feat: add infrastructure automation scripts and master improvement plan
This commit is contained in:
53
scripts/create_zabbix_time_trigger.py
Normal file
53
scripts/create_zabbix_time_trigger.py
Normal file
@@ -0,0 +1,53 @@
|
||||
import json
|
||||
import ssl
|
||||
import urllib.request
|
||||
|
||||
ZABBIX_URL = "https://zabbix.snarfnet.net/api_jsonrpc.php"
|
||||
ZABBIX_USER = "Admin"
|
||||
ZABBIX_PASS = "zabbix"
|
||||
|
||||
ctx = ssl.create_default_context()
|
||||
ctx.check_hostname = False
|
||||
ctx.verify_mode = ssl.CERT_NONE
|
||||
|
||||
def zbx_req(method: str, params: dict, auth: str = None):
|
||||
payload = {"jsonrpc": "2.0", "method": method, "params": params, "id": 1}
|
||||
headers = {"Content-Type": "application/json-rpc"}
|
||||
if auth: headers["Authorization"] = f"Bearer {auth}"
|
||||
req = urllib.request.Request(ZABBIX_URL, data=json.dumps(payload).encode("utf-8"), headers=headers, method="POST")
|
||||
with urllib.request.urlopen(req, timeout=10, context=ctx) as r:
|
||||
resp = json.loads(r.read().decode("utf-8"))
|
||||
if "error" in resp:
|
||||
raise RuntimeError(f"Zabbix API error: {resp['error']}")
|
||||
return resp["result"]
|
||||
|
||||
token = zbx_req("user.login", {"username": ZABBIX_USER, "password": ZABBIX_PASS})
|
||||
|
||||
# Check if trigger already exists
|
||||
existing = zbx_req("trigger.get", {
|
||||
"templateids": "10343",
|
||||
"search": {"description": "System time is out of sync"},
|
||||
"output": ["triggerid", "description", "priority", "expression"]
|
||||
}, auth=token)
|
||||
|
||||
if existing:
|
||||
print(f"Trigger already exists: {existing}")
|
||||
else:
|
||||
print("Creating trigger 'Linux: System time is out of sync (> 5s)' on Template 10343...")
|
||||
res = zbx_req("trigger.create", {
|
||||
"description": "Linux: System time is out of sync (> 5s)",
|
||||
"expression": "fuzzytime(/Linux by Zabbix agent active/system.localtime, 5s)=0",
|
||||
"priority": "4", # High priority
|
||||
"comments": "The host system time differs from Zabbix server time by more than 5 seconds. This is critical as it risks split-brain or consensus loss in K3s etcd and Docker Swarm Raft.",
|
||||
"manual_close": "1"
|
||||
}, auth=token)
|
||||
print("Created trigger:", res)
|
||||
|
||||
# Verify trigger created
|
||||
trigs = zbx_req("trigger.get", {
|
||||
"templateids": "10343",
|
||||
"search": {"description": "System time is out of sync"},
|
||||
"output": ["triggerid", "description", "priority", "expression"]
|
||||
}, auth=token)
|
||||
print("Verified triggers on Template 10343:", json.dumps(trigs, indent=2))
|
||||
|
||||
Reference in New Issue
Block a user