Add runbook for recovering wedged units and new scripts for device management

- Created a comprehensive runbook (`wedged_unit_recovery.md`) detailing the recovery process for units stuck in a call-home loop, including symptoms, recovery steps, and explanations of the failure mode. - Added `blind_stop.sh` script to send stop-monitoring commands in a tight loop for unresponsive devices. - Introduced `rescue_device.sh` script to disable Auto Call Home and erase events from a busy device. - Implemented `slow_drip.sh` script to send stop-monitoring frames at a slow rate to prevent UART overrun. - Developed `spam_stop.sh` script to rapidly send stop-monitoring commands to a device. - Created `watch_unit.sh` script for passive monitoring of device reachability, logging results over time.
2026-05-17 07:58:13 +00:00
parent ae7edac83f
commit 1fff8179d6
8 changed files with 1401 additions and 10 deletions
@@ -0,0 +1,100 @@
+#!/usr/bin/env bash
+# Fire-and-forget Stop Monitoring loop — for wedged or constantly-triggering units.
+#
+# Hammers POST /device/stop_monitoring_blind in a tight loop.  The endpoint
+# opens TCP, dumps SESSION_RESET + a few copies of the SUB 0x97 frame, and
+# closes — without ever reading an S3 response.  Each TCP-won attempt is
+# ~50ms of wire activity instead of the multi-frame handshake the regular
+# rescue endpoint does, so windows that are too small for the full rescue
+# can still land a stop-monitoring command.
+#
+# Usage:
+#   ./blind_stop.sh <host> [tcp_port]
+#
+# Env:
+#   SFM_BASE_URL    Default: http://localhost:8200 (SFM direct).
+#                   Set to http://localhost:8001/api/sfm to route through
+#                   Terra-View's proxy.
+#   MAX_ATTEMPTS    Default: 600
+#   SLEEP_S         Default: 0  (no backoff — hammer it)
+#   MAX_TIME_S      Default: 15
+#   CONNECT_TIMEOUT Default: 5
+#   REPEAT          Frames per TCP session (default 3 — increases hit rate
+#                   if the device is busy reading its own buffer).
+#   STOP_ON_OK      Default: 1.  Set to 0 to keep hammering indefinitely
+#                   even after successful sends (every 503 means the device
+#                   is in *another* session, every 200 means our bytes got
+#                   through — but the device may not have processed them).
+
+set -u
+
+host="${1:-}"
+tcp_port="${2:-9034}"
+if [[ -z "$host" ]]; then
+  echo "usage: $0 <host> [tcp_port]" >&2
+  exit 2
+fi
+
+base="${SFM_BASE_URL:-http://localhost:8200}"
+max_attempts="${MAX_ATTEMPTS:-600}"
+sleep_s="${SLEEP_S:-0}"
+max_time_s="${MAX_TIME_S:-15}"
+connect_timeout="${CONNECT_TIMEOUT:-5}"
+repeat="${REPEAT:-3}"
+stop_on_ok="${STOP_ON_OK:-1}"
+
+url="${base}/device/stop_monitoring_blind?host=${host}&tcp_port=${tcp_port}&connect_timeout=${connect_timeout}&repeat=${repeat}"
+
+echo "blind_stop: target ${host}:${tcp_port}  connect_timeout=${connect_timeout}s  repeat=${repeat}"
+echo "blind_stop: POST ${url}"
+echo "blind_stop: up to ${max_attempts} attempts, ${sleep_s}s between, ${max_time_s}s per request"
+echo "blind_stop: stop_on_ok=${stop_on_ok}"
+echo
+
+ok_count=0
+busy_count=0
+err_count=0
+started=$(date +%s)
+
+for ((i=1; i<=max_attempts; i++)); do
+  printf "[%4d] %s  " "$i" "$(date +%H:%M:%S)"
+  http_code=$(curl -sS -o /tmp/blind_resp.$$ -w "%{http_code}" \
+    --max-time "$max_time_s" \
+    -X POST "$url" || echo "000")
+  body=$(cat /tmp/blind_resp.$$ 2>/dev/null || true)
+  rm -f /tmp/blind_resp.$$
+
+  case "$http_code" in
+    200|201)
+      ok_count=$((ok_count + 1))
+      echo "SENT  $body"
+      if [[ "$stop_on_ok" == "1" ]]; then
+        elapsed=$(( $(date +%s) - started ))
+        echo
+        echo "blind_stop: success after ${i} attempts (${elapsed}s).  ok=${ok_count} busy=${busy_count} err=${err_count}"
+        echo "blind_stop: NEXT — wait ~10s, then try the full rescue:"
+        echo "  /home/serversdown/seismo-relay/scripts/rescue_device.sh ${host} ${tcp_port}"
+        exit 0
+      fi
+      ;;
+    503)
+      busy_count=$((busy_count + 1))
+      echo "busy (503)"
+      ;;
+    000)
+      err_count=$((err_count + 1))
+      echo "curl error"
+      ;;
+    *)
+      err_count=$((err_count + 1))
+      echo "HTTP $http_code  $body" | head -c 400
+      echo
+      ;;
+  esac
+  [[ "$sleep_s" != "0" ]] && sleep "$sleep_s"
+done
+
+elapsed=$(( $(date +%s) - started ))
+echo
+echo "blind_stop: gave up after ${max_attempts} attempts (${elapsed}s).  ok=${ok_count} busy=${busy_count} err=${err_count}" >&2
+exit 1