安装部署

    有了上述编译阶段产出的tar.gz包后,解压后就可以启动inlong-sort-standalone的应用了。
    示例:

    • 可以从ClassPath的SortClusterConfig.conf源文件读取,但不支持实时更新
    • 可以从Inlong Manager的HTTP接口获取配置
      | 配置名 | 是否必须 | 默认值 |描述 | | —————— | —————— | —————— | —————— | |clusterName | Y | NA | 用来唯一标识一个inlong-sort-standalone集群 | |sortTasks | Y | NA | 分发任务列表 |
    配置名是否必须默认值描述
    nameYNA分发任务名
    typeYNA分发任务类型,如HIVE(“hive”), TUBE(“tube”), KAFKA(“kafka”), PULSAR(“pulsar”), ElasticSearch(“ElasticSearch”), UNKNOWN(“n”)
    idParamsYNAInlong数据流参数列表
    sinkParamsYNA分发任务的参数

    Hive分发任务的idParams

    配置名是否必须默认值描述
    hdfsPathYNAHDFS的NameNode
    maxFileOpenDelayMinuteN5单个HDFS文件最大写入时间,单位分钟
    tokenOvertimeMinuteN60单个Inlong数据流的分区创建token最大占用时间,单位分钟
    maxOutputFileSizeGbN2单个HDFS文件最大大小,单位GB
    hiveJdbcUrlYNAHive的JDBC路径
    hiveDatabaseYNAHive的数据库
    hiveUsernameYNAHive的用户名
    hivePasswordYNAHive的密码

    Pulsar分发任务的idParams

    配置名是否必须默认值描述
    serviceUrlYNAPulsar服务路径
    authenticationYNAPulsar集群鉴权
    enableBatchingNtrueenableBatching
    batchingMaxBytesN5242880batchingMaxBytes
    batchingMaxMessagesN3000batchingMaxMessages
    batchingMaxPublishDelayN1batchingMaxPublishDelay
    maxPendingMessagesN1000maxPendingMessages
    maxPendingMessagesAcrossPartitionsN50000maxPendingMessagesAcrossPartitions
    sendTimeoutN0sendTimeout
    compressionTypeNNONEcompressionType
    blockIfQueueFullNtrueblockIfQueueFull
    roundRobinRouterBatchingPartitionSwitchFrequencyN10roundRobinRouterBatchingPartitionSwitchFrequency

    Hive配置样例

    1. {
    2. "data":{
    3. "clusterName":"hivev3-sz-sz1",
    4. "sortTasks":[
    5. {
    6. "idParams":[
    7. {
    8. "inlongGroupId":"0fc00000046",
    9. "inlongStreamId":"",
    10. "separator":"|",
    11. "partitionIntervalMs":3600000,
    12. "idRootPath":"/user/hive/warehouse/t_inlong_v1_0fc00000046",
    13. "partitionSubPath":"/{yyyyMMdd}/{yyyyMMddHH}",
    14. "hiveTableName":"t_inlong_v1_0fc00000046",
    15. "partitionFieldName":"dt",
    16. "partitionFieldPattern":"yyyyMMddHH",
    17. "msgTimeFieldPattern":"yyyy-MM-dd HH:mm:ss",
    18. "maxPartitionOpenDelayHour":8
    19. },
    20. {
    21. "inlongGroupId":"03600000045",
    22. "separator":"|",
    23. "partitionIntervalMs":3600000,
    24. "idRootPath":"/user/hive/warehouse/t_inlong_v1_03600000045",
    25. "partitionSubPath":"/{yyyyMMdd}/{yyyyMMddHH}",
    26. "hiveTableName":"t_inlong_v1_03600000045",
    27. "partitionFieldName":"dt",
    28. "partitionFieldPattern":"yyyyMMddHH",
    29. "maxPartitionOpenDelayHour":8
    30. },
    31. {
    32. "inlongGroupId":"05100054990",
    33. "inlongStreamId":"",
    34. "separator":"|",
    35. "partitionIntervalMs":3600000,
    36. "idRootPath":"/user/hive/warehouse/t_inlong_v1_05100054990",
    37. "partitionSubPath":"/{yyyyMMdd}/{yyyyMMddHH}",
    38. "hiveTableName":"t_inlong_v1_05100054990",
    39. "partitionFieldName":"dt",
    40. "partitionFieldPattern":"yyyyMMddHH",
    41. "msgTimeFieldPattern":"yyyy-MM-dd HH:mm:ss",
    42. "maxPartitionOpenDelayHour":8
    43. },
    44. {
    45. "inlongGroupId":"09c00014434",
    46. "inlongStreamId":"",
    47. "separator":"|",
    48. "partitionIntervalMs":3600000,
    49. "idRootPath":"/user/hive/warehouse/t_inlong_v1_09c00014434",
    50. "partitionSubPath":"/{yyyyMMdd}/{yyyyMMddHH}",
    51. "hiveTableName":"t_inlong_v1_09c00014434",
    52. "partitionFieldName":"dt",
    53. "partitionFieldPattern":"yyyyMMddHH",
    54. "maxPartitionOpenDelayHour":8
    55. },
    56. {
    57. "inlongStreamId":"",
    58. "separator":"|",
    59. "partitionIntervalMs":3600000,
    60. "idRootPath":"/user/hive/warehouse/t_inlong_v1_0c900035509",
    61. "partitionSubPath":"/{yyyyMMdd}/{yyyyMMddHH}",
    62. "hiveTableName":"t_inlong_v1_0c900035509",
    63. "partitionFieldName":"dt",
    64. "partitionFieldPattern":"yyyyMMddHH",
    65. "msgTimeFieldPattern":"yyyy-MM-dd HH:mm:ss",
    66. "maxPartitionOpenDelayHour":8
    67. }
    68. ],
    69. "name":"sid_hive_inlong6th_v3",
    70. "sinkParams":{
    71. "hdfsPath":"hdfs://127.0.0.1:9000",
    72. "maxFileOpenDelayMinute":"5",
    73. "tokenOvertimeMinute":"60",
    74. "maxOutputFileSizeGb":"2",
    75. "hiveJdbcUrl":"jdbc:hive2://127.0.0.2:10000",
    76. "hiveDatabase":"default",
    77. "hiveUsername":"hive",
    78. "hivePassword":"hive"
    79. },
    80. "type":"HIVE"
    81. }
    82. ]
    83. },
    84. "errCode":0,
    85. "md5":"md5",
    86. }