run dpl in k8s from ECS

control-operator/api/v1alpha1/environment_types.go

@@ -81,6 +81,7 @@ type EnvironmentStatus struct {
 type TaskReference struct {
 	Name           string            `json:"name"`
 	TaskID         string            `json:"taskID,omitempty"`
+	NameSuffix     string            `json:"nameSuffix,omitempty"`
 	Env            []v1.EnvVar       `json:"env"`
 	ArgsCLI        []string          `json:"argsCLI"`
 	ArgsTransition map[string]string `json:"argsTransition,omitempty"`

control-operator/config/crd/bases/aliecs.alice.cern_environments.yaml

@@ -4100,6 +4100,8 @@ spec:
                         type: array
                       name:
                         type: string
+                      nameSuffix:
+                        type: string
                       taskID:
                         type: string
                     required:

control-operator/ecs-manifests/control-workflows/stfbuilder-kube-direct.yaml

@@ -0,0 +1,65 @@
+name: stfbuilder
+control:
+  mode: kubernetes_fairmq
+defaults:
+  detector: TST
+  rdh_version: "6"
+  user: flp
+  fmq_severity: info
+  dd_detector_subspec: feeid
+  dd_discovery_endpoint: "no-op://" # location of consul docker instance
+  log_task_stdout: none
+  log_task_stderr: none
+  stfb_dd_mode: "physics"
+  stfb_fee_mask: "0xffff"
+  stfb_enable_datasink: "false"
+  stfb_datasink_dir: "/tmp"
+  stfb_datasink_filesize: "2048"
+  monitoring_dd_interval: "5"
+  _module_cmdline: >-
+    source /etc/profile.d/modules.sh && MODULEPATH={{ modulepath }} module load DataDistribution Control-OCCPlugin &&
+    StfBuilder
+  _plain_cmdline: "{{ o2_install_path }}/bin/StfBuilder"
+wants:
+  cpu: 0.15
+  memory: 128
+bind:
+  - name: dpl-chan
+    type: push
+    rateLogging: "{{ fmq_rate_logging }}"
+    transport: shmem
+    addressing: ipc
+    sndBufSize: "4"
+    global: "readout-proxy-{{ it }}"
+command:
+  env:
+    - O2_INFOLOGGER_MODE={{infologger_mode}}
+    - O2_DETECTOR={{ detector }}
+    - DATADIST_FEE_MASK={{ stfb_fee_mask }}
+    - O2_PARTITION={{ environment_id }}
+  stdout: "{{ log_task_stdout }}"
+  stderr: "{{ log_task_stderr }}"
+  shell: true
+  user: "{{ user }}"
+  value: "{{ len(modulepath)>0 ? _module_cmdline : _plain_cmdline }}"
+  arguments:
+    - "--session=default"
+    - "--shm-segment-id=2"
+    - "--shm-segment-size=33554432"
+    - "--transport=shmem"
+    - "--monitoring-backend={{ monitoring_dd_url }}"
+    - "--monitoring-process-interval={{ monitoring_dd_interval }}"
+    - "--discovery-partition={{ environment_id }}"
+    - "--discovery-endpoint={{ dd_discovery_endpoint }}"
+    - "--detector-rdh={{ rdh_version }}"
+    - "--detector-subspec={{ dd_detector_subspec }}"
+    - "--severity={{ fmq_severity }}"
+    - "--severity-infologger={{ infologger_severity }}"
+    - "--dpl-channel-name=dpl-chan"
+    - "--shm-monitor=false"
+    - "--detector={{ detector }}"
+    - "--run-type={{ stfb_dd_mode }}"
+    - "{{ stfb_enable_datasink == 'true' ? '--data-sink-enable' : ' ' }}"
+    - "{{ stfb_enable_datasink == 'true' ? '--data-sink-dir=' +  stfb_datasink_dir : ' ' }}"
+    - "{{ stfb_enable_datasink == 'true' ? '--data-sink-max-stfs-per-file=0' : ' ' }}"
+    - "{{ stfb_enable_datasink == 'true' ? '--data-sink-max-file-size=' +  stfb_datasink_filesize : ' ' }}"

