New Feature: provide failFast flag, allow a DAG to run all branches of the DAG (either success or failure)

api/openapi-spec/swagger.json

@@ -235,6 +235,10 @@
  "tasks"
  ],
  "properties": {
+ "failFast": {
+ "description": "This flag is for DAG logic. The DAG logic has a built-in \"fail fast\" feature to stop scheduling new steps, as soon as it detects that one of the DAG nodes is failed. Then it waits until all DAG nodes are completed before failing the DAG itself. The FailFast flag default is true, if set to false, it will allow a DAG to run all branches of the DAG to completion (either success or failure), regardless of the failed outcomes of branches in the DAG. More info and example about this feature at https://github.com/argoproj/argo/issues/1442",
+ "type": "boolean"
+ },
  "target": {
  "description": "Target are one or more names of targets to execute in a DAG",
  "type": "string"

pkg/apis/workflow/v1alpha1/types.go

@@ -891,6 +891,14 @@ type DAGTemplate struct {
 
  // Tasks are a list of DAG tasks
  Tasks []DAGTask `json:"tasks"`
+
+ // This flag is for DAG logic. The DAG logic has a built-in "fail fast" feature to stop scheduling new steps,
+ // as soon as it detects that one of the DAG nodes is failed. Then it waits until all DAG nodes are completed
+ // before failing the DAG itself.
+ // The FailFast flag default is true, if set to false, it will allow a DAG to run all branches of the DAG to
+ // completion (either success or failure), regardless of the failed outcomes of branches in the DAG.
+ // More info and example about this feature at https://github.com/argoproj/argo/issues/1442
+ FailFast *bool `json:"failFast,omitempty"`
 }
 
 // DAGTask represents a node in the graph during DAG execution

test/e2e/functional/dag-disable-failFast.yaml

@@ -0,0 +1,49 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Workflow
+metadata:
+ generateName: dag-primay-branch-
+spec:
+ entrypoint: statis
+ templates:
+ - name: a
+ container:
+ image: docker/whalesay:latest
+ command: [cowsay]
+ args: ["hello world"]
+ - name: b
+ retryStrategy:
+ limit: 2
+ container:
+ image: alpine:latest
+ command: [sh, -c]
+ args: ["sleep 30; echo haha"]
+ - name: c
+ retryStrategy:
+ limit: 3
+ container:
+ image: alpine:latest
+ command: [sh, -c]
+ args: ["echo intentional failure; exit 2"]
+ - name: d
+ container:
+ image: docker/whalesay:latest
+ command: [cowsay]
+ args: ["hello world"]
+ - name: statis
+ dag:
+ failFast: false
+ tasks:
+ - name: A
+ template: a
+ - name: B
+ dependencies: [A]
+ template: b
+ - name: C
+ dependencies: [A]
+ template: c
+ - name: D
+ dependencies: [B]
+ template: d
+ - name: E
+ dependencies: [D]
+ template: d

test/e2e/functional/dag-noroot-branch-failed.yaml

@@ -0,0 +1,48 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Workflow
+metadata:
+ generateName: dag-primay-branch-
+spec:
+ entrypoint: statis
+ templates:
+ - name: a
+ container:
+ image: docker/whalesay:latest
+ command: [cowsay]
+ args: ["hello world"]
+ - name: b
+ retryStrategy:
+ limit: 2
+ container:
+ image: alpine:latest
+ command: [sh, -c]
+ args: ["sleep 30; echo haha"]
+ - name: c
+ retryStrategy:
+ limit: 3
+ container:
+ image: alpine:latest
+ command: [sh, -c]
+ args: ["echo intentional failure; exit 2"]
+ - name: d
+ container:
+ image: docker/whalesay:latest
+ command: [cowsay]
+ args: ["hello world"]
+ - name: statis
+ dag:
+ tasks:
+ - name: A
+ template: a
+ - name: B
+ dependencies: [A]
+ template: b
+ - name: C
+ dependencies: [A]
+ template: c
+ - name: D
+ dependencies: [B]
+ template: d
+ - name: E
+ dependencies: [D]
+ template: d

workflow/controller/dag.go

@@ -87,7 +87,31 @@ func (d *dagContext) assessDAGPhase(targetTasks []string, nodes map[string]wfv1.
  retriesExhausted = false
  }
  }
+
  if unsuccessfulPhase != "" {
+ if d.tmpl != nil && d.tmpl.DAG != nil {
+ // If failFast set to false, we should return Running to continue this workflow for other DAG branch
+ if d.tmpl.DAG.FailFast != nil && !*d.tmpl.DAG.FailFast {
+ tmpOverAllFinished := true
+ // If all the nodes have finished, we should mark the failed node to finish overall workflow
+ // So we should check all the targetTasks have finished
+ for _, tmpDepName := range targetTasks {
+ tmpDepNode := d.getTaskNode(tmpDepName)
+ if tmpDepNode == nil {
+ tmpOverAllFinished = false
+ break
+ }
+ if tmpDepNode.Type == wfv1.NodeTypeRetry && hasMoreRetries(tmpDepNode, d.wf) {
+ tmpOverAllFinished = false
+ break
+ }
+ }
+ if !tmpOverAllFinished {
+ return wfv1.NodeRunning
+ }
+ }
+ }
+
  // if we were unsuccessful, we can return *only* if all retry nodes have ben exhausted.
  if retriesExhausted {
  return unsuccessfulPhase

workflow/controller/dag_test.go

@@ -32,3 +32,11 @@ func TestDagRetryExhaustedXfail(t *testing.T) {
  woc.operate()
  assert.Equal(t, string(wfv1.NodeFailed), string(woc.wf.Status.Phase))
 }
+
+// TestDagDisableFailFast test disable fail fast function
+func TestDagDisableFailFast(t *testing.T) {
+ wf := test.LoadTestWorkflow("testdata/dag-disable-fail-fast.yaml")
+ woc := newWoc(*wf)
+ woc.operate()
+ assert.Equal(t, string(wfv1.NodeFailed), string(woc.wf.Status.Phase))
+}