100 lines
3.4 KiB
Go
Raw Normal View History

package twilio
import (
feat(notification): use event worker pool (#8962) # Which Problems Are Solved The current handling of notification follows the same pattern as all other projections: Created events are handled sequentially (based on "position") by a handler. During the process, a lot of information is aggregated (user, texts, templates, ...). This leads to back pressure on the projection since the handling of events might take longer than the time before a new event (to be handled) is created. # How the Problems Are Solved - The current user notification handler creates separate notification events based on the user / session events. - These events contain all the present and required information including the userID. - These notification events get processed by notification workers, which gather the necessary information (recipient address, texts, templates) to send out these notifications. - If a notification fails, a retry event is created based on the current notification request including the current state of the user (this prevents race conditions, where a user is changed in the meantime and the notification already gets the new state). - The retry event will be handled after a backoff delay. This delay increases with every attempt. - If the configured amount of attempts is reached or the message expired (based on config), a cancel event is created, letting the workers know, the notification must no longer be handled. - In case of successful send, a sent event is created for the notification aggregate and the existing "sent" events for the user / session object is stored. - The following is added to the defaults.yaml to allow configuration of the notification workers: ```yaml Notifications: # The amount of workers processing the notification request events. # If set to 0, no notification request events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. Workers: 1 # ZITADEL_NOTIFIACATIONS_WORKERS # The amount of events a single worker will process in a run. BulkLimit: 10 # ZITADEL_NOTIFIACATIONS_BULKLIMIT # Time interval between scheduled notifications for request events RequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_REQUEUEEVERY # The amount of workers processing the notification retry events. # If set to 0, no notification retry events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. RetryWorkers: 1 # ZITADEL_NOTIFIACATIONS_RETRYWORKERS # Time interval between scheduled notifications for retry events RetryRequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_RETRYREQUEUEEVERY # Only instances are projected, for which at least a projection-relevant event exists within the timeframe # from HandleActiveInstances duration in the past until the projection's current time # If set to 0 (default), every instance is always considered active HandleActiveInstances: 0s # ZITADEL_NOTIFIACATIONS_HANDLEACTIVEINSTANCES # The maximum duration a transaction remains open # before it spots left folding additional events # and updates the table. TransactionDuration: 1m # ZITADEL_NOTIFIACATIONS_TRANSACTIONDURATION # Automatically cancel the notification after the amount of failed attempts MaxAttempts: 3 # ZITADEL_NOTIFIACATIONS_MAXATTEMPTS # Automatically cancel the notification if it cannot be handled within a specific time MaxTtl: 5m # ZITADEL_NOTIFIACATIONS_MAXTTL # Failed attempts are retried after a confogired delay (with exponential backoff). # Set a minimum and maximum delay and a factor for the backoff MinRetryDelay: 1s # ZITADEL_NOTIFIACATIONS_MINRETRYDELAY MaxRetryDelay: 20s # ZITADEL_NOTIFIACATIONS_MAXRETRYDELAY # Any factor below 1 will be set to 1 RetryDelayFactor: 1.5 # ZITADEL_NOTIFIACATIONS_RETRYDELAYFACTOR ``` # Additional Changes None # Additional Context - closes #8931
2024-11-27 16:01:17 +01:00
"errors"
"github.com/twilio/twilio-go"
twilioClient "github.com/twilio/twilio-go/client"
openapi "github.com/twilio/twilio-go/rest/api/v2010"
verify "github.com/twilio/twilio-go/rest/verify/v2"
"github.com/zitadel/logging"
2022-06-13 08:34:11 +02:00
"github.com/zitadel/zitadel/internal/eventstore"
"github.com/zitadel/zitadel/internal/notification/channels"
"github.com/zitadel/zitadel/internal/notification/messages"
