1
package org.apache.spark.examples.kafkaToflink;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.PrintStream;
import java.nio.charset.StandardCharsets;
import java.util.Properties;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.sink.RichSinkFunction;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer010;
import org.apache.flink.streaming.util.serialization.SimpleStringSchema;
import com.microsoft.azure.datalake.store.ADLException;
import com.microsoft.azure.datalake.store.ADLFileOutputStream;
import com.microsoft.azure.datalake.store.ADLStoreClient;
import com.microsoft.azure.datalake.store.IfExists;
import com.microsoft.azure.datalake.store.oauth2.AccessTokenProvider;
import com.microsoft.azure.datalake.store.oauth2.ClientCredsTokenProvider;
import scala.util.parsing.combinator.testing.Str;
public class App {
public static void main(String[] args) throws Exception {
final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
Properties properties = new Properties();
properties.setProperty("bootstrap.servers", "192.168.1.72:9092");
properties.setProperty("group.id", "test");
DataStream<String> stream = env.addSource(
new FlinkKafkaConsumer010<String>("tenant", new SimpleStringSchema(), properties), "Kafka_Source");
stream.addSink(new ADLSink()).name("Custom_Sink").setParallelism(128);
env.execute("App");
}
}
class ADLSink<String> extends RichSinkFunction<String> {
private java.lang.String clientId = "***********";
private java.lang.String authTokenEndpoint = "***************";
private java.lang.String clientKey = "*****************";
private java.lang.String accountFQDN = "****************";
private java.lang.String filename = "/Bitfinex/ETHBTC/ORDERBOOK/ORDERBOOK.json";
@Override
public void invoke(String value) {
AccessTokenProvider provider = new ClientCredsTokenProvider(authTokenEndpoint, clientId, clientKey);
ADLStoreClient client = ADLStoreClient.createClient(accountFQDN, provider);
try {
client.setPermission(filename, "744");
ADLFileOutputStream stream = client.getAppendStream(filename);
System.out.println(value);
stream.write(value.toString().getBytes());
stream.close();
} catch (ADLException e) {
System.out.println(e.requestId);
} catch (Exception e) {
System.out.println(e.getMessage());
System.out.println(e.getCause());
}
}
}
我不斷地嘗試使用while循環附加一個位於Azure數據湖Store中的文件。但有時候會出現這種情況,HTTP500操作APPEND失敗,啓動錯誤或10分鐘後有時會失敗。我正在使用java使用HTTP500操作APPEND失敗?
謝謝你提出的問題。 HTTP 500是一個「服務器」錯誤。我要求ADLS小組進行調查並可能與您聯繫。 –
您能否提供有關您是否(a)使用append或concurrentappend(b)這是發生在單個線程還是多個線程中的信息? –
@AmitKulkarni我正在使用append,這是發生在單線程 –