-
Notifications
You must be signed in to change notification settings - Fork 15
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Create SizeViolation bad row for oversized messages sent to Pubsub (c…
…lose #361)
- Loading branch information
Showing
6 changed files
with
226 additions
and
49 deletions.
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
112 changes: 112 additions & 0 deletions
112
...rc/main/scala/com/snowplowanalytics/snowplow/storage/bigquery/streamloader/Producer.scala
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 +1,112 @@ | ||
| /* | ||
| * Copyright (c) 2018-2023 Snowplow Analytics Ltd. All rights reserved. | ||
| * | ||
| * This program is licensed to you under the Apache License Version 2.0, | ||
| * and you may not use this file except in compliance with the Apache License Version 2.0. | ||
| * You may obtain a copy of the Apache License Version 2.0 at http://www.apache.org/licenses/LICENSE-2.0. | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, | ||
| * software distributed under the Apache License Version 2.0 is distributed on an | ||
| * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the Apache License Version 2.0 for the specific language governing permissions and limitations there under. | ||
| */ | ||
| package com.snowplowanalytics.snowplow.storage.bigquery.streamloader | ||
|
|
||
| import java.time.Instant | ||
| import java.nio.charset.StandardCharsets | ||
|
|
||
| import cats.implicits._ | ||
|
|
||
| import cats.effect.{Async, Resource} | ||
|
|
||
| import com.permutive.pubsub.producer.{Model, PubsubProducer} | ||
| import com.permutive.pubsub.producer.encoder.MessageEncoder | ||
| import com.permutive.pubsub.producer.grpc.{GooglePubsubProducer, PubsubProducerConfig} | ||
|
|
||
| import com.snowplowanalytics.snowplow.badrows.{BadRow, Failure, Payload => BadRowPayload} | ||
|
|
||
| import org.typelevel.log4cats.Logger | ||
|
|
||
| import scala.concurrent.duration._ | ||
|
|
||
| trait Producer[F[_], A] { | ||
| def produce(data: A): F[Unit] | ||
| } | ||
|
|
||
| object Producer { | ||
|
|
||
| val MaxPayloadLength = 9000000 // Stay under Pubsub Maximum of 10MB | ||
|
|
||
| def mkProducer[F[_]: Async: Logger, A: MessageEncoder]( | ||
| projectId: String, | ||
| topic: String, | ||
| batchSize: Long, | ||
| delay: FiniteDuration, | ||
| oversizeBadRowProducer: Producer[F, BadRow.SizeViolation] | ||
| ): Resource[F, Producer[F, A]] = | ||
| mkPubsubProducer[F, A](projectId, topic, batchSize, delay).map { p => | ||
| (data: A) => produceWrtToSize[F, A](data, p.produce(_).void, oversizeBadRowProducer) | ||
| } | ||
|
|
||
| def mkBadRowProducers[F[_]: Async: Logger]( | ||
| projectId: String, | ||
| topic: String, | ||
| batchSize: Long, | ||
| delay: FiniteDuration | ||
| ): Resource[F, (Producer[F, BadRow], Producer[F, BadRow.SizeViolation])] = | ||
| mkPubsubProducer[F, BadRow](projectId, topic, batchSize, delay).map { p => | ||
| val badRowProducer = new Producer[F, BadRow] { | ||
| override def produce(badRow: BadRow): F[Unit] = { | ||
| produceWrtToSize[F, BadRow](badRow, p.produce(_).void, p.produce(_).void) | ||
| } | ||
| } | ||
| val oversizeBadRowProducer = new Producer[F, BadRow.SizeViolation] { | ||
| override def produce(data: BadRow.SizeViolation): F[Unit] = | ||
| p.produce(data).void | ||
| } | ||
| (badRowProducer, oversizeBadRowProducer) | ||
| } | ||
|
|
||
| /** Construct a PubSub producer. */ | ||
| private def mkPubsubProducer[F[_]: Async: Logger, A: MessageEncoder]( | ||
| projectId: String, | ||
| topic: String, | ||
| batchSize: Long, | ||
| delay: FiniteDuration | ||
| ): Resource[F, PubsubProducer[F, A]] = | ||
| GooglePubsubProducer.of[F, A]( | ||
| Model.ProjectId(projectId), | ||
| Model.Topic(topic), | ||
| config = PubsubProducerConfig[F]( | ||
| batchSize = batchSize, | ||
| delayThreshold = delay, | ||
| onFailedTerminate = e => Logger[F].error(e)(s"Error in PubSub producer") | ||
| ) | ||
| ) | ||
|
|
||
| def produceWrtToSize[F[_]: Async, A: MessageEncoder]( | ||
| data: A, | ||
| producer: Producer[F, A], | ||
| oversizeBadRowProducer: Producer[F, BadRow.SizeViolation] | ||
| ): F[Unit] = { | ||
| val dataSize = getSize(data) | ||
| if (dataSize >= MaxPayloadLength) { | ||
| val msg = s"Pubsub message exceeds allowed size" | ||
| val payload = MessageEncoder[A].encode(data) | ||
| .map(bytes => new String(bytes, StandardCharsets.UTF_8)) | ||
| .getOrElse("Pubsub message can't be converted to string") | ||
| .take(MaxPayloadLength / 10) | ||
| val badRow = BadRow.SizeViolation( | ||
| processor, | ||
| Failure.SizeViolation(Instant.now(), MaxPayloadLength, dataSize, msg), | ||
| BadRowPayload.RawPayload(payload) | ||
| ) | ||
| oversizeBadRowProducer.produce(badRow) | ||
| } else { | ||
| producer.produce(data).void | ||
| } | ||
| } | ||
|
|
||
| private def getSize[A: MessageEncoder](a: A): Int = | ||
| MessageEncoder[A].encode(a).map(_.length).getOrElse(Int.MaxValue) | ||
| } |
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
75 changes: 75 additions & 0 deletions
75
...est/scala/com/snowplowanalytics/snowplow/storage/bigquery/streamloader/ProducerSpec.scala
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 +1,75 @@ | ||
| /* | ||
| * Copyright (c) 2018-2023 Snowplow Analytics Ltd. All rights reserved. | ||
| * | ||
| * This program is licensed to you under the Apache License Version 2.0, | ||
| * and you may not use this file except in compliance with the Apache License Version 2.0. | ||
| * You may obtain a copy of the Apache License Version 2.0 at http://www.apache.org/licenses/LICENSE-2.0. | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, | ||
| * software distributed under the Apache License Version 2.0 is distributed on an | ||
| * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the Apache License Version 2.0 for the specific language governing permissions and limitations there under. | ||
| */ | ||
| package com.snowplowanalytics.snowplow.storage.bigquery.streamloader | ||
|
|
||
| import scala.collection.mutable.ListBuffer | ||
| import scala.util.Random | ||
| import java.nio.charset.StandardCharsets | ||
| import cats.effect.IO | ||
| import cats.effect.unsafe.IORuntime | ||
| import com.permutive.pubsub.producer.encoder.MessageEncoder | ||
| import com.snowplowanalytics.snowplow.badrows.{BadRow, Payload, Failure} | ||
| import org.specs2.mutable.Specification | ||
|
|
||
| class ProducerSpec extends Specification { | ||
|
|
||
| implicit val runtime: IORuntime = IORuntime.global | ||
|
|
||
| implicit val stringEncoder: MessageEncoder[String] = { str => | ||
| Right(str.getBytes(StandardCharsets.UTF_8)) | ||
| } | ||
|
|
||
| class MockProducer[A] extends Producer[IO, A] { | ||
| val buf: ListBuffer[A] = ListBuffer.empty | ||
| override def produce(data: A): IO[Unit] = IO.delay(buf.addOne(data)) | ||
| def get: List[A] = buf.toList | ||
| } | ||
|
|
||
| "produceWrtToSize" should { | ||
| "send normal size messages to normal producer" in { | ||
| val producer = new MockProducer[String] | ||
| val oversizeBadRowProducer = new MockProducer[BadRow.SizeViolation] | ||
|
|
||
| val messages = (1 to 100).map(i => s"test-$i") | ||
|
|
||
| messages.foreach( | ||
| Producer.produceWrtToSize(_, producer, oversizeBadRowProducer).unsafeRunSync() | ||
| ) | ||
|
|
||
| producer.get must beEqualTo(messages) | ||
| oversizeBadRowProducer.get must beEmpty | ||
| } | ||
|
|
||
| "send oversize messages to oversize bad row producer" in { | ||
| val producer = new MockProducer[String] | ||
| val oversizeBadRowProducer = new MockProducer[BadRow.SizeViolation] | ||
|
|
||
| val messageSize = Producer.MaxPayloadLength + 1 | ||
| val message = Random.alphanumeric.take(messageSize).mkString | ||
|
|
||
| Producer.produceWrtToSize(message, producer, oversizeBadRowProducer).unsafeRunSync() | ||
|
|
||
| val expectedBadRowPayload = message.take(Producer.MaxPayloadLength / 10) | ||
|
|
||
| producer.get must beEmpty | ||
| oversizeBadRowProducer.get must beLike { | ||
| case List(BadRow.SizeViolation( | ||
| `processor`, | ||
| Failure.SizeViolation(_, Producer.MaxPayloadLength, `messageSize`, _), | ||
| Payload.RawPayload(`expectedBadRowPayload`) | ||
| )) => ok | ||
| } | ||
| } | ||
| } | ||
|
|
||
| } |