140 lines
4.7 KiB
Bash
Executable File
140 lines
4.7 KiB
Bash
Executable File
#!/bin/bash
|
||
# =============================================================================
|
||
# WOOO AIOps - SignOz 備份腳本 (ClickHouse + SQLite)
|
||
# 版本: 1.2.0
|
||
# 建立日期: 2026-04-05
|
||
# 2026-04-05 Claude Code: 新增 SignOz 分散式追蹤備份 — 首席架構師備份審計
|
||
# 2026-04-05 Claude Code: v1.1 修正 tar pipeline exit code 處理 + || true
|
||
# 2026-07-15 Codex: v1.2 確保任何 exit/signal/failure 都會受控還原 OTEL Collector
|
||
# =============================================================================
|
||
|
||
set -euo pipefail
|
||
|
||
source "$(dirname "$0")/common.sh"
|
||
|
||
SERVICE="signoz"
|
||
LOCAL_REPO="${BACKUP_BASE}/signoz"
|
||
DUMP_DIR="/tmp/signoz-backup-$$"
|
||
COLLECTOR_RESTORE_PENDING=0
|
||
CLEANUP_COMPLETE=0
|
||
|
||
restore_collector() {
|
||
if [ "${COLLECTOR_RESTORE_PENDING}" -ne 1 ]; then
|
||
return 0
|
||
fi
|
||
|
||
log_info "重啟 signoz-otel-collector..."
|
||
if docker start signoz-otel-collector 2>/dev/null; then
|
||
COLLECTOR_RESTORE_PENDING=0
|
||
return 0
|
||
fi
|
||
|
||
log_warn "signoz-otel-collector 重啟失敗"
|
||
return 1
|
||
}
|
||
|
||
cleanup() {
|
||
local exit_code=$?
|
||
|
||
if [ "${CLEANUP_COMPLETE}" -eq 1 ]; then
|
||
return "${exit_code}"
|
||
fi
|
||
CLEANUP_COMPLETE=1
|
||
|
||
# cleanup 期間忽略重複 signal,避免還原與刪除流程重入。
|
||
trap '' HUP INT TERM
|
||
restore_collector || true
|
||
rm -rf "${DUMP_DIR}"
|
||
return "${exit_code}"
|
||
}
|
||
|
||
on_signal() {
|
||
local signal_number="$1"
|
||
exit "$((128 + signal_number))"
|
||
}
|
||
|
||
backup_volume() {
|
||
local volume_name="$1"
|
||
local output_file="$2"
|
||
local extra_exclude="${3:-}"
|
||
log_info "備份 volume: ${volume_name}"
|
||
# 使用 || true 處理 tar 備份運行中 volume 的 exit 1 警告
|
||
if [ -n "${extra_exclude}" ]; then
|
||
docker run --rm -v "${volume_name}:/data" alpine tar czf - "${extra_exclude}" /data 2>/dev/null > "${output_file}" || true
|
||
else
|
||
docker run --rm -v "${volume_name}:/data" alpine tar czf - /data 2>/dev/null > "${output_file}" || true
|
||
fi
|
||
if [ -s "${output_file}" ]; then
|
||
local size=$(du -h "${output_file}" | cut -f1)
|
||
log_success " Volume ${volume_name} 備份完成 (${size})"
|
||
return 0
|
||
else
|
||
log_error " Volume ${volume_name} 備份失敗 (空檔案)"
|
||
return 1
|
||
fi
|
||
}
|
||
|
||
main() {
|
||
local start_time=$(date +%s)
|
||
|
||
trap cleanup EXIT
|
||
trap 'on_signal 1' HUP
|
||
trap 'on_signal 2' INT
|
||
trap 'on_signal 15' TERM
|
||
|
||
log_info "========== 開始 SignOz 備份 =========="
|
||
mkdir -p "${DUMP_DIR}"
|
||
|
||
local timestamp=$(date "+%Y%m%d_%H%M%S")
|
||
|
||
# Step 1: 停止 OTEL Collector 確保數據一致性
|
||
log_info "暫停 signoz-otel-collector 以確保數據一致性..."
|
||
# 先 arm 還原再停止,消除 signal 發生在 stop 與狀態記錄之間的空窗。
|
||
COLLECTOR_RESTORE_PENDING=1
|
||
docker stop signoz-otel-collector 2>/dev/null || log_warn "signoz-otel-collector 未在運行,繼續"
|
||
docker stop signoz-telemetrystore-migrator 2>/dev/null || true
|
||
|
||
# Step 2: 備份 ClickHouse volume (排除 tmp 目錄降低體積)
|
||
backup_volume "signoz-clickhouse" "${DUMP_DIR}/clickhouse_${timestamp}.tar.gz" "--exclude=/data/tmp" || {
|
||
log_error "ClickHouse volume 備份失敗"
|
||
notify_clawbot "failed" "${SERVICE}" "SignOz ClickHouse 備份失敗"
|
||
exit 1
|
||
}
|
||
|
||
# Step 3: 備份 SQLite volume (SignOz metadata)
|
||
backup_volume "signoz-sqlite" "${DUMP_DIR}/sqlite_${timestamp}.tar.gz" || {
|
||
log_warn "SQLite volume 備份失敗,繼續..."
|
||
}
|
||
|
||
# Step 4: 重啟 Collector
|
||
# 若此處失敗,保留 pending 讓 EXIT cleanup 再做一次有界還原。
|
||
restore_collector || true
|
||
|
||
# Step 5: 初始化 Restic 倉庫
|
||
if [ ! -d "${LOCAL_REPO}/data" ]; then
|
||
log_info "初始化 Restic 倉庫: ${LOCAL_REPO}"
|
||
restic -r "${LOCAL_REPO}" init --password-file "${RESTIC_PASSWORD_FILE}" 2>&1 || {
|
||
log_error "Restic 倉庫初始化失敗"
|
||
exit 1
|
||
}
|
||
fi
|
||
|
||
# Step 6: Restic 備份
|
||
log_info "建立 Restic 備份..."
|
||
local tags=$(build_tags "${SERVICE}")
|
||
restic -r "${LOCAL_REPO}" backup "${DUMP_DIR}" --password-file "${RESTIC_PASSWORD_FILE}" ${tags} 2>&1
|
||
|
||
local snapshot_id=$(restic -r "${LOCAL_REPO}" snapshots --latest 1 --json --password-file "${RESTIC_PASSWORD_FILE}" 2>/dev/null | grep -oP '"short_id":"\K[^"]+' | head -1)
|
||
log_success "Restic 備份完成: ${snapshot_id}"
|
||
|
||
# Step 7: GFS 清理
|
||
cleanup_old_backups "${LOCAL_REPO}"
|
||
|
||
local end_time=$(date +%s)
|
||
local duration=$((end_time - start_time))
|
||
log_success "========== SignOz 備份完成 (${duration}s) =========="
|
||
notify_clawbot "success" "${SERVICE}" "SignOz 備份完成 (ClickHouse+SQLite)" "${duration}"
|
||
}
|
||
|
||
main "$@"
|