0001 ================================================================================================
0002 SQL Single Numeric Column Scan
0003 ================================================================================================
0004
0005 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0006 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0007 SQL Single TINYINT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0008 ------------------------------------------------------------------------------------------------------------------------
0009 SQL CSV 24716 24743 38 0.6 1571.4 1.0X
0010 SQL Json 9669 9686 25 1.6 614.7 2.6X
0011 SQL Parquet Vectorized 172 193 21 91.2 11.0 143.4X
0012 SQL Parquet MR 1929 1942 18 8.2 122.7 12.8X
0013 SQL ORC Vectorized 247 266 19 63.6 15.7 99.9X
0014 SQL ORC MR 1640 1660 29 9.6 104.3 15.1X
0015
0016 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0017 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0018 Parquet Reader Single TINYINT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0019 ------------------------------------------------------------------------------------------------------------------------
0020 ParquetReader Vectorized 197 200 4 79.9 12.5 1.0X
0021 ParquetReader Vectorized -> Row 96 98 3 164.1 6.1 2.1X
0022
0023 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0024 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0025 SQL Single SMALLINT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0026 ------------------------------------------------------------------------------------------------------------------------
0027 SQL CSV 25320 25343 32 0.6 1609.8 1.0X
0028 SQL Json 10460 10465 8 1.5 665.0 2.4X
0029 SQL Parquet Vectorized 206 218 13 76.5 13.1 123.2X
0030 SQL Parquet MR 2032 2036 6 7.7 129.2 12.5X
0031 SQL ORC Vectorized 295 301 4 53.4 18.7 85.9X
0032 SQL ORC MR 1867 1885 25 8.4 118.7 13.6X
0033
0034 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0035 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0036 Parquet Reader Single SMALLINT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0037 ------------------------------------------------------------------------------------------------------------------------
0038 ParquetReader Vectorized 288 294 6 54.6 18.3 1.0X
0039 ParquetReader Vectorized -> Row 252 254 4 62.3 16.0 1.1X
0040
0041 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0042 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0043 SQL Single INT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0044 ------------------------------------------------------------------------------------------------------------------------
0045 SQL CSV 27385 27423 54 0.6 1741.1 1.0X
0046 SQL Json 10118 10133 20 1.6 643.3 2.7X
0047 SQL Parquet Vectorized 180 189 10 87.4 11.4 152.1X
0048 SQL Parquet MR 2548 2552 6 6.2 162.0 10.7X
0049 SQL ORC Vectorized 306 312 8 51.4 19.4 89.5X
0050 SQL ORC MR 1882 1927 64 8.4 119.6 14.6X
0051
0052 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0053 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0054 Parquet Reader Single INT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0055 ------------------------------------------------------------------------------------------------------------------------
0056 ParquetReader Vectorized 255 260 7 61.7 16.2 1.0X
0057 ParquetReader Vectorized -> Row 252 257 6 62.4 16.0 1.0X
0058
0059 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0060 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0061 SQL Single BIGINT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0062 ------------------------------------------------------------------------------------------------------------------------
0063 SQL CSV 36971 37037 94 0.4 2350.5 1.0X
0064 SQL Json 13285 13300 22 1.2 844.6 2.8X
0065 SQL Parquet Vectorized 275 285 5 57.1 17.5 134.3X
0066 SQL Parquet MR 2599 2603 6 6.1 165.3 14.2X
0067 SQL ORC Vectorized 386 395 5 40.7 24.6 95.7X
0068 SQL ORC MR 2059 2075 22 7.6 130.9 18.0X
0069
0070 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0071 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0072 Parquet Reader Single BIGINT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0073 ------------------------------------------------------------------------------------------------------------------------
0074 ParquetReader Vectorized 352 361 14 44.7 22.4 1.0X
0075 ParquetReader Vectorized -> Row 386 392 8 40.7 24.6 0.9X
0076
0077 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0078 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0079 SQL Single FLOAT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0080 ------------------------------------------------------------------------------------------------------------------------
