it is risen - add restore progress and backup/restore history
The watcher scripts now write live status and append-only run history onto the shared volume; the api exposes them via /shopdbbackups/status and /history. The restore modal shows an indeterminate spinner with phase labels, and two cards list backup and restore run records. Timestamps render in UTC to match the Zulu-stamped set ids, the history directory is excluded from the set list, and a stale-status guard stops a previous run's done phase from collapsing the spinner on the next restore.
This commit is contained in:
benjamin.baker
@@ -185,6 +185,38 @@
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<!-- Operational run records, written by the backup container onto the
|
||||
shared volume. Two cards: what was backed up, and what was restored. -->
|
||||
<div class="history-cards">
|
||||
<div class="history-card">
|
||||
<h3 class="history-title">Backup history</h3>
|
||||
<p v-if="!backups.length" class="muted">No backup runs recorded yet.</p>
|
||||
<ul v-else class="history-list">
|
||||
<li v-for="(entry, index) in backups" :key="'b' + index" class="history-row">
|
||||
<span class="history-outcome" :class="outcomeClass(entry.outcome)">
|
||||
{{ outcomeLabel(entry.outcome) }}
|
||||
</span>
|
||||
<span class="history-set">{{ entry.setname || 'unknown set' }}</span>
|
||||
<span class="history-when">{{ formatTaken(entry.finishedat) }}</span>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="history-card">
|
||||
<h3 class="history-title">Restore history</h3>
|
||||
<p v-if="!restores.length" class="muted">No restore runs recorded yet.</p>
|
||||
<ul v-else class="history-list">
|
||||
<li v-for="(entry, index) in restores" :key="'r' + index" class="history-row">
|
||||
<span class="history-outcome" :class="outcomeClass(entry.outcome)">
|
||||
{{ outcomeLabel(entry.outcome) }}
|
||||
</span>
|
||||
<span class="history-set">{{ entry.setname || 'unknown set' }}</span>
|
||||
<span class="history-when">{{ formatTaken(entry.finishedat) }}</span>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Guarded restore modal: the one genuinely risky action, so it spends the
|
||||
UI budget on the compatibility verdict before allowing the click. -->
|
||||
<div v-if="restoreTarget" class="modal-backdrop" @click.self="closeRestore">
|
||||
@@ -192,6 +224,34 @@
|
||||
<h3>Restore this backup?</h3>
|
||||
<p class="modal-set">{{ formatTaken(restoreTarget.takenat || restoreTarget.snapshotid) }}</p>
|
||||
|
||||
<!-- Progress mode: once a restore is queued we swap the compatibility
|
||||
body for an indeterminate spinner and the current phase label. -->
|
||||
<template v-if="restorePhase">
|
||||
<div class="restore-progress" :class="{ failed: restorePhase === 'failed' }">
|
||||
<span v-if="isRestoreRunning" class="spinner" aria-hidden="true"></span>
|
||||
<component
|
||||
:is="restorePhase === 'done' ? ShieldCheck : AlertTriangle"
|
||||
v-else
|
||||
:size="18"
|
||||
/>
|
||||
<span class="restore-phase">{{ restorePhaseLabel }}</span>
|
||||
</div>
|
||||
<p class="restore-hint">
|
||||
Keep this open until the restore finishes. This can take a moment.
|
||||
</p>
|
||||
|
||||
<div class="modal-actions">
|
||||
<button
|
||||
class="btn-ghost"
|
||||
:disabled="isRestoreRunning"
|
||||
@click="closeRestore"
|
||||
>
|
||||
Close
|
||||
</button>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<template v-else>
|
||||
<div class="compat" :class="restoreTarget.iscompatible ? 'ok' : 'warn'">
|
||||
<component :is="restoreTarget.iscompatible ? ShieldCheck : AlertTriangle" :size="18" />
|
||||
<span v-if="restoreTarget.iscompatible">
|
||||
@@ -224,13 +284,14 @@
|
||||
Restore
|
||||
</button>
|
||||
</div>
|
||||
</template>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { ref, computed, onMounted } from 'vue'
|
||||
import { ref, computed, onMounted, onUnmounted } from 'vue'
|
||||
import { ShieldCheck, AlertTriangle, ShieldAlert, Clock } from 'lucide-vue-next'
|
||||
import api from '../../api'
|
||||
import { useToast } from '../../composables/toast'
|
||||
@@ -243,6 +304,37 @@ const isBusy = ref(false)
|
||||
const lastGoodAt = ref(null)
|
||||
const restoreTarget = ref(null)
|
||||
|
||||
// Live restore progress. restoreStatus mirrors the api /status.restore payload;
|
||||
// restorePhase drives the indeterminate spinner and label in the modal.
|
||||
const restoreStatus = ref(null)
|
||||
let statusTimer = null
|
||||
let restoreStartedAt = 0
|
||||
|
||||
const backups = ref([])
|
||||
const restores = ref([])
|
||||
|
||||
// Human labels for the phase names the watcher scripts write. Anything we do
|
||||
// not recognize falls back to the raw phase so a new phase still shows.
|
||||
const RESTORE_PHASE_LABELS = {
|
||||
queued: 'Queued...',
|
||||
checking: 'Checking compatibility...',
|
||||
files: 'Restoring files...',
|
||||
database: 'Loading database...',
|
||||
done: 'Restore complete',
|
||||
failed: 'Restore failed',
|
||||
}
|
||||
|
||||
const restorePhase = computed(() => restoreStatus.value?.phase || null)
|
||||
const isRestoreRunning = computed(() => {
|
||||
const phase = restorePhase.value
|
||||
return !!phase && phase !== 'done' && phase !== 'failed'
|
||||
})
|
||||
const restorePhaseLabel = computed(() => {
|
||||
const phase = restorePhase.value
|
||||
if (!phase) return ''
|
||||
return RESTORE_PHASE_LABELS[phase] || phase
|
||||
})
|
||||
|
||||
const settingsOpen = ref(false)
|
||||
const settingsLoading = ref(true)
|
||||
const savingSettings = ref(false)
|
||||
@@ -332,6 +424,8 @@ function openRestore(set) {
|
||||
}
|
||||
|
||||
function closeRestore() {
|
||||
stopStatusPolling()
|
||||
restoreStatus.value = null
|
||||
restoreTarget.value = null
|
||||
}
|
||||
|
||||
@@ -341,13 +435,73 @@ async function confirmRestore() {
|
||||
try {
|
||||
await api.post(`/shopdbbackups/${restoreTarget.value.snapshotid}/restore`)
|
||||
toast.success('Restore queued and validated against the live schema.')
|
||||
closeRestore()
|
||||
// Keep the modal open and switch it to progress mode; polling drives the
|
||||
// spinner through each phase until the watcher reports done or failed.
|
||||
startStatusPolling()
|
||||
} catch (error) {
|
||||
const message = error.response?.data?.data?.error?.message
|
||||
toast.error(message || 'Could not queue the restore.')
|
||||
} finally {
|
||||
isBusy.value = false
|
||||
}
|
||||
}
|
||||
|
||||
async function loadHistory() {
|
||||
try {
|
||||
const response = await api.get('/shopdbbackups/history')
|
||||
const data = response.data.data || {}
|
||||
backups.value = data.backups || []
|
||||
restores.value = data.restores || []
|
||||
} catch (error) {
|
||||
// History is non-critical; a failure here should not disrupt the page.
|
||||
}
|
||||
}
|
||||
|
||||
async function pollStatus() {
|
||||
let status
|
||||
try {
|
||||
const response = await api.get('/shopdbbackups/status')
|
||||
status = response.data.data?.restore || null
|
||||
} catch (error) {
|
||||
return
|
||||
}
|
||||
// Ignore a terminal status left over from a previous restore: if it finished
|
||||
// before we started this one, it is stale and would close the modal instantly
|
||||
// before the spinner ever paints. Wait for a fresh status from this run.
