fix(backup): 接入 MOMO PG 備份失敗通知
Some checks failed
Code Review / ai-code-review (push) Successful in 11s
Ansible Lint / lint (push) Has been cancelled

This commit is contained in:
Your Name
2026-05-12 15:50:44 +08:00
parent abdab85362
commit 216b7d78e2
3 changed files with 293 additions and 0 deletions

View File

@@ -0,0 +1,184 @@
#!/usr/bin/env bash
# 192.168.0.188 主機層 momo PostgreSQL 備份控制器。
#
# 由 Ansible 部署到:
# /home/ollama/momo-pro/scripts/pg_backup.sh
#
# PostgreSQL 憑證只從 momo-db 容器環境讀取;禁止輸出或落地憑證值。
set -Eeuo pipefail
BACKUP_DIR="${BACKUP_DIR:-/home/ollama/momo_backups}"
DB_CONTAINER="${DB_CONTAINER:-momo-db}"
DB_USER="${DB_USER:-momo}"
DB_NAME="${DB_NAME:-momo_analytics}"
KEEP_DAYS="${KEEP_DAYS:-7}"
MIN_SIZE_BYTES="${MIN_SIZE_BYTES:-1048576}"
LOG_FILE="${LOG_FILE:-${BACKUP_DIR}/backup.log}"
TIMESTAMP="$(date +%Y%m%d_%H%M%S)"
FILENAME="momo_analytics_${TIMESTAMP}.sql.gz"
FILEPATH="${BACKUP_DIR}/${FILENAME}"
TMP_FILE="${FILEPATH}.tmp"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
START_TS="$(date +%s)"
log() {
local line
line="$(printf '[%s] %s' "$(date '+%Y-%m-%d %H:%M:%S')" "$*")"
printf '%s\n' "$line" >> "${LOG_FILE}"
if [[ "${AWOOI_BACKUP_LOG_STDOUT:-0}" == "1" || -t 1 ]]; then
printf '%s\n' "$line"
fi
}
cleanup_tmp() {
rm -f "${TMP_FILE}"
}
elapsed_seconds() {
local now
now="$(date +%s)"
echo "$((now - START_TS))"
}
notify_awoooi_ops() {
local status="$1"
local summary="$2"
local detail="$3"
local helper="${SCRIPT_DIR}/notify-awoooi-ops.sh"
if [[ "${AWOOI_BACKUP_NOTIFY_ENABLED:-1}" != "1" ]]; then
return 0
fi
[[ -x "$helper" ]] || return 1
AWOOI_OPS_ALERTNAME="Backup.MomoPostgres" \
AWOOI_OPS_JOB_NAME="MOMO PostgreSQL 備份" \
AWOOI_OPS_STATUS="$status" \
AWOOI_OPS_SEVERITY="info" \
AWOOI_OPS_SOURCE="momo-pg-backup" \
AWOOI_OPS_COMPONENT="momo-postgres-backup" \
AWOOI_OPS_SUMMARY="$summary" \
AWOOI_OPS_DETAIL="$detail" \
AWOOI_OPS_DURATION_SECONDS="$(elapsed_seconds)" \
"$helper" >/dev/null
}
notify_best_effort() {
local status="$1"
local summary="$2"
local detail="$3"
if [[ "$status" == "success" && "${AWOOI_BACKUP_NOTIFY_SUCCESS:-0}" != "1" ]]; then
log "略過 AwoooP 成功通知backup-health exporter 作為健康狀態來源"
return 0
fi
notify_awoooi_ops "$status" "$summary" "$detail" || log "WARN AwoooP notification failed"
}
on_error() {
local exit_code="$?"
local line_no="${1:-unknown}"
set +e
notify_awoooi_ops \
"failed" \
"MOMO PostgreSQL 備份失敗" \
"line=${line_no}; container=${DB_CONTAINER}; db=${DB_NAME}; file=${FILENAME}; log=${LOG_FILE}" \
|| true
exit "$exit_code"
}
fail_backup() {
local message="$1"
log "ERROR ${message}"
notify_awoooi_ops \
"failed" \
"MOMO PostgreSQL 備份失敗" \
"${message}; container=${DB_CONTAINER}; db=${DB_NAME}; file=${FILENAME}; log=${LOG_FILE}" \
