Home-Network/home-network-k3s-impl
2
0 Fork 0
Code Issues 2 Pull Requests 5 Actions Packages Projects Releases Wiki Activity

test(conformance): R-STATE-03 PROVEN on prod — DR restore from R2, off-cluster

Browse Source 
Phase 7's outstanding exit criterion. The only previous dr-restore proof was
recorded on the dev cluster (decommissioned 2026-09-12) against MinIO, so it
could not speak for prod or for today's Cloudflare R2 target.

Run 20260914T021505Z-24b8111, env=prod, kube v1.36.4+k3s1, chainsaw v0.2.12,
150.70s, 1 passed / 0 failed / 0 skipped. Sentinel
DR_RESTORED_FROM_OFF_CLUSTER_BACKUP_OK.

What makes it a real proof rather than a green check: the test seeds a canary
on the replicated longhorn class, backs the namespace AND volume data up to
the off-cluster store, then DESTROYS every in-cluster copy — namespace, PVC
and PV — before restoring into a clean, previously-nonexistent namespace. It
asserts the restored PVC binds a DIFFERENT PersistentVolume
(pvc-f0c061e1 != pvc-4107d59d) and fails explicitly if it rebinds the
original, because that would be an in-cluster survival masquerading as a
restore. The canary came back byte-identical.

It touches no real service's namespace, PVC or PV — the scratch namespaces are
named after its own Chainsaw namespace and are destroyed by design.

This is the run whose first attempt was discarded for recording env=dev; the
recorder fix is 24b8111, which this proof is recorded against.

Co-Authored-By: Claude Opus 5 <[email protected]>
This commit is contained in:
jakman85andClaude Opus 5 committed 2026-09-13 21:18:11 -05:00
1 parent 24b8111d0c
commit bd17b65db9
3 files changed
+677
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

conformance/runs/20260914T021505Z-24b8111/report.junit.xml
+4
View File
@@ -0,0 +1,4 @@
<testsuites name="chainsaw-report" tests="1" failures="0" errors="0" time="0.000000"><testsuite name="/work/conformance/tests/l3-fault-injection/dr-restore" tests="1" failures="0" errors="0" id="0" time="">
<testcase name="dr-restore" classname="" time="150.698290" />
</testsuite>
</testsuites>
conformance/runs/20260914T021505Z-24b8111/run.log
+672
View File
@@ -0,0 +1,672 @@
[run.sh] Coverage report first (always)
[coverage] 51/51 requirements have a scaffolded test (100.0%); 0 gap(s), 0 safety-critical gap(s).
[coverage] wrote /work/conformance/_artifacts/coverage/coverage.md and /work/conformance/_artifacts/coverage/coverage.json
[run.sh] No L0/L1 offline checks match the selection (layer=l3 reqs='R-STATE-03').
[run.sh] LIGHT pass: no tests selected.
[run.sh] HEAVY pass: 1 test(s) SERIAL (parallel=1) — dr-restore
Version: 0.2.12
Loading config (/work/conformance/config/chainsaw-config.yaml)...
- Using test file: chainsaw-test
- TestDirs [/work/conformance/tests/l3-fault-injection/dr-restore]
- SkipDelete false
- FailFast false
- ReportFormat 'JUNIT-TEST'
- ReportName 'chainsaw-report-heavy'
- ReportPath '/work/conformance/_artifacts'
- Namespace ''
- FullName false
- IncludeTestRegex ''
- ExcludeTestRegex ''
- ApplyTimeout 1m30s
- AssertTimeout 3m0s
- CleanupTimeout 2m0s
- DeleteTimeout 2m0s
- ErrorTimeout 1m0s
- ExecTimeout 3m0s
- DeletionPropagationPolicy Background
- Parallel 1
- Template true
- NoCluster false
- PauseOnFailure false
Loading tests...
- dr-restore (/work/conformance/tests/l3-fault-injection/dr-restore)
Loading values...
Running tests...
=== RUN chainsaw
=== PAUSE chainsaw
=== CONT chainsaw
=== RUN chainsaw/dr-restore
=== PAUSE chainsaw/dr-restore
=== CONT chainsaw/dr-restore
l.go:52: | 02:15:05 | dr-restore | @chainsaw  | CREATE | OK | v1/Namespace @ chainsaw-glorious-sheep
l.go:52: | 02:15:05 | dr-restore | assert-backup-target-is-off-cluster  | TRY | BEGIN |
l.go:52: | 02:15:05 | dr-restore | assert-backup-target-is-off-cluster  | CMD | RUN |
