forked from kubernetes/kubernetes
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
fix a bug in nvidia gpu allocation and added unit test
Signed-off-by: Vishnu kannan <[email protected]>
- Loading branch information
Showing
5 changed files
with
170 additions
and
8 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,144 @@ | ||
| /* | ||
| Copyright 2017 The Kubernetes Authors. | ||
| Licensed under the Apache License, Version 2.0 (the "License"); | ||
| you may not use this file except in compliance with the License. | ||
| You may obtain a copy of the License at | ||
| http://www.apache.org/licenses/LICENSE-2.0 | ||
| Unless required by applicable law or agreed to in writing, software | ||
| distributed under the License is distributed on an "AS IS" BASIS, | ||
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| See the License for the specific language governing permissions and | ||
| limitations under the License. | ||
| */ | ||
|
|
||
| package nvidia | ||
|
|
||
| import ( | ||
| "testing" | ||
|
|
||
| "github.com/stretchr/testify/assert" | ||
|
|
||
| "k8s.io/apimachinery/pkg/api/resource" | ||
| metav1 "k8s.io/apimachinery/pkg/apis/meta/v1" | ||
| "k8s.io/apimachinery/pkg/util/sets" | ||
| "k8s.io/apimachinery/pkg/util/uuid" | ||
| "k8s.io/kubernetes/pkg/api/v1" | ||
| ) | ||
|
|
||
| type testActivePodsLister struct { | ||
| activePods []*v1.Pod | ||
| } | ||
|
|
||
| func (tapl *testActivePodsLister) GetRunningPods() ([]*v1.Pod, error) { | ||
| return tapl.activePods, nil | ||
| } | ||
|
|
||
| func makeTestPod(numContainers int) *v1.Pod { | ||
| quantity := resource.NewQuantity(1, resource.DecimalSI) | ||
| resources := v1.ResourceRequirements{ | ||
| Limits: v1.ResourceList{ | ||
| v1.ResourceNvidiaGPU: *quantity, | ||
| }, | ||
| } | ||
| pod := &v1.Pod{ | ||
| ObjectMeta: metav1.ObjectMeta{ | ||
| UID: uuid.NewUUID(), | ||
| }, | ||
| Spec: v1.PodSpec{ | ||
| Containers: []v1.Container{}, | ||
| }, | ||
| } | ||
| for ; numContainers > 0; numContainers-- { | ||
| pod.Spec.Containers = append(pod.Spec.Containers, v1.Container{ | ||
| Resources: resources, | ||
| }) | ||
| } | ||
| return pod | ||
| } | ||
|
|
||
| func TestMultiContainerPodGPUAllocation(t *testing.T) { | ||
| podLister := &testActivePodsLister{} | ||
|
|
||
| testGpuManager := &nvidiaGPUManager{ | ||
| activePodsLister: podLister, | ||
| allGPUs: sets.NewString("/dev/nvidia0", "/dev/nvidia1"), | ||
| allocated: newPodGPUs(), | ||
| } | ||
|
|
||
| // Expect that no devices are in use. | ||
| gpusInUse, err := testGpuManager.gpusInUse() | ||
| as := assert.New(t) | ||
| as.Nil(err) | ||
| as.Equal(len(gpusInUse.devices()), 0) | ||
|
|
||
| // Allocated GPUs for a pod with two containers. | ||
| pod := makeTestPod(2) | ||
| // Allocate for the first container. | ||
| devices1, err := testGpuManager.AllocateGPU(pod, &pod.Spec.Containers[0]) | ||
| as.Nil(err) | ||
| as.Equal(len(devices1), 1) | ||
|
|
||
| podLister.activePods = append(podLister.activePods, pod) | ||
| // Allocate for the second container. | ||
| devices2, err := testGpuManager.AllocateGPU(pod, &pod.Spec.Containers[1]) | ||
| as.Nil(err) | ||
| as.Equal(len(devices2), 1) | ||
|
|
||
| as.NotEqual(devices1, devices2, "expected containers to get different devices") | ||
|
|
||
| // further allocations should fail. | ||
| newPod := makeTestPod(2) | ||
| devices1, err = testGpuManager.AllocateGPU(newPod, &newPod.Spec.Containers[0]) | ||
| as.NotNil(err, "expected gpu allocation to fail. got: %v", devices1) | ||
|
|
||
| // Now terminate the original pod and observe that GPU allocation for new pod succeeds. | ||
| podLister.activePods = podLister.activePods[:0] | ||
|
|
||
| devices1, err = testGpuManager.AllocateGPU(newPod, &newPod.Spec.Containers[0]) | ||
| as.Nil(err) | ||
| as.Equal(len(devices1), 1) | ||
|
|
||
| podLister.activePods = append(podLister.activePods, newPod) | ||
|
|
||
| devices2, err = testGpuManager.AllocateGPU(newPod, &newPod.Spec.Containers[1]) | ||
| as.Nil(err) | ||
| as.Equal(len(devices2), 1) | ||
|
|
||
| as.NotEqual(devices1, devices2, "expected containers to get different devices") | ||
| } | ||
|
|
||
| func TestMultiPodGPUAllocation(t *testing.T) { | ||
| podLister := &testActivePodsLister{} | ||
|
|
||
| testGpuManager := &nvidiaGPUManager{ | ||
| activePodsLister: podLister, | ||
| allGPUs: sets.NewString("/dev/nvidia0", "/dev/nvidia1"), | ||
| allocated: newPodGPUs(), | ||
| } | ||
|
|
||
| // Expect that no devices are in use. | ||
| gpusInUse, err := testGpuManager.gpusInUse() | ||
| as := assert.New(t) | ||
| as.Nil(err) | ||
| as.Equal(len(gpusInUse.devices()), 0) | ||
|
|
||
| // Allocated GPUs for a pod with two containers. | ||
| podA := makeTestPod(1) | ||
| // Allocate for the first container. | ||
| devicesA, err := testGpuManager.AllocateGPU(podA, &podA.Spec.Containers[0]) | ||
| as.Nil(err) | ||
| as.Equal(len(devicesA), 1) | ||
|
|
||
| podLister.activePods = append(podLister.activePods, podA) | ||
|
|
||
| // further allocations should fail. | ||
| podB := makeTestPod(1) | ||
| // Allocate for the first container. | ||
| devicesB, err := testGpuManager.AllocateGPU(podB, &podB.Spec.Containers[0]) | ||
| as.Nil(err) | ||
| as.Equal(len(devicesB), 1) | ||
| as.NotEqual(devicesA, devicesB, "expected pods to get different devices") | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters