# In-cluster capacity ramp for the tidalDB multi-process cluster (m11p5 k8s/cluster/).
#
# Runs the load generator AS A POD so requests take the real cluster network path
# (a `kubectl port-forward` serializes everything through the API server and adds
# tens of ms — useless for capacity numbers). Targets the three region pods by
# their per-pod headless-Service DNS (tidaldb-N.tidaldb-peers...); reads
# round-robin across them (each serves locally), leader-path writes are pinned to
# tidaldb-0 to measure the single-leader funnel. (Post-election the leader can
# move; for a long elasticity run let writes forward — every pod forwards to the
# current leader — or re-point --leader-url after a deliberate promote.)
#
# Apply:  kubectl apply -f tidal-stress/k8s/stress-job.yaml
# Watch:  kubectl logs -f job/tidal-stress -n tidaldb-cluster
# Re-run: kubectl delete job tidal-stress -n tidaldb-cluster; kubectl apply -f ...
#
# To compare the horizontally-scaled path, change `--write-path leader` to
# `--write-path sharded` (hash-partitions writes across all 3 regions, no funnel).
apiVersion: batch/v1
kind: Job
metadata:
  name: tidal-stress
  namespace: tidaldb-cluster
  labels:
    app.kubernetes.io/name: tidal-stress
    app.kubernetes.io/part-of: tidaldb
spec:
  backoffLimit: 0              # a load run is not retried — read the logs
  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 leader's node so it never steals CPU from
          # the write bottleneck we are measuring. The leader is pod tidaldb-0;
          # StatefulSet pods carry the auto label statefulset.kubernetes.io/pod-name.
          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@sha256:77395cc2857e2adabaa37607b198316d6f1cd0ec04f749caf2de959e6bade55b  # :v1
          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
            - --ramp
            - peach-100k
            - --stage-secs
            - "45"
            - --mix
            - peach
            - --write-path
            - leader
            - --corpus
            - "20000"
            - --users
            - "100000"
            - --poll-status
          env:
            - name: TIDAL_API_KEY
              valueFrom:
                secretKeyRef:
                  name: tidaldb-credentials
                  key: TIDAL_API_KEY
            - name: TIDAL_STRESS_LOG
              value: warn
          resources:
            # Small REQUEST (the cluster is request-saturated though ~15% utilised)
            # with a high LIMIT: the generator bursts to the cycles it needs on the
            # idle node. If it ever CPU-saturates, the report's schedule-lag /
            # client-shed will say so — then split the load across multiple Jobs.
            requests:
              cpu: 250m
              memory: 256Mi
            limits:
              cpu: "3"
              memory: 1Gi
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
            capabilities:
              drop: ["ALL"]