기계 번역으로 제공되는 번역입니다. 제공된 번역과 원본 영어의 내용이 상충하는 경우에는 영어 버전이 우선합니다.

Amazon Neptune에 사용되는 AWS Lambda 함수 예제

Java, JavaScript, Python으로 작성된 다음 예제 AWS Lambda 함수는 fold().coalesce().unfold() 표현 양식을 사용하여 무작위로 생성된 ID로 단일 버텍스를 업서트하는 방법을 보여줍니다.

각 함수의 코드 대부분은 연결을 관리하고 오류가 발생할 경우 연결 및 쿼리를 다시 시도하는 보일러플레이트 코드입니다. 실제 애플리케이션 로직과 Gremlin 쿼리는 각각 doQuery() 및 query() 메서드에서 구현됩니다. 이 예제를 자체 Lambda 함수의 기반으로 사용하면 doQuery() 및 query() 수정에 집중할 수 있습니다.

함수는 실패한 쿼리를 5번 재시도하고 재시도 사이에 1초 동안 대기하도록 구성됩니다.

함수를 사용하려면 다음 Lambda 환경 변수에 값이 있어야 합니다.

Amazon Neptune용 Java Lambda 함수 예제

Java AWS Lambda 함수에 대해 고려해야 할 몇 가지 사항이 있습니다.

package com.amazonaws.examples.social;

import com.amazonaws.services.lambda.runtime.Context;
import com.amazonaws.services.lambda.runtime.RequestStreamHandler;
import com.evanlennick.retry4j.CallExecutor;
import com.evanlennick.retry4j.CallExecutorBuilder;
import com.evanlennick.retry4j.Status;
import com.evanlennick.retry4j.config.RetryConfig;
import com.evanlennick.retry4j.config.RetryConfigBuilder;
import org.apache.tinkerpop.gremlin.driver.Cluster;
import com.amazonaws.auth.DefaultAWSCredentialsProviderChain;
import com.amazonaws.neptune.auth.NeptuneNettyHttpSigV4Signer;
import org.apache.tinkerpop.gremlin.driver.remote.DriverRemoteConnection;
import org.apache.tinkerpop.gremlin.driver.ser.Serializers;
import org.apache.tinkerpop.gremlin.process.traversal.AnonymousTraversalSource;
import org.apache.tinkerpop.gremlin.process.traversal.dsl.graph.GraphTraversalSource;
import org.apache.tinkerpop.gremlin.structure.T;

import java.io.*;
import java.time.temporal.ChronoUnit;
import java.util.HashMap;
import java.util.Map;
import java.util.Random;
import java.util.concurrent.Callable;
import java.util.function.Function;

import static java.nio.charset.StandardCharsets.UTF_8;
import static org.apache.tinkerpop.gremlin.process.traversal.dsl.graph.__.addV;
import static org.apache.tinkerpop.gremlin.process.traversal.dsl.graph.__.unfold;

public class MyHandler implements RequestStreamHandler {

  private final GraphTraversalSource g;
  private final CallExecutor<Object> executor;
  private final Random idGenerator = new Random();

  public MyHandler() {

    this.g = AnonymousTraversalSource
            .traversal()
            .withRemote(DriverRemoteConnection.using(createCluster()));


    this.executor = new CallExecutorBuilder<Object>()
            .config(createRetryConfig())
            .build();

  }

  @Override
  public void handleRequest(InputStream input,
                            OutputStream output,
                            Context context) throws IOException {

    doQuery(input, output);
  }

  private void doQuery(InputStream input, OutputStream output) throws IOException {
    try {

      Map<String, Object> args = new HashMap<>();
      args.put("id", idGenerator.nextInt());

      String result = query(args);

      try (Writer writer = new BufferedWriter(new OutputStreamWriter(output, UTF_8))) {
          writer.write(result);
      }

    } finally {
        input.close();
        output.close();
    }
  }

  private String query(Map<String, Object> args) {
    int id = (int) args.get("id");

    @SuppressWarnings("unchecked")
    Callable<Object> query = () -> g.V(id)
      .fold()
      .coalesce(
        unfold(),
        addV("Person").property(T.id, id))
      .id().next();

    Status<Object> status = executor.execute(query);

    return status.getResult().toString();
  }

  private Cluster createCluster() {
    Cluster.Builder builder = Cluster.build()
                                     .addContactPoint(System.getenv("NEPTUNE_ENDPOINT"))
                                     .port(Integer.parseInt(System.getenv("NEPTUNE_PORT")))
                                     .enableSsl(true)
                                     .minConnectionPoolSize(1)
                                     .maxConnectionPoolSize(1)
                                     .serializer(Serializers.GRAPHBINARY_V1D0)
                                     .reconnectInterval(2000);

  if (Boolean.parseBoolean(getOptionalEnv("USE_IAM", "true"))) {
    // For versions of TinkerPop 3.4.11 or higher:
    builder.handshakeInterceptor( r ->
      {
        NeptuneNettyHttpSigV4Signer sigV4Signer = new NeptuneNettyHttpSigV4Signer(region, new DefaultAWSCredentialsProviderChain());
        sigV4Signer.signRequest(r);
        return r;
      }
    )

    // Versions of TinkerPop prior to 3.4.11 should use the following approach.
    // Be sure to adjust the  imports to include:
    //   import org.apache.tinkerpop.gremlin.driver.SigV4WebSocketChannelizer;
    //   builder = builder.channelizer(SigV4WebSocketChannelizer.class);
    
    return builder.create();
  }

  private RetryConfig createRetryConfig() {
    return new RetryConfigBuilder().retryOnCustomExceptionLogic(retryLogic())
                                   .withDelayBetweenTries(1000, ChronoUnit.MILLIS)
                                   .withMaxNumberOfTries(5)
                                   .withFixedBackoff()
                                   .build();
  }

  private Function<Exception, Boolean> retryLogic() {
    return e -> {
      StringWriter stringWriter = new StringWriter();
      e.printStackTrace(new PrintWriter(stringWriter));
      String message = stringWriter.toString();

      // Check for connection issues
      if ( message.contains("Timed out while waiting for an available host") ||
           message.contains("Timed-out waiting for connection on Host") ||
           message.contains("Connection to server is no longer active") ||
           message.contains("Connection reset by peer") ||
           message.contains("SSLEngine closed already") ||
           message.contains("Pool is shutdown") ||
           message.contains("ExtendedClosedChannelException") ||
           message.contains("Broken pipe")) {
        return true;
      }

      // Concurrent writes can sometimes trigger a ConcurrentModificationException.
      // In these circumstances you may want to backoff and retry.
      if (message.contains("ConcurrentModificationException")) {
          return true;
      }

      // If the primary fails over to a new instance, existing connections to the old primary will
      // throw a ReadOnlyViolationException. You may want to back and retry.
      if (message.contains("ReadOnlyViolationException")) {
          return true;
      }

      return false;
    };
  }

  private String getOptionalEnv(String name, String defaultValue) {
    String value = System.getenv(name);
    if (value != null && value.length() > 0) {
      return value;
    } else {
      return defaultValue;
    }
  }
}

함수에 재연결 로직을 포함하려면 Java 재연결 샘플을 참조하세요.

Amazon Neptune용 JavaScript Lambda 함수 예제

Javascript 코드

const gremlin = require('gremlin');
const async = require('async');
const {getUrlAndHeaders} = require('gremlin-aws-sigv4/lib/utils');

const traversal = gremlin.process.AnonymousTraversalSource.traversal;
const DriverRemoteConnection = gremlin.driver.DriverRemoteConnection;
const t = gremlin.process.t;
const __ = gremlin.process.statics;

let conn = null;
let g = null;

async function query(context) {

  const id = context.id;

  return g.V(id)
    .fold()
    .coalesce(
      __.unfold(), 
      __.addV('User').property(t.id, id)
    )
    .id().next();
}

async function doQuery() {
  const id = Math.floor(Math.random() * 10000).toString();

  let result = await query({id: id}); 
  return result['value'];
}

exports.handler = async (event, context) => {

  const getConnectionDetails = () => {
    if (process.env['USE_IAM'] == 'true'){
       return getUrlAndHeaders(
         process.env['NEPTUNE_ENDPOINT'],
         process.env['NEPTUNE_PORT'],
         {},
         '/gremlin',
         'wss'); 
    } else {
      const database_url = 'wss://' + process.env['NEPTUNE_ENDPOINT'] + ':' + process.env['NEPTUNE_PORT'] + '/gremlin';
      return { url: database_url, headers: {}};
    }    
  };


  const createRemoteConnection = () => {
    const { url, headers } = getConnectionDetails();

    const c = new DriverRemoteConnection(
      url, 
      { 
        mimeType: 'application/vnd.gremlin-v2.0+json', 
        headers: headers 
      });  

     c._client._connection.on('close', (code, message) => {
         console.info(`close - ${code} ${message}`);
         if (code == 1006){
           console.error('Connection closed prematurely');
           throw new Error('Connection closed prematurely');
         }
       });  

     return c;     
  };

  const createGraphTraversalSource = (conn) => {
    return traversal().withRemote(conn);
  };

  if (conn == null){
    console.info("Initializing connection")
    conn = createRemoteConnection();
    g = createGraphTraversalSource(conn);
  }

  return async.retry(
    { 
      times: 5,
      interval: 1000,
      errorFilter: function (err) { 

        // Add filters here to determine whether error can be retried
        console.warn('Determining whether retriable error: ' + err.message);

        // Check for connection issues
        if (err.message.startsWith('WebSocket is not open')){
          console.warn('Reopening connection');
          conn.close();
          conn = createRemoteConnection();
          g = createGraphTraversalSource(conn);
          return true;
        }

        // Check for ConcurrentModificationException
        if (err.message.includes('ConcurrentModificationException')){
          console.warn('Retrying query because of ConcurrentModificationException');
          return true;
        }

