ultix perf/ops workbench: complete 2026-08-31 optimization pass for VM 5111

Everything for the ultix-streaming (VM 5111, pfv-tsys5) performance pass: full report + host audit results, staged/gated configs, guest prep + host one-shot + post-reboot-fix + netcheck lifecycle scripts, grow-root manual runbook, rolling tracking HUD, questions v1, and the gateway boot-race hardening units. Applied and verified live 2026-08-31; open work is tracked in Redmine project 55 as #601-#607. [#602] 💘 Generated with Crush Assisted-by: Crush:glm-5.2
2026-08-31 16:46:13 -05:00
commit cba2a64d67
43 changed files with 3137 additions and 0 deletions
@@ -0,0 +1,56 @@
+#!/usr/bin/env bash
+# UKRRS Proxmox control wrapper for harness/human use. HARD RULES baked in:
+#   - vmids listed in PROTECTED are never touched (list THIS VM first).
+#   - graceful shutdown only; no reset, no hard stop, no bare down (house rule).
+# Env:
+#   PVE_LOCAL=1                      run ON the pve host itself (pvesh direct)
+#   or PVE_HOST + PVE_TOKEN          remote, token format: user@realm!tokenid=secret
+#   PVE_NODE                         node name (required for vm ops)
+#   PROTECTED                        required, comma-separated vmids
+# Usage:
+#   proxmox-ctl.sh vms
+#   proxmox-ctl.sh shutdown <vmid>
+#   proxmox-ctl.sh start <vmid>
+#   proxmox-ctl.sh snapshot <vmid> <name>
+# Token setup (on the pve host, see REPORT.md appendix B):
+#   pveum user add ukrrs-infra@pam
+#   pveum user token add ukrrs-infra@pam harness -privsep 0 -expire 0
+#   pveum acl modify /pool/<preprod-pool> -user ukrrs-infra@pam -role PVEVMUser
+set -euo pipefail
+: "${PROTECTED:?set PROTECTED=vmid1,vmid2,... (this VM must be in the list)}"
+
+pvesh_() {
+  if [ "${PVE_LOCAL:-0}" = 1 ]; then
+    command pvesh "$@"
+  else
+    : "${PVE_HOST:?}" "${PVE_TOKEN:?}"
+    command pvesh --host "$PVE_HOST" --api-token "$PVE_TOKEN" "$@"
+  fi
+}
+
+guard() {
+  case ",$PROTECTED," in
+    *",$1,"*) echo "REFUSED: vmid $1 is PROTECTED" >&2; exit 3 ;;
+  esac
+}
+
+cmd=${1:-}; shift || true
+case "$cmd" in
+  vms)
+    pvesh_ get /cluster/resources --type vm ;;
+  shutdown)
+    [ $# = 1 ] || { echo "usage: $0 shutdown <vmid>" >&2; exit 2; }
+    guard "$1"; : "${PVE_NODE:?}"
+    pvesh_ create "/nodes/$PVE_NODE/qemu/$1/status/shutdown" --timeout 120 ;;
+  start)
+    [ $# = 1 ] || { echo "usage: $0 start <vmid>" >&2; exit 2; }
+    guard "$1"; : "${PVE_NODE:?}"
+    pvesh_ create "/nodes/$PVE_NODE/qemu/$1/status/start" ;;
+  snapshot)
+    [ $# = 2 ] || { echo "usage: $0 snapshot <vmid> <name>" >&2; exit 2; }
+    guard "$1"; : "${PVE_NODE:?}"
+    pvesh_ create "/nodes/$PVE_NODE/qemu/$1/snapshot" snapname="$2" ;;
+  *)
+    echo "usage: $0 vms|shutdown <vmid>|start <vmid>|snapshot <vmid> <name>" >&2
+    exit 2 ;;
+esac