payload = {
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "status": "healthy" if result["ok"] else "unhealthy",
+        "http_status": result.get("http_status"),
+        "response_time_ms": result.get("response_time_ms"),
+        "consecutive_failures": consecutive_failures,
+    }
+    with open(STATUS_FILE, "w") as f:
+        json.dump(payload, f, indent=2)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Poll /health endpoint on an interval.")
+    parser.add_argument("--url", required=True, help="Base URL of the app, e.g. https://myapp.ghaymah.systems")
+    parser.add_argument("--interval", type=int, default=30, help="Seconds between checks (default: 30)")
+    args = parser.parse_args()
+
+    health_url = args.url.rstrip("/") + "/health"
+    log.info("Starting monitor for %s every %ss", health_url, args.interval)
+
+    consecutive_failures = 0
+
+    while True:
+        result = check_health(health_url)
+        write_status(result, consecutive_failures)
+
+        if result["ok"]:
+            if consecutive_failures > 0:
+                log.info("Service RECOVERED after %d failed check(s).", consecutive_failures)
+            consecutive_failures = 0
+            log.info("OK  status=%s  response_time=%sms", result["http_status"], result["response_time_ms"])
+        else:
+            consecutive_failures += 1
+            log.warning(
+                "FAIL attempt=%d  status=%s  error=%s",
+                consecutive_failures, result.get("http_status"), result.get("error"),
+            )
+            if consecutive_failures >= FAILURE_THRESHOLD:
+                log.error("ALERT: %s has failed %d consecutive health checks!", args.url, consecutive_failures)
+
+        time.sleep(args.interval)
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except KeyboardInterrupt:
+        log.info("Monitor stopped by user.")