feat(backup): skip-if-unchanged + scheduled CronJob in the chart #32

Merged
arcodange merged 1 commits from claude/dolibarr-backup-cronjob into main 2026-06-30 15:53:58 +02:00
6 changed files with 202 additions and 67 deletions
Showing only changes of commit a3f0586c77 - Show all commits

87
chart/files/backup-job.sh Executable file
View File

@@ -0,0 +1,87 @@
#!/bin/sh
# In-container backup logic for Dolibarr — the single source of truth shared by the
# manual orchestrator (ops/backup/dolibarr-backup.sh) and the scheduled CronJob
# (chart/templates/backup-cronjob.yaml). Driven entirely by environment:
# BUCKET PREFIX DB PGHOST (config)
# PGUSER PGPASSWORD (DB creds, from vso-db-credentials)
# AWS_ACCESS_KEY_ID AWS_SECRET_ACCESS_KEY AWS_ENDPOINTS (S3 creds)
# Dumps the DB (pg_dump -Fc) + tars the documents mounted at /docs, pushes both to
# s3://$BUCKET/$PREFIX/{db,docs}/, then prunes to a tiered retention.
#
# Skip-if-unchanged: each half carries a content fingerprint at $PREFIX/.fp-{db,docs};
# a half is dumped+uploaded ONLY if its fingerprint differs from the last run, so a
# quiet ERP day re-uploads nothing. DB fingerprint = count + max(tms) over every
# tms-bearing table (catches insert/update/delete); docs = path|size|mtime per file.
set -eu
apk add --no-cache aws-cli tar gzip findutils >/dev/null 2>&1 || { echo "ABORT apk add"; exit 1; }
: "${BUCKET:?}"; : "${PREFIX:?}"; : "${DB:?}"; : "${PGHOST:?}"
export AWS_DEFAULT_REGION="${AWS_DEFAULT_REGION:-us-east-1}"
# GCS / S3-compatible stores reject aws-cli v2.23+ default integrity checksums
# ("SignatureDoesNotMatch / Invalid argument") — only sign/validate when required.
export AWS_REQUEST_CHECKSUM_CALCULATION=when_required
export AWS_RESPONSE_CHECKSUM_VALIDATION=when_required
S3() { aws --endpoint-url "$AWS_ENDPOINTS" s3 "$@"; }
PSQL() { PGPASSWORD="$PGPASSWORD" psql -h "$PGHOST" -U "$PGUSER" -d "$DB" -tAc "$1"; }
TS=$(date -u +%Y-%m-%dT%H-%M-%SZ)
echo "timestamp=$TS db=$DB -> s3://$BUCKET/$PREFIX"
# --- fingerprints: has either half changed since last time? ---
# Restrict to durable BUSINESS content — ignore volatile noise that changes every
# cron tick / page view (else a quiet ERP would never skip):
# DB: exclude llx_const, llx_user (login/counter churn), session/cron tables
# docs: exclude */temp/* (Dolibarr stats cache regenerated constantly)
# Excludes are identical for the fingerprint AND the upload, so "unchanged" means
# "the backed-up set is unchanged".
DENY="'llx_const','llx_user','llx_session','llx_cronjob','llx_user_param'"
GEN=$(PSQL "select coalesce(string_agg(format('select count(*) c, coalesce(max(tms)::text,''0'') m from %I', table_name), ' union all '), 'select 0 c, ''0'' m') from information_schema.columns where column_name='tms' and table_schema='public' and table_name not in ($DENY)")
FP_DB=$(PSQL "$GEN" | sort | md5sum | cut -d' ' -f1)
FP_DOCS=$(find /docs -type f -not -path '*/temp/*' -printf '%p|%s|%T@\n' 2>/dev/null | sort | md5sum | cut -d' ' -f1)
LAST_DB=$(S3 cp "s3://$BUCKET/$PREFIX/.fp-db" - 2>/dev/null || true)
LAST_DOCS=$(S3 cp "s3://$BUCKET/$PREFIX/.fp-docs" - 2>/dev/null || true)
uploaded=0
if [ "$FP_DB" != "$LAST_DB" ]; then
pg_dump -h "$PGHOST" -U "$PGUSER" -d "$DB" -Fc -f /tmp/db.dump
S3 cp /tmp/db.dump "s3://$BUCKET/$PREFIX/db/$TS.dump"
printf '%s' "$FP_DB" | S3 cp - "s3://$BUCKET/$PREFIX/.fp-db"
echo "db: backed up ($(wc -c < /tmp/db.dump) bytes)"; uploaded=1
else
echo "db: unchanged — skipped"
fi
if [ "$FP_DOCS" != "$LAST_DOCS" ]; then
tar -C /docs --exclude='*/temp/*' -czf /tmp/docs.tar.gz . 2>/dev/null
S3 cp /tmp/docs.tar.gz "s3://$BUCKET/$PREFIX/docs/$TS.tar.gz"
printf '%s' "$FP_DOCS" | S3 cp - "s3://$BUCKET/$PREFIX/.fp-docs"
echo "docs: backed up ($(wc -c < /tmp/docs.tar.gz) bytes)"; uploaded=1
else
echo "docs: unchanged — skipped"
fi
# --- tiered retention prune (daily 30d / monthly 12m / yearly ~10y); always runs ---
cat > /tmp/prune.py <<'PY'
import sys, datetime
keys=[k.strip() for k in open(sys.argv[1]) if k.strip()]
now=datetime.datetime.strptime(sys.argv[2][:10], "%Y-%m-%d").date()
def d(k):
try: return datetime.datetime.strptime(k[:10], "%Y-%m-%d").date()
except Exception: return None
dated=sorted([(d(k),k) for k in keys if d(k)], key=lambda x:x[0])
keep=set(); bymonth={}; byyear={}
for dt,k in dated:
age=(now-dt).days
if age <= 30: keep.add(k)
elif age <= 365: bymonth[(dt.year,dt.month)]=k
elif age <= 3660: byyear[dt.year]=k
keep |= set(bymonth.values()) | set(byyear.values())
for dt,k in dated:
if k not in keep: print(k)
PY
for SUB in db docs; do
S3 ls "s3://$BUCKET/$PREFIX/$SUB/" | awk '{print $4}' > /tmp/keys.$SUB || true
python3 /tmp/prune.py "/tmp/keys.$SUB" "$TS" > /tmp/del.$SUB || true
while read -r DK; do
[ -n "$DK" ] && S3 rm "s3://$BUCKET/$PREFIX/$SUB/$DK" && echo "pruned $SUB/$DK"
done < /tmp/del.$SUB
done
echo "DONE (uploaded=$uploaded)."