|
||||
if (status && (status.phase === 'done' || status.phase === 'failed')) {
|
||||
const finishedAt = new Date(normalizeStamp(status.updatedat || '')).getTime()
|
||||
if (Number.isNaN(finishedAt) || finishedAt < restoreStartedAt) {
|
||||
return
|
||||
}
|
||||
}
|
||||
restoreStatus.value = status
|
||||
const phase = status?.phase
|
||||
if (phase === 'done' || phase === 'failed') {
|
||||
stopStatusPolling()
|
||||
if (phase === 'done') {
|
||||
toast.success('Restore complete.')
|
||||
closeRestore()
|
||||
} else {
|
||||
toast.error(status?.message || 'Restore failed.')
|
||||
}
|
||||
load()
|
||||
loadHistory()
|
||||
}
|
||||
}
|
||||
|
||||
function startStatusPolling() {
|
||||
stopStatusPolling()
|
||||
restoreStartedAt = Date.now()
|
||||
restoreStatus.value = { phase: 'queued', message: 'Restore queued' }
|
||||
// Poll on an interval only; skip the immediate call so the seeded "queued"
|
||||
// phase is guaranteed to paint before the first real status can replace it.
|
||||
statusTimer = setInterval(pollStatus, 1000)
|
||||
}
|
||||
|
||||
function stopStatusPolling() {
|
||||
if (statusTimer) {
|
||||
clearInterval(statusTimer)
|
||||
statusTimer = null
|
||||
}
|
||||
}
|
||||
|
||||
@@ -385,7 +539,17 @@ function formatTaken(value) {
|
||||
if (!value) return 'unknown'
|
||||
const date = new Date(normalizeStamp(value))
|
||||
if (Number.isNaN(date.getTime())) return value
|
||||
return date.toLocaleString()
|
||||
// Stamps are UTC; render them in UTC so the displayed time matches the
|
||||
// Zulu-stamped set id rather than shifting to the operator's local zone.
|
||||
return date.toLocaleString(undefined, { timeZone: 'UTC', timeZoneName: 'short' })
|
||||
}
|
||||
|
||||
function outcomeClass(outcome) {
|
||||
return outcome === 'success' ? 'outcome-success' : 'outcome-failed'
|
||||
}
|
||||
|
||||
function outcomeLabel(outcome) {
|
||||
return outcome === 'success' ? 'Success' : 'Failed'
|
||||
}
|
||||
|
||||
// Backup ids and manifest stamps use a filename-safe UTC form with no colons
|
||||
@@ -425,6 +589,11 @@ function statusLabel(set) {
|
||||
onMounted(() => {
|
||||
load()
|
||||
loadSettings()
|
||||
loadHistory()
|
||||
})
|
||||
|
||||
onUnmounted(() => {
|
||||
stopStatusPolling()
|
||||
})
|
||||
</script>
|
||||
|
||||
@@ -570,6 +739,85 @@ onMounted(() => {
|
||||
.compat.ok { background: rgba(56, 161, 105, 0.15); color: #9ae6b4; }
|
||||
.compat.warn { background: rgba(214, 158, 46, 0.15); color: #f6e05e; }
|
||||
|
||||
.restore-progress {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.6rem;
|
||||
padding: 0.7rem 0.8rem;
|
||||
border-radius: 8px;
|
||||
background: rgba(56, 161, 105, 0.15);
|
||||
color: #9ae6b4;
|
||||
font-size: 0.9rem;
|
||||
}
|
||||
.restore-progress.failed { background: rgba(197, 48, 48, 0.15); color: #feb2b2; }
|
||||
.restore-phase { font-weight: 600; }
|
||||
.restore-hint {
|
||||
