Files
Varaverk/Monitors/bandwidth_monitor.sh
T
Gmer4Lfe 95151c2278 Watchdogs/ folder + host conf rename
Move all watchdog scripts to a dedicated Watchdogs/ folder:
  Docker_Essentials/docker_watchdog.sh   → Watchdogs/
  unRAID_Essentials/system_watchdog.sh   → Watchdogs/
  unRAID_Essentials/resource_watchdog.sh → Watchdogs/
  Orchestrators/watchdog_orchestrator.sh → Watchdogs/
  Tools/watchdog_skip_list_manager.sh    → Watchdogs/

Rename host config files:
  master_host1.conf → host1.conf
  master_host2.conf → host2.conf

Update all references across the ecosystem:
  master.conf: WATCHDOG_ORCHESTRATOR_SCRIPTS paths → Watchdogs/
  load_config.sh: host*.conf glob + all comments
  git_pull_execute.sh: sparse checkout glob + all comments
  Partnership/ssh_setup.sh: HOST_CONF path construction
  user_script_plug-in.sh: all script paths + per-host conf path
  common.sh, README.md, README-User_Script_Plug-in.md: comment refs
  All Partnership, Fallback, Monitors, Transcodes, Tools scripts: comment refs
2026-05-22 17:08:36 -04:00

308 lines
14 KiB
Bash

#!/bin/bash
# ==============================================================================================
# ============================= Bandwidth Monitor ==============================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# rsync transfer history logging and weekly summary reporting. Log mode is called
# automatically by rsync.sh after each sync — no manual scheduling needed for
# logging. Report mode scheduled weekly (Sunday 11am).
#
# Log mode (--log-transfer): appends one line per sync to BANDWIDTH_LOG, trims
# entries older than BANDWIDTH_LOG_RETENTION days. One bounded write per rsync run.
#
# Report mode (default): reads the accumulated log and generates a summary —
# per-profile breakdown, run count, total transferred, average duration, failures,
# last 7 days activity timeline, any transfers or days exceeding BANDWIDTH_WARN_GB.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# Version-Proof Log Format
# Earlier designs parsed rsync's human-readable output for bytes transferred.
# rsync changes its output format between versions — those parsers break silently.
# The log line (YYYY-MM-DD|HH:MM|profile|duration|status|bytes) captures bytes
# from rsync --stats via awk using version-stable field names. Survives any rsync
# update with no changes.
#
# Minimal Flash Drive Impact
# unRAID boots from USB flash. One append + one trim per rsync run. The log file
# is bounded to BANDWIDTH_LOG_RETENTION days and never grows unbounded.
# Atomic write: tmp file + mv prevents partial writes during trim.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Lock With Wait
# acquire_lock "wait" — multiple rsync profiles may complete close together.
# Waiting (not skipping) prevents log entries from being lost.
#
# Atomic Log Write
# Trim uses tmp file + mv — partial writes on log trim cannot corrupt the log.
#
# Log Directory Guard
# Creates the log directory if it doesn't exist. Exits cleanly if unwritable.
#
# Notification Validated
# validate_unraid_cmd confirms the notify script is present before use.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# master.conf
#
# BANDWIDTH_LOG
# Log file path. Stored on /boot/ to survive reboots.
# (default: /boot/config/bandwidth_history.db)
#
# BANDWIDTH_LOG_RETENTION
# Days before old entries are purged. File stays bounded. (default: 90)
#
# BANDWIDTH_WARN_GB
# Flag transfers or daily totals exceeding this in the report. (default: 50)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
