Initial commit: Fenris NVMe wear monitor with rolling-24h dashboard

2026-08-23 18:47:12 +05:30
commit 53cc6c81b9
5 changed files with 1534 additions and 0 deletions
@@ -0,0 +1,128 @@
+#!/usr/bin/env bash
+# Fenris — interactive menu for the NVMe wear monitor & dashboard.
+# Created by Bongbetic.
+
+set -euo pipefail
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PY="$SCRIPT_DIR/fenris.py"
+PORT_DEFAULT=8420
+INTERVAL_DEFAULT=300
+
+banner() {
+  cat <<'EOF'
+ _____           _
+|   __|___ ___ _| |___
+|   __| -_|   | . |  _|
+|__|  |___|_|_|_|___|_|
+
+ NVMe wear monitor & live dashboard
+ Created by Bongbetic
+EOF
+}
+
+pause() { read -rp "Press Enter to continue..." _; }
+
+detect_device() {
+  # Query Python's auto-detect for the default device.
+  python3 -c "import sys; sys.path.insert(0,'$SCRIPT_DIR'); from fenris import detect_device; print(detect_device())" 2>/dev/null || echo /dev/nvme0
+}
+
+menu() {
+  clear
+  banner
+  echo
+  echo "  1) Start monitoring (background daemon + dashboard)"
+  echo "  2) Stop monitoring"
+  echo "  3) Status / current wear stats"
+  echo "  4) Take one sample right now"
+  echo "  5) Open dashboard URL"
+  echo "  ---"
+  echo "  h) Help / how this works"
+  echo "  q) Exit"
+  echo
+  read -rp "Choose an option: " choice
+  echo
+  case "$choice" in
+    1) start_flow ;;
+    2) python3 "$PY" stop; pause ;;
+    3) python3 "$PY" status; pause ;;
+    4) read -rp "Device [default: auto-detect]: " dev
+       if [ -z "$dev" ]; then python3 "$PY" sample; else python3 "$PY" sample --device "$dev"; fi
+       pause ;;
+    5) show_url; pause ;;
+    h|H) help_text; pause ;;
+    q|Q) echo "Bye. — Fenris, by Bongbetic"; exit 0 ;;
+    *) echo "Invalid choice."; pause ;;
+  esac
+}
+
+start_flow() {
+  read -rp "NVMe device [Enter = auto-detect]: " dev
+  read -rp "Sample interval in seconds [Enter = ${INTERVAL_DEFAULT}]: " interval
+  read -rp "Dashboard port [Enter = ${PORT_DEFAULT}]: " port
+  interval="${interval:-$INTERVAL_DEFAULT}"
+  port="${port:-$PORT_DEFAULT}"
+
+  args=(start --interval "$interval" --port "$port")
+  if [ -n "${dev:-}" ]; then args+=(--device "$dev"); fi
+
+  echo
+  echo "Note: reading NVMe SMART data needs root."
+  echo "Fenris runs 'sudo -n smartctl ...' (no-prompt sudo). If this fails,"
+  echo "either run this menu with sudo, or allow passwordless smartctl via:"
+  echo "  sudo visudo   ->   youruser ALL=(root) NOPASSWD: /usr/sbin/smartctl"
+  echo
+
+  python3 "$PY" "${args[@]}"
+  pause
+}
+
+show_url() {
+  if [ -f "$SCRIPT_DIR/data/fenris.pid" ]; then
+    # Try to read actual port from running process cmdline, else guess default.
+    local pid port
+    pid=$(<"$SCRIPT_DIR/data/fenris.pid")
+    port=$(tr '\0' '\n' < /proc/"$pid"/cmdline 2>/dev/null | grep -A1 -- '--port' | tail -1 || true)
+    port="${port:-$PORT_DEFAULT}"
+    echo "Dashboard: http://localhost:${port}"
+  else
+    echo "Fenris is not currently running. Start it first (option 1)."
+  fi
+}
+
+help_text() {
+  cat <<EOF
+What Fenris does:
+  - Periodically reads your NVMe drive's SMART health data (via smartctl),
+    including "percentage_used" (the drive's own wear indicator), total
+    bytes written/read, temperature, spare capacity, and error counts.
+  - Logs every sample to: $SCRIPT_DIR/data/history.jsonl
+    and per-hour aggregates to: $SCRIPT_DIR/data/hourly.jsonl (GB/hour,
+    rebuilt from history on restart). Used for the trailing-24h bar chart
+    and exact rolling-24h write volume.
+  - Serves a live HTML dashboard (dense layout, interval-synced polling)
+    with wear-over-time and trailing-24h hourly-write charts, plus a
+    projected life-remaining estimate in hours/days/years derived from
+    your actual rolling-24h write rate and implied TBW endurance.
+
+Requirements:
+  - smartmontools (smartctl) installed.
+  - Root access to read NVMe SMART logs — either run Fenris via sudo,
+    or set up passwordless sudo for smartctl (see option 1).
+
+CLI usage (equivalent to this menu):
+  python3 fenris.py start    [--device /dev/nvme0] [--interval 300] [--port 8420]
+  python3 fenris.py stop
+  python3 fenris.py status
+  python3 fenris.py sample   [--device /dev/nvme0]
+
+Leave it running in the background (option 1) and check back after a
+few days/weeks of normal use — more samples = a more accurate lifespan
+estimate.
+
+Fenris — created by Bongbetic.
+EOF
+}
+
+# Loop instead of recurse to avoid stack overflow.
+while true; do menu; done