NetPlagStream/docker-compose.yml at main · Yasouimo/NetPlagStream · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
services:
  # HDFS NameNode - accessible from Windows host at localhost:8020
  namenode:
    image: bde2020/hadoop-namenode:2.0.0-hadoop3.2.1-java8
    container_name: hadoop-namenode
    hostname: namenode
    ports:
      - "9870:9870"  # Web UI (NameNode Web Interface)
      - "9000:9000"   # HDFS Client Protocol (legacy, not used)
      - "8020:8020"   # NameNode RPC (for external connections from Windows host)
    environment:
      - CLUSTER_NAME=netplag
      - CORE_CONF_fs_defaultFS=hdfs://namenode:8020  # Internal (container) URL
      # External connections from Windows host should use: hdfs://localhost:8020
    volumes:
      - hadoop_namenode:/hadoop/dfs/name
      - ./hadoop-config/hdfs-site.xml:/opt/hadoop-3.2.1/etc/hadoop/hdfs-site.xml:ro
    networks:
      - hadoop-net
    healthcheck:
      test: ["CMD-SHELL", "hdfs dfsadmin -report || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    restart: unless-stopped  # Prevents auto-restart on corruption, allows manual control
    stop_grace_period: 60s   # Give NameNode time to save metadata gracefully
    deploy:
      resources:
        limits:
          memory: 2G
        reservations:
          memory: 1G

  # HDFS DataNode - accessible from Windows host at localhost:9866
  datanode:
    image: bde2020/hadoop-datanode:2.0.0-hadoop3.2.1-java8
    container_name: hadoop-datanode
    hostname: datanode
    ports:
      - "9864:9864"  # Web UI
      - "9866:9866"   # Data transfer port (critical for Windows host access)
    environment:
      - SERVICE_PRECONDITION=namenode:9870
      - CORE_CONF_fs_defaultFS=hdfs://namenode:8020
      # Force DataNode to bind to all interfaces
      - HDFS_CONF_datanode_address=0.0.0.0:9866
      - HDFS_CONF_datanode_http_address=0.0.0.0:9864
    volumes:
      - hadoop_datanode:/hadoop/dfs/data
      - ./hadoop-config/hdfs-site.xml:/opt/hadoop-3.2.1/etc/hadoop/hdfs-site.xml:ro
    networks:
      - hadoop-net
    depends_on:
      namenode:
        condition: service_healthy  # Wait for NameNode to be healthy before starting
    healthcheck:
      test: ["CMD-SHELL", "hdfs dfsadmin -report || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    restart: unless-stopped  # Prevents auto-restart on corruption, allows manual control
    stop_grace_period: 30s   # Give DataNode time to close connections gracefully
    deploy:
      resources:
        limits:
          memory: 2G
        reservations:
          memory: 1G

  # Dashboard - Web interface for visualizing plagiarism results
  dashboard:
    build:
      context: .
      dockerfile: Dockerfile.dashboard
    container_name: netplag-dashboard
    hostname: dashboard
    ports:
      - "5000:5000"
    environment:
      - IN_DOCKER=true
      - ES_HOST=elasticsearch
      - ES_PORT=9200
    networks:
      - hadoop-net
    depends_on:
      elasticsearch:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:5000/api/stats"]
      interval: 30s
      timeout: 15s
      retries: 5
      start_period: 10s

  # Elasticsearch - for indexing and searching plagiarism results
  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:8.11.0
    container_name: netplag-elasticsearch
    hostname: elasticsearch
    environment:
      - discovery.type=single-node
      - xpack.security.enabled=false
      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
      - bootstrap.memory_lock=true
    ulimits:
      memlock:
        soft: -1
        hard: -1
    ports:
      - "9200:9200"  # REST API
      - "9300:9300"  # Transport (if needed)
    volumes:
      - elasticsearch_data:/usr/share/elasticsearch/data
    networks:
      - hadoop-net
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:9200/_cluster/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s

volumes:
  hadoop_namenode:
  hadoop_datanode:
  elasticsearch_data:

networks:
  hadoop-net: