------------------------------------------------------------------------------------ Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. SPDX-License-Identifier: MIT-0 ------------------------------------------------------------------------------------ 1. td-agent-gem install fluent-plugin-kinesis -v 2.1.0 2. td-agent-gem list | grep plugin-kinesis 3. export AWS_REGION="ap-northeast-1" 4. /etc/init.d/td-agent restart 6. create table ec2log ( timestamp varchar, alarmlevel varchar, host varchar, number int2, text varchar ); 7. copy ec2log from 's3://[S3 BUCKET NAME]/minilake-in1' format as json 'auto' iam_role '[作成したIAMロールのARN]'; 8. create external schema my_first_external_schema from data catalog database 'spectrumdb' iam_role '[作成したIAMロールのARN]' create external database if not exists; 9. create external table my_first_external_schema.ec2log_external ( timestamp varchar(max), alarmlevel varchar(max), host varchar(max), number int2, text varchar(max) ) partitioned by (year char(4), month char(2), day char(2), hour char(2)) ROW FORMAT SERDE 'org.openx.data.jsonserde.JsonSerDe' WITH SERDEPROPERTIES ( 'paths'='timestamp,alarmlevel,host,number,text') STORED AS INPUTFORMAT 'org.apache.hadoop.mapred.TextInputFormat' OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' location 's3://[S3 BUCKET NAME]/minilake-in1/'; 10. select * from svv_external_schemas; 11. select * from svv_external_databases; 12. select * from svv_external_tables; 13. "ADD PARTITION"句の各パーティションの値は、LOCATION句のS3バケットパスのパーティションの値と合わせてください。下記は一例です。 ALTER TABLE my_first_external_schema.ec2log_external ADD PARTITION (year='2019', month='09', day='27', hour='14') LOCATION 's3://[S3 BUCKET NAME]/minilake-in1/2019/09/27/14'; もしパーティション作成を間違えた場合は、以下を参考にDrop Partitionしてください。 上記ADD PARTITIONで指定したパーティションの値を指定して削除します。 ALTER TABLE my_first_external_schema.ec2log_external DROP PARTITION (year='2019', month='09', day='27', hour='14')