kylin-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "bingli3@iflytek.com" <bing...@iflytek.com>
Subject How Kylin Cuboid Scheduler Work With Aggregation Groups ?
Date Fri, 31 Mar 2017 07:49:31 GMT
  Hiļ¼Œall
      I have a Cube, the desc is :
{
  "uuid": "bcf11be2-83e4-497e-9e35-a402460a6446",
  "last_modified": 1490860973892,
  "version": "1.6.0",
  "name": "adx_flow_insight",
  "model_name": "adx_operator",
  "description": "",
  "null_string": null,
  "dimensions": [
    {
      "name": "GENDER",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "GENDER",
      "derived": null
    },
    {
      "name": "AGE",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "AGE",
      "derived": null
    },
    {
      "name": "BRAND",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "BRAND",
      "derived": null
    },
    {
      "name": "MODEL",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "MODEL",
      "derived": null
    },
    {
      "name": "RESOLUTION",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "RESOLUTION",
      "derived": null
    },
    {
      "name": "OS_VERSION",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "OS_VERSION",
      "derived": null
    },
    {
      "name": "NTT",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "NTT",
      "derived": null
    },
    {
      "name": "TS_MINUTE",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "TS_MINUTE",
      "derived": null
    },
    {
      "name": "TS_HOUR",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "TS_HOUR",
      "derived": null
    },
    {
      "name": "DAY_TIME",
      "table": "FLOW_INSIGHT.VIEW_FLOW_INSIGHT",
      "column": "DAY_TIME",
      "derived": null
    }
  ],
  "measures": [
    {
      "name": "_COUNT_",
      "function": {
        "expression": "COUNT",
        "parameter": {
          "type": "constant",
          "value": "1",
          "next_parameter": null
        },
        "returntype": "bigint"
      },
      "dependent_measure_ref": null
    },
    {
      "name": "REQUEST_PV",
      "function": {
        "expression": "SUM",
        "parameter": {
          "type": "column",
          "value": "REQUEST",
          "next_parameter": null
        },
        "returntype": "bigint"
      },
      "dependent_measure_ref": null
    },
    {
      "name": "IMPRESS_PV",
      "function": {
        "expression": "SUM",
        "parameter": {
          "type": "column",
          "value": "IMPRESS",
          "next_parameter": null
        },
        "returntype": "bigint"
      },
      "dependent_measure_ref": null
    },
    {
      "name": "CLICK_PV",
      "function": {
        "expression": "SUM",
        "parameter": {
          "type": "column",
          "value": "CLICK",
          "next_parameter": null
        },
        "returntype": "bigint"
      },
      "dependent_measure_ref": null
    },
    {
      "name": "FILL_PV",
      "function": {
        "expression": "SUM",
        "parameter": {
          "type": "column",
          "value": "FILL",
          "next_parameter": null
        },
        "returntype": "bigint"
      },
      "dependent_measure_ref": null
    },
    {
      "name": "UV_DID",
      "function": {
        "expression": "COUNT_DISTINCT",
        "parameter": {
          "type": "column",
          "value": "DID",
          "next_parameter": null
        },
        "returntype": "hllc(10)"
      },
      "dependent_measure_ref": null
    }
  ],
  "dictionaries": [],
  "rowkey": {
    "rowkey_columns": [
      {
        "column": "DAY_TIME",
        "encoding": "date",
        "isShardBy": false
      },
      {
        "column": "TS_MINUTE",
        "encoding": "integer:4",
        "isShardBy": false
      },
      {
        "column": "TS_HOUR",
        "encoding": "integer:4",
        "isShardBy": false
      },
      {
        "column": "GENDER",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "AGE",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "BRAND",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "MODEL",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "RESOLUTION",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "OS_VERSION",
        "encoding": "dict",
        "isShardBy": false
      },
      {
        "column": "NTT",
        "encoding": "dict",
        "isShardBy": false
      }
    ]
  },
  "hbase_mapping": {
    "column_family": [
      {
        "name": "F1",
        "columns": [
          {
            "qualifier": "M",
            "measure_refs": [
              "_COUNT_",
              "REQUEST_PV",
              "IMPRESS_PV",
              "CLICK_PV",
              "FILL_PV"
            ]
          }
        ]
      },
      {
        "name": "F2",
        "columns": [
          {
            "qualifier": "M",
            "measure_refs": [
              "UV_DID"
            ]
          }
        ]
      }
    ]
  },
  "aggregation_groups": [
    {
      "includes": [
        "DAY_TIME",
        "GENDER"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "DAY_TIME"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "DAY_TIME",
        "AGE"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "DAY_TIME"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "DAY_TIME",
        "BRAND"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "DAY_TIME"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "DAY_TIME",
        "MODEL"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "DAY_TIME"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "DAY_TIME",
        "RESOLUTION"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "RESOLUTION"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "DAY_TIME",
        "OS_VERSION"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "DAY_TIME"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "DAY_TIME",
        "NTT"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "DAY_TIME"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "TS_MINUTE"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "TS_MINUTE"
        ],
        "joint_dims": []
      }
    },
    {
      "includes": [
        "TS_HOUR"
      ],
      "select_rule": {
        "hierarchy_dims": [],
        "mandatory_dims": [
          "TS_HOUR"
        ],
        "joint_dims": []
      }
    }
  ],
  "signature": "DSSmByHn2sATiETlBdjANQ==",
  "notify_list": [],
  "status_need_notify": [
    "ERROR",
    "DISCARDED",
    "SUCCEED"
  ],
  "partition_date_start": 1488326400000,
  "partition_date_end": 3153600000000,
  "auto_merge_time_ranges": [
    604800000,
    2419200000
  ],
  "retention_range": 0,
  "engine_type": 2,
  "storage_type": 2,
  "override_kylin_properties": {
    "kylin.job.mr.config.override.mapreduce.job.queuename": "ad"
  } 
} 

   There have 10 dims, and use aggregation groups. I want Cube only contains 10 combs:
       <day_time, gender> 576
       <day_time, age> 544
       <day_time, brand> 528
       <day_time, model> 520
       <day_time, resolution> 516
       <day_time, os_version> 514
       <day_time, ntt>        513
       <ts_minute>     256
       <ts_hour>     128
       <day_time>   512

     But the Cuboid Scheduler parse as follower:
        
2017-03-31 15:32:47,735 (main) [INFO - org.apache.kylin.cube.CubeManager.loadAllCubeInstance(CubeManager.java:908)]
Loaded 4 cubes, fail on 0 cubes
1023 
516
576
513
528
514
544
520
2017-03-31 15:32:47,742 (Thread-0) [INFO - org.apache.hadoop.hbase.client.ConnectionManager$HConnectionImplementation.closeMasterService(ConnectionManager.java:2259)]
Closing master protocol: MasterService 
  
Question:
     How Aggregation Groups  Work? I can not set single dim in aggregation?

Thanks for you suggestion~~~



bingli3@iflytek.com
Mime
View raw message