=== COMMAND
/usr/bin/sh -c set -eu
# ---- helpers -------------------------------------------------------
# Classify a kubectl failure: an RBAC denial is a HARNESS DEFECT and must
# fail loudly; an absent API is a genuine precondition gap and may skip.
die_or_skip() {
case "$2" in
*orbidden*|*Unauthorized*|*cannot\ list*|*cannot\ get*)
echo "FAIL: conformance runner lacks RBAC for $1 -- fix conformance/incluster/rbac.yaml" >&2
echo "$2" >&2
exit 1 ;;
*)
echo "SKIP: $1 not available on this cluster -- $2"
echo DR_RESTORE_SKIPPED_OK
exit 0 ;;
esac
}
ip2int() {
_q="$(echo "$1" | tr '.' ' ')"
set -- $_q
[ $# -eq 4 ] || { echo -1; return 0; }
echo $(( ($1 * 16777216) + ($2 * 65536) + ($3 * 256) + $4 ))
}
# in_cidr <ip> <a.b.c.d/len> -> 0 when the ip is inside the prefix
in_cidr() {
case "$2" in *"/"*) ;; *) return 1 ;; esac
_net="${2%/*}"; _len="${2#*/}"
case "$_len" in ''|*[!0-9]*) return 1 ;; esac
[ "$_len" -ge 0 ] && [ "$_len" -le 32 ] || return 1
_i="$(ip2int "$1")"; _n="$(ip2int "$_net")"
[ "$_i" -ge 0 ] && [ "$_n" -ge 0 ] || return 1
[ "$_len" -eq 0 ] && return 0
_d=1; _s=0
while [ "$_s" -lt $((32 - _len)) ]; do _d=$((_d * 2)); _s=$((_s + 1)); done
[ $(( _i / _d )) -eq $(( _n / _d )) ]
}
# ---- Gate 1: the replicated storage tier the DR-critical data lives on --
if ! kubectl get storageclass longhorn >/dev/null 2>&1; then
echo "SKIP: 'longhorn' StorageClass absent -- no DR-critical data tier on this cluster yet"
echo DR_RESTORE_SKIPPED_OK
exit 0
fi
# ---- Gate 2: the Velero API + a configured BackupStorageLocation --------
BSL_LINES="$(kubectl get backupstoragelocations.velero.io -A \
-o jsonpath='{range .items[*]}{.metadata.namespace}{" "}{.metadata.name}{" "}{.status.phase}{" "}{.spec.provider}{" "}{.spec.default}{" "}{.spec.config.s3Url}{" "}{.spec.objectStorage.bucket}{"\n"}{end}' \
2>&1)" || die_or_skip "velero.io/backupstoragelocations" "$BSL_LINES"
if [ -z "$(echo "$BSL_LINES" | tr -d '[:space:]')" ]; then
echo "SKIP: Velero API present but NO BackupStorageLocation is configured -- no off-cluster backup target yet"
echo DR_RESTORE_SKIPPED_OK
exit 0
fi
echo "backup storage locations:"
echo "$BSL_LINES"
VNS="$(echo "$BSL_LINES" | head -1 | cut -d' ' -f1)"
# ---- Gate 3: Velero server + node-agent (kopia FSB) actually ready -------
# File System Backup is the volume-DATA path (platform/velero/helmrelease.yaml:
# deployNodeAgent=true, uploaderType=kopia, snapshotsEnabled=false). Without a
# ready node-agent no volume data can be captured, so the drill is not runnable.
VREADY=0; NAREADY=0
for i in $(seq 1 12); do
VREADY="$(kubectl -n "$VNS" get deploy velero -o jsonpath='{.status.readyReplicas}' 2>/dev/null || true)"
NAREADY="$(kubectl -n "$VNS" get daemonset node-agent -o jsonpath='{.status.numberReady}' 2>/dev/null || true)"
echo "poll $i: velero readyReplicas=${VREADY:-0} node-agent numberReady=${NAREADY:-0}"
if [ "${VREADY:-0}" -ge 1 ] && [ "${NAREADY:-0}" -ge 1 ]; then break; fi
sleep 10
done
if [ "${VREADY:-0}" -lt 1 ] || [ "${NAREADY:-0}" -lt 1 ]; then
echo "SKIP: Velero server and/or its node-agent DaemonSet are not ready in ns '$VNS' -- backup/restore path not available"
echo DR_RESTORE_SKIPPED_OK
exit 0
fi
# ---- Pick the BSL this drill will use: prefer the default, and it MUST be
# Available. A CONFIGURED-BUT-UNAVAILABLE target is NOT a precondition
# gap -- it is a live R-STATE-03 defect, so it FAILS (after a bounded
# wait for first-validation on a cold start), it does not skip. --------
BSL_NS=""; BSL_NAME=""; BSL_URL=""; BSL_BUCKET=""
for i in $(seq 1 12); do
BSL_LINES="$(kubectl get backupstoragelocations.velero.io -A \
-o jsonpath='{range .items[*]}{.metadata.namespace}{" "}{.metadata.name}{" "}{.status.phase}{" "}{.spec.provider}{" "}{.spec.default}{" "}{.spec.config.s3Url}{" "}{.spec.objectStorage.bucket}{"\n"}{end}' 2>/dev/null || true)"
CAND="$(echo "$BSL_LINES" | grep ' Available ' | grep ' true ' | head -1 || true)"
[ -n "$CAND" ] || CAND="$(echo "$BSL_LINES" | grep ' Available ' | head -1 || true)"
if [ -n "$CAND" ]; then
BSL_NS="$(echo "$CAND" | cut -d' ' -f1)"
BSL_NAME="$(echo "$CAND" | cut -d' ' -f2)"
BSL_URL="$(echo "$CAND" | cut -d' ' -f6)"
BSL_BUCKET="$(echo "$CAND" | cut -d' ' -f7)"
break
fi
echo "poll $i: no Available BackupStorageLocation yet"
sleep 10
done
if [ -z "$BSL_NAME" ]; then
echo "FAIL: a BackupStorageLocation is configured but NONE reached phase 'Available'." >&2
echo " The off-cluster backup target is unreachable -- R-STATE-03 is BROKEN, not merely untested." >&2
echo "$BSL_LINES" >&2
exit 1
fi
echo "using BSL ${BSL_NS}/${BSL_NAME} bucket=${BSL_BUCKET} endpoint=${BSL_URL}"
# ---- OFF-CLUSTER PROOF (1): an endpoint we can evaluate ------------------
if [ -z "$BSL_URL" ]; then
echo "FAIL: BackupStorageLocation ${BSL_NS}/${BSL_NAME} exposes no spec.config.s3Url;" >&2
echo " the OFF-CLUSTER property of the backup target cannot be established, so this" >&2
echo " test refuses to claim it. (Extend this check for a non-S3 provider.)" >&2
exit 1
fi
HOST="${BSL_URL#*://}" # strip scheme
HOST="${HOST%%/*}" # strip path
HOST="${HOST%%:*}" # strip port
echo "backup endpoint host: $HOST"
case "$HOST" in
localhost|*.svc|*.svc.cluster.local|*.cluster.local)
echo "FAIL: backup endpoint '$HOST' is a CLUSTER-INTERNAL name -- the backup target is IN the cluster." >&2
echo " An in-cluster backup store cannot satisfy R-STATE-03 (off-cluster backup)." >&2
exit 1 ;;
