android_cast/examples/network/wan-snapshot.sh

#!/bin/sh
#
# Log WAN vs LAN ping quality on the Debian edge router.
# Use to compare "rocketship" evenings vs slow periods (ISP/upstream vs local).
#
# Topology (see docs/INFRA.md):
#   world -> 134.17.26.161 (router 10.7.6.228) -> 10.7.0.10 (FE) -> 10.7.0.0/8 (BE, …)
#
# Install on router:
#   sudo cp wan-snapshot.sh /usr/local/bin/wan-snapshot.sh
#   sudo chmod +x /usr/local/bin/wan-snapshot.sh
#   sudo mkdir -p /var/log
#
# Cron (every 15 minutes):
#   */15 * * * * root /usr/local/bin/wan-snapshot.sh
#
# Env overrides:
#   WAN_SNAPSHOT_LOG=/var/log/wan-quality.log
#   WAN_PING_TARGET=1.1.1.1
#   FE_PING_TARGET=10.7.0.10
#   BE_PING_TARGET=10.7.16.128   (set to "none" to skip)
#   PING_COUNT=10
#   PING_DEADLINE_S=15
#
set -eu

WAN_SNAPSHOT_LOG="${WAN_SNAPSHOT_LOG:-/var/log/wan-quality.log}"
WAN_PING_TARGET="${WAN_PING_TARGET:-1.1.1.1}"
FE_PING_TARGET="${FE_PING_TARGET:-10.7.0.10}"
BE_PING_TARGET="${BE_PING_TARGET-10.7.16.128}"
PING_COUNT="${PING_COUNT:-10}"
PING_DEADLINE_S="${PING_DEADLINE_S:-15}"

usage() {
  sed -n '2,22p' "$0"
  printf '\nCommands:\n'
  printf '  (default)     append one snapshot line to the log\n'
  printf '  --report      summarize today vs yesterday averages\n'
  printf '  --tail [N]    print last N log lines (default 24)\n'
  printf '  --help        this text\n'
}

need_ping() {
  command -v ping >/dev/null 2>&1 || {
    echo "wan-snapshot: missing ping" >&2
    exit 1
  }
}

# ping_summary HOST -> prints: loss_pct avg_ms (or loss_pct=-1 avg_ms=-1 on total failure)
ping_summary() {
  _host="$1"
  _out=""
  _out="$(ping -c "$PING_COUNT" -w "$PING_DEADLINE_S" "$_host" 2>/dev/null)" || true
  if [ -z "$_out" ]; then
    printf '%s %s' "-1" "-1"
    return 0
  fi
  _loss="$(printf '%s\n' "$_out" | awk '/packet loss/ {
    for (i = 1; i <= NF; i++) if ($i ~ /%$/) { gsub(/%/, "", $i); print $i; exit }
  }')"
  _avg="$(printf '%s\n' "$_out" | awk -F'[=/ ]' '/min\/avg\/max/ { print $8; exit }')"
  [ -n "$_loss" ] || _loss="-1"
  [ -n "$_avg" ] || _avg="-1"
  printf '%s %s' "$_loss" "$_avg"
}

snapshot_once() {
  need_ping
  _ts="$(date -Iseconds 2>/dev/null || date '+%Y-%m-%dT%H:%M:%S%z')"
  _wan="$(ping_summary "$WAN_PING_TARGET")"
  _wan_loss="${_wan%% *}"
  _wan_avg="${_wan#* }"
  _fe="$(ping_summary "$FE_PING_TARGET")"
  _fe_loss="${_fe%% *}"
  _fe_avg="${_fe#* }"

  _line="ts=$_ts wan=$WAN_PING_TARGET wan_loss=${_wan_loss}% wan_avg_ms=${_wan_avg} fe=$FE_PING_TARGET fe_loss=${_fe_loss}% fe_avg_ms=${_fe_avg}"

  if [ -n "$BE_PING_TARGET" ] && [ "$BE_PING_TARGET" != "none" ]; then
    _be="$(ping_summary "$BE_PING_TARGET")"
    _be_loss="${_be%% *}"
    _be_avg="${_be#* }"
    _line="$_line be=$BE_PING_TARGET be_loss=${_be_loss}% be_avg_ms=${_be_avg}"
  fi

  _dir="$(dirname "$WAN_SNAPSHOT_LOG")"
  [ -d "$_dir" ] || mkdir -p "$_dir" 2>/dev/null || true
  printf '%s\n' "$_line" >> "$WAN_SNAPSHOT_LOG"
  printf '%s\n' "$_line"
}

