Github user QiangCai commented on the issue: https://github.com/apache/incubator-carbondata/pull/635 Data Records : 1 * 1000 * 1000 ``` SORT BY ALL DIMENSION: c1,c2,c3,c4,c5 CREATE TABLE IF NOT EXISTS default.carbon_perftest_table (c1 STRING, c2 STRING, c3 STRING, c4 STRING, c5 STRING, c6 INT, c7 INT, c8 INT, c9 INT, c10 INT) STORED BY 'org.apache.carbondata.format' LOAD DATA INPATH '/home/david/Documents/incubator-carbondata/examples/spark/target/store/tempCSV_default_carbon_perftest_table_4113107653051' INTO TABLE default.carbon_perftest_table OPTIONS ('FILEHEADER' = 'c1,c2,c3,c4,c5,c6,c7,c8,c9,c10', 'USE_KETTLE' = 'false') load performance: 1782, 3217, 10171 OLAP Query 0: 736, 1690, 664 [sql: SELECT c3, c4, sum(c8) FROM tableName WHERE c1 = 'P1_23' and c2 = 'P2_43' GROUP BY c3, c4] OLAP Query 1: 527, 1874, 542 [sql: SELECT c2, c3, sum(c9) FROM tableName WHERE c1 = 'P1_432' and c4 = 'P4_3' and c5 = 'P5_2' GROUP by c2, c3 ] OLAP Query 2: 3088, 3973, 2996 [sql: SELECT c2, count(distinct c1), sum(c8) FROM tableName WHERE c3="P3_4" and c5="P5_4" GROUP BY c2 ] OLAP Query 3: 2493, 3710, 2622 [sql: SELECT c2, c5, count(distinct c1), sum(c7) FROM tableName WHERE c4="P4_4" and c5="P5_7" and c8>4 GROUP BY c2, c5 ] Point Query 0: 114, 516, 98 [sql: SELECT c4 FROM tableName WHERE c1="P1_43" ] Point Query 1: 126, 664, 99 [sql: SELECT c3 FROM tableName WHERE c1="P1_542" and c2="P2_23" ] Point Query 2: 128, 817, 165 [sql: SELECT c3, c5 FROM tableName WHERE c1="P1_52" and c7=4] Point Query 3: 113, 530, 155 [sql: SELECT c4, c9 FROM tableName WHERE c1="P1_43" and c8<3] Filter Query 0: 209, 1319, 154 [sql: SELECT * FROM tableName WHERE c2="P2_43" ] Filter Query 1: 283, 1686, 289 [sql: SELECT * FROM tableName WHERE c3="P3_3" ] Filter Query 2: 319, 1306, 137 [sql: SELECT * FROM tableName WHERE c2="P2_32" and c3="P3_23" ] Filter Query 3: 234, 1242, 154 [sql: SELECT * FROM tableName WHERE c3="P3_28" and c4="P4_3" ] Scan Query 0: 162, 318, 327 [sql: SELECT sum(c7), sum(c8), avg(c9), max(c10) FROM tableName ] Scan Query 1: 107, 406, 97 [sql: SELECT sum(c7) FROM tableName WHERE c2="P2_32" ] Scan Query 2: 157, 546, 141 [sql: SELECT sum(c7), sum(c8), sum(9), sum(c10) FROM tableName WHERE c4="P4_4" ] Scan Query 3: 121, 480, 170 [sql: SELECT sum(c7), sum(c8), sum(9), sum(c10) FROM tableName WHERE c2="P2_75" and c6<5 ] Total time: 8924.109771, 21083.679769, 8817.163649 SORT_COLUMNS: c1,c3 CREATE TABLE IF NOT EXISTS default.carbon_perftest_table (c1 STRING, c2 STRING, c3 STRING, c4 STRING, c5 STRING, c6 INT, c7 INT, c8 INT, c9 INT, c10 INT) STORED BY 'org.apache.carbondata.format' TBLPROPERTIES('SORT_COLUMNS'='c1,c3') LOAD DATA INPATH '/home/david/Documents/incubator-carbondata/examples/spark/target/store/tempCSV_default_carbon_perftest_table_4448597034063' INTO TABLE default.carbon_perftest_table OPTIONS ('FILEHEADER' = 'c1,c2,c3,c4,c5,c6,c7,c8,c9,c10', 'USE_KETTLE' = 'false') load performance: 1649, 3108, 9070 OLAP Query 0: 651, 1567, 615 [sql: SELECT c3, c4, sum(c8) FROM tableName WHERE c1 = 'P1_23' and c2 = 'P2_43' GROUP BY c3, c4] OLAP Query 1: 502, 1792, 448 [sql: SELECT c2, c3, sum(c9) FROM tableName WHERE c1 = 'P1_432' and c4 = 'P4_3' and c5 = 'P5_2' GROUP by c2, c3 ] OLAP Query 2: 3028, 3741, 2600 [sql: SELECT c2, count(distinct c1), sum(c8) FROM tableName WHERE c3="P3_4" and c5="P5_4" GROUP BY c2 ] OLAP Query 3: 2535, 3777, 2704 [sql: SELECT c2, c5, count(distinct c1), sum(c7) FROM tableName WHERE c4="P4_4" and c5="P5_7" and c8>4 GROUP BY c2, c5 ] Point Query 0: 107, 566, 82 [sql: SELECT c4 FROM tableName WHERE c1="P1_43" ] Point Query 1: 158, 681, 96 [sql: SELECT c3 FROM tableName WHERE c1="P1_542" and c2="P2_23" ] Point Query 2: 151, 747, 149 [sql: SELECT c3, c5 FROM tableName WHERE c1="P1_52" and c7=4] Point Query 3: 128, 530, 141 [sql: SELECT c4, c9 FROM tableName WHERE c1="P1_43" and c8<3] Filter Query 0: 212, 1292, 124 [sql: SELECT * FROM tableName WHERE c2="P2_43" ] Filter Query 1: 214, 1271, 329 [sql: SELECT * FROM tableName WHERE c3="P3_3" ] Filter Query 2: 203, 1216, 102 [sql: SELECT * FROM tableName WHERE c2="P2_32" and c3="P3_23" ] Filter Query 3: 274, 1256, 108 [sql: SELECT * FROM tableName WHERE c3="P3_28" and c4="P4_3" ] Scan Query 0: 152, 345, 306 [sql: SELECT sum(c7), sum(c8), avg(c9), max(c10) FROM tableName ] Scan Query 1: 133, 344, 86 [sql: SELECT sum(c7) FROM tableName WHERE c2="P2_32" ] Scan Query 2: 122, 485, 126 [sql: SELECT sum(c7), sum(c8), sum(9), sum(c10) FROM tableName WHERE c4="P4_4" ] Scan Query 3: 141, 451, 168 [sql: SELECT sum(c7), sum(c8), sum(9), sum(c10) FROM tableName WHERE c2="P2_75" and c6<5 ] Total time: 8718.807424, 20070.015716, 8191.425242 ```
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---