esac
# Resolve to an IPv4 address. If it cannot be resolved we CANNOT establish the
# off-cluster property -- that is a failure, never a silent pass.
case "$HOST" in
*[!0-9.]*)
# Endpoint given as a name. Try the resolvers that may exist in the
# runner image, in order; if none is available or none resolves, the
# test FAILS below rather than guessing.
EPIP="$(getent ahostsv4 "$HOST" 2>/dev/null | head -1 | cut -d' ' -f1 || true)"
[ -n "$EPIP" ] || EPIP="$(getent hosts "$HOST" 2>/dev/null | head -1 | cut -d' ' -f1 || true)"
[ -n "$EPIP" ] || EPIP="$(nslookup "$HOST" 2>/dev/null | grep -A2 '^Name:' | grep '^Address' | head -1 | sed 's/.*: *//' || true)" ;;
*) EPIP="$HOST" ;;
esac
if [ -z "$EPIP" ]; then
echo "FAIL: could not resolve backup endpoint host '$HOST' to an IPv4 address;" >&2
echo " the OFF-CLUSTER property cannot be asserted, so this test does not pass." >&2
exit 1
fi
echo "backup endpoint resolves to: $EPIP"
# ---- OFF-CLUSTER PROOF (2): the endpoint is outside every cluster address --
case "$EPIP" in 127.*|0.0.0.0) echo "FAIL: backup endpoint $EPIP is loopback -- not off-cluster" >&2; exit 1 ;; esac
NODE_IPS="$(kubectl get nodes -o jsonpath='{range .items[*]}{range .status.addresses[*]}{.address}{"\n"}{end}{end}' 2>/dev/null || true)"
for a in $NODE_IPS; do
if [ "$a" = "$EPIP" ]; then
echo "FAIL: backup endpoint $EPIP is a NODE address of this cluster -- the backup is not off-cluster." >&2
exit 1
fi
done
echo "endpoint is not any node address (checked $(echo "$NODE_IPS" | grep -c . || true) node addresses)"
SVC_IPS="$(kubectl get svc -A -o jsonpath='{range .items[*]}{.spec.clusterIP}{"\n"}{end}' 2>/dev/null || true)"
for a in $SVC_IPS; do
if [ "$a" = "$EPIP" ]; then
echo "FAIL: backup endpoint $EPIP is a Service ClusterIP -- the backup target lives INSIDE the cluster." >&2
exit 1
fi
done
echo "endpoint is not any Service ClusterIP (checked $(echo "$SVC_IPS" | grep -c . || true))"
POD_IPS="$(kubectl get pods -A -o jsonpath='{range .items[*]}{.status.podIP}{"\n"}{end}' 2>/dev/null || true)"
for a in $POD_IPS; do
if [ "$a" = "$EPIP" ]; then
echo "FAIL: backup endpoint $EPIP is a POD IP -- the backup target is an in-cluster pod." >&2
exit 1
fi
done
echo "endpoint is not any Pod IP (checked $(echo "$POD_IPS" | grep -c . || true))"
POD_CIDRS="$(kubectl get nodes -o jsonpath='{range .items[*]}{.spec.podCIDR}{"\n"}{range .spec.podCIDRs[*]}{@}{"\n"}{end}{end}' 2>/dev/null || true)"
for c in $POD_CIDRS; do
case "$c" in *:*) continue ;; esac # IPv6 prefixes are out of scope here
if in_cidr "$EPIP" "$c"; then
echo "FAIL: backup endpoint $EPIP falls inside node podCIDR $c -- it is in the cluster pod network." >&2
exit 1
fi
done
echo "endpoint is outside every node podCIDR (checked: $(echo "$POD_CIDRS" | tr '\n' ' '))"
# Best-effort (needs networking.k8s.io/ServiceCIDR, which the least-privilege
# runner may not read): the checks above are the authoritative ones.
SVC_CIDRS="$(kubectl get servicecidrs.networking.k8s.io -o jsonpath='{range .items[*]}{range .spec.cidrs[*]}{@}{"\n"}{end}{end}' 2>/dev/null || true)"
if [ -n "$SVC_CIDRS" ]; then
for c in $SVC_CIDRS; do
case "$c" in *:*) continue ;; esac
if in_cidr "$EPIP" "$c"; then
echo "FAIL: backup endpoint $EPIP falls inside the Service CIDR $c -- it is in the cluster." >&2
exit 1
fi
done
echo "endpoint is outside every ServiceCIDR ($(echo "$SVC_CIDRS" | tr '\n' ' '))"
else
echo "(ServiceCIDR objects unreadable -- skipping that best-effort check; ClusterIP/PodIP/podCIDR checks stand)"
fi
echo "OFF_CLUSTER_TARGET_OK bsl=${BSL_NS}/${BSL_NAME} endpoint=${EPIP} bucket=${BSL_BUCKET}"
l.go:52: | 02:15:08 | dr-restore | assert-backup-target-is-off-cluster  | SCRIPT | LOG |
=== STDOUT
backup storage locations:
velero default Available aws true https://7ce452a1b3d6c86daf2c020edcb82d37.r2.cloudflarestorage.com k3s-prod-backup
poll 1: velero readyReplicas=1 node-agent numberReady=3
using BSL velero/default bucket=k3s-prod-backup endpoint=https://7ce452a1b3d6c86daf2c020edcb82d37.r2.cloudflarestorage.com
backup endpoint host: 7ce452a1b3d6c86daf2c020edcb82d37.r2.cloudflarestorage.com
backup endpoint resolves to: 172.64.66.1
endpoint is not any node address (checked 6 node addresses)
endpoint is not any Service ClusterIP (checked 82)
endpoint is not any Pod IP (checked 197)
endpoint is outside every node podCIDR (checked: 10.42.0.0/24 10.42.0.0/24 10.42.1.0/24 10.42.1.0/24 10.42.2.0/24 10.42.2.0/24 )
endpoint is outside every ServiceCIDR (10.43.0.0/16 )
OFF_CLUSTER_TARGET_OK bsl=velero/default endpoint=172.64.66.1 bucket=k3s-prod-backup
l.go:52: | 02:15:08 | dr-restore | assert-backup-target-is-off-cluster  | SCRIPT | DONE |
l.go:52: | 02:15:08 | dr-restore | assert-backup-target-is-off-cluster  | TRY | END |
l.go:52: | 02:15:08 | dr-restore | assert-backups-are-scheduled  | TRY | BEGIN |
l.go:52: | 02:15:08 | dr-restore | assert-backups-are-scheduled  | CMD | RUN |
=== COMMAND
/usr/bin/sh -c set -eu
SCHED="$(kubectl get schedules.velero.io -A \
-o jsonpath='{range .items[*]}{.metadata.namespace}{"/"}{.metadata.name}{" phase="}{.status.phase}{" cron="}{.spec.schedule}{" lastBackup="}{.status.lastBackup}{"\n"}{end}' 2>/dev/null || true)"
if [ -z "$(echo "$SCHED" | tr -d '[:space:]')" ]; then
# Distinguish "Velero absent" (skip, in lock-step with step 1) from
# "Velero present but nothing scheduled" (a real R-STATE-03 defect).
if kubectl get backupstoragelocations.velero.io -A >/dev/null 2>&1; then
if [ -z "$(kubectl get backupstoragelocations.velero.io -A -o name 2>/dev/null || true)" ]; then
echo "SKIP: no BackupStorageLocation configured -- scheduling not applicable yet"
echo DR_SCHEDULE_SKIPPED_OK
exit 0
fi
echo "FAIL: Velero is configured with a backup target but declares NO Schedule --" >&2
echo " R-STATE-03 requires SCHEDULED off-cluster backups, not manual ones." >&2
exit 1
fi
echo "SKIP: Velero API absent -- backup scheduling not applicable on this cluster yet"
echo DR_SCHEDULE_SKIPPED_OK
exit 0
fi
echo "velero schedules:"
echo "$SCHED"
# A Schedule that exists but is paused/disabled backs nothing up.
if echo "$SCHED" | grep -q 'phase=Enabled'; then
echo BACKUPS_ARE_SCHEDULED_OK
else
echo "FAIL: no Velero Schedule is in phase 'Enabled' -- scheduled off-cluster backups are not running." >&2
exit 1
fi
l.go:52: | 02:15:08 | dr-restore | assert-backups-are-scheduled  | SCRIPT | LOG |
=== STDOUT
velero schedules:
velero/velero-daily phase=Enabled cron=0 3 * * * lastBackup=2026-09-13T04:01:06Z
velero/velero-daily-resources-only phase=Enabled cron=0 3 * * * lastBackup=2026-09-13T03:00:03Z
BACKUPS_ARE_SCHEDULED_OK
l.go:52: | 02:15:08 | dr-restore | assert-backups-are-scheduled  | SCRIPT | DONE |
l.go:52: | 02:15:08 | dr-restore | assert-backups-are-scheduled  | TRY | END |
l.go:52: | 02:15:08 | dr-restore | data-restores-from-the-off-cluster-backup | TRY | BEGIN |
l.go:52: | 02:15:08 | dr-restore | data-restores-from-the-off-cluster-backup | CMD | RUN |
=== COMMAND
/usr/bin/sh -c set -eu
NS="$NAMESPACE"
SRC="${NS}-dr-src" # scratch source namespace (destroyed by design)
DST="${NS}-dr-dst" # clean restore target (must not pre-exist)
BK="${NS}-dr-backup"
RS="${NS}-dr-restore"
OWNER_LABEL="conformance.home.k3s/created-by=${NS}"
# ---- Re-derive the preconditions (steps do not share shell state). Every
# skip below mirrors step 1 exactly, so the whole test skips or runs
# as a unit -- it can never half-run. -----------------------------
if ! kubectl get storageclass longhorn >/dev/null 2>&1; then
echo "SKIP: 'longhorn' StorageClass absent"; echo DR_RESTORE_SKIPPED_OK; exit 0
fi
BSL_LINES="$(kubectl get backupstoragelocations.velero.io -A \
-o jsonpath='{range .items[*]}{.metadata.namespace}{" "}{.metadata.name}{" "}{.status.phase}{" "}{.spec.default}{"\n"}{end}' 2>/dev/null || true)"
CAND="$(echo "$BSL_LINES" | grep ' Available ' | grep ' true$' | head -1 || true)"
[ -n "$CAND" ] || CAND="$(echo "$BSL_LINES" | grep ' Available ' | head -1 || true)"
if [ -z "$CAND" ]; then
echo "SKIP: no Available BackupStorageLocation (see the off-cluster step for the authoritative verdict)"
echo DR_RESTORE_SKIPPED_OK; exit 0
fi
VNS="$(echo "$CAND" | cut -d' ' -f1)"
BSL_NAME="$(echo "$CAND" | cut -d' ' -f2)"
if [ "$(kubectl -n "$VNS" get daemonset node-agent -o jsonpath='{.status.numberReady}' 2>/dev/null || echo 0)" -lt 1 ]; then
echo "SKIP: Velero node-agent (kopia FSB) not ready -- volume data cannot be backed up"
echo DR_RESTORE_SKIPPED_OK; exit 0
fi
echo "velero ns=$VNS bsl=$BSL_NAME src=$SRC dst=$DST"
# A clean restore target means PREVIOUSLY NONEXISTENT, and the source name must
# be free. If either is lying around from an aborted run, remove it before we
# claim "clean" -- and fail loudly if it will not go, because a half-deleted
# namespace would silently invalidate the destroy proof below.
kubectl delete namespace "$DST" "$SRC" --ignore-not-found --wait=true --timeout=300s
# ============================ GIVEN ==============================
# A DR-critical stateful workload with known data on the replicated tier.
CANARY="dr-canary-$(date +%s%N)"
kubectl create namespace "$SRC"
kubectl label namespace "$SRC" "$OWNER_LABEL" --overwrite
kubectl -n "$SRC" apply -f - <<EOF
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: dr-data
labels:
conformance.home.k3s/created-by: ${NS}
spec:
accessModes: [ReadWriteOnce]
storageClassName: longhorn
resources:
requests:
storage: 1Gi
EOF
kubectl -n "$SRC" apply -f - <<EOF
apiVersion: v1
kind: Pod
metadata:
name: dr-workload
labels:
app: dr-workload
conformance.home.k3s/created-by: ${NS}
spec:
restartPolicy: Never
containers:
- name: app
image: busybox:1.36.1
command: ["sh", "-c", "sleep 7200"]
volumeMounts:
- name: data
mountPath: /data
volumes:
- name: data
persistentVolumeClaim:
claimName: dr-data
EOF
kubectl -n "$SRC" wait --for=condition=Ready pod/dr-workload --timeout=300s
printf '%s' "$CANARY" | kubectl -n "$SRC" exec -i dr-workload -- sh -c 'cat > /data/canary && sync'
echo "seeded canary: $(kubectl -n "$SRC" exec dr-workload -- cat /data/canary)"
ORIG_PV="$(kubectl -n "$SRC" get pvc dr-data -o jsonpath='{.spec.volumeName}')"
[ -n "$ORIG_PV" ] || { echo "FAIL: source PVC never bound to a PV" >&2; exit 1; }
echo "original in-cluster PersistentVolume: $ORIG_PV"
# ======================= WHEN (part 1): back up off-cluster =======
# Created as a Velero Backup CR -- exactly what `velero backup create` does.
# defaultVolumesToFsBackup:true selects the kopia File System Backup path, so
# the VOLUME DATA (not just the resource JSON) is uploaded to the object store.
# ttl is short: if the finally-step DeleteBackupRequest is ever lost, Velero's
# own GC still removes this drill's objects from the bucket.
kubectl apply -f - <<EOF
apiVersion: velero.io/v1
kind: Backup
metadata:
name: ${BK}
namespace: ${VNS}
labels:
conformance.home.k3s/created-by: ${NS}
spec:
includedNamespaces: [${SRC}]
storageLocation: ${BSL_NAME}
snapshotVolumes: false
defaultVolumesToFsBackup: true
ttl: 2h0m0s
EOF
BPHASE=""
for i in $(seq 1 90); do
BPHASE="$(kubectl -n "$VNS" get backups.velero.io "$BK" -o jsonpath='{.status.phase}' 2>/dev/null || true)"
echo "poll $i: backup phase=${BPHASE:-<pending>}"
case "${BPHASE:-}" in
Completed|Failed|PartiallyFailed|FailedValidation) break ;;
esac
sleep 10
done
if [ "${BPHASE:-}" != "Completed" ]; then
echo "FAIL: off-cluster backup did not complete (phase=${BPHASE:-<timeout>})" >&2
kubectl -n "$VNS" get backups.velero.io "$BK" -o yaml >&2 || true
exit 1
fi
echo "backup $BK Completed to ${BSL_NAME}"
# ---- OFF-CLUSTER PROOF (3): the VOLUME DATA really landed in the remote
# kopia repository -- a PodVolumeBackup Completed with a snapshot ID.
PVB="$(kubectl -n "$VNS" get podvolumebackups.velero.io \
-l velero.io/backup-name="$BK" \
-o jsonpath='{range .items[*]}{.metadata.name}{" "}{.status.phase}{" "}{.status.snapshotID}{"\n"}{end}' 2>/dev/null || true)"
echo "pod volume backups:"
echo "$PVB"
if [ -z "$(echo "$PVB" | tr -d '[:space:]')" ]; then
echo "FAIL: the backup captured NO pod volume data (no PodVolumeBackup)." >&2
echo " Resource-only backups cannot restore DR-critical DATA." >&2
exit 1
fi
# A line is "<name> <phase> <snapshotID>"; require Completed AND a
# non-empty snapshot ID (an empty ID means nothing reached the repository).
GOOD_PVB="$(echo "$PVB" | grep -cE ' Completed [^[:space:]]+$' || true)"
if [ "${GOOD_PVB:-0}" -lt 1 ]; then
echo "FAIL: no PodVolumeBackup reached phase Completed with a snapshot ID --" >&2
echo " the volume data did not reach the off-cluster repository." >&2
exit 1
fi
echo "volume data uploaded off-cluster (PodVolumeBackup Completed with a kopia snapshotID)"
# ============ WHEN (part 2): FAULT INJECTION -- annihilate the source ====
# Destroy EVERY in-cluster copy: the pod, the PVC, the namespace, and the
# underlying PersistentVolume (and with it the Longhorn replicas). After this
# there is no in-cluster source the restore could quietly read from.
kubectl delete namespace "$SRC" --wait=true --timeout=420s
for i in $(seq 1 30); do
if ! kubectl get namespace "$SRC" >/dev/null 2>&1; then break; fi
echo "poll $i: waiting for namespace $SRC to disappear"
sleep 10
done
if kubectl get namespace "$SRC" >/dev/null 2>&1; then
echo "FAIL: source namespace $SRC did not terminate; the destroy step is not convincing" >&2
exit 1
fi
echo "source namespace destroyed"
# The longhorn StorageClass reclaims Delete, so the PV should already be gone;
# force it if a Retain policy (or a stuck finalizer) left it behind, because a
# surviving PV would make the restore prove nothing about off-cluster recovery.
kubectl delete pv "$ORIG_PV" --ignore-not-found --wait=false || true
for i in $(seq 1 30); do
if ! kubectl get pv "$ORIG_PV" >/dev/null 2>&1; then break; fi
echo "poll $i: waiting for PersistentVolume $ORIG_PV to disappear"
sleep 10
done
if kubectl get pv "$ORIG_PV" >/dev/null 2>&1; then
echo "FAIL: the original PersistentVolume $ORIG_PV SURVIVED the destroy step." >&2
echo " An in-cluster copy of the data still exists, so a successful restore" >&2
echo " would NOT prove recovery from the off-cluster backup. Refusing to pass." >&2
exit 1
fi
echo "original PersistentVolume $ORIG_PV is GONE -- no in-cluster copy of the data remains"
# Best-effort corroboration (the least-privilege runner may not read longhorn.io):
# the Longhorn Volume CR and its replicas should be gone too.
if kubectl -n longhorn-system get volumes.longhorn.io "$ORIG_PV" >/dev/null 2>&1; then
echo "FAIL: Longhorn Volume $ORIG_PV still exists after PV deletion -- replicas survive in-cluster" >&2
exit 1
fi
echo "(longhorn Volume CR $ORIG_PV not present -- either deleted or not readable by this identity)"
# ============================ RESTORE ============================
# Into a CLEAN, previously-nonexistent namespace (Velero creates it), which is
# the catalog's "restored into a clean state".
kubectl apply -f - <<EOF
apiVersion: velero.io/v1
kind: Restore
metadata:
name: ${RS}
namespace: ${VNS}
labels:
conformance.home.k3s/created-by: ${NS}
spec:
backupName: ${BK}
includedNamespaces: [${SRC}]
namespaceMapping:
${SRC}: ${DST}
existingResourcePolicy: none
EOF
RPHASE=""
for i in $(seq 1 90); do
RPHASE="$(kubectl -n "$VNS" get restores.velero.io "$RS" -o jsonpath='{.status.phase}' 2>/dev/null || true)"
echo "poll $i: restore phase=${RPHASE:-<pending>}"
case "${RPHASE:-}" in
Completed|Failed|PartiallyFailed|FailedValidation) break ;;
esac
sleep 10
done
if [ "${RPHASE:-}" != "Completed" ]; then
echo "FAIL: restore did not complete (phase=${RPHASE:-<timeout>})" >&2
kubectl -n "$VNS" get restores.velero.io "$RS" -o yaml >&2 || true
kubectl -n "$VNS" get podvolumerestores.velero.io -l velero.io/restore-name="$RS" -o wide >&2 || true
exit 1
fi
echo "restore $RS Completed into $DST"