control-operator/ecs-manifests/kubernetes-manifests/dpl-qccheck-test.yaml

@@ -0,0 +1,110 @@
+apiVersion: aliecs.alice.cern/v1alpha1
+kind: Task
+metadata:
+  labels:
+    environment: 34xmvqdqcsu
+    node: mtichak-ost
+    taskID: 34XmVrU4GeE
+  name: mtichak-ost-dpl-qc-check-daq-qccheck
+  namespace: alice-tasks
+spec:
+  control:
+    mode: fairmq
+    port: 31000
+  nodeName: mtichak-ost.cern.ch
+  pod:
+    containers:
+    - args:
+      - source /etc/profile.d/o2.sh &&  o2-dpl-raw-proxy -b --session default --dataspec
+        'x:TST/RAWDATA;dd:FLP/DISTSUBTIMEFRAME/0' --inject-missing-data --readout-proxy
+        '--channel-config "name=readout-proxy,type=pull,method=connect,address=ipc:///tmp/stf-builder-dpl-pipe-0,transport=shmem,rateLogging=10"'
+        | o2-qc -b --config apricot://mtichak-ost.cern.ch:32188/o2/components/qc/ANY/any/stfb_to_daqtask-mtichak-ost
+        | o2-dpl-output-proxy --environment DPL_OUTPUT_PROXY_ORDERED=1 -b --session
+        default --dataspec 'x:TST/RAWDATA;dd:FLP/DISTSUBTIMEFRAME/0' --dpl-output-proxy
+        '--channel-config "name=downstream,type=push,method=bind,address=ipc:///tmp/stf-pipe-0,rateLogging=10,transport=shmem"'
+        | o2-qc -b --exit-transition-timeout '40' --data-processing-timeout '20' --monitoring-backend
+        'influxdb-unix:///tmp/telegraf-dpl.sock' --session 'default' --infologger-severity
+        'info' --infologger-mode 'infoLoggerD' --driver-client-backend 'stdout://'
+        --shm-segment-size '10000000000' --shm-throw-bad-alloc 'false' --resources-monitoring
+        '15' --id 'qc-check-DAQ-QcCheck' --shm-monitor 'false' --log-color 'false'
+        --batch --aod-file '' --aod-memory-rate-limit '0' --aod-writer-json '' --aod-writer-keep
+        '' --aod-writer-maxfilesize '0' --aod-writer-ntfmerge -1 --aod-writer-resdir
+        '' --aod-writer-resfile '' --aod-writer-resmode 'RECREATE' --bad-alloc-attempt-interval
+        '50' --bad-alloc-max-attempts '1' --channel-prefix '' --clone '' --config
+        'apricot://mtichak-ost.cern.ch:32188/o2/components/qc/ANY/any/stfb_to_daqtask-mtichak-ost'
+        --configKeyValues '' --early-forward-policy 'never' --fairmq-ipc-prefix '@'
+        --fairmq-rate-logging '0' --fairmq-recv-buffer-size '4' --fairmq-send-buffer-size
+        '4' --forwarding-destination 'drop' --forwarding-policy 'dangling' --host
+        '' --io-threads '1' --labels '' --local-batch '' --override-values '' --pipeline
+        '' --readers '1' --remote-batch '' --severity 'info' --shm-allocation 'rbtree_best_fit'
+        --shm-metadata-msg-size '0' --shm-mlock-segment 'false' --shm-mlock-segment-on-creation
+        'false' --shm-no-cleanup 'false' --shm-segment-id '0' --shm-zero-segment 'false'
+        --signposts '' --spawners '1' --stacktrace-on-signal 'simple' --timeframes-rate-limit
+        '0' --timeframes-rate-limit-ipcid -1 --workflow-suffix '' --qcConfiguration
+        '{}' --runNumber '' -S $CONTROL_OCCPLUGIN_ROOT/lib/ -P OCClite --color false
+        --control-port 31000
+      command:
+      - bash
+      - -c
+      env:
+      - name: O2_DETECTOR
+        value: TST
+      - name: O2_PARTITION
+        value: 34XmVqDQCsU
+      - name: HOME
+        value: /tmp
+      - name: O2_SYSTEM
+        value: FLP
+      - name: O2_ROLE
+        value: mtichak-ost
+      - name: OCC_CONTROL_PORT
+        value: "31000"
+      image: gitlab-registry.cern.ch/pkonopka/dockerfiles/flp-sw:20260729-1
+      imagePullPolicy: IfNotPresent
+      name: dpl
+      resources: {}
+      securityContext:
+        privileged: true
+        runAsGroup: 1100
+        runAsUser: 1100
+      volumeMounts:
+      - mountPath: /dev/shm
+        name: host-shm
+      - mountPath: /etc/group
+        name: group
+        readOnly: true
+      - mountPath: /etc/passwd
+        name: passwd
+        readOnly: true
+      - mountPath: /tmp
+        name: tmp
+      - mountPath: /lib/modules
+        name: modules
+    hostIPC: true
+    hostNetwork: true
+    imagePullSecrets:
+    - name: gitlab-registry-secret
+    nodeName: mtichak-ost.cern.ch
+    securityContext:
+      fsGroup: 1100
+      supplementalGroups:
+      - 10
+      - 1105
+    volumes:
+    - hostPath:
+        path: /dev/shm
+        type: Directory
+      name: host-shm
+    - hostPath:
+        path: /etc/group
+      name: group
+    - hostPath:
+        path: /etc/passwd
+      name: passwd
+    - hostPath:
+        path: /tmp
+      name: tmp
+    - hostPath:
+        path: /lib/modules
+      name: modules
+  state: standby