color: var(--text-light);
|
||||
font-size: 0.8rem;
|
||||
margin: 0.5rem 0 0 0;
|
||||
}
|
||||
.spinner {
|
||||
width: 16px;
|
||||
height: 16px;
|
||||
border: 2px solid rgba(154, 230, 180, 0.35);
|
||||
border-top-color: #9ae6b4;
|
||||
border-radius: 50%;
|
||||
animation: spin 0.8s linear infinite;
|
||||
flex-shrink: 0;
|
||||
}
|
||||
@keyframes spin {
|
||||
to { transform: rotate(360deg); }
|
||||
}
|
||||
|
||||
.history-cards {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 1rem;
|
||||
margin-top: 1.5rem;
|
||||
}
|
||||
.history-card {
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 8px;
|
||||
background: var(--bg-card);
|
||||
padding: 1rem 1.1rem;
|
||||
}
|
||||
.history-title {
|
||||
margin: 0 0 0.75rem 0;
|
||||
font-size: 0.95rem;
|
||||
}
|
||||
.history-list {
|
||||
list-style: none;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
.history-row {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.8rem;
|
||||
padding: 0.5rem 0;
|
||||
border-top: 1px solid var(--border);
|
||||
font-size: 0.85rem;
|
||||
}
|
||||
.history-row:first-child { border-top: none; }
|
||||
.history-outcome {
|
||||
flex-shrink: 0;
|
||||
padding: 0.1rem 0.5rem;
|
||||
border-radius: 999px;
|
||||
font-size: 0.72rem;
|
||||
font-weight: 600;
|
||||
}
|
||||
.outcome-success { background: rgba(56, 161, 105, 0.15); color: #9ae6b4; }
|
||||
.outcome-failed { background: rgba(197, 48, 48, 0.15); color: #feb2b2; }
|
||||
.history-set {
|
||||
flex: 1;
|
||||
font-family: monospace;
|
||||
color: var(--text);
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
white-space: nowrap;
|
||||
}
|
||||
.history-when { color: var(--text-light); flex-shrink: 0; }
|
||||
|
||||
.modal-actions {
|
||||
display: flex;
|
||||
justify-content: flex-end;
|
||||
|
||||
@@ -23,9 +23,28 @@ STAMP="$(date -u +%Y-%m-%dT%H%M%SZ)"
|
||||
SETNAME="${SITE}-${STAMP}"
|
||||
SETDIR="${BACKUPS_ROOT}/${SETNAME}"
|
||||
|
||||
# shellcheck source=scripts/backup/status.sh
|
||||
. /opt/backup/status.sh
|
||||
|
||||
log() { echo "[backup] $*"; }
|
||||
|
||||
# Record the run outcome on any exit so a failed backup is visible in the UI
|
||||
# history, not just a silent gap.
|
||||
BACKUP_DONE=false
|
||||
_on_exit() {
|
||||
code=$?
|
||||
if [ "${BACKUP_DONE}" = true ]; then
|
||||
status_write backup done "${SETNAME}" "Backup complete"
|
||||
history_append backup success "${SETNAME}" "Backup complete"
|
||||
else
|
||||
status_write backup failed "${SETNAME}" "Backup failed (exit ${code})"
|
||||
history_append backup failed "${SETNAME}" "Backup failed (exit ${code})"
|
||||
fi
|
||||
}
|
||||
trap _on_exit EXIT
|
||||
|
||||
mkdir -p "${SETDIR}"
|
||||
status_write backup database "${SETNAME}" "Dumping database"
|
||||
|
||||
# 1. Database: whole-DB logical dump, consistent and non-blocking on InnoDB.
|
||||
log "dumping database ${MYSQL_DATABASE} from ${MYSQL_HOST}"