# ============================= THEN ==============================
# The service returns WITH ITS DATA. With kopia FSB the restored pod carries a
# `restore-wait` init container that blocks until the node-agent has written the
# volume contents back, so Ready here already implies the data landed.
if ! kubectl -n "$DST" wait --for=condition=Ready pod/dr-workload --timeout=600s; then
echo "FAIL: restored workload never became Ready in the clean namespace $DST" >&2
kubectl -n "$DST" describe pod dr-workload >&2 || true
kubectl -n "$VNS" get podvolumerestores.velero.io -l velero.io/restore-name="$RS" -o wide >&2 || true
exit 1
fi
NEW_PV="$(kubectl -n "$DST" get pvc dr-data -o jsonpath='{.spec.volumeName}' 2>/dev/null || true)"
echo "restored PVC bound to PersistentVolume: ${NEW_PV:-<none>}"
[ -n "$NEW_PV" ] || { echo "FAIL: restored PVC did not bind a PV" >&2; exit 1; }
if [ "$NEW_PV" = "$ORIG_PV" ]; then
echo "FAIL: the restored PVC rebound the ORIGINAL PersistentVolume ($ORIG_PV)." >&2
echo " That is an in-cluster survival, not an off-cluster restore." >&2
exit 1
fi
echo "restored onto a NEW volume ($NEW_PV != $ORIG_PV) -- the data came from outside the cluster"
GOT="$(kubectl -n "$DST" exec dr-workload -- cat /data/canary)"
echo "recovered='$GOT' expected='$CANARY'"
if [ "$GOT" != "$CANARY" ]; then
echo "FAIL: restored data does not match what was backed up -- DR restore lost/corrupted data" >&2
exit 1
fi
echo DR_RESTORED_FROM_OFF_CLUSTER_BACKUP_OK
l.go:52: | 02:17:18 | dr-restore | data-restores-from-the-off-cluster-backup | SCRIPT | LOG |
=== STDOUT
velero ns=velero bsl=default src=chainsaw-glorious-sheep-dr-src dst=chainsaw-glorious-sheep-dr-dst
namespace/chainsaw-glorious-sheep-dr-src created
namespace/chainsaw-glorious-sheep-dr-src labeled
persistentvolumeclaim/dr-data created
pod/dr-workload created
pod/dr-workload condition met
seeded canary: dr-canary-1789352108935754215
original in-cluster PersistentVolume: pvc-4107d59d-a34f-4cba-bd2a-c5b2446156d9
backup.velero.io/chainsaw-glorious-sheep-dr-backup created
poll 1: backup phase=InProgress
poll 2: backup phase=InProgress
poll 3: backup phase=InProgress
poll 4: backup phase=Completed
backup chainsaw-glorious-sheep-dr-backup Completed to default
pod volume backups:
chainsaw-glorious-sheep-dr-backup-2gjrq Completed 979eed437233b45c7f85ba80074ab56b
volume data uploaded off-cluster (PodVolumeBackup Completed with a kopia snapshotID)
namespace "chainsaw-glorious-sheep-dr-src" deleted
source namespace destroyed
original PersistentVolume pvc-4107d59d-a34f-4cba-bd2a-c5b2446156d9 is GONE -- no in-cluster copy of the data remains
(longhorn Volume CR pvc-4107d59d-a34f-4cba-bd2a-c5b2446156d9 not present -- either deleted or not readable by this identity)
restore.velero.io/chainsaw-glorious-sheep-dr-restore created
poll 1: restore phase=InProgress
poll 2: restore phase=InProgress
poll 3: restore phase=InProgress
poll 4: restore phase=Completed
restore chainsaw-glorious-sheep-dr-restore Completed into chainsaw-glorious-sheep-dr-dst
pod/dr-workload condition met
restored PVC bound to PersistentVolume: pvc-f0c061e1-c080-49f2-a381-23da5c886df2
restored onto a NEW volume (pvc-f0c061e1-c080-49f2-a381-23da5c886df2 != pvc-4107d59d-a34f-4cba-bd2a-c5b2446156d9) -- the data came from outside the cluster
recovered='dr-canary-1789352108935754215' expected='dr-canary-1789352108935754215'
DR_RESTORED_FROM_OFF_CLUSTER_BACKUP_OK
=== STDERR
Defaulted container "app" out of: app, restore-wait (init)
l.go:52: | 02:17:18 | dr-restore | data-restores-from-the-off-cluster-backup | SCRIPT | DONE |
l.go:52: | 02:17:18 | dr-restore | data-restores-from-the-off-cluster-backup | TRY | END |
l.go:52: | 02:17:18 | dr-restore | data-restores-from-the-off-cluster-backup | FINALLY | BEGIN |
l.go:52: | 02:17:18 | dr-restore | data-restores-from-the-off-cluster-backup | CMD | RUN |
=== COMMAND
/usr/bin/sh -c set -u
NS="$NAMESPACE"
SRC="${NS}-dr-src"; DST="${NS}-dr-dst"; BK="${NS}-dr-backup"; RS="${NS}-dr-restore"
VNS="$(kubectl get backupstoragelocations.velero.io -A -o jsonpath='{.items[0].metadata.namespace}' 2>/dev/null || true)"
# Velero objects first: a DeleteBackupRequest makes Velero remove the backup
# DATA from the off-cluster bucket, not just the CR (self-cleaning contract).
if [ -n "$VNS" ]; then
kubectl -n "$VNS" delete restores.velero.io "$RS" --ignore-not-found --wait=false || true
if kubectl -n "$VNS" get backups.velero.io "$BK" >/dev/null 2>&1; then
kubectl apply -f - <<EOF || true
apiVersion: velero.io/v1
kind: DeleteBackupRequest
metadata:
name: ${BK}-delete
namespace: ${VNS}
labels:
conformance.home.k3s/created-by: ${NS}
spec:
backupName: ${BK}
EOF
for i in $(seq 1 18); do
kubectl -n "$VNS" get backups.velero.io "$BK" >/dev/null 2>&1 || break
sleep 10
done
# Backstop if Velero could not process the request (the 2h ttl also GCs it).
kubectl -n "$VNS" delete backups.velero.io "$BK" --ignore-not-found --wait=false || true
kubectl -n "$VNS" delete deletebackuprequests.velero.io "${BK}-delete" --ignore-not-found --wait=false || true
fi
echo "velero objects for $NS cleaned up (ns $VNS)"
fi
# Scratch namespaces (both, in case the run aborted at any point).
for n in "$DST" "$SRC"; do
kubectl delete namespace "$n" --ignore-not-found --wait=false || true
done
# Anything left labelled as ours (defensive; the two names above are the only
# namespaces this test ever creates).
kubectl delete namespace -l "conformance.home.k3s/created-by=${NS}" --ignore-not-found --wait=false || true