|| true
exit 1
}
container_running() {
docker inspect -f '{{.State.Running}}' "${DB_CONTAINER}" 2>/dev/null | grep -qx true
}
run_pg_dump() {
docker exec "${DB_CONTAINER}" sh -eu -c '
: "${POSTGRES_PASSWORD:?POSTGRES_PASSWORD missing in container env}"
PGPASSWORD="${POSTGRES_PASSWORD}" exec pg_dump \
-U "${POSTGRES_USER:-momo}" \
-d "${POSTGRES_DB:-momo_analytics}" \
--no-password \
--no-owner \
--no-acl
'
}
insert_backup_log() {
local size_bytes="$1"
local duration="$2"
docker exec \
-e BACKUP_FILENAME="${FILENAME}" \
-e BACKUP_SIZE_BYTES="${size_bytes}" \
-e BACKUP_DURATION_SECONDS="${duration}" \
-e BACKUP_HOST="$(hostname)" \
-e BACKUP_STORAGE_PATH="${FILEPATH}" \
"${DB_CONTAINER}" sh -eu -c '
: "${POSTGRES_PASSWORD:?POSTGRES_PASSWORD missing in container env}"
PGPASSWORD="${POSTGRES_PASSWORD}" psql \
-U "${POSTGRES_USER:-momo}" \
-d "${POSTGRES_DB:-momo_analytics}" \
--no-password \
-v ON_ERROR_STOP=1 \
-c "INSERT INTO backup_log (filename, file_size_bytes, duration_seconds, status, host, storage_path, completed_at)
VALUES (E'\''${BACKUP_FILENAME}'\'', ${BACKUP_SIZE_BYTES}, ${BACKUP_DURATION_SECONDS}, '\''success'\'', E'\''${BACKUP_HOST}'\'', E'\''${BACKUP_STORAGE_PATH}'\'', CURRENT_TIMESTAMP);"
' >/dev/null 2>&1
}
main() {
mkdir -p "${BACKUP_DIR}"
trap cleanup_tmp EXIT
trap 'on_error ${LINENO}' ERR
log "===== momo PostgreSQL backup start ====="
if ! container_running; then
fail_backup "${DB_CONTAINER} is not running"
fi
local start_ts end_ts duration size_bytes size_human deleted backup_log_status
start_ts="$(date +%s)"
if run_pg_dump | gzip >"${TMP_FILE}"; then
size_bytes="$(stat -c%s "${TMP_FILE}" 2>/dev/null || stat -f%z "${TMP_FILE}" 2>/dev/null || echo 0)"
if [ "${size_bytes}" -lt "${MIN_SIZE_BYTES}" ]; then
fail_backup "backup file too small: ${size_bytes} bytes"
fi
mv "${TMP_FILE}" "${FILEPATH}"
chmod 0640 "${FILEPATH}"
else
fail_backup "pg_dump failed"
fi
end_ts="$(date +%s)"
duration="$((end_ts - start_ts))"
size_human="$(du -h "${FILEPATH}" | awk '{print $1}')"
log "Backup success: ${FILENAME} (${size_human}, ${duration}s)"
backup_log_status="success"
if insert_backup_log "${size_bytes}" "${duration}"; then
log "backup_log insert success"
else
backup_log_status="warning"
log "WARN backup_log insert failed; backup file is still valid"
fi
deleted="$(find "${BACKUP_DIR}" -name 'momo_analytics_*.sql.gz' -mtime "+${KEEP_DAYS}" -print -delete | wc -l | tr -d ' ')"
log "Deleted old backups: ${deleted}"
log "===== momo PostgreSQL backup complete ====="
notify_best_effort \
"success" \
"MOMO PostgreSQL 備份完成" \
"file=${FILENAME}; size=${size_human}; duration=${duration}s; backup_log=${backup_log_status}; deleted_old=${deleted}"
}
main "$@"