[HUDI-573] Rolling stats written twice onto commit metadata

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.5.2
• Component/s: writer-core
• Labels: pull-request-available
• Assignee: Nishith Agarwal
• Reporter: Vinoth Chandar
• Created: 23/Jan/20 18:48
• Updated: 20/Feb/20 18:28
• Resolved: 20/Feb/20 18:28

Description

To reproduce, simply write a commit and observe the file locally 

  "extraMetadataMap" : {
    "ROLLING_STAT" : "{\n  \"partitionToRollingStats\" : {\n    \"date-0\" : {\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-1\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-1\",\n        \"inserts\" : 86046,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 49691893\n      },\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-0\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-0\",\n        \"inserts\" : 214350,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 123138517\n      }\n    },\n    \"date-2\" : {\n      \"f8924f32-09e6-4049-8830-9fb623d6c1e9-2\" : {\n        \"fileId\" : \"f8924f32-09e6-4049-8830-9fb623d6c1e9-2\",\n        \"inserts\" : 186262,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 107012887\n      },\n      \"f8924f32-09e6-4049-8830-9fb623d6c1e9-1\" : {\n        \"fileId\" : \"f8924f32-09e6-4049-8830-9fb623d6c1e9-1\",\n        \"inserts\" : 214350,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 123081042\n      }\n    },\n    \"date-1\" : {\n      \"f8924f32-09e6-4049-8830-9fb623d6c1e9-0\" : {\n        \"fileId\" : \"f8924f32-09e6-4049-8830-9fb623d6c1e9-0\",\n        \"inserts\" : 63043,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 36528903\n      },\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-3\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-3\",\n        \"inserts\" : 21632,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 12820469\n      },\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-2\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-2\",\n        \"inserts\" : 214319,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 123119553\n      }\n    }\n  },\n  \"actionType\" : \"commit\"\n}",
    "schema" : "{\"type\":\"record\",\"name\":\"hoodie_benchmark_record\",\"namespace\":\"hoodie.hoodie_benchmark\",\"fields\":[{\"name\":\"key\",\"type\":[\"string\",\"null\"]},{\"name\":\"partition\",\"type\":[\"string\",\"null\"]},{\"name\":\"ts\",\"type\":[\"long\",\"null\"]},{\"name\":\"textField\",\"type\":[\"string\",\"null\"]},{\"name\":\"decimalField\",\"type\":[\"float\",\"null\"]},{\"name\":\"longField\",\"type\":[\"long\",\"null\"]},{\"name\":\"arrayField\",\"type\":[{\"type\":\"array\",\"items\":[\"int\",\"null\"]},\"null\"]},{\"name\":\"mapField\",\"type\":[{\"type\":\"map\",\"values\":[\"int\",\"null\"]},\"null\"]}]}"
  },
  "extraMetadata" : {
    "ROLLING_STAT" : "{\n  \"partitionToRollingStats\" : {\n    \"date-0\" : {\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-1\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-1\",\n        \"inserts\" : 86046,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 49691893\n      },\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-0\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-0\",\n        \"inserts\" : 214350,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 123138517\n      }\n    },\n    \"date-2\" : {\n      \"f8924f32-09e6-4049-8830-9fb623d6c1e9-2\" : {\n        \"fileId\" : \"f8924f32-09e6-4049-8830-9fb623d6c1e9-2\",\n        \"inserts\" : 186262,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 107012887\n      },\n      \"f8924f32-09e6-4049-8830-9fb623d6c1e9-1\" : {\n        \"fileId\" : \"f8924f32-09e6-4049-8830-9fb623d6c1e9-1\",\n        \"inserts\" : 214350,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 123081042\n      }\n    },\n    \"date-1\" : {\n      \"f8924f32-09e6-4049-8830-9fb623d6c1e9-0\" : {\n        \"fileId\" : \"f8924f32-09e6-4049-8830-9fb623d6c1e9-0\",\n        \"inserts\" : 63043,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 36528903\n      },\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-3\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-3\",\n        \"inserts\" : 21632,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 12820469\n      },\n      \"b2404182-a20b-48f3-9386-1fd46e233aa6-2\" : {\n        \"fileId\" : \"b2404182-a20b-48f3-9386-1fd46e233aa6-2\",\n        \"inserts\" : 214319,\n        \"upserts\" : 0,\n        \"deletes\" : 0,\n        \"totalInputWriteBytesToDisk\" : 0,\n        \"totalInputWriteBytesOnDisk\" : 123119553\n      }\n    }\n  },\n  \"actionType\" : \"commit\"\n}",
    "schema" : "{\"type\":\"record\",\"name\":\"hoodie_benchmark_record\",\"namespace\":\"hoodie.hoodie_benchmark\",\"fields\":[{\"name\":\"key\",\"type\":[\"string\",\"null\"]},{\"name\":\"partition\",\"type\":[\"string\",\"null\"]},{\"name\":\"ts\",\"type\":[\"long\",\"null\"]},{\"name\":\"textField\",\"type\":[\"string\",\"null\"]},{\"name\":\"decimalField\",\"type\":[\"float\",\"null\"]},{\"name\":\"longField\",\"type\":[\"long\",\"null\"]},{\"name\":\"arrayField\",\"type\":[{\"type\":\"array\",\"items\":[\"int\",\"null\"]},\"null\"]},{\"name\":\"mapField\",\"type\":[{\"type\":\"map\",\"values\":[\"int\",\"null\"]},\"null\"]}]}"
  },
  "fileIdAndRelativePaths" : {
 

Issue Links

• links to: GitHub Pull Request #1278