|
||||
@@ -53,6 +72,7 @@ python3 /opt/backup/manifest.py \
|
||||
# 3. restic snapshot: db dump + instance tree + manifest, one point in time.
|
||||
# Skips gracefully when restic/repo are not configured (local-only sites).
|
||||
IS_CHECK_PASSED=false
|
||||
status_write backup snapshot "${SETNAME}" "Snapshotting to backup store"
|
||||
if command -v restic >/dev/null 2>&1 && [ -n "${RESTIC_REPOSITORY:-}" ]; then
|
||||
if ! restic snapshots >/dev/null 2>&1; then
|
||||
log "initializing restic repository at ${RESTIC_REPOSITORY}"
|
||||
@@ -95,4 +115,5 @@ python3 /opt/backup/manifest.py \
|
||||
# Clear the request sentinel the UI drops when an operator clicks "Back up now".
|
||||
rm -f "${BACKUPS_ROOT}/.backup-requested" 2>/dev/null || true
|
||||
|
||||
BACKUP_DONE=true
|
||||
log "backup set ${SETNAME} complete"
|
||||
|
||||
@@ -21,11 +21,32 @@ set -euo pipefail
|
||||
BACKUPS_ROOT="${SHOPDB_BACKUPS_ROOT:-/backups}"
|
||||
SETNAME="${1:-}"
|
||||
|
||||
# shellcheck source=scripts/backup/status.sh
|
||||
. /opt/backup/status.sh
|
||||
|
||||
log() { echo "[restore] $*"; }
|
||||
|
||||
# On any exit, stamp the terminal phase and append a history record so the UI
|
||||
# reflects success or failure even when a step aborts early (set -e).
|
||||
RESTORE_DONE=false
|
||||
_on_exit() {
|
||||
code=$?
|
||||
if [ "${RESTORE_DONE}" = true ]; then
|
||||
status_write restore done "${SETNAME}" "Restore complete"
|
||||
history_append restore success "${SETNAME}" "Restore complete"
|
||||
else
|
||||
status_write restore failed "${SETNAME}" "Restore failed (exit ${code})"
|
||||
history_append restore failed "${SETNAME}" "Restore failed (exit ${code})"
|
||||
fi
|
||||
}
|
||||
trap _on_exit EXIT
|
||||
|
||||
die() { echo "[restore] ERROR: $*" >&2; exit 1; }
|
||||
|
||||
[ -n "${SETNAME}" ] || die "usage: restore.sh <snapshot-set-name>"
|
||||
|
||||
status_write restore checking "${SETNAME}" "Checking schema compatibility"
|
||||
|
||||
SETDIR="${BACKUPS_ROOT}/${SETNAME}"
|
||||
DBDUMP="${SETDIR}/db.sql.gz"
|
||||
|
||||
@@ -60,11 +81,13 @@ fi
|
||||
|
||||
# Files first, then DB, so the two land together.
|
||||
if command -v restic >/dev/null 2>&1 && [ -n "${RESTIC_REPOSITORY:-}" ]; then
|
||||
status_write restore files "${SETNAME}" "Restoring instance files"
|
||||
log "restoring instance files from restic"
|
||||
restic restore latest --target / --include /app/instance \
|
||||
|| die "restic restore of instance files failed"
|
||||
fi
|
||||
|
||||
status_write restore database "${SETNAME}" "Loading database dump"
|
||||
log "loading database dump"
|
||||
gunzip -c "${DBDUMP}" | mysql \
|
||||
--host="${MYSQL_HOST}" \
|
||||
@@ -73,4 +96,5 @@ gunzip -c "${DBDUMP}" | mysql \
|
||||
|| die "database load failed"
|
||||
|
||||
rm -f "${BACKUPS_ROOT}/.restore-requested" 2>/dev/null || true
|
||||
RESTORE_DONE=true
|
||||
log "restore of ${SETNAME} complete"