# Average wan_avg_ms / fe_avg_ms for lines matching DATE prefix (YYYY-MM-DD).
day_avg() {
  _log="$1"
  _date="$2"
  _field="$3"
  [ -r "$_log" ] || return 0
  awk -v d="$_date" -v f="$_field" '
    $0 ~ "^ts=" d {
      for (i = 1; i <= NF; i++) {
        if ($i ~ "^" f "=") {
          split($i, a, "=")
          v = a[2]
          gsub(/%/, "", v)
          if (v + 0 == v && v >= 0) { n++; s += v }
        }
      }
    }
    END {
      if (n > 0) printf "%.2f", s / n
      else print "n/a"
    }
  ' "$_log"
}

day_max_loss() {
  _log="$1"
  _date="$2"
  _field="$3"
  [ -r "$_log" ] || return 0
  awk -v d="$_date" -v f="$_field" '
    $0 ~ "^ts=" d {
      for (i = 1; i <= NF; i++) {
        if ($i ~ "^" f "=") {
          split($i, a, "=")
          v = a[2]
          gsub(/%/, "", v)
          if (v + 0 == v && v >= 0 && v > max) max = v
        }
      }
    }
    END {
      if (max == "") print "n/a"
      else printf "%.0f", max
    }
  ' "$_log"
}

report() {
  _log="$WAN_SNAPSHOT_LOG"
  _today="$(date '+%Y-%m-%d')"
  _yesterday="$(date -d 'yesterday' '+%Y-%m-%d' 2>/dev/null || date -v-1d '+%Y-%m-%d' 2>/dev/null || echo '')"

  if [ ! -r "$_log" ]; then
    echo "wan-snapshot: no log at $_log (run default command first)" >&2
    exit 1
  fi

  _samples_today="$(grep -c "^ts=$_today" "$_log" 2>/dev/null || echo 0)"
  printf 'log=%s\n' "$_log"
  printf 'today=%s samples=%s\n' "$_today" "$_samples_today"
  printf '  wan_avg_ms=%s  wan_max_loss%%=%s\n' \
    "$(day_avg "$_log" "$_today" "wan_avg_ms")" \
    "$(day_max_loss "$_log" "$_today" "wan_loss")"
  printf '  fe_avg_ms=%s   fe_max_loss%%=%s\n' \
    "$(day_avg "$_log" "$_today" "fe_avg_ms")" \
    "$(day_max_loss "$_log" "$_today" "fe_loss")"

  if [ -n "$_yesterday" ] && grep -q "^ts=$_yesterday" "$_log" 2>/dev/null; then
    _samples_y="$(grep -c "^ts=$_yesterday" "$_log" 2>/dev/null || echo 0)"
    printf 'yesterday=%s samples=%s\n' "$_yesterday" "$_samples_y"
    printf '  wan_avg_ms=%s  wan_max_loss%%=%s\n' \
      "$(day_avg "$_log" "$_yesterday" "wan_avg_ms")" \
      "$(day_max_loss "$_log" "$_yesterday" "wan_loss")"
    printf '  fe_avg_ms=%s   fe_max_loss%%=%s\n' \
      "$(day_avg "$_log" "$_yesterday" "fe_avg_ms")" \
      "$(day_max_loss "$_log" "$_yesterday" "fe_loss")"
  fi

  printf '\nInterpretation:\n'
  printf '  wan bad + fe good  -> likely ISP/upstream (world -> 134.17.26.161)\n'
  printf '  wan + fe bad       -> router or LAN (10.7.6.228 -> 10.7.0.10)\n'
  printf '  wan + fe good, apps slow -> DNAT/nginx above ping path\n'
}

tail_log() {
  _n="${1:-24}"
  [ -r "$WAN_SNAPSHOT_LOG" ] || {
    echo "wan-snapshot: no log at $WAN_SNAPSHOT_LOG" >&2
    exit 1
  }
  tail -n "$_n" "$WAN_SNAPSHOT_LOG"
}

case "${1:-}" in
  -h|--help|help)
    usage
    ;;
  --report|report)
    report
    ;;
  --tail|tail)
    tail_log "${2:-24}"
    ;;
  "")
    snapshot_once
    ;;
  *)
    echo "wan-snapshot: unknown command: $1 (try --help)" >&2
    exit 1
    ;;
esac