Test script for Hive with ORC. It mounts data on S3 which is provided at here: https://amplab.cs.berkeley.edu/benchmark/ as external table. Then we import it from external table to internal table.

hive_orc_test.hql

CREATE EXTERNAL TABLE rankings_external (
     pageURL VARCHAR(300),
     pageRank INT,
     avgDuration INT
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
STORED AS SEQUENCEFILE
LOCATION 's3a://big-data-benchmark/pavlo/sequence/1node/rankings/';

CREATE TABLE rankings (
     pageURL VARCHAR(300),
     pageRank INT,
     avgDuration INT
)
STORED AS ORC;
INSERT OVERWRITE TABLE rankings SELECT * FROM rankings_external;

SELECT pagerank, count(1) AS cnt FROM rankings GROUP BY pagerank ORDER BY cnt DESC LIMIT 10;