control-operator/ecs-manifests/task-templates/dpl-tasktemplate.yaml

@@ -0,0 +1,62 @@
+apiVersion: aliecs.alice.cern/v1alpha1
+kind: TaskTemplate
+metadata:
+  name: dpl
+  namespace: alice-tasks
+spec:
+  envVars:
+    - O2_DETECTOR
+    - O2_PARTITION
+    - OCC_CONTROL_PORT
+    - O2_SYSTEM
+    - O2_ROLE
+  pod:
+    hostNetwork: true
+    hostIPC: true
+    securityContext:
+      fsGroup: 1100
+      supplementalGroups: [10, 1105]
+    containers:
+      - name: dpl
+        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/o2suite:20261001-1
+        command: ["bash", "-c"]
+        securityContext:
+          privileged: true
+          runAsUser: 1100
+          runAsGroup: 1100
+        volumeMounts:
+          - name: host-shm
+            mountPath: /dev/shm
+          - name: group
+            mountPath: /etc/group
+            readOnly: true
+          - name: passwd
+            mountPath: /etc/passwd
+            readOnly: true
+          - name: tmp
+            mountPath: /tmp
+          - name: modules
+            mountPath: /lib/modules
+        imagePullPolicy: IfNotPresent
+    volumes:
+      - name: host-shm
+        hostPath:
+          path: /dev/shm
+          type: Directory
+      - name: group
+        hostPath:
+          path: /etc/group
+      - name: passwd
+        hostPath:
+          path: /etc/passwd
+      - name: tmp
+        hostPath:
+          path: /tmp
+      - name: modules
+        hostPath:
+          path: /lib/modules
+    imagePullSecrets:
+      - name: gitlab-registry-secret
+  control:
+    mode: "fairmq"
+    # port: ${OCC_CONTROL_PORT} # to be filled in automatically by TaskController

control-operator/ecs-manifests/task-templates/readout-tasktemplate.yaml

@@ -17,7 +17,7 @@ spec:
       supplementalGroups: [10, 1105]
     containers:
       - name: readout
-        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/readout:1
+        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/o2suite:20261001-1
         command: ["/opt/o2/bin/o2-readout-exe"]
         env:
           - name: OCC_CONTROL_PORT
@@ -61,4 +61,4 @@ spec:
       - name: gitlab-registry-secret
   control:
     mode: "direct"
-    # port: ${OCC_CONTROL_PORT} # to be filled in
+    # port: ${OCC_CONTROL_PORT} # to be filled in automatically by TaskController

control-operator/ecs-manifests/task-templates/stfbuilder-senderoutput-tasktemplate.yaml

