update gang-scheduling benchmark

Signed-off-by: Dmitry Shmulevich <[email protected]>

resources/benchmarks/gang-scheduling/README.md

@@ -0,0 +1,29 @@
+# Gang Scheduling Benchmark Test
+
+This directory contains benchmark tests for various workload managers and schedulers. The supported systems include:
+
+- Jobset
+- Kueue
+- Volcano
+- Yunikorn
+- Run:ai
+
+## Usage
+
+For all workload managers except Run:ai, the benchmark test involves two sequential workflows. The first workflow registers the CRDs, and the second workflow runs the common part of the test.
+
+### Example
+
+To run the benchmark test for Kueue:
+
+```bash
+./bin/knavigator -workflow resources/benchmarks/gang-scheduling/workflows/config-kueue.yml,resources/benchmarks/gang-scheduling/workflows/run-test-common.yml
+```
+
+### Run:ai
+
+Run:ai requires additional customization and thus has a separate workflow:
+
+```bash
+./bin/knavigator -workflow resources/benchmarks/gang-scheduling/workflows/run-test-runai.yml
+```

resources/benchmarks/gang-scheduling/workflows/config-jobset.yml

@@ -0,0 +1,9 @@
+name: config-jobset
+tasks:
+- id: register
+  type: RegisterObj
+  params:
+    template: "resources/benchmarks/gang-scheduling/templates/k8s/jobset.yml"
+    nameFormat: "jobset{{._ENUM_}}"
+    podNameFormat: "{{._NAME_}}-workers-[0-9]+-[0-9]+-.+"
+    podCount: "{{.replicas}}"

resources/benchmarks/gang-scheduling/workflows/config-kueue.yml

@@ -0,0 +1,50 @@
+name: config-kueue
+tasks:
+- id: register-cluster-queue
+  type: RegisterObj
+  params:
+    template: "resources/templates/kueue/cluster-queue.yml"
+- id: register-local-queue
+  type: RegisterObj
+  params:
+    template: "resources/templates/kueue/local-queue.yml"
+- id: register-resource-flavor
+  type: RegisterObj
+  params:
+    template: "resources/templates/kueue/resource-flavor.yml"
+- id: register
+  type: RegisterObj
+  params:
+    template: "resources/benchmarks/templates/kueue/job.yml"
+    nameFormat: "job{{._ENUM_}}"
+    podNameFormat: "{{._NAME_}}-[0-9]-.*"
+    podCount: "{{.replicas}}"
+- id: create-resource-flavor
+  type: SubmitObj
+  params:
+    refTaskId: register-resource-flavor
+    canExist: true
+    params:
+      name: "gpu-node"
+      nodeLabels:
+        nvidia.com/gpu.count: "8"
+- id: create-cluster-queue
+  type: SubmitObj
+  params:
+    refTaskId: register-cluster-queue
+    canExist: true
+    params:
+      name: team
+      flavor: gpu-node
+      cpu: 8
+      memory: 36Gi
+      gpu: 256
+- id: create-local-queue
+  type: SubmitObj
+  params:
+    refTaskId: register-local-queue
+    canExist: true
+    params:
+      name: team-queue
+      namespace: default
+      clusterQueue: team

resources/benchmarks/gang-scheduling/workflows/config-volcano.yml

@@ -0,0 +1,31 @@
+name: config-volcano
+tasks:
+- id: register
+  type: RegisterObj
+  params:
+    template: "resources/benchmarks/templates/volcano/job.yml"
+    nameFormat: "j{{._ENUM_}}"
+    podNameFormat: "{{._NAME_}}-test-[0-9]+"
+    podCount: "{{.replicas}}"
+- id: configure
+  type: Configure
+  params:
+    configmaps:
+    - name: volcano-scheduler-configmap
+      namespace: volcano-system
+      op: create
+      data:
+        volcano-scheduler.conf: |
+          actions: "enqueue, allocate, backfill"
+          tiers:
+          - plugins:
+            - name: priority
+            - name: gang
+            - name: conformance
+          - plugins:
+            - name: drf
+            - name: predicates
+            - name: proportion
+            - name: nodeorder
+            - name: binpack
+    timeout: 1m

resources/benchmarks/gang-scheduling/workflows/config-yunikorn.yml

@@ -0,0 +1,29 @@
+name: config-yunikorn
+tasks:
+- id: register
+  type: RegisterObj
+  params:
+    template: "resources/benchmarks/templates/yunikorn/job.yml"
+    nameFormat: "job{{._ENUM_}}"
+    podNameFormat: "{{._NAME_}}-.*"
+    podCount: "{{.replicas}}"
+- id: configure
+  type: Configure
+  params:
+    configmaps:
+    - name: yunikorn-configs
+      namespace: yunikorn
+      op: create
+      data:
+        queues.yaml: |
+          partitions:
+            - name: default
+              queues:
+              - name: root
+                queues:
+                - name: sandbox
+                  submitacl: '*'
+                  resources:
+                    max:
+                      {memory: 36Gi, vcore: 8000m, nvidia.com/gpu: 256}
+    timeout: 1m

resources/benchmarks/gang-scheduling/workflows/run-test-common.yml

@@ -0,0 +1,131 @@
+name: test-gang-scheduling
+tasks:
+- id: configure
+  type: Configure
+  params:
+    nodes:
+    - type: dgxa100.80g
+      count: 32
+      labels:
+        nvidia.com/gpu.count: "8"
+    timeout: 1m
+- id: job1
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 1
+    params:
+      replicas: 32
+      ttl: 30s
+- id: job2
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 2
+    params:
+      replicas: 16
+      ttl: 30s
+- id: job3
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 3
+    params:
+      replicas: 10
+      ttl: 30s
+- id: job3.1
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 1
+    params:
+      replicas: 2
+      ttl: 30s
+- id: job4
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 4
+    params:
+      replicas: 8
+      ttl: 30s
+- id: job5
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 5
+    params:
+      replicas: 6
+      ttl: 30s
+- id: job5.1
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 2
+    params:
+      replicas: 1
+      ttl: 30s
+- id: job6
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 6
+    params:
+      replicas: 5
+      ttl: 30s
+- id: job6.1
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 1
+    params:
+      replicas: 2
+      ttl: 30s
+- id: job7
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 7
+    params:
+      replicas: 4
+      ttl: 30s
+- id: job7.1
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 1
+    params:
+      replicas: 2
+      ttl: 30s
+- id: job7.2
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 2
+    params:
+      replicas: 1
+      ttl: 30s
+- id: job8
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 8
+    params:
+     replicas: 4
+     ttl: 30s
+- id: job9
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 9
+    params:
+      replicas: 3
+      ttl: 30s
+- id: job9.1
+  type: SubmitObj
+  params:
+    refTaskId: register
+    count: 1
+    params:
+      replicas: 5
+      ttl: 30s

resources/benchmarks/gang-scheduling/workflows/run-test-runai.yml

@@ -1,5 +1,14 @@
-name: test-gang-scheduling
+name: test-gang-scheduling-runai
 tasks:
+- id: configure
+  type: Configure
+  params:
+    nodes:
+    - type: dgxa100.80g
+      count: 32
+      labels:
+        nvidia.com/gpu.count: "8"
+    timeout: 1m
 - id: register-trainingworkload
   type: RegisterObj
   params: