github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2025-07-23 19:56:01 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #48199 from MaciekPytel/fix_autoscaler_e2e_on_gke

Browse Source 
Automatic merge from submit-queue (batch tested with PRs 48168, 48199)

Fix some flakes in autoscaler e2e on gke

This PR should fix some of the flakes we found in e2e runs, while testing for 1.7 release:
 - if one of the nodes is unschedulable in set up (causing set up to fail) we used to wait for wrong number of nodes in clean-up, adding unnecessary 20 minute wait to failing test
 - we did not check for errors when creating RC in test, leading to tests failing later in hard to debug way (added retry loop and explicit test failure)
This commit is contained in:
Kubernetes Submit Queue 2017-06-28 11:54:03 -07:00 committed by GitHub
commit 40f33a4b10
1 changed files with 26 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
test/e2e/autoscaling/cluster_size_autoscaling.go
View File

@ -50,13 +50,15 @@ import (
)
const (
defaultTimeout = 3 * time.Minute
resizeTimeout = 5 * time.Minute
scaleUpTimeout = 5 * time.Minute
scaleUpTriggerTimeout = 2 * time.Minute
scaleDownTimeout = 20 * time.Minute
podTimeout = 2 * time.Minute
nodesRecoverTimeout = 5 * time.Minute
defaultTimeout = 3 * time.Minute
resizeTimeout = 5 * time.Minute
scaleUpTimeout = 5 * time.Minute
scaleUpTriggerTimeout = 2 * time.Minute
scaleDownTimeout = 20 * time.Minute
podTimeout = 2 * time.Minute
nodesRecoverTimeout = 5 * time.Minute
rcCreationRetryTimeout = 4 * time.Minute
rcCreationRetryDelay = 20 * time.Second
gkeEndpoint = "https://test-container.sandbox.googleapis.com"
gkeUpdateTimeout = 15 * time.Minute
@ -95,6 +97,7 @@ var _ = framework.KubeDescribe("Cluster size autoscaling [Slow]", func() {
nodes := framework.GetReadySchedulableNodesOrDie(f.ClientSet)
nodeCount = len(nodes.Items)
By(fmt.Sprintf("Initial number of schedulable nodes: %v", nodeCount))
Expect(nodeCount).NotTo(BeZero())
cpu := nodes.Items[0].Status.Capacity[v1.ResourceCPU]
mem := nodes.Items[0].Status.Capacity[v1.ResourceMemory]
@ -116,7 +119,11 @@ var _ = framework.KubeDescribe("Cluster size autoscaling [Slow]", func() {
AfterEach(func() {
By(fmt.Sprintf("Restoring initial size of the cluster"))
setMigSizes(originalSizes)
framework.ExpectNoError(framework.WaitForClusterSize(c, nodeCount, scaleDownTimeout))
expectedNodes := 0
for _, size := range originalSizes {
expectedNodes += size
}
framework.ExpectNoError(framework.WaitForClusterSize(c, expectedNodes, scaleDownTimeout))
nodes, err := c.Core().Nodes().List(metav1.ListOptions{})
framework.ExpectNoError(err)
for _, n := range nodes.Items {
@ -862,10 +869,18 @@ func ReserveMemory(f *framework.Framework, id string, replicas, megabytes int, e
Replicas: replicas,
MemRequest: request,
}
err := framework.RunRC(*config)
if expectRunning {
framework.ExpectNoError(err)
for start := time.Now(); time.Since(start) < rcCreationRetryTimeout; time.Sleep(rcCreationRetryDelay) {
err := framework.RunRC(*config)
if err != nil && strings.Contains(err.Error(), "Error creating replication controller") {
glog.Warningf("Failed to create memory reservation: %v", err)
continue
}
if expectRunning {
framework.ExpectNoError(err)
}
return
}
framework.Failf("Failed to reserve memory within timeout")
}
// WaitForClusterSize waits until the cluster size matches the given function.