"github.com/zitadel/zitadel/internal/zerrors"
)
const (
aggregateTypeNotification = "notification"
)
func InitChannel(config Config) channels.NotificationChannel {
feat(notification): use event worker pool (#8962) # Which Problems Are Solved The current handling of notification follows the same pattern as all other projections: Created events are handled sequentially (based on "position") by a handler. During the process, a lot of information is aggregated (user, texts, templates, ...). This leads to back pressure on the projection since the handling of events might take longer than the time before a new event (to be handled) is created. # How the Problems Are Solved - The current user notification handler creates separate notification events based on the user / session events. - These events contain all the present and required information including the userID. - These notification events get processed by notification workers, which gather the necessary information (recipient address, texts, templates) to send out these notifications. - If a notification fails, a retry event is created based on the current notification request including the current state of the user (this prevents race conditions, where a user is changed in the meantime and the notification already gets the new state). - The retry event will be handled after a backoff delay. This delay increases with every attempt. - If the configured amount of attempts is reached or the message expired (based on config), a cancel event is created, letting the workers know, the notification must no longer be handled. - In case of successful send, a sent event is created for the notification aggregate and the existing "sent" events for the user / session object is stored. - The following is added to the defaults.yaml to allow configuration of the notification workers: ```yaml Notifications: # The amount of workers processing the notification request events. # If set to 0, no notification request events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. Workers: 1 # ZITADEL_NOTIFIACATIONS_WORKERS # The amount of events a single worker will process in a run. BulkLimit: 10 # ZITADEL_NOTIFIACATIONS_BULKLIMIT # Time interval between scheduled notifications for request events RequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_REQUEUEEVERY # The amount of workers processing the notification retry events. # If set to 0, no notification retry events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. RetryWorkers: 1 # ZITADEL_NOTIFIACATIONS_RETRYWORKERS # Time interval between scheduled notifications for retry events RetryRequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_RETRYREQUEUEEVERY # Only instances are projected, for which at least a projection-relevant event exists within the timeframe # from HandleActiveInstances duration in the past until the projection's current time # If set to 0 (default), every instance is always considered active HandleActiveInstances: 0s # ZITADEL_NOTIFIACATIONS_HANDLEACTIVEINSTANCES # The maximum duration a transaction remains open # before it spots left folding additional events # and updates the table. TransactionDuration: 1m # ZITADEL_NOTIFIACATIONS_TRANSACTIONDURATION # Automatically cancel the notification after the amount of failed attempts MaxAttempts: 3 # ZITADEL_NOTIFIACATIONS_MAXATTEMPTS # Automatically cancel the notification if it cannot be handled within a specific time MaxTtl: 5m # ZITADEL_NOTIFIACATIONS_MAXTTL # Failed attempts are retried after a confogired delay (with exponential backoff). # Set a minimum and maximum delay and a factor for the backoff MinRetryDelay: 1s # ZITADEL_NOTIFIACATIONS_MINRETRYDELAY MaxRetryDelay: 20s # ZITADEL_NOTIFIACATIONS_MAXRETRYDELAY # Any factor below 1 will be set to 1 RetryDelayFactor: 1.5 # ZITADEL_NOTIFIACATIONS_RETRYDELAYFACTOR ``` # Additional Changes None # Additional Context - closes #8931
2024-11-27 16:01:17 +01:00
client := twilio.NewRestClientWithParams(twilio.ClientParams{Username: config.SID, Password: config.Token})
2022-06-13 08:34:11 +02:00
logging.Debug("successfully initialized twilio sms channel")
return channels.HandleMessageFunc(func(message channels.Message) error {
twilioMsg, ok := message.(*messages.SMS)