|
||||
|
||||
100
scripts/backup/status.sh
Normal file
100
scripts/backup/status.sh
Normal file
@@ -0,0 +1,100 @@
|
||||
# ShopDB backup/restore status + history helper.
|
||||
#
|
||||
# WHY this exists: the restore and backup runs happen in the watcher container,
|
||||
# but the operator watches the UI, which only talks to the api. This helper is
|
||||
# the bridge: it writes two kinds of state onto the shared /backups volume that
|
||||
# the api can read.
|
||||
#
|
||||
# 1. A LIVE status file (.restore-status.json / .backup-status.json) rewritten
|
||||
# at each phase so the UI can show an indeterminate spinner with a phase
|
||||
# label (queued, restoring files, loading database, done, failed).
|
||||
# 2. An append-only HISTORY file (history/restores.json / history/backups.json)
|
||||
# that keeps the record of past runs so the UI can list them in a card.
|
||||
#
|
||||
# Both writes are atomic (write temp, rename) so the api never reads a half
|
||||
# written file. History is bounded to the most recent HISTORY_MAX entries.
|
||||
#
|
||||
# This file is SOURCED, not executed. It exposes:
|
||||
# status_write <kind> <phase> <setname> [message]
|
||||
# history_append <kind> <outcome> <setname> [message]
|
||||
#
|
||||
# kind is "restore" or "backup". ASCII only, no emojis - matches the style gate.
|
||||
|
||||
STATUS_BACKUPS_ROOT="${SHOPDB_BACKUPS_ROOT:-/backups}"
|
||||
HISTORY_MAX="${BACKUP_HISTORY_MAX:-50}"
|
||||
|
||||
_status_now() { date -u +%Y-%m-%dT%H%M%SZ; }
|
||||
|
||||
_status_json_escape() {
|
||||
# Escape backslashes and double quotes for embedding in a JSON string.
|
||||
printf '%s' "${1:-}" | sed 's/\\/\\\\/g; s/"/\\"/g'
|
||||
}
|
||||
|
||||
# status_write <kind> <phase> <setname> [message]
|
||||
# Rewrites the live status file for this run kind.
|
||||
status_write() {
|
||||
kind="$1"
|
||||
phase="$2"
|
||||
setname="${3:-}"
|
||||
message="${4:-}"
|
||||
statusfile="${STATUS_BACKUPS_ROOT}/.${kind}-status.json"
|
||||
tmpfile="${statusfile}.tmp.$$"
|
||||
{
|
||||
printf '{'
|
||||
printf '"kind":"%s",' "$(_status_json_escape "${kind}")"
|
||||
printf '"phase":"%s",' "$(_status_json_escape "${phase}")"
|
||||
printf '"setname":"%s",' "$(_status_json_escape "${setname}")"
|
||||
printf '"message":"%s",' "$(_status_json_escape "${message}")"
|
||||
printf '"updatedat":"%s"' "$(_status_now)"
|
||||
printf '}\n'
|
||||
} > "${tmpfile}" 2>/dev/null || return 0
|
||||
mv -f "${tmpfile}" "${statusfile}" 2>/dev/null || rm -f "${tmpfile}" 2>/dev/null
|
||||
return 0
|
||||
}
|
||||
|
||||
# history_append <kind> <outcome> <setname> [message]
|
||||
# Appends a completed run record and trims to HISTORY_MAX newest entries.
|
||||
history_append() {
|
||||
kind="$1"
|
||||
outcome="$2"
|
||||
setname="${3:-}"
|
||||
message="${4:-}"
|
||||
historydir="${STATUS_BACKUPS_ROOT}/history"
|
||||
historyfile="${historydir}/${kind}s.json"
|
||||
tmpfile="${historyfile}.tmp.$$"
|
||||
mkdir -p "${historydir}" 2>/dev/null || return 0
|
||||
|
||||
record="$(printf '{"setname":"%s","outcome":"%s","message":"%s","finishedat":"%s"}' \
|
||||
"$(_status_json_escape "${setname}")" \
|
||||
"$(_status_json_escape "${outcome}")" \
|
||||
"$(_status_json_escape "${message}")" \
