chore: Refactoring/domain handler updates (#7403)

<!-- Describe what has changed in this PR --> **What changed?** - Unified the FailoverDomain Handler code with the UpdateDomain Failover path - Flattened out the path for failover for normal domains and active/active a bit - Added a few bits missing for the FailoverDomain hander in both the CLI and the mappers to support active/active This is not a perfect refactor, I changed a few behaviours while I was here since I considered them low risk: - Stopped publishing active/active failover events to the Domain-data field, since this will be replaced by the FailoverHistory endpoint - Rewrote one of the unit tests for FailoverHandler for clarity <!-- Tell your future self why have you made these changes --> **Why?** <!-- How have you verified this change? Tested locally? Added a unit test? Checked in staging env? --> **How did you test it?** - [X] Unit tests - [X] Manual testing: - UpdateDomain - [X] Active/passive domain: Failover - [X] Active/Active - FailoverDomain - [X] Active/Passive domain - [X] Active/Active domain <!-- Assuming the worst case, what can be broken when deploying this change to production? --> **Potential risks** <!-- Is it notable for release? e.g. schema updates, configuration or data migration required? If so, please mention it, and also update CHANGELOG.md --> **Release notes** <!-- Is there any documentation updates should be made for config, https://cadenceworkflow.io/docs/operation-guide/setup/ ? If so, please open an PR in https://github.com/cadence-workflow/cadence-docs --> **Documentation Changes** --------- Signed-off-by: David Porter <david.porter@uber.com>

Author: davidporter-id-au

common/domain/handler.go

@@ -4514,7 +4514,8 @@ func FromFailoverDomainRequest(t *types.FailoverDomainRequest) *apiv1.FailoverDo
 }
 return &apiv1.FailoverDomainRequest{
 DomainName: t.DomainName,
-DomainActiveClusterName: *t.DomainActiveClusterName,
+DomainActiveClusterName: t.GetDomainActiveClusterName(),
+ActiveClusters: FromActiveClusters(t.ActiveClusters),
 }
 }
 
@@ -4525,6 +4526,7 @@ func ToFailoverDomainRequest(t *apiv1.FailoverDomainRequest) *types.FailoverDoma
 return &types.FailoverDomainRequest{
 DomainName: t.DomainName,
 DomainActiveClusterName: common.StringPtr(t.DomainActiveClusterName),
+ActiveClusters: ToActiveClusters(t.ActiveClusters),
 }
 }
 
@@ -5810,7 +5812,6 @@ func ToActiveClusters(t *apiv1.ActiveClusters) *types.ActiveClusters {
 
 var attributeScopes map[string]types.ClusterAttributeScope
 
-// Start with ActiveClustersByClusterAttribute if it exists
 if t.ActiveClustersByClusterAttribute != nil {
 attributeScopes = make(map[string]types.ClusterAttributeScope)
 for scopeType, scope := range t.ActiveClustersByClusterAttribute {

common/domain/handler_test.go

@@ -1622,6 +1622,7 @@ func FromFailoverDomainRequest(t *types.FailoverDomainRequest) *shared.FailoverD
 return &shared.FailoverDomainRequest{
 DomainName: &t.DomainName,
 DomainActiveClusterName: t.DomainActiveClusterName,
+ActiveClusters: FromActiveClusters(t.ActiveClusters),
 }
 }
 
@@ -1633,6 +1634,7 @@ func ToFailoverDomainRequest(t *shared.FailoverDomainRequest) *types.FailoverDom
 return &types.FailoverDomainRequest{
 DomainName: t.GetDomainName(),
 DomainActiveClusterName: t.DomainActiveClusterName,
+ActiveClusters: ToActiveClusters(t.ActiveClusters),
 }
 }
 

common/types/mapper/proto/api.go

@@ -1779,8 +1779,20 @@ func (v *DescribeDomainResponse) GetFailoverInfo() (o *FailoverInfo) {
 
 // FailoverDomainRequest is an internal type (TBD...)
 type FailoverDomainRequest struct {
-DomainName string `json:"domainName,omitempty"`
-DomainActiveClusterName *string `json:"domainActiveClusterName,omitempty"`
+DomainName string `json:"domainName,omitempty"`
+DomainActiveClusterName *string `json:"domainActiveClusterName,omitempty"`
+ActiveClusters *ActiveClusters `json:"activeClusters,omitempty"`
+}
+
+func (v *FailoverDomainRequest) ToUpdateDomainRequest() *UpdateDomainRequest {
+if v == nil {
+return nil
+}
+return &UpdateDomainRequest{
+Name: v.DomainName,
+ActiveClusterName: v.DomainActiveClusterName,
+ActiveClusters: v.ActiveClusters,
+}
 }
 
 // GetDomainName is an internal getter (TBD...)
@@ -8053,6 +8065,19 @@ type UpdateDomainResponse struct {
 IsGlobalDomain bool `json:"isGlobalDomain,omitempty"`
 }
 
+func (v *UpdateDomainResponse) ToFailoverDomainResponse() *FailoverDomainResponse {
+if v == nil {
+return nil
+}
+return &FailoverDomainResponse{
+DomainInfo: v.DomainInfo,
+Configuration: v.Configuration,
+ReplicationConfiguration: v.ReplicationConfiguration,
+FailoverVersion: v.FailoverVersion,
+IsGlobalDomain: v.IsGlobalDomain,
+}
+}
+
 // GetDomainInfo is an internal getter (TBD...)
 func (v *UpdateDomainResponse) GetDomainInfo() (o *DomainInfo) {
 if v != nil && v.DomainInfo != nil {

common/types/mapper/thrift/shared.go

@@ -374,8 +374,8 @@ func (v *requestValidatorImpl) ValidateFailoverDomainRequest(ctx context.Context
 return validate.ErrDomainNotSet
 }
 
-if failoverDomainRequest.DomainActiveClusterName == nil {
-return &types.BadRequestError{Message: "DomainActiveClusterName must be provided to failover the domain"}
+if failoverDomainRequest.DomainActiveClusterName == nil && failoverDomainRequest.ActiveClusters == nil {
+return &types.BadRequestError{Message: "DomainActiveClusterName or ActiveClusters must be provided to failover the domain"}
 }
 
 // Security token is not required for failover request - reject the failover if the cluster is in lockdown

common/types/shared.go

@@ -457,22 +457,30 @@ func (d *domainCLIImpl) FailoverDomain(c *cli.Context) error {
 return commoncli.Problem("Required flag not found: ", err)
 }
 
-var failoverRequest *types.FailoverDomainRequest
+failoverRequest := &types.FailoverDomainRequest{
+DomainName: domainName,
+}
 
 ctx, cancel, err := newContext(c)
 defer cancel()
 if err != nil {
 return commoncli.Problem("Error in creating context: ", err)
 }
 
+if !c.IsSet(FlagActiveClusterName) && !c.IsSet(FlagActiveClusters) {
+return commoncli.Problem("At least one of the flags --active-cluster-name or --active-clusters must be provided.", nil)
+}
+
 if c.IsSet(FlagActiveClusterName) { // active-passive domain failover
 activeCluster := c.String(FlagActiveClusterName)
-fmt.Printf("Will set active cluster name to: %s, other flag will be omitted.\n", activeCluster)
-
-failoverRequest = &types.FailoverDomainRequest{
-DomainName: domainName,
-DomainActiveClusterName: common.StringPtr(activeCluster),
+failoverRequest.DomainActiveClusterName = common.StringPtr(activeCluster)
+}
+if c.IsSet(FlagActiveClusters) { // active-active domain failover
+ac, err := parseActiveClustersByClusterAttribute(c.String(FlagActiveClusters))
+if err != nil {
+return err
 }
+failoverRequest.ActiveClusters = &ac
 }
 _, err = d.failoverDomain(ctx, failoverRequest)
 if err != nil {

service/frontend/api/request_validator.go

@@ -270,6 +270,11 @@ var (
 Aliases: []string{"ac"},
 Usage: "Active cluster name",
 },
+&cli.StringSliceFlag{
+Name: FlagActiveClusters,
+Aliases: []string{"acs"},
+Usage: "Active clusters by cluster attribute in the format '<cluster-attr>.<scope>:<name> ie: region.manilla:cluster0,region.newyork:cluster1'",
+},
 }
 
 listFailoverHistoryFlags = []cli.Flag{