Scheduler does not place pods on nodes that have disk pressure

docs/devel/scheduler_algorithm.md

@@ -49,6 +49,7 @@ The purpose of filtering the nodes is to filter out the nodes that do not meet c
 - `MaxEBSVolumeCount`: Ensure that the number of attached ElasticBlockStore volumes does not exceed a maximum value (by default, 39, since Amazon recommends a maximum of 40 with one of those 40 reserved for the root volume -- see [Amazon's documentation](http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/volume_limits.html#linux-specific-volume-limits)).  The maximum value can be controlled by setting the `KUBE_MAX_PD_VOLS` environment variable.
 - `MaxGCEPDVolumeCount`: Ensure that the number of attached GCE PersistentDisk volumes does not exceed a maximum value (by default, 16, which is the maximum GCE allows -- see [GCE's documentation](https://cloud.google.com/compute/docs/disks/persistent-disks#limits_for_predefined_machine_types)).  The maximum value can be controlled by setting the `KUBE_MAX_PD_VOLS` environment variable.
 - `CheckNodeMemoryPressure`: Check if a pod can be scheduled on a node reporting memory pressure condition. Currently, no ``BestEffort`` should be placed on a node under memory pressure as it gets automatically evicted by kubelet.
+- `CheckNodeDiskPressure`: Check if a pod can be scheduled on a node reporting disk pressure condition. Currently, no pods should be placed on a node under disk pressure as it gets automatically evicted by kubelet.
 
 The details of the above predicates can be found in [plugin/pkg/scheduler/algorithm/predicates/predicates.go](http://releases.k8s.io/HEAD/plugin/pkg/scheduler/algorithm/predicates/predicates.go). All predicates mentioned above can be used in combination to perform a sophisticated filtering policy. Kubernetes uses some, but not all, of these predicates by default. You can see which ones are used by default in [plugin/pkg/scheduler/algorithmprovider/defaults/defaults.go](http://releases.k8s.io/HEAD/plugin/pkg/scheduler/algorithmprovider/defaults/defaults.go).
 

plugin/pkg/scheduler/algorithm/predicates/error.go

@@ -39,6 +39,7 @@ var (
 	ErrServiceAffinityViolated   = newPredicateFailureError("CheckServiceAffinity")
 	ErrMaxVolumeCountExceeded    = newPredicateFailureError("MaxVolumeCount")
 	ErrNodeUnderMemoryPressure   = newPredicateFailureError("NodeUnderMemoryPressure")
+	ErrNodeUnderDiskPressure     = newPredicateFailureError("NodeUnderDiskPressure")
 	// ErrFakePredicate is used for test only. The fake predicates returning false also returns error
 	// as ErrFakePredicate.
 	ErrFakePredicate = newPredicateFailureError("FakePredicateError")

plugin/pkg/scheduler/algorithm/predicates/predicates.go

@@ -1041,3 +1041,21 @@ func CheckNodeMemoryPressurePredicate(pod *api.Pod, meta interface{}, nodeInfo *
 
 	return true, nil
 }
+
+// CheckNodeDiskPressurePredicate checks if a pod can be scheduled on a node
+// reporting disk pressure condition.
+func CheckNodeDiskPressurePredicate(pod *api.Pod, meta interface{}, nodeInfo *schedulercache.NodeInfo) (bool, error) {
+	node := nodeInfo.Node()
+	if node == nil {
+		return false, fmt.Errorf("node not found")
+	}
+
+	// is node under presure?
+	for _, cond := range node.Status.Conditions {
+		if cond.Type == api.NodeDiskPressure && cond.Status == api.ConditionTrue {
+			return false, ErrNodeUnderDiskPressure
+		}
+	}
+
+	return true, nil
+}

plugin/pkg/scheduler/algorithm/predicates/predicates_test.go

@@ -2906,3 +2906,72 @@ func TestPodSchedulesOnNodeWithMemoryPressureCondition(t *testing.T) {
 		}
 	}
 }
+
+func TestPodSchedulesOnNodeWithDiskPressureCondition(t *testing.T) {
+	pod := &api.Pod{
+		Spec: api.PodSpec{
+			Containers: []api.Container{
+				{
+					Name:            "container",
+					Image:           "image",
+					ImagePullPolicy: "Always",
+				},
+			},
+		},
+	}
+
+	// specify a node with no disk pressure condition on
+	noPressureNode := &api.Node{
+		Status: api.NodeStatus{
+			Conditions: []api.NodeCondition{
+				{
+					Type:   "Ready",
+					Status: "True",
+				},
+			},
+		},
+	}
+
+	// specify a node with pressure condition on
+	pressureNode := &api.Node{
+		Status: api.NodeStatus{
+			Conditions: []api.NodeCondition{
+				{
+					Type:   "DiskPressure",
+					Status: "True",
+				},
+			},
+		},
+	}
+
+	tests := []struct {
+		pod      *api.Pod
+		nodeInfo *schedulercache.NodeInfo
+		fits     bool
+		name     string
+	}{
+		{
+			pod:      pod,
+			nodeInfo: makeEmptyNodeInfo(noPressureNode),
+			fits:     true,
+			name:     "pod schedulable on node without pressure condition on",
+		},
+		{
+			pod:      pod,
+			nodeInfo: makeEmptyNodeInfo(pressureNode),
+			fits:     false,
+			name:     "pod not schedulable on node with pressure condition on",
+		},
+	}
+
+	for _, test := range tests {
+		fits, err := CheckNodeDiskPressurePredicate(test.pod, test.nodeInfo)
+		if fits != test.fits {
+			t.Errorf("%s: expected %v got %v", test.name, test.fits, fits)
+		}
+
+		if err != nil && err != ErrNodeUnderDiskPressure {
+			t.Errorf("%s: unexpected error: %v", test.name, err)
+		}
+	}
+}

plugin/pkg/scheduler/algorithmprovider/defaults/defaults.go

@@ -151,6 +151,9 @@ func defaultPredicates() sets.String {
 
 		// Fit is determined by node memory pressure condition.
 		factory.RegisterFitPredicate("CheckNodeMemoryPressure", predicates.CheckNodeMemoryPressurePredicate),
+
+		// Fit is determined by node disk pressure condition.
+		factory.RegisterFitPredicate("CheckNodeDiskPressure", predicates.CheckNodeDiskPressurePredicate),
 	)
 }