@@ -19,7 +19,7 @@ spec:
       supplementalGroups: [10, 1105]
     containers:
       - name: stfbuilder
-        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/dd:1
+        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/o2suite:20261001-1
         command: [/opt/o2/bin/StfBuilder]
         env:
           - name: OCC_CONTROL_PORT
@@ -63,7 +63,7 @@ spec:
       - name: gitlab-registry-secret
   control:
     mode: "fairmq"
-    # port: ${OCC_CONTROL_PORT} #to be filled in
+    # port: ${OCC_CONTROL_PORT} # to be filled in automatically by TaskController
   bind:
     - name: buildertosender
       type: push

control-operator/ecs-manifests/task-templates/stfbuilder-tasktemplate.yaml

@@ -0,0 +1,77 @@
+apiVersion: aliecs.alice.cern/v1alpha1
+kind: TaskTemplate
+metadata:
+  name: stfbuilder
+  namespace: alice-tasks
+spec:
+  envVars:
+    - O2_DETECTOR
+    - O2_PARTITION
+    - O2_SYSTEM
+    - O2_ROLE
+    - O2_INFOLOGGER_MODE
+    - DATADIST_FEE_MASK
+  pod:
+    hostNetwork: true
+    hostIPC: true
+    securityContext:
+      fsGroup: 1100
+      supplementalGroups: [10, 1105]
+    containers:
+      - name: stfbuilder
+        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/o2suite:20261001-1
+        command: [/opt/o2/bin/StfBuilder]
+        env:
+          - name: OCC_CONTROL_PORT
+            value: "47102"
+        securityContext:
+          privileged: true
+          runAsUser: 1100
+          runAsGroup: 1100
+        volumeMounts:
+          - name: host-shm
+            mountPath: /dev/shm
+          - name: group
+            mountPath: /etc/group
+            readOnly: true
+          - name: passwd
+            mountPath: /etc/passwd
+            readOnly: true
+          - name: tmp
+            mountPath: /tmp
+          - name: modules
+            mountPath: /lib/modules
+        imagePullPolicy: IfNotPresent
+    volumes:
+      - name: host-shm
+        hostPath:
+          path: /dev/shm
+          type: Directory
+      - name: group
+        hostPath:
+          path: /etc/group
+      - name: passwd
+        hostPath:
+          path: /etc/passwd
+      - name: tmp
+        hostPath:
+          path: /tmp
+      - name: modules
+        hostPath:
+          path: /lib/modules
+    imagePullSecrets:
+      - name: gitlab-registry-secret
+  control:
+    mode: "fairmq"
+    # port: ${OCC_CONTROL_PORT} # to be filled in automatically by TaskController
+  bind:
+    - name: dpl-chan
+      type: push
+      rateLogging: "0"
+      addressing: ipc
+      transport: shmem
+      sndBufSize: 4
+      global: ""
+      target: ""
+  connect: []
+  properties: {}

control-operator/ecs-manifests/task-templates/stfsender-tasktemplate.yaml

@@ -26,7 +26,7 @@ spec:
       supplementalGroups: [10, 1105]
     containers:
       - name: stfsender
-        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/dd:1
+        image: gitlab-registry.cern.ch/aliceo2group/dockerfiles/alma9-flp-node/o2suite:20261001-1
         command: ["numactl"]
         env:
           - name: OCC_CONTROL_PORT
@@ -70,4 +70,4 @@ spec:
       - name: gitlab-registry-secret
   control:
     mode: "fairmq"
-    # port: ${OCC_CONTROL_PORT} # to be filled in
+    # port: ${OCC_CONTROL_PORT} # to be filled in automatically by TaskController