|
||||
"$(_status_now)")"
|
||||
|
||||
if command -v python3 >/dev/null 2>&1; then
|
||||
HISTORY_FILE="${historyfile}" HISTORY_RECORD="${record}" \
|
||||
HISTORY_MAX="${HISTORY_MAX}" python3 - "${tmpfile}" <<'PY' 2>/dev/null || return 0
|
||||
import json, os, sys
|
||||
|
||||
path = os.environ["HISTORY_FILE"]
|
||||
record = json.loads(os.environ["HISTORY_RECORD"])
|
||||
limit = int(os.environ.get("HISTORY_MAX", "50"))
|
||||
tmp = sys.argv[1]
|
||||
|
||||
try:
|
||||
with open(path, "r", encoding="utf-8") as handle:
|
||||
entries = json.load(handle)
|
||||
if not isinstance(entries, list):
|
||||
entries = []
|
||||
except (OSError, ValueError):
|
||||
entries = []
|
||||
|
||||
entries.append(record)
|
||||
entries = entries[-limit:]
|
||||
|
||||
with open(tmp, "w", encoding="utf-8") as handle:
|
||||
json.dump(entries, handle)
|
||||
os.replace(tmp, path)
|
||||
PY
|
||||
fi
|
||||
return 0
|
||||
}
|
||||
@@ -19,6 +19,9 @@ INTERVAL="${BACKUP_POLL_SECONDS:-10}"
|
||||
|
||||
log() { echo "[backup-watch] $*"; }
|
||||
|
||||
# shellcheck source=scripts/backup/status.sh
|
||||
. /opt/backup/status.sh
|
||||
|
||||
mkdir -p "${BACKUPS_ROOT}"
|
||||
# The api container runs unprivileged and only drops sentinel files here; it
|
||||
# cannot write into a root-owned 0755 directory. Make the backups root
|
||||
@@ -29,6 +32,7 @@ log "watcher up; polling ${SENTINEL} and ${RESTORE_SENTINEL} every ${INTERVAL}s"
|
||||
while true; do
|
||||
if [ -f "${SENTINEL}" ]; then
|
||||
log "backup requested - running one-shot"
|
||||
status_write backup queued "" "Backup queued"
|
||||
if /opt/backup/backup.sh; then
|
||||
log "backup completed"
|
||||
else
|
||||
@@ -45,6 +49,7 @@ while true; do
|
||||
# fails so a bad set cannot pin the watcher in a tight retry loop.
|
||||
setname="$(head -n1 "${RESTORE_SENTINEL}" 2>/dev/null | tr -d '\r\n')"
|
||||
log "restore requested - running restore for ${setname}"
|
||||
status_write restore queued "${setname}" "Restore queued"
|
||||
if /opt/backup/restore.sh "${setname}"; then
|
||||
log "restore completed"
|
||||
else
|
||||
|
||||
@@ -85,6 +85,51 @@ def _backups_root():
|
||||
return os.environ.get(BACKUPS_ROOT_ENV, DEFAULT_BACKUPS_ROOT)
|
||||
|
||||
|
||||
def _read_json(path):
|
||||
"""Load a JSON file, or None when it is absent or unreadable."""
|
||||
try:
|
||||
with open(path, 'r', encoding='utf-8') as handle:
|
||||
return json.load(handle)
|
||||
except (OSError, ValueError):
|
||||
return None
|
||||
|
||||
|
||||
def _read_status(kind):
|
||||
"""Return the live status dict for a run kind, or None when idle."""
|
||||
root = _backups_root()
|
||||
return _read_json(os.path.join(root, '.' + kind + '-status.json'))
|
||||
|
||||
|
||||
def _read_history(kind):
|
||||
"""Return the recorded run history for a kind, newest first."""
|
||||
root = _backups_root()
|
||||
entries = _read_json(os.path.join(root, 'history', kind + 's.json'))
|
||||
if not isinstance(entries, list):
|
||||
return []
|
||||
return list(reversed(entries))
|
||||
|
||||
|
||||
def _write_status(kind, phase, setname, message):
|
||||
"""Seed a live status file so the UI shows movement the instant a run is
|
||||
queued, before the watcher has picked up the sentinel."""
