tidaldb/tidal-stress/k8s/stress-job-t2b.yaml

91 lines
3.2 KiB
YAML

# T2-B: leader-kill chaos under quorum write load.
# Sustained 1500 rps (solidly within SLO per T2-A) for 10 min.
# Kill the leader pod mid-run, promote a survivor, observe recovery.
#
# Apply: kubectl apply -f tidal-stress/k8s/stress-job-t2b.yaml
# Watch: kubectl logs -f job/tidal-stress-t2b -n tidaldb-cluster
# Rearm: kubectl delete job tidal-stress-t2b -n tidaldb-cluster
apiVersion: batch/v1
kind: Job
metadata:
name: tidal-stress-t2b
namespace: tidaldb-cluster
labels:
app.kubernetes.io/name: tidal-stress
app.kubernetes.io/part-of: tidaldb
spec:
backoffLimit: 0
ttlSecondsAfterFinished: 7200
template:
metadata:
labels:
app.kubernetes.io/name: tidal-stress
app.kubernetes.io/part-of: tidaldb
spec:
restartPolicy: Never
automountServiceAccountToken: false
affinity:
podAntiAffinity:
# Keep the generator off the initial leader's node (pod tidaldb-0).
# NOTE: this kill drill deposes that leader mid-run; the antiaffinity
# pins the generator off tidaldb-0's node only — after failover the new
# leader may share the generator's node (acceptable for a recovery drill).
requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector:
matchLabels:
statefulset.kubernetes.io/pod-name: tidaldb-0
topologyKey: kubernetes.io/hostname
securityContext:
runAsNonRoot: true
runAsUser: 1000
runAsGroup: 1000
seccompProfile:
type: RuntimeDefault
containers:
- name: stress
image: registry.threesix.ai/tidal/stress@sha256:3a75c311e53f8eb7caf6441bfb40bc9c0611ab739ee33909ca700c7d5c29db16 # :m11p3
imagePullPolicy: IfNotPresent
args:
- --target
- http://tidaldb-0.tidaldb-peers.tidaldb-cluster.svc.cluster.local:9500 # region tidaldb-0 (initial leader)
- --target
- http://tidaldb-1.tidaldb-peers.tidaldb-cluster.svc.cluster.local:9500 # region tidaldb-1
- --target
- http://tidaldb-2.tidaldb-peers.tidaldb-cluster.svc.cluster.local:9500 # region tidaldb-2
- --leader-url
- http://tidaldb-0.tidaldb-peers.tidaldb-cluster.svc.cluster.local:9500
- --ack
- quorum
- --ramp
- 1500:600 # 1500 rps sustained for 10 min
- --mix
- writes
- --write-path
- leader
- --corpus
- "20000"
- --users
- "100000"
- --skip-seed # corpus seeded during T2-A
- --poll-status
env:
- name: TIDAL_API_KEY
valueFrom:
secretKeyRef:
name: tidaldb-credentials
key: TIDAL_API_KEY
- name: TIDAL_STRESS_LOG
value: warn
resources:
requests:
cpu: 250m
memory: 256Mi
limits:
cpu: "3"
memory: 1Gi
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: ["ALL"]