if !ok {
return zerrors.ThrowInternal(nil, "TWILI-s0pLc", "message is not SMS")
}
if config.VerifyServiceSID != "" {
params := &verify.CreateVerificationParams{}
params.SetTo(twilioMsg.RecipientPhoneNumber)
params.SetChannel("sms")
resp, err := client.VerifyV2.CreateVerification(config.VerifyServiceSID, params)
feat(notification): use event worker pool (#8962) # Which Problems Are Solved The current handling of notification follows the same pattern as all other projections: Created events are handled sequentially (based on "position") by a handler. During the process, a lot of information is aggregated (user, texts, templates, ...). This leads to back pressure on the projection since the handling of events might take longer than the time before a new event (to be handled) is created. # How the Problems Are Solved - The current user notification handler creates separate notification events based on the user / session events. - These events contain all the present and required information including the userID. - These notification events get processed by notification workers, which gather the necessary information (recipient address, texts, templates) to send out these notifications. - If a notification fails, a retry event is created based on the current notification request including the current state of the user (this prevents race conditions, where a user is changed in the meantime and the notification already gets the new state). - The retry event will be handled after a backoff delay. This delay increases with every attempt. - If the configured amount of attempts is reached or the message expired (based on config), a cancel event is created, letting the workers know, the notification must no longer be handled. - In case of successful send, a sent event is created for the notification aggregate and the existing "sent" events for the user / session object is stored. - The following is added to the defaults.yaml to allow configuration of the notification workers: ```yaml Notifications: # The amount of workers processing the notification request events. # If set to 0, no notification request events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. Workers: 1 # ZITADEL_NOTIFIACATIONS_WORKERS # The amount of events a single worker will process in a run. BulkLimit: 10 # ZITADEL_NOTIFIACATIONS_BULKLIMIT # Time interval between scheduled notifications for request events RequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_REQUEUEEVERY # The amount of workers processing the notification retry events. # If set to 0, no notification retry events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. RetryWorkers: 1 # ZITADEL_NOTIFIACATIONS_RETRYWORKERS # Time interval between scheduled notifications for retry events RetryRequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_RETRYREQUEUEEVERY # Only instances are projected, for which at least a projection-relevant event exists within the timeframe # from HandleActiveInstances duration in the past until the projection's current time # If set to 0 (default), every instance is always considered active HandleActiveInstances: 0s # ZITADEL_NOTIFIACATIONS_HANDLEACTIVEINSTANCES # The maximum duration a transaction remains open # before it spots left folding additional events # and updates the table. TransactionDuration: 1m # ZITADEL_NOTIFIACATIONS_TRANSACTIONDURATION # Automatically cancel the notification after the amount of failed attempts MaxAttempts: 3 # ZITADEL_NOTIFIACATIONS_MAXATTEMPTS # Automatically cancel the notification if it cannot be handled within a specific time MaxTtl: 5m # ZITADEL_NOTIFIACATIONS_MAXTTL # Failed attempts are retried after a confogired delay (with exponential backoff). # Set a minimum and maximum delay and a factor for the backoff MinRetryDelay: 1s # ZITADEL_NOTIFIACATIONS_MINRETRYDELAY MaxRetryDelay: 20s # ZITADEL_NOTIFIACATIONS_MAXRETRYDELAY # Any factor below 1 will be set to 1 RetryDelayFactor: 1.5 # ZITADEL_NOTIFIACATIONS_RETRYDELAYFACTOR ``` # Additional Changes None # Additional Context - closes #8931
2024-11-27 16:01:17 +01:00
// In case of any client error (4xx), we should not retry sending the verification code
// as it would be a waste of resources and could potentially result in a rate limit.
