Schemas dev - Schema Manager

Schema Name: sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq

created: 2022-05-19 12:22:40
disabled: False
format: raw
id: 1799
is_partitioned: True
is_schema_datatyped: True

name:

{
    "database": "sfdl_test_rds",
    "table": "sparefoot_account_modifiers_partitioned_pq"
}

type: rds

Schema Versions: 4

Version 4689194

created: 2022-05-23 15:04:06

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "DROP TABLE IF EXISTS `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\n(\n `account_id`  bigint , `active`  bigint , `created_at`  string , `modifier_name`  string , `modifier_value`  double , `updated_at`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/separated_dt/account_modifiers'\n",
    "MSCK REPAIR TABLE sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq"
]

hive_path: s3://sfdl-rds-testing-dev/separated_dt/account_modifiers
id: 4689194
processed: 1

raw_data:

{
    "account_id": "int64",
    "active": "int64",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

schema_attributes:

{
    "account_id": "bigint",
    "active": "bigint",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

schema_name_id: 1799
schema_scan_id: 5925017
updated: 2022-05-23 15:04:20

Version 4689193

created: 2022-05-23 15:00:22

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "DROP TABLE IF EXISTS `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\n(\n `account_id`  string , `active`  string , `created_at`  string , `modifier_name`  string , `modifier_value`  string , `updated_at`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/separated_dt/account_modifiers'\n",
    "MSCK REPAIR TABLE sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq"
]

hive_path: s3://sfdl-rds-testing-dev/separated_dt/account_modifiers
id: 4689193
processed: 1

raw_data:

{
    "account_id": "int64",
    "active": "int64",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

schema_attributes:

{
    "account_id": "string",
    "active": "string",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "string",
    "updated_at": "string"
}

schema_name_id: 1799
schema_scan_id: 5925010
updated: 2022-05-23 15:00:36

Version 4689175

created: 2022-05-19 12:26:28

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "DROP TABLE IF EXISTS `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\n(\n `modifier_name`  string , `account_id`  bigint , `modifier_value`  double , `active`  bigint , `updated_at`  string , `created_at`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/separated_dt/account_modifiers'\n",
    "MSCK REPAIR TABLE sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq"
]

hive_path: s3://sfdl-rds-testing-dev/separated_dt/account_modifiers
id: 4689175
processed: 1

raw_data:

{
    "account_id": "bigint",
    "active": "bigint",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

schema_attributes:

{
    "account_id": "bigint",
    "active": "bigint",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

schema_name_id: 1799
schema_scan_id: 5923708
updated: 2022-05-19 12:26:42

Version 4689174

created: 2022-05-19 12:22:40

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "DROP TABLE IF EXISTS `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\n(\n `account_id`  bigint , `modifier_name`  string , `active`  bigint , `modifier_value`  double , `created_at`  string , `updated_at`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/parquet'\n",
    "MSCK REPAIR TABLE sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq"
]

hive_path: s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/parquet
id: 4689174
processed: 0

raw_data:

{
    "account_id": "bigint",
    "active": "bigint",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

schema_attributes:

{
    "account_id": "bigint",
    "active": "bigint",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

schema_name_id: 1799
schema_scan_id: 5923698
updated: None

Schema Scans: 4

Last at 2022-05-23 15:03:35

Scan 5925017

duration: 0:00:48.597426

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 2,
    "partitions_applied": false,
    "success": true
}

id: 5925017

payload:

{
    "datatype_dict": null,
    "file_format": "parquet",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-17/",
        "name": "dt",
        "type": "string",
        "value": "2022-05-17"
    },
    "s3": {
        "bucket": "sfdl-rds-testing-dev",
        "hive_path": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers",
        "key": "separated_dt/account_modifiers/dt=2022-05-17/account_modifiers_1.parquet"
    },
    "schema": {
        "name": "sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq",
        "type": "rds"
    }
}

running: False
schema_name_id: 1799
start_time: 2022-05-23 15:03:35
success: True
trace_id: 8433909941924227581

Scan 5925010

duration: 0:00:22.186918

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 2,
    "partitions_applied": false,
    "success": true
}

id: 5925010

payload:

{
    "datatype_dict": {
        "account_id": "string",
        "active": "string",
        "created_at": "string",
        "modifier_name": "string",
        "modifier_value": "string",
        "updated_at": "string"
    },
    "file_format": "parquet",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-17/",
        "name": "dt",
        "type": "string",
        "value": "2022-05-17"
    },
    "s3": {
        "bucket": "sfdl-rds-testing-dev",
        "hive_path": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers",
        "key": "separated_dt/account_modifiers/dt=2022-05-17/account_modifiers_1.parquet"
    },
    "schema": {
        "name": "sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq",
        "type": "rds"
    }
}

running: False
schema_name_id: 1799
start_time: 2022-05-23 15:00:16
success: True
trace_id: 7695591994790411753

Scan 5923708

duration: 0:00:17.030635

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 1,
    "partitions_applied": false,
    "success": true
}

id: 5923708

payload:

{
    "datatype_dict": {
        "account_id": "bigint",
        "active": "bigint",
        "created_at": "string",
        "modifier_name": "string",
        "modifier_value": "double",
        "updated_at": "string"
    },
    "file_format": "parquet",
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-18/",
        "name": "dt",
        "type": "string",
        "value": "2022-05-18"
    },
    "s3": {
        "bucket": "sfdl-rds-testing-dev",
        "hive_path": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers",
        "key": "separated_dt/account_modifiers/dt=2022-05-18/parquet/account_modifiers_1.parquet"
    },
    "schema": {
        "name": "sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq",
        "type": "rds"
    }
}

running: False
schema_name_id: 1799
start_time: 2022-05-19 12:26:28
success: True
trace_id: 13939074228125400743

