Wait for handover state update before serving the requests #7028
+203
−26
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,142 @@ | ||
| package interceptor | ||
|
|
||
| import ( | ||
| "context" | ||
| "strings" | ||
| "time" | ||
|
|
||
| "github.com/google/uuid" | ||
| enumspb "go.temporal.io/api/enums/v1" | ||
| "go.temporal.io/server/common" | ||
| "go.temporal.io/server/common/api" | ||
| "go.temporal.io/server/common/clock" | ||
| "go.temporal.io/server/common/dynamicconfig" | ||
| "go.temporal.io/server/common/log" | ||
| "go.temporal.io/server/common/metrics" | ||
| "go.temporal.io/server/common/namespace" | ||
| "google.golang.org/grpc" | ||
| ) | ||
|
|
||
| const ( | ||
| ctxTailRoom = time.Millisecond * 100 | ||
| ) | ||
|
|
||
| var _ grpc.UnaryServerInterceptor = (*NamespaceHandoverInterceptor)(nil).Intercept | ||
|
|
||
| type ( | ||
| // NamespaceHandoverInterceptor handles the namespace in handover replication state | ||
| NamespaceHandoverInterceptor struct { | ||
| namespaceRegistry namespace.Registry | ||
| timeSource clock.TimeSource | ||
| enabledForNS dynamicconfig.BoolPropertyFnWithNamespaceFilter | ||
| nsCacheRefreshInterval dynamicconfig.DurationPropertyFn | ||
| metricsHandler metrics.Handler | ||
| logger log.Logger | ||
| } | ||
| ) | ||
|
|
||
| func NewNamespaceHandoverInterceptor( | ||
| dc *dynamicconfig.Collection, | ||
| namespaceRegistry namespace.Registry, | ||
| metricsHandler metrics.Handler, | ||
| logger log.Logger, | ||
| timeSource clock.TimeSource, | ||
| ) *NamespaceHandoverInterceptor { | ||
|
|
||
| return &NamespaceHandoverInterceptor{ | ||
| enabledForNS: dynamicconfig.EnableNamespaceHandoverWait.Get(dc), | ||
| nsCacheRefreshInterval: dynamicconfig.NamespaceCacheRefreshInterval.Get(dc), | ||
| namespaceRegistry: namespaceRegistry, | ||
| metricsHandler: metricsHandler, | ||
| logger: logger, | ||
| timeSource: timeSource, | ||
| } | ||
| } | ||
|
|
||
| func (i *NamespaceHandoverInterceptor) Intercept( | ||
| ctx context.Context, | ||
| req any, | ||
| info *grpc.UnaryServerInfo, | ||
| handler grpc.UnaryHandler, | ||
| ) (_ any, retError error) { | ||
| defer log.CapturePanic(i.logger, &retError) | ||
|
|
||
| if !strings.HasPrefix(info.FullMethod, api.WorkflowServicePrefix) { | ||
| return handler(ctx, req) | ||
| } | ||
|
|
||
| // review which method is allowed | ||
| methodName := api.MethodName(info.FullMethod) | ||
| namespaceName := MustGetNamespaceName(i.namespaceRegistry, req) | ||
|
|
||
| if namespaceName != namespace.EmptyName && i.enabledForNS(namespaceName.String()) { | ||
| var waitTime *time.Duration | ||
| defer func() { | ||
| if waitTime != nil { | ||
| metrics.HandoverWaitLatency.With(i.metricsHandler).Record(*waitTime) | ||
| } | ||
| }() | ||
| waitTime, err := i.waitNamespaceHandoverUpdate(ctx, namespaceName, methodName) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| } | ||
|
|
||
| return handler(ctx, req) | ||
| } | ||
|
|
||
| func (i *NamespaceHandoverInterceptor) waitNamespaceHandoverUpdate( | ||
| ctx context.Context, | ||
| namespaceName namespace.Name, | ||
| methodName string, | ||
| ) (waitTime *time.Duration, retErr error) { | ||
| if _, ok := allowedMethodsDuringHandover[methodName]; ok { | ||
| return | ||
| } | ||
|
|
||
| startTime := i.timeSource.Now() | ||
| namespaceData, err := i.namespaceRegistry.GetNamespace(namespaceName) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| if namespaceData.ReplicationState() == enumspb.REPLICATION_STATE_HANDOVER { | ||
| cbID := uuid.New() | ||
| waitReplicationStateUpdate := make(chan struct{}) | ||
| i.namespaceRegistry.RegisterStateChangeCallback(cbID, func(ns *namespace.Namespace, deletedFromDb bool) { | ||
|
There was a problem hiding this comment. we probably should be change the impl to listen on changes for a specific namespace... |
||
| if ns.ID().String() != namespaceData.ID().String() { | ||
| return | ||
| } | ||
| if ns.State() != enumspb.NAMESPACE_STATE_REGISTERED || | ||
| deletedFromDb || | ||
| ns.ReplicationState() != enumspb.REPLICATION_STATE_HANDOVER || | ||
| !ns.IsGlobalNamespace() { | ||
| // Stop wait on state change if: | ||
| // 1. namespace is deleting/deleted | ||
| // 2. namespace is not in handover | ||
| // 3. namespace is not global | ||
| select { | ||
| case <-waitReplicationStateUpdate: | ||
yycptt marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| default: | ||
| close(waitReplicationStateUpdate) | ||
| } | ||
| } | ||
| }) | ||
|
|
||
| maxWaitDuration := i.nsCacheRefreshInterval() // cache refresh time | ||
| if deadline, ok := ctx.Deadline(); ok { | ||
| maxWaitDuration = max(0, time.Until(deadline)-ctxTailRoom) | ||
| } | ||
| returnTimer := time.NewTimer(maxWaitDuration) | ||
| var handoverErr error | ||
| select { | ||
| case <-returnTimer.C: | ||
| handoverErr = common.ErrNamespaceHandover | ||
| case <-waitReplicationStateUpdate: | ||
| returnTimer.Stop() | ||
| } | ||
| i.namespaceRegistry.UnregisterStateChangeCallback(cbID) | ||
| waitTime := time.Since(startTime) | ||
| return &waitTime, handoverErr | ||
| } | ||
| return nil, nil | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: returning
nil, nilis surprising I think for the caller.