feat(notification): use event worker pool (#8962) # Which Problems Are Solved The current handling of notification follows the same pattern as all other projections: Created events are handled sequentially (based on "position") by a handler. During the process, a lot of information is aggregated (user, texts, templates, ...). This leads to back pressure on the projection since the handling of events might take longer than the time before a new event (to be handled) is created. # How the Problems Are Solved - The current user notification handler creates separate notification events based on the user / session events. - These events contain all the present and required information including the userID. - These notification events get processed by notification workers, which gather the necessary information (recipient address, texts, templates) to send out these notifications. - If a notification fails, a retry event is created based on the current notification request including the current state of the user (this prevents race conditions, where a user is changed in the meantime and the notification already gets the new state). - The retry event will be handled after a backoff delay. This delay increases with every attempt. - If the configured amount of attempts is reached or the message expired (based on config), a cancel event is created, letting the workers know, the notification must no longer be handled. - In case of successful send, a sent event is created for the notification aggregate and the existing "sent" events for the user / session object is stored. - The following is added to the defaults.yaml to allow configuration of the notification workers: ```yaml Notifications: # The amount of workers processing the notification request events. # If set to 0, no notification request events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. Workers: 1 # ZITADEL_NOTIFIACATIONS_WORKERS # The amount of events a single worker will process in a run. BulkLimit: 10 # ZITADEL_NOTIFIACATIONS_BULKLIMIT # Time interval between scheduled notifications for request events RequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_REQUEUEEVERY # The amount of workers processing the notification retry events. # If set to 0, no notification retry events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. RetryWorkers: 1 # ZITADEL_NOTIFIACATIONS_RETRYWORKERS # Time interval between scheduled notifications for retry events RetryRequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_RETRYREQUEUEEVERY # Only instances are projected, for which at least a projection-relevant event exists within the timeframe # from HandleActiveInstances duration in the past until the projection's current time # If set to 0 (default), every instance is always considered active HandleActiveInstances: 0s # ZITADEL_NOTIFIACATIONS_HANDLEACTIVEINSTANCES # The maximum duration a transaction remains open # before it spots left folding additional events # and updates the table. TransactionDuration: 1m # ZITADEL_NOTIFIACATIONS_TRANSACTIONDURATION # Automatically cancel the notification after the amount of failed attempts MaxAttempts: 3 # ZITADEL_NOTIFIACATIONS_MAXATTEMPTS # Automatically cancel the notification if it cannot be handled within a specific time MaxTtl: 5m # ZITADEL_NOTIFIACATIONS_MAXTTL # Failed attempts are retried after a confogired delay (with exponential backoff). # Set a minimum and maximum delay and a factor for the backoff MinRetryDelay: 1s # ZITADEL_NOTIFIACATIONS_MINRETRYDELAY MaxRetryDelay: 20s # ZITADEL_NOTIFIACATIONS_MAXRETRYDELAY # Any factor below 1 will be set to 1 RetryDelayFactor: 1.5 # ZITADEL_NOTIFIACATIONS_RETRYDELAYFACTOR ``` # Additional Changes None # Additional Context - closes #8931
2024-11-27 16:01:17 +01:00
var twilioErr *twilioClient.TwilioRestError
if errors.As(err, &twilioErr) && twilioErr.Status >= 400 && twilioErr.Status < 500 {
userID, notificationID := userAndNotificationIDsFromEvent(twilioMsg.TriggeringEvent)
logging.WithFields(
"error", twilioErr.Message,
"status", twilioErr.Status,
"code", twilioErr.Code,
"instanceID", twilioMsg.TriggeringEvent.Aggregate().InstanceID,
"userID", userID,
"notificationID", notificationID).
