Files
Varaverk/Transcodes/transcode_cleanup.sh
T
Gmer4Lfe e8b114094a Bring script headers onto the template and close safeguard gaps
Headers claimed protections the code never had, and several destructive paths had no
guard against a collapsed config value.
2026-08-01 20:37:59 -04:00

393 lines
19 KiB
Bash
Executable File

#!/bin/bash
# ==============================================================================================
# ================================= Transcode Cleanup ==========================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Removes stale transcode files from both ramdisk and SSD fallback locations.
# Called by transcode_management.sh (Orchestrators/) before transcode_manager.sh —
# cleanup must run first so the manager sees real active-session usage, not
# inflated usage from stale files. Must be fast and non-blocking.
#
# A file is eligible for deletion only if ALL conditions are true:
# 1. Older than TRANSCODE_MAX_AGE minutes (mtime — last write time)
# 2. Not currently open by any process (checked via lsof pre-built map)
#
# ==============================================================================================
# OPERATIONAL MODEL
# ==============================================================================================
#
# Two locations cleaned in sequence, each through the same routine:
#
# Ramdisk — only if mountpoint -q confirms it is actually mounted. An unmounted
# ramdisk means the underlying directory is the real filesystem, and
# cleaning it would delete from disk rather than from tmpfs.
# SSD fallback — only if the directory exists.
#
# Per location:
# 1. Path sanity check — refuse anything shallower than two components
# 2. Count total and age-eligible files (-mmin +TRANSCODE_MAX_AGE)
# 3. One lsof +D call → in-memory open-file map for the whole location
# 4. Per eligible file: open → skip and count as active; otherwise rm -f
# 5. Remove empty directories older than TRANSCODE_ORPHAN_AGE, never transcoding-temp
#
# Afterwards, if the ramdisk recovered enough headroom, the symlink is flipped back to
# it so new sessions return to RAM.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# Two Independent Conditions, Both Required
