Skip to content
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

[Improvement] no need to wait after a successful retry #138

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -90,6 +90,10 @@ public interface ConfigurationOptions {

int DORIS_SINK_BATCH_INTERVAL_MS_DEFAULT = 50;

String DORIS_SINK_RETRY_INTERVAL_MS = "doris.sink.retry.interval.ms";

int DORIS_SINK_RETRY_INTERVAL_MS_DEFAULT = 50;

/**
* set types to ignore, split by comma
* e.g.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -176,7 +176,6 @@ private[spark] object Utils {
val result = Try(f)
result match {
case Success(result) =>
LockSupport.parkNanos(interval.toNanos)
Success(result)
case Failure(exception: T) if retryTimes > 0 =>
logger.warn(s"Execution failed caused by: ", exception)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,8 @@ import java.io.IOException
import java.time.Duration
import java.util
import java.util.Objects
import java.util.concurrent.TimeUnit
import java.util.concurrent.locks.LockSupport
import scala.collection.JavaConverters._
import scala.collection.mutable
import scala.util.{Failure, Success}
Expand All @@ -46,8 +48,10 @@ class DorisWriter(settings: SparkSettings) extends Serializable {
private val sinkTaskPartitionSize: Integer = settings.getIntegerProperty(ConfigurationOptions.DORIS_SINK_TASK_PARTITION_SIZE)
private val sinkTaskUseRepartition: Boolean = settings.getProperty(ConfigurationOptions.DORIS_SINK_TASK_USE_REPARTITION,
ConfigurationOptions.DORIS_SINK_TASK_USE_REPARTITION_DEFAULT.toString).toBoolean
private val batchInterValMs: Integer = settings.getIntegerProperty(ConfigurationOptions.DORIS_SINK_BATCH_INTERVAL_MS,
private val batchIntervalMs: Integer = settings.getIntegerProperty(ConfigurationOptions.DORIS_SINK_BATCH_INTERVAL_MS,
ConfigurationOptions.DORIS_SINK_BATCH_INTERVAL_MS_DEFAULT)
private val retryIntervalMs: Integer = settings.getIntegerProperty(ConfigurationOptions.DORIS_SINK_RETRY_INTERVAL_MS,
ConfigurationOptions.DORIS_SINK_RETRY_INTERVAL_MS_DEFAULT)

private val enable2PC: Boolean = settings.getBooleanProperty(ConfigurationOptions.DORIS_SINK_ENABLE_2PC,
ConfigurationOptions.DORIS_SINK_ENABLE_2PC_DEFAULT);
Expand Down Expand Up @@ -84,10 +88,12 @@ class DorisWriter(settings: SparkSettings) extends Serializable {
resultRdd.foreachPartition(iterator => {
while (iterator.hasNext) {
// do load batch with retries
Utils.retry[Int, Exception](maxRetryTimes, Duration.ofMillis(batchInterValMs.toLong), logger) {
Utils.retry[Int, Exception](maxRetryTimes, Duration.ofMillis(retryIntervalMs.toLong), logger) {
loadFunc(iterator.asJava, schema)
} match {
case Success(txnId) => if (enable2PC) handleLoadSuccess(txnId, preCommittedTxnAcc)
case Success(txnId) =>
if (enable2PC) handleLoadSuccess(txnId, preCommittedTxnAcc)
LockSupport.parkNanos(TimeUnit.MILLISECONDS.toNanos(batchIntervalMs.toLong))
case Failure(e) =>
if (enable2PC) handleLoadFailure(preCommittedTxnAcc)
throw new IOException(
Expand Down