Merge pull request #1951 from SkynetLabs/silence-health-checks-when-container-not-running

skip health checks if container is not running

setup-scripts/bot_utils.py

@@ -33,6 +33,13 @@ sc_precision = 10**24
 setup_done = False
 
 
+# get docker container id and return None if container not found
+def get_docker_container_id(container_name):
+    docker_cmd = "docker ps -q -f name=" + container_name
+    output = subprocess.check_output(docker_cmd, shell=True).decode("utf-8")
+    return None if output == "" else output
+
+
 # find out local siad ip by inspecting its docker container
 def get_docker_container_ip(container_name):
     ip_regex = re.compile(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$")

setup-scripts/health-checker.py

@@ -10,7 +10,7 @@ import traceback
 from datetime import datetime, timedelta
 
 import requests
-from bot_utils import setup, send_msg, get_docker_container_ip
+from bot_utils import setup, send_msg, get_docker_container_id, get_docker_container_ip
 
 """
 health-checker reads the /health-check endpoint of the portal and dispatches
@@ -135,6 +135,12 @@ async def check_disk():
 async def check_health():
     print("\nChecking portal health status...")
 
+    # do not try to run health checks if health-check container does not exist
+    # possible use case is fresh or taken down server that has only skyd running
+    if not get_docker_container_id("health-check"):
+        print("Container health-check not found - skipping health checks")
+        return
+
     try:
         endpoint = "http://{}:{}".format(get_docker_container_ip("health-check"), 3100)
     except: