-
Notifications
You must be signed in to change notification settings - Fork 202
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Early-return sample #366
Early-return sample #366
Changes from 6 commits
7c726e9
509449f
3565530
9b4a47a
733a0b6
ecd78c8
2097b86
a0d812c
d400b38
c509f54
3c68ea4
eac75d8
fb87344
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,17 @@ | ||
### Early-Return Sample | ||
|
||
This sample demonstrates an early-return from a workflow. | ||
|
||
By utilizing Update-with-Start, a client can start a new workflow and synchronously receive | ||
a response mid-workflow, while the workflow continues to run to completion. | ||
|
||
### Steps to run this sample: | ||
1) Run a [Temporal service](https://github.com/temporalio/samples-go/tree/main/#how-to-use). | ||
2) Run the following command to start the worker | ||
``` | ||
go run early-return/worker/main.go | ||
``` | ||
3) Run the following command to start the example | ||
``` | ||
go run early-return/starter/main.go | ||
``` |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,36 @@ | ||
package earlyreturn | ||
|
||
import ( | ||
"context" | ||
"errors" | ||
"time" | ||
|
||
"go.temporal.io/sdk/activity" | ||
) | ||
|
||
func InitTransaction(ctx context.Context, tx Transaction) error { | ||
logger := activity.GetLogger(ctx) | ||
if tx.FromAccount == "" { | ||
return errors.New("invalid fromAccount") | ||
} | ||
if tx.ToAccount == "" { | ||
return errors.New("invalid toAccount") | ||
} | ||
if tx.Amount == 0 { | ||
return errors.New("invalid amount") | ||
} | ||
logger.Info("Transaction initialized") | ||
return nil | ||
} | ||
|
||
func CancelTransaction(ctx context.Context, tx Transaction) { | ||
logger := activity.GetLogger(ctx) | ||
time.Sleep(1 * time.Second) | ||
logger.Info("Transaction cancelled") | ||
} | ||
|
||
func CompleteTransaction(ctx context.Context, tx Transaction) { | ||
logger := activity.GetLogger(ctx) | ||
time.Sleep(1 * time.Second) | ||
logger.Info("Transaction completed") | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,56 @@ | ||
package main | ||
|
||
import ( | ||
"context" | ||
"log" | ||
"time" | ||
|
||
"github.com/pborman/uuid" | ||
"github.com/temporalio/samples-go/early-return" | ||
"go.temporal.io/sdk/client" | ||
) | ||
|
||
func main() { | ||
c, err := client.Dial(client.Options{}) | ||
if err != nil { | ||
log.Fatalln("Unable to create client", err) | ||
} | ||
defer c.Close() | ||
|
||
ctxWithTimeout, cancel := context.WithTimeout(context.Background(), 5*time.Second) | ||
defer cancel() | ||
|
||
updateOperation := client.NewUpdateWithStartWorkflowOperation( | ||
client.UpdateWorkflowOptions{ | ||
UpdateName: earlyreturn.UpdateName, | ||
WaitForStage: client.WorkflowUpdateStageCompleted, | ||
}) | ||
|
||
tx := earlyreturn.Transaction{ID: uuid.New(), FromAccount: "Bob", ToAccount: "Alice", Amount: 100.0} | ||
workflowOptions := client.StartWorkflowOptions{ | ||
ID: "early-return-workflow-ID-" + tx.ID, | ||
TaskQueue: earlyreturn.TaskQueueName, | ||
WithStartOperation: updateOperation, | ||
} | ||
we, err := c.ExecuteWorkflow(ctxWithTimeout, workflowOptions, earlyreturn.Workflow, tx) | ||
if err != nil { | ||
log.Fatalln("Error executing workflow:", err) | ||
} | ||
|
||
log.Println("Started workflow", "WorkflowID", we.GetID(), "RunID", we.GetRunID()) | ||
|
||
updateHandle, err := updateOperation.Get(ctxWithTimeout) | ||
if err != nil { | ||
log.Fatalln("Error obtaining update handle:", err) | ||
} | ||
|
||
err = updateHandle.Get(ctxWithTimeout, nil) | ||
if err != nil { | ||
// NOTE: If the error is retryable, a retry attempt must use a unique workflow ID. | ||
log.Fatalln("Error obtaining update result:", err) | ||
} | ||
|
||
log.Println("Transaction initialized successfully") | ||
|
||
// The workflow will continue running, either completing or cancelling the transaction. | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,27 @@ | ||
package main | ||
|
||
import ( | ||
"log" | ||
|
||
"github.com/temporalio/samples-go/early-return" | ||
"go.temporal.io/sdk/client" | ||
"go.temporal.io/sdk/worker" | ||
) | ||
|
||
func main() { | ||
// The client and worker are heavyweight objects that should be created once per process. | ||
c, err := client.Dial(client.Options{}) | ||
if err != nil { | ||