# Age and open-file state are checked separately and a file must pass both. Age alone
# would delete a long-running session's segments; lsof alone cannot see HLS segments,
# which are written and closed atomically. Neither signal is sufficient on its own,
# which is exactly why both are applied rather than picking the better one.
#
# Mounted-Only Ramdisk Cleaning
# The ramdisk is only cleaned when it is genuinely mounted. If the tmpfs failed to
# mount, that same path is an ordinary directory on the array — cleaning it then would
# delete real files from disk while believing it was clearing RAM.
#
# lsof Called Once, Not Per File
# On a busy Live TV system the ramdisk contains thousands of HLS segment files.
# Calling lsof once per file creates thousands of subprocess calls every 7 minutes.
# lsof is called once per location to build a complete open-file map. All subsequent
# checks are O(1) lookups against that map — thousands of files, one lsof call.
#
# find -printf Instead of Per-File stat/basename (2026-07-17)
# Same fork-elimination principle as above, applied to the file-processing loop. find
# already has to stat() every entry to know it's -type f, so -printf '%s %p' gets the
# size for free during the walk instead of a separate stat fork per file. basename was
# also forking per file in the dry-run log line -- replaced with parameter expansion
# (${file##*/}). Same class of bug found and measured (~28-185x per call) in the arr
# cleanup scripts' classification loops the same day.
#
# No Session-Aware Cleanup
# ffmpeg generates folder names independently of the media server API session IDs.
# There is no reliable correlation between API session IDs and transcoding-temp
# subfolder names. Attempting to correlate them would falsely treat active sessions
# as ended. lsof is the correct check — if ffmpeg has a file open, it is active
# regardless of folder naming or session state.
#
# transcoding-temp Is Never Deleted
# If cleanup removes the empty transcoding-temp folder from the ramdisk, Emby
# searches all accessible paths for an existing one, finds the SSD fallback version,
# and routes all new sessions there until Emby restarts. The directory is excluded
# from find by name — protected even when completely empty.
#
# Post-Cleanup Flip-Back
# After removing stale files, checks whether ramdisk usage dropped below
# RAMDISK_LOW_GB. If so — and symlink currently points at SSD — triggers a
# flip back to ramdisk. This is the recovery path; the manager handles
# the fill-up path.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Location Path Guard
# cleanup_location() refuses any path that is not absolute with at least two
# components. Neither caller's own check catches a collapsed value — mountpoint -q
# returns true for /, and -d is true for both / and /mnt — so the guard lives inside
# the function that does the deleting, covering both call sites.
#
#
# Wait Lock
# acquire_lock "wait" — waits if a previous cleanup run is still active rather
# than exiting. The caller's 7-minute interval can overlap on a slow system.
#
# lsof Timeout
# lsof call capped at 15 seconds per location — prevents blocking indefinitely
# on a system with many open files.
#
# transcoding-temp Guard
# `! -name "transcoding-temp"` in the find command — protected unconditionally.
#
# Silent by Default
# Runs every 7 minutes — must not produce noise when healthy.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# host*.conf
#
# HOST*_RAMDISK_PATH / HOST*_TRANSCODE_SSD / HOST*_RAMDISK_LOW_GB
# Aliased by detect_hosts() → RAMDISK_PATH / TRANSCODE_SSD / RAMDISK_LOW_GB.
#
# master.conf
#
# TRANSCODE_MAX_AGE
# Minutes before an inactive transcode file is eligible for deletion. (default: 20)
#
# TRANSCODE_ORPHAN_AGE
# Minutes for orphan folder detection. (default: 30)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
# transcode_cleanup.sh
# Remove stale files from ramdisk and SSD. Check for flip-back opportunity.
#
# transcode_cleanup.sh --dry-run
# Show which files would be deleted. No deletions, no flip.
#
# transcode_cleanup.sh --status
# Show current file counts, ages, and open-file status per location.
#
# transcode_cleanup.sh --log
# Verbose per-file output including age, open status, and deletion result.
#
# ==============================================================================================
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/../load_config.sh"
parse_args "$@"
STATE_FILE="${TRANSCODE_STATE_FILE:-${STATE_DIR:-/tmp}/transcode_state.db}"
# ==============================================================================================
# ━━━ Setup ━━━
# ==============================================================================================
if [[ "$EUID" -ne 0 ]]; then
error "Must be run as root"
exit 1
fi
acquire_lock "wait"
# detect_hosts() sets MY_ID and aliases RAMDISK_PATH, TRANSCODE_SSD, RAMDISK_LOW_GB
detect_hosts
# lsof availability check
LSOF_AVAILABLE=false
if command -v lsof >/dev/null 2>&1; then
LSOF_AVAILABLE=true
log "lsof available — active file check enabled"
else
warn "lsof not available — active file check skipped, all aged files eligible for deletion"
fi
log "Identity: $MY_ID ($LOCAL_SERVER_NAME)"
log "$ICON_GEAR Config: max-age=${TRANSCODE_MAX_AGE}min orphan-age=${TRANSCODE_ORPHAN_AGE}min flip-back-below=${RAMDISK_LOW_GB}GB"
log "$ICON_RAM Locations: ramdisk=$RAMDISK_PATH ssd=$TRANSCODE_SSD"
# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
if [[ "$SHOW_STATUS" == true ]]; then
echo ""
echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_RAM Ramdisk: $RAMDISK_PATH"
echo "$ICON_DISK SSD fallback: $TRANSCODE_SSD"
echo "$ICON_TRASH Max age: ${TRANSCODE_MAX_AGE} minutes"
echo "$ICON_TRASH Orphan age: ${TRANSCODE_ORPHAN_AGE} minutes"
echo "$ICON_RAM Flip at: ${RAMDISK_LOW_GB}GB"
echo "$ICON_GEAR lsof check: $LSOF_AVAILABLE"
echo "$ICON_GEAR Dry Run: $DRY_RUN"
echo ""
if mountpoint -q "$RAMDISK_PATH" 2>/dev/null; then
USAGE=$(df -BG "$RAMDISK_PATH" | awk 'NR==2 {print $3}')
AVAIL=$(df -BG "$RAMDISK_PATH" | awk 'NR==2 {print $4}')
echo " $ICON_RAM Ramdisk: mounted — $USAGE used / $AVAIL available ✅"
else
echo " $ICON_RAM Ramdisk: not mounted"
fi
CURRENT_TARGET=$(grep "^current_target=" "$STATE_FILE" 2>/dev/null | cut -d= -f2)
echo " $ICON_LINK Current target: ${CURRENT_TARGET:-unknown}"
echo "━━━━━━━━━━━━━━━━━━━━━━━"
exit 0
fi
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no files will be deleted"
