CrazyBeeline commented on issue #7102:
URL: https://github.com/apache/hudi/issues/7102#issuecomment-1299606850
@nsivabalan
I disable metadata table and unset hoodie.write.concurrency.mode now ！
but why error find when spark-shell read hive table which is synced by
hudi
spark.sql("select count(1) from ods_test_aa_rt").show
spark.sql("select count(1) from ods_test_aa_rt").show
spark.sql("select count(1) from ods_test_aa_rt").show
spark.sql("select count(1) from ods_test_aa_rt").show
.....
....
hive> show create table ods_test_aa_rt;
OK
CREATE EXTERNAL TABLE `ods_test_aa_rt`(
`_hoodie_commit_time` string COMMENT '',
`_hoodie_commit_seqno` string COMMENT '',
`_hoodie_record_key` string COMMENT '',
`_hoodie_partition_path` string COMMENT '',
`_hoodie_file_name` string COMMENT '',
`id` string COMMENT 'id',
`name` string COMMENT 'name',
`qsdiaccesstime` bigint COMMENT 'access time')
COMMENT 'test'
PARTITIONED BY (
`dt` string COMMENT '(yyyy-MM-dd)')
ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
WITH SERDEPROPERTIES (
'hoodie.query.as.ro.table'='false',
'path'='hdfs:///hudi/kafka/test_aa')
STORED AS INPUTFORMAT
'org.apache.hudi.hadoop.realtime.HoodieParquetRealtimeInputFormat'
OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
LOCATION
'hdfs://bigdata.hadoop.master01:8020/hudi/kafka/test_aa'
TBLPROPERTIES (
'last_commit_time_sync'='20221101132439896',
'spark.sql.sources.provider'='hudi',
'spark.sql.sources.schema.numPartCols'='1',
'spark.sql.sources.schema.numParts'='1',
'spark.sql.sources.schema.part.0'='{"type":"struct","fields":[{"name":"_hoodie_commit_time","type":"string","nullable":true,"metadata":{}},{"name":"_hoodie_commit_seqno","type":"string","nullable":true,"metadata":{}},{"name":"_hoodie_record_key","type":"string","nullable":true,"metadata":{}},{"name":"_hoodie_partition_path","type":"string","nullable":true,"metadata":{}},{"name":"_hoodie_file_name","type":"string","nullable":true,"metadata":{}},{"name":"id","type":"string","nullable":false,"metadata":{}},{"name":"name","type":"string","nullable":true,"metadata":{}},{"name":"qsdiAccessTime","type":"long","nullable":false,"metadata":{}},{"name":"dt","type":"string","nullable":false,"metadata":{}}]}',
'spark.sql.sources.schema.partCol.0'='dt',
'transient_lastDdlTime'='1667099169')
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