View File

@@ -0,0 +1,77 @@
{{- if .Values.backup.enabled }}
# Dedicated Dolibarr backup (ops/backup/README.md): DB + documents -> offsite GCS,
# tiered retention, skip-if-unchanged. Disabled by default — enable once the S3
# creds VaultStaticSecret below resolves (the `auth` Vault role must be allowed to
# read kvv2/{{ .Values.backup.vaultS3Path }}).
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "erp.fullname" . }}-backup-job
labels:
{{- include "erp.labels" . | nindent 4 }}
data:
backup-job.sh: |
{{- .Files.Get "files/backup-job.sh" | nindent 4 }}
---
apiVersion: secrets.hashicorp.com/v1beta1
kind: VaultStaticSecret
metadata:
name: {{ include "erp.fullname" . }}-backup-s3
namespace: {{ .Release.Namespace }}
spec:
type: kv-v2
mount: kvv2
# kvv2/<path> must hold AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY / AWS_ENDPOINTS
# (the GCS HMAC creds — same shape as longhorn-gcs-backup-credentials).
path: {{ .Values.backup.vaultS3Path }}
destination:
name: dolibarr-backup-s3
create: true
refreshAfter: 24h
vaultAuthRef: auth
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: {{ include "erp.fullname" . }}-backup
labels:
{{- include "erp.labels" . | nindent 4 }}
spec:
schedule: {{ .Values.backup.schedule | quote }}
concurrencyPolicy: Forbid
successfulJobsHistoryLimit: 3
failedJobsHistoryLimit: 3
jobTemplate:
spec:
backoffLimit: 1
template:
spec:
restartPolicy: Never
volumes:
- name: docs
persistentVolumeClaim:
claimName: {{ include "erp.fullname" . }}
readOnly: true
- name: job
configMap:
name: {{ include "erp.fullname" . }}-backup-job
containers:
- name: backup
image: {{ .Values.backup.image | quote }}
envFrom:
- secretRef:
name: dolibarr-backup-s3
env:
- { name: BUCKET, value: {{ .Values.backup.bucket | quote }} }
- { name: PREFIX, value: {{ printf "erp/%s" .Values.env | quote }} }
- { name: DB, value: {{ .Values.db.name | quote }} }
- { name: PGHOST, value: {{ .Values.backup.pgHost | quote }} }
- name: PGUSER
valueFrom: { secretKeyRef: { name: vso-db-credentials, key: username } }
- name: PGPASSWORD
valueFrom: { secretKeyRef: { name: vso-db-credentials, key: password } }
volumeMounts:
- { name: docs, mountPath: /docs, readOnly: true }
- { name: job, mountPath: /job }
command: ["/bin/sh", "/job/backup-job.sh"]
{{- end }}