        // Check for ReadOnlyViolationException
        if (err.message.includes('ReadOnlyViolationException')){
          console.warn('Retrying query because of ReadOnlyViolationException');
          return true;
        }

        return false; 
      }

    }, 
    doQuery);
};

Amazon Neptune용 Python Lambda 함수 예제

다음 Python AWS Lambda 예제 함수에 대해 알아두어야 할 몇 가지 사항은 아래와 같습니다.

import os, sys, backoff, math
from random import randint
from gremlin_python import statics
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection
from gremlin_python.driver.protocol import GremlinServerError
from gremlin_python.driver import serializer
from gremlin_python.process.anonymous_traversal import traversal
from gremlin_python.process.graph_traversal import __
from gremlin_python.process.strategies import *
from gremlin_python.process.traversal import T
from aiohttp.client_exceptions import ClientConnectorError
from botocore.auth import SigV4Auth
from botocore.awsrequest import AWSRequest
from botocore.credentials import ReadOnlyCredentials
from types import SimpleNamespace

import logging
logger = logging.getLogger()
logger.setLevel(logging.INFO)


reconnectable_err_msgs = [ 
    'ReadOnlyViolationException',
    'Server disconnected',
    'Connection refused',
    'Connection was already closed',
    'Connection was closed by server',
    'Failed to connect to server: HTTP Error code 403 - Forbidden'
]

retriable_err_msgs = ['ConcurrentModificationException'] + reconnectable_err_msgs

network_errors = [OSError, ClientConnectorError]

retriable_errors = [GremlinServerError, RuntimeError, Exception] + network_errors      

def prepare_iamdb_request(database_url):
        
    service = 'neptune-db'
    method = 'GET'

    access_key = os.environ['AWS_ACCESS_KEY_ID']
    secret_key = os.environ['AWS_SECRET_ACCESS_KEY']
    region = os.environ['AWS_REGION']
    session_token = os.environ['AWS_SESSION_TOKEN']
    
    creds = SimpleNamespace(
        access_key=access_key, secret_key=secret_key, token=session_token, region=region,
    )

    request = AWSRequest(method=method, url=database_url, data=None)
    SigV4Auth(creds, service, region).add_auth(request)
    
    return (database_url, request.headers.items())
        
def is_retriable_error(e):

    is_retriable = False
    err_msg = str(e)
    
    if isinstance(e, tuple(network_errors)):
        is_retriable = True
    else:
        is_retriable = any(retriable_err_msg in err_msg for retriable_err_msg in retriable_err_msgs)
    
    logger.error('error: [{}] {}'.format(type(e), err_msg))
    logger.info('is_retriable: {}'.format(is_retriable))
    
    return is_retriable

def is_non_retriable_error(e):      
    return not is_retriable_error(e)
        
def reset_connection_if_connection_issue(params):
    
    is_reconnectable = False

    e = sys.exc_info()[1]
    err_msg = str(e)
    
    if isinstance(e, tuple(network_errors)):
        is_reconnectable = True
    else:
        is_reconnectable = any(reconnectable_err_msg in err_msg for reconnectable_err_msg in reconnectable_err_msgs)
        
    logger.info('is_reconnectable: {}'.format(is_reconnectable))
        
    if is_reconnectable:
        global conn
        global g
        conn.close()
        conn = create_remote_connection()
        g = create_graph_traversal_source(conn)
     
@backoff.on_exception(backoff.constant,
    tuple(retriable_errors),
    max_tries=5,
    jitter=None,
    giveup=is_non_retriable_error,
    on_backoff=reset_connection_if_connection_issue,
    interval=1)
def query(**kwargs):
    
    id = kwargs['id']
    
    return (g.V(id)
        .fold()
        .coalesce(
            __.unfold(), 
            __.addV('User').property(T.id, id)
        )
        .id().next())
        
def doQuery(event):
    return query(id=str(randint(0, 10000)))

def lambda_handler(event, context):
    result = doQuery(event)
    logger.info('result – {}'.format(result))
    return result
    
def create_graph_traversal_source(conn):
    return traversal().withRemote(conn)
    
def create_remote_connection():
    logger.info('Creating remote connection')
    
    (database_url, headers) = connection_info()
    
    return DriverRemoteConnection(
        database_url,
        'g',
        pool_size=1,
        message_serializer=serializer.GraphSONSerializersV2d0(),
        headers=headers)
    
def connection_info():
    
    database_url = 'wss://{}:{}/gremlin'.format(os.environ['neptuneEndpoint'], os.environ['neptunePort'])
    
    if 'USE_IAM' in os.environ and os.environ['USE_IAM'] == 'true':
        return prepare_iamdb_request(database_url)
    else:
        return (database_url, {})
    
conn = create_remote_connection()
g = create_graph_traversal_source(conn)

다음은 무거운 부하와 가벼운 부하가 번갈아 나타나는 기간을 보여주는 샘플 결과입니다.