# ==============================================================================================
# ── CLEANUP FUNCTION ──────────────────────────────────────────────────────────────────────────
# ==============================================================================================
# Scans a location and removes eligible files.
# Calls lsof ONCE per location — builds in-memory OPEN_FILES_MAP for O(1) lookup.
# Returns via LOCATION_REMOVED, LOCATION_FREED, LOCATION_SKIPPED, LOCATION_ACTIVE, LOCATION_FAILED
cleanup_location() {
local location="$1" label="$2" max_age="$3"
local files_removed=0 bytes_freed=0 files_skipped=0 files_active=0 files_streaming=0 files_too_young=0 files_failed=0
if [[ ! -d "$location" ]]; then
log "$label does not exist — skipping"
LOCATION_REMOVED=0 LOCATION_FREED="0B" LOCATION_SKIPPED=0 LOCATION_ACTIVE=0 LOCATION_STREAMING=0 LOCATION_TOO_YOUNG=0 LOCATION_FAILED=0
return
fi
# This function deletes every file under $location past the age gate. Neither caller's
# own check catches a collapsed path: mountpoint -q returns true for /, and -d is true
# for / and /mnt alike. Require at least two path components so a blank or truncated
# RAMDISK_PATH / TRANSCODE_SSD can never point this at a system directory.
local _loc_slashes="${location//[^\/]/}"
if [[ "$location" != /* || "${#_loc_slashes}" -lt 2 ]]; then
error "Refusing to clean unsafe location: '$location' ($label)"
notify "Transcode cleanup refused unsafe path on $(hostname): '$location'" \
"Transcode Cleanup" "warning"
LOCATION_REMOVED=0 LOCATION_FREED="0B" LOCATION_SKIPPED=0 LOCATION_ACTIVE=0 LOCATION_STREAMING=0 LOCATION_TOO_YOUNG=0 LOCATION_FAILED=0
return
fi
local file_count eligible_count
file_count=$(find "$location" -type f 2>/dev/null | wc -l)
eligible_count=$(find "$location" -type f -mmin +"$max_age" 2>/dev/null | wc -l)
files_too_young=$(( file_count - eligible_count ))
log "$label: $file_count files ($eligible_count eligible, $files_too_young < ${max_age}min)"
# Build in-memory open file map — O(1) lookup per file
# One lsof call per location — never per file
# Note: HLS/remux segments (Live TV, Direct Stream) are written atomically and immediately
# closed — lsof will not detect them. The age check is the effective guard for those files.
declare -A OPEN_FILES_MAP
if [[ "$LSOF_AVAILABLE" == true ]]; then
log "Building open file map for $label..."
while IFS= read -r open_file; do
[[ -n "$open_file" ]] && OPEN_FILES_MAP["$open_file"]=1
done < <(timeout 15 lsof +D "$location" 2>/dev/null | awk 'NR>1 {print $9}' | sort -u)
files_streaming=${#OPEN_FILES_MAP[@]}
log "$files_streaming files currently open in $label"
fi
# Process aged files. -printf gets size directly from find's own stat() during the walk
# instead of a separate stat fork per file (2026-07-17, same fix as the arr cleanup
# scripts) — mtime isn't needed here since -mmin above already did the age filtering.
local file_size file
while read -r file_size file; do
[[ -z "$file" ]] && continue
# O(1) open file check — in-memory map
if [[ -n "${OPEN_FILES_MAP[$file]:-}" ]]; then
(( files_active++ ))
log "Skipping open file: $file"
continue
fi
if [[ "$DRY_RUN" == true ]]; then
log "DRY RUN — would delete: ${file##*/}"
(( files_skipped++ ))
else
if rm -f "$file" 2>/dev/null; then
(( files_removed++ ))
bytes_freed=$(( bytes_freed + file_size ))
log "Deleted: $file"
else
warn "Could not delete: $file"
(( files_failed++ ))
fi
fi
done < <(find "$location" -type f -mmin +"$max_age" -printf '%s %p\n' 2>/dev/null)