View File

@@ -132,3 +132,15 @@ nodeSelector: {}
tolerations: []
affinity: {}
# Dedicated offsite backup of the Dolibarr DB + documents (see ops/backup/README.md).
# DISABLED by default — enable once the S3 creds VaultStaticSecret resolves (the
# `auth` Vault role must be granted read on kvv2/<vaultS3Path>). The manual
# orchestrator ops/backup/dolibarr-backup.sh works today without this.
backup:
enabled: false
schedule: "0 3 * * *" # daily 03:00 UTC
bucket: arcodange-backup
pgHost: "192.168.1.202" # direct Postgres host (matches ops/sandbox + ops/backup)
image: postgres:16-alpine
vaultS3Path: erp/backup # kvv2/<this> → AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY / AWS_ENDPOINTS

View File

@@ -25,6 +25,13 @@ This tool backs up **both halves** of Dolibarr state to the existing object stor
then prunes to a **tiered retention**: daily for 30 days, monthly for 12 months,
yearly for ~10 years.
**Skip-if-unchanged:** each half carries a content fingerprint at `erp/<env>/.fp-{db,docs}`
and is dumped+uploaded only if it **differs** from the last run — so a quiet ERP day
re-uploads nothing. The fingerprint is over **durable business content only**: the DB
side is `count + max(tms)` over every `tms` table *except* volatile ones (`llx_const`,
`llx_user`, sessions/cron), and the documents side excludes `*/temp/*` (Dolibarr's
constantly-regenerated stats cache) — from both the fingerprint *and* the tar.
## Safety (mirrors `ops/sandbox/sandbox-lifecycle.sh`)
- **prod is read-only**: `pg_dump` and `tar` only read; the only writes go to the
@@ -45,9 +52,9 @@ ops/backup/dolibarr-backup.sh backup --env sandbox
ops/backup/dolibarr-backup.sh list --env prod
```
`backup-job.sh` is the in-container logic (env-driven: `BUCKET PREFIX DB PGHOST` +
the mounted DB/S3 creds) — the single source of truth, also intended for the
scheduled CronJob (see "Automation" below).
`chart/files/backup-job.sh` is the in-container logic (env-driven: `BUCKET PREFIX
DB PGHOST` + the mounted DB/S3 creds) — the single source of truth shared by this
orchestrator and the scheduled CronJob (see "Automation" below).
**Status:** the first real prod backup was taken 2026-06-30
(`erp/prod/db/…` 1.2 MB, `erp/prod/docs/…` 12.5 MB). Proven end-to-end live on the
@@ -62,14 +69,22 @@ sandbox (dump + tar + GCS upload + retention prune).
The sandbox iso-prod refresh (`ops/sandbox/sandbox-lifecycle.sh`) is the natural
restore-drill bench. A `restore` subcommand is wired next.
## Automation (next step — gated on creds)
## Automation — the CronJob (gated on creds)
The recurring form is a k8s **CronJob** (ArgoCD-managed, in the chart) running the
same `backup-job.sh` daily. It needs its **own** S3 creds rather than borrowing the
Longhorn secret cross-namespace: a `VaultStaticSecret` in the erp namespace reading
the GCS backup creds, which requires the `erp` Vault role to be granted read on that
path (a `tools` change). Until that lands, run the orchestrator above on demand /
from a host cron — it works today by borrowing the Longhorn creds transiently.
The recurring form ships in the chart (`chart/templates/backup-cronjob.yaml`,
`backup.enabled=false` by default): a daily **CronJob** (ConfigMap-mounted
`backup-job.sh`) with its **own** S3 creds via a `VaultStaticSecret` — no
cross-namespace borrowing of the Longhorn secret. To activate:
1. store the GCS HMAC creds (`AWS_ACCESS_KEY_ID` / `AWS_SECRET_ACCESS_KEY` /
`AWS_ENDPOINTS`, same shape as `longhorn-gcs-backup-credentials`) at
`kvv2/<backup.vaultS3Path>` (default `erp/backup`);
