feat: add cluster auditing, management, and upgrade scripts

scripts/uncordon_and_inspect_errors.py

@@ -0,0 +1,33 @@
+import paramiko
+import sys
+
+sys.stdout.reconfigure(encoding='utf-8')
+
+ssh = paramiko.SSHClient()
+ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
+ssh.connect('140.44.4.11', username='root', key_filename=r'C:\Users\Snarf\.ssh\id_ed25519_snarfnet', timeout=8)
+
+print("=== UNCORDONING WRK07 ===")
+_, out, _ = ssh.exec_command('kubectl uncordon sninfr2lnxwrk07')
+print(out.read().decode())
+
+print("=== CHECKING WRK07 STATUS ===")
+_, out, _ = ssh.exec_command('kubectl get node sninfr2lnxwrk07')
+print(out.read().decode())
+
+print("=== INSPECTING LONGHORN-MANAGER-SQTL9 ===")
+_, out, _ = ssh.exec_command('kubectl get pod -n longhorn-system longhorn-manager-sqtl9 -o wide')
+print(out.read().decode())
+_, out, _ = ssh.exec_command('kubectl logs -n longhorn-system longhorn-manager-sqtl9 -c longhorn-manager --tail=25')
+print("Logs:\n", out.read().decode())
+
+print("=== INSPECTING HELM-INSTALL-TRAEFIK CRASH ===")
+_, out, _ = ssh.exec_command('kubectl logs -n kube-system helm-install-traefik-96s4n --tail=25')
+print(out.read().decode())
+
+print("=== INSPECTING UNKNOWN PODS IN INFRA ===")
+_, out, _ = ssh.exec_command('kubectl get pods -n infra -o wide | grep Unknown')
+print(out.read().decode())
+
+ssh.close()
+