# Released PVs from either namespace's PVCs would otherwise leak storage.
for pv in $(kubectl get pv -o jsonpath='{range .items[*]}{.metadata.name}{" "}{.spec.claimRef.namespace}{"\n"}{end}' 2>/dev/null | grep -E " (${SRC}|${DST})$" | cut -d' ' -f1 || true); do
kubectl delete pv "$pv" --ignore-not-found --wait=false || true
echo "released leftover PersistentVolume: $pv"
done
echo "dr-restore teardown complete (best-effort; every object was created by this test)"
l.go:52: | 02:17:30 | dr-restore | data-restores-from-the-off-cluster-backup | SCRIPT | LOG |
=== STDOUT
restore.velero.io "chainsaw-glorious-sheep-dr-restore" deleted from velero namespace
deletebackuprequest.velero.io/chainsaw-glorious-sheep-dr-backup-delete created
velero objects for chainsaw-glorious-sheep cleaned up (ns velero)
namespace "chainsaw-glorious-sheep-dr-dst" deleted
namespace "chainsaw-glorious-sheep-dr-dst" deleted
persistentvolume "pvc-f0c061e1-c080-49f2-a381-23da5c886df2" deleted
released leftover PersistentVolume: pvc-f0c061e1-c080-49f2-a381-23da5c886df2
dr-restore teardown complete (best-effort; every object was created by this test)
l.go:52: | 02:17:30 | dr-restore | data-restores-from-the-off-cluster-backup | SCRIPT | DONE |
l.go:52: | 02:17:30 | dr-restore | data-restores-from-the-off-cluster-backup | FINALLY | END |
l.go:52: | 02:17:30 | dr-restore | @chainsaw  | CLEANUP | BEGIN |
l.go:52: | 02:17:30 | dr-restore | @chainsaw  | DELETE | OK | v1/Namespace @ chainsaw-glorious-sheep
l.go:52: | 02:17:36 | dr-restore | @chainsaw  | CLEANUP | END |
--- PASS: chainsaw (0.00s)
--- PASS: chainsaw/dr-restore (150.70s)
PASS
Tests Summary...
- Passed tests 1
- Failed tests 0
- Skipped tests 0
Done.
merge_junit: merged 1 report(s) -> /work/conformance/_artifacts/report.junit.xml (tests=1 failures=0 errors=0 skipped=0)
[run.sh] Done. JUnit: /work/conformance/_artifacts/report.junit.xml | Coverage: /work/conformance/_artifacts/coverage/coverage.md
conformance/runs/ledger.jsonl
+1
View File
@@ -3,3 +3,4 @@
{"chainsaw_version": "v0.2.12", "env": "prod", "git_sha": "19fc8bcb27eab42a0007b28a831519d3e325c7b6", "junit_result": "passed", "kube_version": "v1.36.4+k3s1", "layer": "L1", "note": "L1 offline check exited 0; run_l1_offline.py renders its skips as JUnit <skipped/>, so a green JUnit is truthful without a sentinel", "proof": "proven", "requirements": ["R-NET-05", "R-NET-06", "R-NET-07"], "run_id": "20260913T014321Z-19fc8bc", "sentinel": null, "test": "egress-class-render", "ts_utc": "2026-09-13T01:43:21Z"}
{"chainsaw_version": "v0.2.12", "env": "prod", "git_sha": "19fc8bcb27eab42a0007b28a831519d3e325c7b6-dirty", "junit_result": "passed", "kube_version": "v1.36.4+k3s1", "layer": "L3", "note": "run log OUTPUT carries every declared pass token (NS_PRIVILEGED_OK, TUNNEL_HEALTHY_OK, NO_LEAK_OK, INTERNET_UNAFFECTED_OK, TUNNEL_SELF_HEAL_OK, TUNNEL_RECOVERED_OK) and no skip token [log scoped to this testcase; tokens read from real-output sections only]", "proof": "proven", "requirements": ["R-NET-06"], "run_id": "20260913T014437Z-19fc8bc", "sentinel": "TUNNEL_RECOVERED_OK", "test": "vpn-killswitch", "ts_utc": "2026-09-13T01:44:37Z"}
{"chainsaw_version": "v0.2.12", "env": "prod", "git_sha": "9d0814ae61e6a0ba64d3789a71f1cd9c985efbf0", "junit_result": "passed", "kube_version": "v1.36.4+k3s1", "layer": "L3", "note": "run log OUTPUT carries every declared pass token (NS_PRIVILEGED_OK, TUNNEL_HEALTHY_OK, NO_LEAK_OK, INTERNET_UNAFFECTED_OK, TUNNEL_SELF_HEAL_OK, TUNNEL_RECOVERED_OK) and no skip token [log scoped to this testcase; tokens read from real-output sections only]", "proof": "proven", "requirements": ["R-NET-06"], "run_id": "20260913T014923Z-9d0814a", "sentinel": "TUNNEL_RECOVERED_OK", "test": "vpn-killswitch", "ts_utc": "2026-09-13T01:49:23Z"}
{"chainsaw_version": "v0.2.12", "env": "prod", "git_sha": "24b8111d0c39e9417e9f4d782f333f683540cfa7", "junit_result": "passed", "kube_version": "v1.36.4+k3s1", "layer": "L3", "note": "run log OUTPUT carries every declared pass token (OFF_CLUSTER_TARGET_OK, BACKUPS_ARE_SCHEDULED_OK, DR_RESTORED_FROM_OFF_CLUSTER_BACKUP_OK) and no skip token [log scoped to this testcase; tokens read from real-output sections only]", "proof": "proven", "requirements": ["R-STATE-03"], "run_id": "20260914T021505Z-24b8111", "sentinel": "DR_RESTORED_FROM_OFF_CLUSTER_BACKUP_OK", "test": "dr-restore", "ts_utc": "2026-09-14T02:15:05Z"}