feat: add homelab deployment configs, documentation, and automation scripts

scripts/check_prom_live_targets.py

@@ -0,0 +1,29 @@
+import paramiko
+import json
+
+c = paramiko.SSHClient()
+c.set_missing_host_key_policy(paramiko.AutoAddPolicy())
+c.connect('140.44.4.11', username='root', key_filename=r'C:\Users\Snarf\.ssh\id_ed25519_snarfnet', timeout=10)
+
+def run(cmd):
+    _, o, e = c.exec_command(cmd)
+    return o.read().decode().strip()
+
+out = run("kubectl exec deployment/prometheus -- wget -qO- http://localhost:9090/api/v1/targets")
+data = json.loads(out)
+print("=== ACTIVE TARGETS ===")
+for t in data.get('data', {}).get('activeTargets', []):
+    print(f"[{t.get('health')}] pool: {t.get('scrapePool')} | job: {t.get('labels', {}).get('job')} | instance: {t.get('labels', {}).get('instance')} | url: {t.get('scrapeUrl')}")
+    if t.get('lastError'):
+        print(f"    ERROR: {t.get('lastError')}")
+
+print("\n=== SAMPLE NODE EXPORTER QUERY ===")
+out = run("kubectl exec deployment/prometheus -- wget -qO- 'http://localhost:9090/api/v1/query?query=count(node_cpu_seconds_total{mode=\"idle\"})_by_(instance)'")
+print(out)
+
+print("\n=== SAMPLE CADVISOR QUERY ===")
+out = run("kubectl exec deployment/prometheus -- wget -qO- 'http://localhost:9090/api/v1/query?query=count(container_cpu_usage_seconds_total)'")
+print(out)
+
+c.close()
+