uptime-monitor

app/main.py

@@ -0,0 +1,61 @@
+from __future__ import annotations
+
+import logging
+import os
+import sys
+import time
+
+from app.checker import check_all
+from app.config import ConfigError, load_config
+from app.influx_writer import write_results
+
+logger = logging.getLogger("uptime_monitor")
+
+
+def setup_logging() -> None:
+    logging.basicConfig(
+        level=os.environ.get("LOG_LEVEL", "INFO"),
+        format="%(asctime)s %(levelname)s %(name)s: %(message)s",
+        stream=sys.stdout,
+    )
+
+
+def run_cycle(cfg) -> list:
+    timestamp_ns = time.time_ns()
+    results = check_all(cfg.endpoints, cfg.check.timeout_seconds, timestamp_ns)
+    write_results(cfg.influx, results)
+    return results
+
+
+def main() -> None:
+    setup_logging()
+    config_path = os.environ.get("CONFIG_PATH", "/config/config.yaml")
+
+    try:
+        cfg = load_config(config_path)
+    except ConfigError as e:
+        logger.error("configuration error: %s", e)
+        sys.exit(1)
+
+    logger.info(
+        "loaded %d endpoint(s) from %s; interval=%ss, immediate recheck on failure enabled",
+        len(cfg.endpoints), config_path, cfg.check.interval_seconds,
+    )
+
+    while True:
+        results = run_cycle(cfg)
+
+        if any(not r.success for r in results):
+            logger.warning(
+                "at least one endpoint failed this cycle; "
+                "re-checking all endpoints immediately in %.0fs",
+                cfg.check.immediate_recheck_delay_seconds,
+            )
+            time.sleep(cfg.check.immediate_recheck_delay_seconds)
+            run_cycle(cfg)
+
+        time.sleep(cfg.check.interval_seconds)
+
+
+if __name__ == "__main__":
+    main()