|
||||
root = _backups_root()
|
||||
stamp = datetime.now(timezone.utc).replace(tzinfo=None).isoformat() + 'Z'
|
||||
payload = {
|
||||
'kind': kind,
|
||||
'phase': phase,
|
||||
'setname': setname,
|
||||
'message': message,
|
||||
'updatedat': stamp,
|
||||
}
|
||||
try:
|
||||
path = os.path.join(root, '.' + kind + '-status.json')
|
||||
with open(path, 'w', encoding='utf-8') as handle:
|
||||
json.dump(payload, handle)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
|
||||
|
||||
def _read_manifest(setdir):
|
||||
"""Load a set's manifest.json, or None when absent/unreadable.
|
||||
|
||||
@@ -146,6 +191,11 @@ def _is_compatible(manifest, current):
|
||||
return setrevs.issubset(currevs)
|
||||
|
||||
|
||||
# Reserved entries under the backups root that are not backup sets: the run
|
||||
# history store and any dotfile sentinels/status files the watcher drops.
|
||||
_NON_SET_ENTRIES = ('history',)
|
||||
|
||||
|
||||
def _list_sets():
|
||||
"""Enumerate backup sets newest-first, each summarized for the list view."""
|
||||
root = _backups_root()
|
||||
@@ -154,6 +204,8 @@ def _list_sets():
|
||||
current = _current_schema_revisions()
|
||||
sets = []
|
||||
for name in sorted(os.listdir(root), reverse=True):
|
||||
if name in _NON_SET_ENTRIES or name.startswith('.'):
|
||||
continue
|
||||
setdir = os.path.join(root, name)
|
||||
if not os.path.isdir(setdir):
|
||||
continue
|
||||
@@ -235,6 +287,7 @@ def trigger_backup():
|
||||
return error_response(ErrorCodes.INTERNAL_ERROR,
|
||||
'Could not queue a backup: ' + str(error),
|
||||
http_code=500)
|
||||
_write_status('backup', 'queued', '', 'Backup queued')
|
||||
AuditLog.log('requested', 'Backup', entityname=stamp)
|
||||
return success_response(
|
||||
data={'isrunning': False, 'isqueued': True, 'requestedat': stamp},
|
||||
@@ -276,6 +329,8 @@ def restore_backup(snapshotid):
|
||||
return error_response(ErrorCodes.INTERNAL_ERROR,
|
||||
'Could not queue the restore: ' + str(error),
|
||||
http_code=500)
|
||||
_write_status('restore', 'queued', os.path.basename(snapshotid),
|
||||
'Restore queued')
|
||||
AuditLog.log('restore-requested', 'Backup',
|
||||
entityname=os.path.basename(snapshotid))
|
||||
return success_response(
|
||||
@@ -283,6 +338,35 @@ def restore_backup(snapshotid):
|
||||
message='Restore queued and validated against the live schema.')
|
||||
|
||||
|
||||
@shopdbbackups_bp.route('/status', methods=['GET'])
|
||||
@require_role('admin')
|
||||
def get_status():
|
||||
"""Return the live status of the most recent backup and restore runs.
|
||||
|
||||
The watcher writes these files as it moves through each phase; the UI polls
|
||||
this endpoint to drive the restore progress spinner and phase label. Either
|
||||
value is None when that kind of run has never been requested.
|
||||
"""
|
||||
return success_response(data={
|
||||
'backup': _read_status('backup'),
|
||||
'restore': _read_status('restore'),
|
||||
})
|
||||
|
||||
|
||||
@shopdbbackups_bp.route('/history', methods=['GET'])
|
||||
@require_role('admin')
|
||||
def get_history():
|
||||
"""Return the recorded history of backup and restore runs, newest first.
|
||||
|
||||
These are operational run logs written by the backup container onto the
|
||||
shared volume, not the audit trail (AuditLog records the requested intent).
|
||||
"""
|
||||
return success_response(data={
|
||||
'backups': _read_history('backup'),
|
||||
'restores': _read_history('restore'),
|
||||
})
|
||||
|
||||
|
||||
@shopdbbackups_bp.route('/settings', methods=['GET'])
|
||||
@require_role('admin')
|
||||
def get_backup_settings():
|
||||
|
||||
Reference in New Issue
Block a user