Scan 5923698

duration: 0:00:00.510040

exit_message:

{
    "exception": "Invalid partition location `s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/`, does not appear to be in table location `s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/parquet`\nTraceback (most recent call last):\n  File \"/schema_manager/schema_generator/schema_scanner.py\", line 102, in scan\n    response = service.run()\n  File \"/schema_manager/schema_generator/process_hive_table.py\", line 95, in run\n    partition_generator.detect_new_partition(self.partition_request)\n  File \"/schema_manager/schema_generator/partition_generator.py\", line 31, in detect_new_partition\n    location=partition_request['value'].location\n  File \"/schema_manager/schema_manager/service/partition_bag.py\", line 43, in scan_insert\n    return PartitionBagService._insert(schema_name, name, type, value, location)\n  File \"/schema_manager/schema_manager/service/partition_bag.py\", line 99, in _insert\n    .format(location, psd.hive_path))\nschema_manager.service.partition_bag.PartitionBagException: Invalid partition location `s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/`, does not appear to be in table location `s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/parquet`\n: Expecting value: line 1 column 1 (char 0)"
}

id: 5923698

payload:

{
    "datatype_dict": {
        "account_id": "bigint",
        "active": "bigint",
        "created_at": "string",
        "modifier_name": "string",
        "modifier_value": "double",
        "updated_at": "string"
    },
    "file_format": "parquet",
    "is_schema_datatyped": true,
    "partition": {
        "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/",
        "name": "dt",
        "type": "string",
        "value": "2022-05-18"
    },
    "s3": {
        "bucket": "sfdl-rds-testing-dev",
        "hive_path": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/2022-05-18/parquet",
        "key": "separated_dt/account_modifiers/2022-05-18/parquet/account_modifiers_1.parquet"
    },
    "schema": {
        "name": "sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq",
        "type": "rds"
    }
}

running: False
schema_name_id: 1799
start_time: 2022-05-19 12:22:40
success: False
trace_id: 7528112656258403935

Partitions:

count: 2

ddl:

[
    "ALTER TABLE\n    `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\nADD\n\n\n PARTITION (dt='2022-05-17') location 's3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-17/'\n PARTITION (dt='2022-05-18') location 's3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-18/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 184852,
            "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-17/",
            "name": "dt",
            "value": "2022-05-17"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2022-05-19 13:23:55",
                "last_data": "2022-05-23 16:35:47"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 184851,
            "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-18/",
            "name": "dt",
            "value": "2022-05-18"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2022-05-19 12:26:28",
                "last_data": "2022-05-19 12:26:28"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "account_id": "bigint",
    "active": "bigint",
    "created_at": "string",
    "modifier_name": "string",
    "modifier_value": "double",
    "updated_at": "string"
}

created: 2022-05-23 15:04:06

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\n(\n `account_id`  bigint , `active`  bigint , `created_at`  string , `modifier_name`  string , `modifier_value`  double , `updated_at`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/separated_dt/account_modifiers'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`",
    "repair_table": "MSCK REPAIR TABLE sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq"
}

Server:

hostname: schemamanager-5447774fc6-4w58v
name: schema_manager
process_start: 2026-04-02 21:43:44
sf_env: dev
version: 2427328685

Raw:

{
    "name": {
        "created": "2022-05-19 12:22:40",
        "disabled": false,
        "format": "raw",
        "id": 1799,
        "is_partitioned": true,
        "is_schema_datatyped": true,
        "name": {
            "database": "sfdl_test_rds",
            "table": "sparefoot_account_modifiers_partitioned_pq"
        },
        "type": "rds"
    },
    "partition": {
        "count": 2,
        "ddl": [
            "ALTER TABLE\n    `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\nADD\n\n\n PARTITION (dt='2022-05-17') location 's3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-17/'\n PARTITION (dt='2022-05-18') location 's3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-18/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 184852,
                    "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-17/",
                    "name": "dt",
                    "value": "2022-05-17"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2022-05-19 13:23:55",
                        "last_data": "2022-05-23 16:35:47"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 184851,
                    "location": "s3://sfdl-rds-testing-dev/separated_dt/account_modifiers/dt=2022-05-18/",
                    "name": "dt",
                    "value": "2022-05-18"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2022-05-19 12:26:28",
                        "last_data": "2022-05-19 12:26:28"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "account_id": "bigint",
            "active": "bigint",
            "created_at": "string",
            "modifier_name": "string",
            "modifier_value": "double",
            "updated_at": "string"
        },
        "created": "2022-05-23 15:04:06",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_test_rds`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`\n(\n `account_id`  bigint , `active`  bigint , `created_at`  string , `modifier_name`  string , `modifier_value`  double , `updated_at`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-rds-testing-dev/separated_dt/account_modifiers'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq`",
            "repair_table": "MSCK REPAIR TABLE sfdl_test_rds.sparefoot_account_modifiers_partitioned_pq"
        }
    },
    "server": {
        "hostname": "schemamanager-5447774fc6-4w58v",
        "name": "schema_manager",
        "process_start": "2026-04-02 21:43:44",
        "sf_env": "dev",
        "version": "2427328685"
    }
}

Schema Info