Warn("twilio create verification error")
feat(notification): use event worker pool (#8962) # Which Problems Are Solved The current handling of notification follows the same pattern as all other projections: Created events are handled sequentially (based on "position") by a handler. During the process, a lot of information is aggregated (user, texts, templates, ...). This leads to back pressure on the projection since the handling of events might take longer than the time before a new event (to be handled) is created. # How the Problems Are Solved - The current user notification handler creates separate notification events based on the user / session events. - These events contain all the present and required information including the userID. - These notification events get processed by notification workers, which gather the necessary information (recipient address, texts, templates) to send out these notifications. - If a notification fails, a retry event is created based on the current notification request including the current state of the user (this prevents race conditions, where a user is changed in the meantime and the notification already gets the new state). - The retry event will be handled after a backoff delay. This delay increases with every attempt. - If the configured amount of attempts is reached or the message expired (based on config), a cancel event is created, letting the workers know, the notification must no longer be handled. - In case of successful send, a sent event is created for the notification aggregate and the existing "sent" events for the user / session object is stored. - The following is added to the defaults.yaml to allow configuration of the notification workers: ```yaml Notifications: # The amount of workers processing the notification request events. # If set to 0, no notification request events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. Workers: 1 # ZITADEL_NOTIFIACATIONS_WORKERS # The amount of events a single worker will process in a run. BulkLimit: 10 # ZITADEL_NOTIFIACATIONS_BULKLIMIT # Time interval between scheduled notifications for request events RequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_REQUEUEEVERY # The amount of workers processing the notification retry events. # If set to 0, no notification retry events will be handled. This can be useful when running in # multi binary / pod setup and allowing only certain executables to process the events. RetryWorkers: 1 # ZITADEL_NOTIFIACATIONS_RETRYWORKERS # Time interval between scheduled notifications for retry events RetryRequeueEvery: 2s # ZITADEL_NOTIFIACATIONS_RETRYREQUEUEEVERY # Only instances are projected, for which at least a projection-relevant event exists within the timeframe # from HandleActiveInstances duration in the past until the projection's current time # If set to 0 (default), every instance is always considered active HandleActiveInstances: 0s # ZITADEL_NOTIFIACATIONS_HANDLEACTIVEINSTANCES # The maximum duration a transaction remains open # before it spots left folding additional events # and updates the table. TransactionDuration: 1m # ZITADEL_NOTIFIACATIONS_TRANSACTIONDURATION # Automatically cancel the notification after the amount of failed attempts MaxAttempts: 3 # ZITADEL_NOTIFIACATIONS_MAXATTEMPTS # Automatically cancel the notification if it cannot be handled within a specific time MaxTtl: 5m # ZITADEL_NOTIFIACATIONS_MAXTTL # Failed attempts are retried after a confogired delay (with exponential backoff). # Set a minimum and maximum delay and a factor for the backoff MinRetryDelay: 1s # ZITADEL_NOTIFIACATIONS_MINRETRYDELAY MaxRetryDelay: 20s # ZITADEL_NOTIFIACATIONS_MAXRETRYDELAY # Any factor below 1 will be set to 1 RetryDelayFactor: 1.5 # ZITADEL_NOTIFIACATIONS_RETRYDELAYFACTOR ``` # Additional Changes None # Additional Context - closes #8931
2024-11-27 16:01:17 +01:00
return channels.NewCancelError(twilioErr)
}
if err != nil {
return zerrors.ThrowInternal(err, "TWILI-0s9f2", "could not send verification")
}
logging.WithFields("sid", resp.Sid, "status", resp.Status).Debug("verification sent")
twilioMsg.VerificationID = resp.Sid
return nil
}
content, err := twilioMsg.GetContent()
if err != nil {
return err
}
params := &openapi.CreateMessageParams{}
params.SetTo(twilioMsg.RecipientPhoneNumber)
params.SetFrom(twilioMsg.SenderPhoneNumber)
params.SetBody(content)
m, err := client.Api.CreateMessage(params)
if err != nil {
return zerrors.ThrowInternal(err, "TWILI-osk3S", "could not send message")
}
2022-06-13 08:34:11 +02:00
logging.WithFields("message_sid", m.Sid, "status", m.Status).Debug("sms sent")
return nil
})
}
func userAndNotificationIDsFromEvent(event eventstore.Event) (userID, notificationID string) {
aggID := event.Aggregate().ID
// we cannot cast to the actual event type because of circular dependencies
// so we just check the type...
if event.Aggregate().Type != aggregateTypeNotification {
// in case it's not a notification event, we can directly return the aggregate ID (as it's a user event)
return aggID, ""
}
// ...and unmarshal the event data from the notification event into a struct that contains the fields we need
var data struct {
Request struct {
UserID string `json:"userID"`
} `json:"request"`
}
if err := event.Unmarshal(&data); err != nil {
return "", aggID
}
return data.Request.UserID, aggID
}