# bandwidth_monitor.sh
# Generate transfer history report from accumulated log.
#
# bandwidth_monitor.sh --report
# Generate report (explicit form).
#
# bandwidth_monitor.sh --log-transfer profile secs status bytes
# Log a completed rsync transfer. Called by rsync.sh — do not call manually.
#
# bandwidth_monitor.sh --status
# Show log path, retention, warn threshold, and log statistics. Then exit.
#
# bandwidth_monitor.sh --log
# Verbose output during report generation.
#
# ==============================================================================================
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/../load_config.sh"
parse_args "$@"
# ── Parse mode from PARSED_ARGS ───────────────────────────────────────────────────────────────
LOG_TRANSFER_MODE=false
TRANSFER_PROFILE=""
TRANSFER_DURATION=0
TRANSFER_STATUS="success"
TRANSFER_BYTES=0
for arg in "${PARSED_ARGS[@]}"; do
case "$arg" in
--log-transfer) LOG_TRANSFER_MODE=true ;;
--report) LOG_TRANSFER_MODE=false ;;
*)
if [[ "$LOG_TRANSFER_MODE" == true ]]; then
if [[ -z "$TRANSFER_PROFILE" ]]; then
TRANSFER_PROFILE="$arg"
elif [[ "$TRANSFER_DURATION" -eq 0 && "$arg" =~ ^[0-9]+$ ]]; then
TRANSFER_DURATION="$arg"
elif [[ "$arg" == "success" || "$arg" == "failed" ]]; then
TRANSFER_STATUS="$arg"
elif [[ "$arg" =~ ^[0-9]+$ ]]; then
TRANSFER_BYTES="$arg"
fi
fi
;;
esac
done
# ── Ensure log file exists and is writable ────────────────────────────────────────────────────
mkdir -p "$(dirname "$BANDWIDTH_LOG")"
touch "$BANDWIDTH_LOG" 2>/dev/null || {
error "Cannot write to bandwidth log: $BANDWIDTH_LOG"
exit 1
}
# ==============================================================================================
# ━━━ Setup ━━━
# ==============================================================================================
if [[ "$EUID" -ne 0 ]]; then
error "Must be run as root"
exit 1
fi
validate_unraid_cmd \
"/usr/local/emhttp/plugins/dynamix/scripts/notify" \
"" "" \
"unRAID notify script" || warn "unRAID notify script not found — native notifications disabled"
# detect_hosts() sets MY_ID for report header
detect_hosts
# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
if [[ "$SHOW_STATUS" == true ]]; then
echo ""
echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_BANDWIDTH Log file: $BANDWIDTH_LOG"
echo "$ICON_BANDWIDTH Retention: ${BANDWIDTH_LOG_RETENTION} days"
echo "$ICON_BANDWIDTH Warn GB: ${BANDWIDTH_WARN_GB}GB"
entry_count=0
[[ -f "$BANDWIDTH_LOG" ]] && entry_count=$(wc -l < "$BANDWIDTH_LOG")
echo "$ICON_BANDWIDTH Log entries: $entry_count"
echo "━━━━━━━━━━━━━━━━━━━━━━━"
exit 0
fi
# ==============================================================================================
# ━━━ Log Transfer Mode ━━━
# ==============================================================================================
# Called by rsync.sh after each sync — appends one line and trims old entries.
# Uses "wait" lock — if two rsync jobs finish simultaneously, wait and write in order.
# Usage: bandwidth_monitor.sh --log-transfer "profile" duration_seconds status [bytes]
if [[ "$LOG_TRANSFER_MODE" == true ]]; then
[[ -z "$TRANSFER_PROFILE" ]] && { error "No profile specified for --log-transfer"; exit 1; }
acquire_lock "wait"
TODAY=$(date '+%Y-%m-%d')
NOW=$(date '+%H:%M')
DURATION_FMT=$(format_duration "$TRANSFER_DURATION")
# Check if transfer exceeds warn threshold
WARN_FLAG=""
if [[ -n "$TRANSFER_BYTES" && "$TRANSFER_BYTES" -gt 0 ]]; then
WARN_BYTES=$(awk "BEGIN {printf \"%d\", $BANDWIDTH_WARN_GB * 1073741824}")
[[ "$TRANSFER_BYTES" -gt "$WARN_BYTES" ]] && WARN_FLAG="LARGE"
fi
# Append entry — format: date|time|profile|duration|status|bytes|warn_flag
echo "${TODAY}|${NOW}|${TRANSFER_PROFILE}|${TRANSFER_DURATION}|${TRANSFER_STATUS}|${TRANSFER_BYTES}|${WARN_FLAG}" \
>> "$BANDWIDTH_LOG"
echo "$ICON_BANDWIDTH Logged: $TRANSFER_PROFILE${DURATION_FMT}$TRANSFER_STATUS${WARN_FLAG:+ [$WARN_FLAG]}"
# Trim entries older than retention — atomic write via temp file
CUTOFF=$(date -d "${BANDWIDTH_LOG_RETENTION} days ago" '+%Y-%m-%d')
TEMP_FILE="${BANDWIDTH_LOG}.tmp"
awk -F'|' -v cutoff="$CUTOFF" '$1 >= cutoff' "$BANDWIDTH_LOG" > "$TEMP_FILE" && \
mv "$TEMP_FILE" "$BANDWIDTH_LOG"
log "$ICON_BANDWIDTH Log trimmed — retaining entries from $CUTOFF"
exit 0
fi
# ==============================================================================================
# ━━━ Report Mode ━━━
# ==============================================================================================
acquire_lock "wait"
echo ""
echo "━━━ $ICON_BANDWIDTH Bandwidth Report — $(date '+%Y-%m-%d %H:%M:%S') ━━━"
echo "$ICON_HOST $MY_ID ($LOCAL_SERVER_NAME)"
echo ""
if [[ ! -s "$BANDWIDTH_LOG" ]]; then
warn "No bandwidth data yet — log is empty"
warn "Data accumulates as rsync jobs complete via rsync.sh"
exit 0
fi
START=$(date +%s)
# ── Log overview ──────────────────────────────────────────────────────────────────────────────
OLDEST=$(awk -F'|' 'NR==1{print $1}' "$BANDWIDTH_LOG")
NEWEST=$(awk -F'|' 'END{print $1}' "$BANDWIDTH_LOG")
ENTRY_COUNT=$(wc -l < "$BANDWIDTH_LOG")
SUCCESS_COUNT=$(awk -F'|' '$5=="success"' "$BANDWIDTH_LOG" | wc -l)
FAILED_COUNT=$(awk -F'|' '$5=="failed"' "$BANDWIDTH_LOG" | wc -l)
LARGE_COUNT=$(awk -F'|' '$7=="LARGE"' "$BANDWIDTH_LOG" | wc -l)
info "Log covers: $OLDEST$NEWEST ($ENTRY_COUNT runs)"
echo ""
# ── Per-profile breakdown ─────────────────────────────────────────────────────────────────────
echo "━━━ $ICON_BANDWIDTH Per-Profile Summary ━━━"
awk -F'|' '{
runs[$3]++
duration[$3] += $4
if ($5 == "failed") fails[$3]++
if ($7 == "LARGE") large[$3]++
}
END {
for (profile in runs) {
avg = (runs[profile] > 0) ? duration[profile] / runs[profile] : 0
mins = int(avg / 60)
secs = int(avg % 60)
fail_count = (profile in fails) ? fails[profile] : 0
large_count = (profile in large) ? large[profile] : 0
large_str = (large_count > 0) ? " ⚠️ " large_count " large" : ""
printf " %-22s %3d runs avg %dm%ds failed: %d%s\n", \
profile, runs[profile], mins, secs, fail_count, large_str
}
}' "$BANDWIDTH_LOG" | sort
echo ""
# ── Last 7 days ───────────────────────────────────────────────────────────────────────────────
echo "━━━ $ICON_BANDWIDTH Last 7 Days ━━━"
for i in 6 5 4 3 2 1 0; do
day=$(date -d "$i days ago" '+%Y-%m-%d')
day_name=$(date -d "$i days ago" '+%a')
day_runs=$(awk -F'|' -v d="$day" '$1==d' "$BANDWIDTH_LOG" | wc -l)
day_failed=$(awk -F'|' -v d="$day" '$1==d && $5=="failed"' "$BANDWIDTH_LOG" | wc -l)
day_large=$(awk -F'|' -v d="$day" '$1==d && $7=="LARGE"' "$BANDWIDTH_LOG" | wc -l)
day_duration=$(awk -F'|' -v d="$day" '$1==d{sum+=$4} END{print sum+0}' "$BANDWIDTH_LOG")
day_duration_fmt=$(format_duration "$day_duration")
if [[ "$day_runs" -eq 0 ]]; then
echo " $ICON_TIME $day ($day_name) — no syncs"
elif [[ "$day_failed" -gt 0 ]]; then
echo " $ICON_WARN $day ($day_name) — $day_runs runs / ${day_duration_fmt} total / $ICON_ERROR $day_failed failed"
elif [[ "$day_large" -gt 0 ]]; then
echo " $ICON_WARN $day ($day_name) — $day_runs runs / ${day_duration_fmt} total / ⚠️ $day_large large"
else
echo " $ICON_DONE $day ($day_name) — $day_runs runs / ${day_duration_fmt} total"
fi
done
echo ""
# ── Large transfers ───────────────────────────────────────────────────────────────────────────
if [[ "$LARGE_COUNT" -gt 0 ]]; then
echo "━━━ $ICON_WARN Large Transfers (>${BANDWIDTH_WARN_GB}GB) ━━━"
awk -F'|' '$7=="LARGE" {
bytes=$6+0
gb=bytes/1073741824
printf " %s %s %-20s %.1fGB\n", $1, $2, $3, gb
}' "$BANDWIDTH_LOG" | tail -10
echo ""
fi
# ── Totals ────────────────────────────────────────────────────────────────────────────────────
TOTAL_DURATION=$(awk -F'|' '{sum+=$4} END{print sum+0}' "$BANDWIDTH_LOG")
TOTAL_DURATION_FMT=$(format_duration "$TOTAL_DURATION")
END=$(date +%s)
echo "━━━━━ $ICON_SUMMARY BANDWIDTH SUMMARY ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_BANDWIDTH Runs: $ENTRY_COUNT ($SUCCESS_COUNT success / $FAILED_COUNT failed)"
[[ "$LARGE_COUNT" -gt 0 ]] && \
warn "Large: $LARGE_COUNT transfer(s) exceeded ${BANDWIDTH_WARN_GB}GB"
echo "$ICON_TIME Total: $TOTAL_DURATION_FMT"
echo "$ICON_TIME Period: $OLDEST$NEWEST"
echo "$ICON_GEAR Retention: ${BANDWIDTH_LOG_RETENTION} days"
echo "$ICON_TIME Generated: $(format_duration $(( END - START )))"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
# Only notify if there are failures or large transfers worth flagging
if [[ "$FAILED_COUNT" -gt 0 ]]; then
notify "Bandwidth report on $(hostname)$FAILED_COUNT failed sync(s) in ${BANDWIDTH_LOG_RETENTION} day window" \
"Bandwidth Monitor" "warning"
elif [[ "$LARGE_COUNT" -gt 0 ]]; then
notify "Bandwidth report on $(hostname)$LARGE_COUNT large transfer(s) exceeded ${BANDWIDTH_WARN_GB}GB" \
"Bandwidth Monitor" "normal"
fi