expose is replaying flag (#419)

* expose is replay flag

* adding more warnings

Author: yiminc

internal/internal_event_handlers.go

@@ -315,6 +315,10 @@ func (wc *workflowEnvironmentImpl) GetMetricsScope() tally.Scope {
 	return wc.metricsScope
 }
 
+func (wc *workflowEnvironmentImpl) IsReplaying() bool {
+	return wc.isReplay
+}
+
 func (wc *workflowEnvironmentImpl) GenerateSequenceID() string {
 	return fmt.Sprintf("%d", wc.GenerateSequence())
 }

internal/internal_worker_base.go

@@ -69,6 +69,7 @@ type (
 		RegisterSignalHandler(handler func(name string, input []byte))
 		SignalExternalWorkflow(domainName, workflowID, runID, signalName string, input []byte, arg interface{}, childWorkflowOnly bool, callback resultHandler)
 		RegisterQueryHandler(handler func(queryType string, queryArgs []byte) ([]byte, error))
+		IsReplaying() bool
 	}
 
 	// WorkflowDefinition wraps the code that can execute a workflow.

internal/internal_workflow_testsuite.go

@@ -1266,6 +1266,11 @@ func (env *testWorkflowEnvironmentImpl) RequestCancelExternalWorkflow(domainName
 	}()
 }
 
+func (env *testWorkflowEnvironmentImpl) IsReplaying() bool {
+	// this test environment never replay
+	return false
+}
+
 func (env *testWorkflowEnvironmentImpl) SignalExternalWorkflow(domainName, workflowID, runID, signalName string, input []byte, arg interface{}, childWorkflowOnly bool, callback resultHandler) {
 	// check if target workflow is a known workflow
 	if childHandle, ok := env.runningWorkflows[workflowID]; ok {

internal/workflow.go

@@ -890,3 +890,20 @@ func SetQueryHandler(ctx Context, queryType string, handler interface{}) error {
 	}
 	return setQueryHandler(ctx, queryType, handler)
 }
+
+// IsReplaying returns whether the current workflow code is replaying.
+//
+// Warning! Never make decisions, like schedule activity/childWorkflow/timer or send/wait on future/channel, based on
+// this flag as it is going to break workflow determinism requirement.
+// The only reasonable use case for this flag is to avoid some external actions during replay, like custom logging or
+// metric reporting. Please note that Cadence already provide standard logging/metric via workflow.GetLogger(ctx) and
+// workflow.GetMetricsScope(ctx), and those standard mechanism are replay-aware and it will automatically suppress during
+// replay. Only use this flag if you need custom logging/metrics reporting, for example if you want to log to kafka.
+//
+// Warning! Any action protected by this flag should not fail or if it does fail should ignore that failure or panic
+// on the failure. If workflow don't want to be blocked on those failure, it should ignore those failure; if workflow do
+// want to make sure it proceed only when that action succeed then it should panic on that failure. Panic raised from a
+// workflow causes decision task to fail and cadence server will rescheduled later to retry.
+func IsReplaying(ctx Context) bool {
+	return getWorkflowEnvironment(ctx).IsReplaying()
+}

workflow/workflow.go

@@ -367,3 +367,20 @@ func GetVersion(ctx Context, changeID string, minSupported, maxSupported Version
 func SetQueryHandler(ctx Context, queryType string, handler interface{}) error {
 	return internal.SetQueryHandler(ctx, queryType, handler)
 }
+
+// IsReplaying returns whether the current workflow code is replaying.
+//
+// Warning! Never make decisions, like schedule activity/childWorkflow/timer or send/wait on future/channel, based on
+// this flag as it is going to break workflow determinism requirement.
+// The only reasonable use case for this flag is to avoid some external actions during replay, like custom logging or
+// metric reporting. Please note that Cadence already provide standard logging/metric via workflow.GetLogger(ctx) and
+// workflow.GetMetricsScope(ctx), and those standard mechanism are replay-aware and it will automatically suppress during
+// replay. Only use this flag if you need custom logging/metrics reporting, for example if you want to log to kafka.
+//
+// Warning! Any action protected by this flag should not fail or if it does fail should ignore that failure or panic
+// on the failure. If workflow don't want to be blocked on those failure, it should ignore those failure; if workflow do
+// want to make sure it proceed only when that action succeed then it should panic on that failure. Panic raised from a
+// workflow causes decision task to fail and cadence server will rescheduled later to retry.
+func IsReplaying(ctx Context) bool {
+	return internal.IsReplaying(ctx)
+}