# Remove empty directories older than TRANSCODE_ORPHAN_AGE — but NEVER remove
# transcoding-temp. Age gate avoids deleting a session folder ffmpeg just
# created but hasn't written its first segment into yet.
if [[ "$DRY_RUN" == false ]]; then
find "$location" -mindepth 1 -type d -empty -mmin +"${TRANSCODE_ORPHAN_AGE:-30}" \
! -name "transcoding-temp" -delete 2>/dev/null
fi
# Format bytes freed
local freed_human
freed_human=$(format_bytes "$bytes_freed")
log "$label — removed $files_removed ($freed_human) | active(fresh): $files_too_young | streaming(lsof): $files_streaming | protected(old+open): $files_active | skipped: $files_skipped | failed: $files_failed"
LOCATION_REMOVED=$files_removed
LOCATION_FREED=$freed_human
LOCATION_SKIPPED=$files_skipped
LOCATION_ACTIVE=$files_active
LOCATION_STREAMING=$files_streaming
LOCATION_TOO_YOUNG=$files_too_young
LOCATION_FAILED=$files_failed
}
# ==============================================================================================
# ━━━ Transcode Cleanup ━━━
# ==============================================================================================
START=$(date +%s)
TOTAL_REMOVED=0 TOTAL_SKIPPED=0 TOTAL_ACTIVE=0 TOTAL_STREAMING=0 TOTAL_TOO_YOUNG=0 TOTAL_FAILED=0
RAMDISK_FREED="0B" SSD_FREED="0B"
# Cleanup ramdisk
if mountpoint -q "$RAMDISK_PATH" 2>/dev/null; then
cleanup_location "$RAMDISK_PATH" "Ramdisk" "$TRANSCODE_MAX_AGE"
TOTAL_REMOVED=$(( TOTAL_REMOVED + LOCATION_REMOVED ))
TOTAL_SKIPPED=$(( TOTAL_SKIPPED + LOCATION_SKIPPED ))
TOTAL_ACTIVE=$(( TOTAL_ACTIVE + LOCATION_ACTIVE ))
TOTAL_STREAMING=$(( TOTAL_STREAMING + LOCATION_STREAMING ))
TOTAL_TOO_YOUNG=$(( TOTAL_TOO_YOUNG + LOCATION_TOO_YOUNG ))
TOTAL_FAILED=$(( TOTAL_FAILED + LOCATION_FAILED ))
RAMDISK_FREED=$LOCATION_FREED
else
log "Ramdisk not mounted — skipping ramdisk cleanup"
fi
# Cleanup SSD fallback
if [[ -d "$TRANSCODE_SSD" ]]; then
cleanup_location "$TRANSCODE_SSD" "SSD fallback" "$TRANSCODE_MAX_AGE"
TOTAL_REMOVED=$(( TOTAL_REMOVED + LOCATION_REMOVED ))
TOTAL_SKIPPED=$(( TOTAL_SKIPPED + LOCATION_SKIPPED ))
TOTAL_ACTIVE=$(( TOTAL_ACTIVE + LOCATION_ACTIVE ))
TOTAL_STREAMING=$(( TOTAL_STREAMING + LOCATION_STREAMING ))
TOTAL_TOO_YOUNG=$(( TOTAL_TOO_YOUNG + LOCATION_TOO_YOUNG ))
TOTAL_FAILED=$(( TOTAL_FAILED + LOCATION_FAILED ))
SSD_FREED=$LOCATION_FREED
else
log "SSD fallback not found — skipping SSD cleanup"
fi
# Post-cleanup — check if ramdisk recovered enough to flip symlink back to ramdisk
if [[ "$DRY_RUN" == false ]] && mountpoint -q "$RAMDISK_PATH" 2>/dev/null; then
RAMDISK_USED_KB=$(df "$RAMDISK_PATH" --output=used 2>/dev/null | tail -1 | tr -d ' ')
RAMDISK_USED_GB=$(kb_to_gb "$RAMDISK_USED_KB")
LOW_RECOVERED=$(awk "BEGIN {print ($RAMDISK_USED_GB < $RAMDISK_LOW_GB) ? 1 : 0}")
CURRENT_TARGET=$(grep "^current_target=" "$STATE_FILE" 2>/dev/null | cut -d= -f2)
if [[ "$LOW_RECOVERED" == "1" && "$CURRENT_TARGET" == "$TRANSCODE_SSD" ]]; then
echo "Ramdisk has space after cleanup (${RAMDISK_USED_GB}GB < ${RAMDISK_LOW_GB}GB) — triggering manager to flip back"
bash "$SCRIPT_DIR/transcode_manager.sh" --no-log
fi
fi
END=$(date +%s)
# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo "━━━━━ $ICON_SUMMARY TRANSCODE CLEANUP SUMMARY ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_RAM Ramdisk freed: $RAMDISK_FREED"
echo "$ICON_DISK SSD freed: $SSD_FREED"
echo "$ICON_TRASH Removed: $TOTAL_REMOVED files"
echo "$ICON_RUNNING Active: $TOTAL_TOO_YOUNG files (< ${TRANSCODE_MAX_AGE}min old — Live TV / Direct Stream segments)"
echo "$ICON_RUNNING Streaming: $TOTAL_STREAMING files (open file handle — long-running transcode)"
echo "$ICON_SHIELD Protected: $TOTAL_ACTIVE aged files saved by open-file check"
echo "$ICON_TRASH Skipped: $TOTAL_SKIPPED files"
[[ "$TOTAL_FAILED" -gt 0 ]] && echo "$ICON_ERROR Failed: $TOTAL_FAILED files could not be deleted"
echo "$ICON_TIME Duration: $(format_duration $(( END - START )))"
if [[ "$DRY_RUN" == true ]]; then
warn "DRY RUN — no files deleted"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
exit 0
elif [[ "$TOTAL_FAILED" -gt 0 ]]; then
warn "Status: $TOTAL_FAILED file(s) failed to delete"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
exit 1
else
echo "$ICON_DONE Status: done ✅"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
exit 0
fi