2. grant the erp `auth` Vault role read on that path (a `tools` change) if its
policy doesn't already cover it;
3. set `backup.enabled: true` (+ tune `schedule`).
Until then, run the orchestrator above on demand / from a host cron — it works
today by borrowing the Longhorn creds transiently.
> The generic Longhorn gap (the orphaned `default` group) should be fixed too, as a
> platform concern — but this dedicated, offsite, 10-year-retention backup is the

View File

@@ -1,56 +0,0 @@
#!/bin/sh
# In-container backup logic for Dolibarr — the single source of truth shared by the
# manual orchestrator (ops/backup/dolibarr-backup.sh) and the scheduled CronJob
# (chart/templates/backup-cronjob.yaml). Driven entirely by environment:
# BUCKET PREFIX DB PGHOST (config)
# PGUSER PGPASSWORD (DB creds, from vso-db-credentials)
# AWS_ACCESS_KEY_ID AWS_SECRET_ACCESS_KEY AWS_ENDPOINTS (S3 creds)
# It dumps the DB (pg_dump -Fc) + tars the documents mounted at /docs, pushes both
# to s3://$BUCKET/$PREFIX/{db,docs}/, then prunes to a tiered retention.
set -eu
apk add --no-cache aws-cli tar gzip >/dev/null 2>&1 || { echo "ABORT apk add"; exit 1; }
: "${BUCKET:?}"; : "${PREFIX:?}"; : "${DB:?}"; : "${PGHOST:?}"
export AWS_DEFAULT_REGION="${AWS_DEFAULT_REGION:-us-east-1}"
# GCS / S3-compatible stores reject aws-cli v2.23+ default integrity checksums
# ("SignatureDoesNotMatch / Invalid argument") — only sign/validate when required.
export AWS_REQUEST_CHECKSUM_CALCULATION=when_required
export AWS_RESPONSE_CHECKSUM_VALIDATION=when_required
S3() { aws --endpoint-url "$AWS_ENDPOINTS" s3 "$@"; }
TS=$(date -u +%Y-%m-%dT%H-%M-%SZ)
echo "timestamp=$TS db=$DB -> s3://$BUCKET/$PREFIX"
pg_dump -h "$PGHOST" -U "$PGUSER" -d "$DB" -Fc -f /tmp/db.dump
echo "db.dump $(wc -c < /tmp/db.dump) bytes"
tar -C /docs -czf /tmp/docs.tar.gz . 2>/dev/null
echo "docs.tar.gz $(wc -c < /tmp/docs.tar.gz) bytes"
S3 cp /tmp/db.dump "s3://$BUCKET/$PREFIX/db/$TS.dump"
S3 cp /tmp/docs.tar.gz "s3://$BUCKET/$PREFIX/docs/$TS.tar.gz"
echo "uploaded to s3://$BUCKET/$PREFIX/{db,docs}/$TS.*"
# tiered retention: daily 30d / monthly 12m (latest per month) / yearly ~10y
cat > /tmp/prune.py <<'PY'
import sys, datetime
keys=[k.strip() for k in open(sys.argv[1]) if k.strip()]
now=datetime.datetime.strptime(sys.argv[2][:10], "%Y-%m-%d").date()
def d(k):
try: return datetime.datetime.strptime(k[:10], "%Y-%m-%d").date()
except Exception: return None
dated=sorted([(d(k),k) for k in keys if d(k)], key=lambda x:x[0])
keep=set(); bymonth={}; byyear={}
for dt,k in dated:
age=(now-dt).days
if age <= 30: keep.add(k)
elif age <= 365: bymonth[(dt.year,dt.month)]=k
elif age <= 3660: byyear[dt.year]=k
keep |= set(bymonth.values()) | set(byyear.values())
for dt,k in dated:
if k not in keep: print(k)
PY
for SUB in db docs; do
S3 ls "s3://$BUCKET/$PREFIX/$SUB/" | awk '{print $4}' > /tmp/keys.$SUB || true
python3 /tmp/prune.py "/tmp/keys.$SUB" "$TS" > /tmp/del.$SUB || true
while read -r DK; do
[ -n "$DK" ] && S3 rm "s3://$BUCKET/$PREFIX/$SUB/$DK" && echo "pruned $SUB/$DK"
done < /tmp/del.$SUB
done
echo "DONE."

View File

@@ -86,7 +86,7 @@ run_backup() {
log "Copying GCS creds into a transient secret in $NS (values stay base64)"
copy_s3_secret
log "Backup ${ENV}: DB=$DB PVC=$PVC -> s3://$BUCKET/$PREFIX/{db,docs}/"
local B64; B64="$(b64 "$(cat "${SCRIPT_DIR}/backup-job.sh")")"
local B64; B64="$(b64 "$(cat "${SCRIPT_DIR}/../../chart/files/backup-job.sh")")"
kubectl delete job dolibarr-backup -n "$NS" --ignore-not-found >/dev/null 2>&1 || true
kubectl apply -f - >/dev/null <<EOF
apiVersion: batch/v1