log.Fatalln("Unable to create client", err) | ||
} | ||
defer c.Close() | ||
|
||
w := worker.New(c, earlyreturn.TaskQueueName, worker.Options{}) | ||
|
||
w.RegisterWorkflow(earlyreturn.Workflow) | ||
|
||
err = w.Run(worker.InterruptCh()) | ||
if err != nil { | ||
log.Fatalln("Unable to start worker", err) | ||
} | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,79 @@ | ||
package earlyreturn | ||
|
||
import ( | ||
"errors" | ||
"fmt" | ||
"time" | ||
|
||
"go.temporal.io/sdk/workflow" | ||
) | ||
|
||
const ( | ||
UpdateName = "early-return" | ||
TaskQueueName = "early-return-tq" | ||
activityTimeout = 2 * time.Second | ||
earlyReturnTimeout = 5 * time.Second | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. This is aggressive. Our usual advice is to have more generous timeouts but to monitor latencies and keep them low. One common heuristic: Calibrate this number relative to your overall remaining client timeout. So, if your client will timeout in 29 more seconds, you might choose 28s to give time to return and report the correct error. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Curious if @cretz 's advice would be similar. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Completely situational I think. No strong opinion. Arguably the caller should determine how long they're willing to wait. A timer inside a workflow does not account for, say, the workflow being slow to start. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I've removed the "Await" timeout ( And I've bumped the local activity timeout to 5s now; and the async activity to 30s. |
||
) | ||
|
||
type Transaction struct { | ||
ID string | ||
FromAccount string | ||
ToAccount string | ||
Amount float64 | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Usually a sin these days when talking about money to use floats There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I had the same thought at first, but I figured it's more intuitive this way in the context of a sample? If this has shifted and I didn't get the memo, I'm happy to change it. I didn't want to add extra complexity/confusion. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think int would be better, I doubt it adds complexity. We do this in our tutorial too at https://github.com/temporalio/money-transfer-project-template-go/blob/2bb1672af07cb76d449f14beb046e412f44a7afb/shared.go#L12 There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I see 👍 I'll change it. I thought this would go into the idea of representing cents, too, but the linked example just uses "250" without any denomination. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I'd be ok if you documented that it was in cents or added |
||
} | ||
|
||
// Workflow processes a transaction in two phases. First, the transaction is initialized, and if successful, | ||
// it proceeds to completion. However, if initialization fails - due to validation errors or transient | ||
// issues (e.g., network connectivity problems) - the transaction is cancelled. | ||
// | ||
// By utilizing Update-with-Start, the client can initiate the workflow and immediately receive the result of | ||
// the initialization in a single round trip, even before the transaction processing completes. The remainder | ||
// of the transaction is then processed asynchronously. | ||
func Workflow(ctx workflow.Context, tx Transaction) error { | ||
var initErr error | ||
var initDone bool | ||
logger := workflow.GetLogger(ctx) | ||
|
||
if err := workflow.SetUpdateHandler( | ||
ctx, | ||
UpdateName, | ||
func(ctx workflow.Context) error { | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Feel free to make a struct with your state and your run as a method and your update handler as a method instead of all in one function. What is here is fine of course, but usually when workflows branch out to handlers and many anonymous functions, it is clearer to use traditional structs with method declarations. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Good idea 👍 Only part I don't quite follow is the "run as a method". Is that possible in the Go SDK? I saw an error when trying to register the workflow method of the struct and couldn't find any example doing that (only for activities). There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more.
You'd do the wrapping w/ a one-liner, so something like: type myWorkflow struct { SomeState }
func MyWorkflow(ctx workflow.Context, someState SomeState) (*SomeResult, error) {
return myWorkflow{ someState }.run(ctx)
}
func (m *myWorkflow) run(ctx workflow.Context) (*SomeResult, error) {
// This kind of setup could go into a newMyWorkflow(...) call instead of in here
if err := workflow.SetUpdateHandler(ctx, "myUpdate", m.myUpdate); err != nil {
return nil, err
}
panic("TODO")
}
func (m *myWorkflow) myUpdate(ctx workflow.Context, someParam SomeParam) (*SomeUpdateResult, error) {
panic("TODO")
} There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 👍 I thought I might have missed a trick to do it with a single method |
||
condition := func() bool { return initDone } | ||
if completed, err := workflow.AwaitWithTimeout(ctx, earlyReturnTimeout, condition); err != nil { | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think you should leave how long a caller is willing to wait for the initial update up to them unless it's really important to differentiate start-to-update timeout from schedule-to-update timeout. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Okay; I thought there was a risk that the caller might accidentally wait indefinitely if they don't specify a deadline on their end. But I just turned off the worker, and the ExecuteWorkflow request times out after 10s, even though I'm using I'm learning a lot about writing workflows right now. |
||
return fmt.Errorf("update cancelled: %w", err) | ||
} else if !completed { | ||
return errors.New("update timed out") | ||
} | ||
return initErr | ||
}, | ||
); err != nil { | ||
return err | ||
} | ||
|
||
// Phase 1: Initialize the transaction synchronously. | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Arguably this logic could be flipped and users may prefer that in many scenarios. Can flip where the update is the init and the primary workflow waits for an init update before continuing. There are tradeoffs to both. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. In all my examples until now, I've actually had it flipped. Drew convinced me to do it the other way around, but I'm not quite sure anymore why. What makes you say that the other way might be more preferable? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Since updates are not durable on admitted that is why we did it this way so this is the only safe way to write this type of workflow. if I remember correctly There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I don't necessarily think it's more preferable, there are just tradeoffs. The main tradeoff is probably what you want the workflow to do when it's not called via update with start. If you want it to function normally, no problem, if you want it to wait for an update to get it moving, probably want logic flipped. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It isn't more preferable this is the only safe way to write it since update with start is not transactional There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. My main reasoning is what chad said: you want the workflow to function properly when the client doesn't call it with an update. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more.
Do we at least guarantee the update and the start are in the same task? If we don't, all latency bets are off anyways. But whether primary workflow waits on init from update or update waits on init from primary workflow is immaterial I'd think (except if the update can come in a separate task which would be a concern). There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. We do guarantee it for Update-with-Start. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 👍 Then yeah I think it's probably just semantics on which coroutine waits on the other and probably doesn't matter There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Another strong reason to do it this way is that, if the update did the init, then the workflow author has to make sure the workflow is correct in the face of multiple calls to the update handler, i.e. normal updates being sent subsequent to the update with start. But with all steps in the main workflow, multiple calls to the update handler are automatically correct. |
||
// | ||
// By using a local activity, an additional server roundtrip is avoided. | ||
// See https://docs.temporal.io/activities#local-activity for more details. | ||
|
||
activityOptions := workflow.WithLocalActivityOptions(ctx, workflow.LocalActivityOptions{ | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I doubt you'll want the default retry options with such an aggressive schedule to close of 2s |
||
ScheduleToCloseTimeout: activityTimeout, | ||
}) | ||
initErr = workflow.ExecuteLocalActivity(activityOptions, InitTransaction, tx).Get(ctx, nil) | ||
initDone = true | ||
|
||
// Phase 2: Complete or cancel the transaction asychronously. | ||
activityCtx := workflow.WithActivityOptions(ctx, workflow.ActivityOptions{ | ||
StartToCloseTimeout: 10 * time.Second, | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It is confusing that the There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Right; I've just made them global to make it easier to see at a glance what the timeouts are without reading line-by-line. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. But you've only made some global and the global name is ambiguous because it's not general activity timeout (that's hardcoded right here), it's init transaction timeout. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. nit: can you use a different, longer timeout here? since this is the async part, and I think 10s was used elsewhere? I think 30s is a fairly standard timeout for a rando activity. |
||
}) | ||
if initErr != nil { | ||
logger.Info("cancelling transaction due to error: %v", initErr) | ||
|
||
// Transaction failed to be initialized or not quickly enough; cancel the transaction. | ||
return workflow.ExecuteActivity(activityCtx, CancelTransaction, tx).Get(ctx, nil) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Not usually a common practice to swallow an error as an info-level logger and possibly return success. Usually you would want to mark the workflow failed for various observability reasons. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I see your point. My only worry is that users wouldn't be able to distinguish between "failed to init" and "failed to cancel/complete" - which might require very different actions. At the same time, they would probably have some kind of monitoring themselves? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. What I mean here is that if |
||
} | ||
|
||
logger.Info("completing transaction") | ||
|
||
// Transaction was initialized successfully; complete the transaction. | ||
return workflow.ExecuteActivity(activityCtx, CompleteTransaction, tx).Get(ctx, nil) | ||
} |
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.
I understand we want to demonstrate low latency, but this is a pretty aggressive timeout. But it is probably ok.
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.
Yeah, the idea for the sample is to push the low latency story; and this is actually on the upper end of what I'm hearing for customer use cases.
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.
If that's the case, may not want a default retry policy with an initial interval of a second. May actually want max attempts as 1.
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.
I would be as lax as you can on these timeouts. Don't want to unnecessarily fail requests that would have otherwise succeeded. So if the overall workflow task timeout is 10s, maybe give it 9 or 10s?