0081 SQL CSV 29272 29322 71 0.5 1861.1 1.0X
0082 SQL Json 15022 15099 108 1.0 955.1 1.9X
0083 SQL Parquet Vectorized 172 178 6 91.5 10.9 170.2X
0084 SQL Parquet MR 2184 2206 31 7.2 138.9 13.4X
0085 SQL ORC Vectorized 477 485 6 32.9 30.4 61.3X
0086 SQL ORC MR 2036 2054 26 7.7 129.4 14.4X
0087
0088 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0089 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0090 Parquet Reader Single FLOAT Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0091 ------------------------------------------------------------------------------------------------------------------------
0092 ParquetReader Vectorized 251 255 5 62.6 16.0 1.0X
0093 ParquetReader Vectorized -> Row 248 254 7 63.5 15.7 1.0X
0094
0095 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0096 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0097 SQL Single DOUBLE Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0098 ------------------------------------------------------------------------------------------------------------------------
0099 SQL CSV 38020 38024 6 0.4 2417.2 1.0X
0100 SQL Json 20449 20463 19 0.8 1300.1 1.9X
0101 SQL Parquet Vectorized 268 274 8 58.7 17.0 141.8X
0102 SQL Parquet MR 2484 2493 12 6.3 157.9 15.3X
0103 SQL ORC Vectorized 580 582 2 27.1 36.9 65.6X
0104 SQL ORC MR 2179 2199 29 7.2 138.5 17.5X
0105
0106 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0107 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0108 Parquet Reader Single DOUBLE Column Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0109 ------------------------------------------------------------------------------------------------------------------------
0110 ParquetReader Vectorized 344 350 7 45.7 21.9 1.0X
0111 ParquetReader Vectorized -> Row 346 352 12 45.5 22.0 1.0X
0112
0113
0114 ================================================================================================
0115 Int and String Scan
0116 ================================================================================================
0117
0118 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0119 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0120 Int and String Scan: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0121 ------------------------------------------------------------------------------------------------------------------------
0122 SQL CSV 27652 28221 804 0.4 2637.1 1.0X
0123 SQL Json 12827 12842 21 0.8 1223.3 2.2X
0124 SQL Parquet Vectorized 2297 2311 19 4.6 219.1 12.0X
0125 SQL Parquet MR 4207 4217 15 2.5 401.2 6.6X
0126 SQL ORC Vectorized 2316 2342 36 4.5 220.9 11.9X
0127 SQL ORC MR 4158 4236 110 2.5 396.5 6.7X
0128
0129
0130 ================================================================================================
0131 Repeated String Scan
0132 ================================================================================================
0133
0134 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0135 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0136 Repeated String: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0137 ------------------------------------------------------------------------------------------------------------------------
0138 SQL CSV 19185 19343 224 0.5 1829.6 1.0X
0139 SQL Json 7682 7692 14 1.4 732.6 2.5X
0140 SQL Parquet Vectorized 796 805 9 13.2 75.9 24.1X
0141 SQL Parquet MR 1880 1891 17 5.6 179.2 10.2X
0142 SQL ORC Vectorized 553 558 5 19.0 52.7 34.7X
0143 SQL ORC MR 2105 2128 32 5.0 200.8 9.1X
0144
0145
0146 ================================================================================================
0147 Partitioned Table Scan
0148 ================================================================================================
0149
0150 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0151 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0152 Partitioned Table: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0153 ------------------------------------------------------------------------------------------------------------------------
0154 Data column - CSV 43759 43811 73 0.4 2782.1 1.0X
0155 Data column - Json 13866 13874 11 1.1 881.6 3.2X
0156 Data column - Parquet Vectorized 292 302 10 53.9 18.5 150.1X
0157 Data column - Parquet MR 2681 2697 23 5.9 170.5 16.3X
0158 Data column - ORC Vectorized 416 422 12 37.8 26.4 105.2X
0159 Data column - ORC MR 2256 2275 27 7.0 143.4 19.4X
0160 Partition column - CSV 13909 13949 56 1.1 884.3 3.1X
0161 Partition column - Json 11248 11252 7 1.4 715.1 3.9X
0162 Partition column - Parquet Vectorized 83 95 13 189.4 5.3 526.9X
0163 Partition column - Parquet MR 1531 1532 2 10.3 97.3 28.6X
0164 Partition column - ORC Vectorized 81 97 17 193.1 5.2 537.3X
0165 Partition column - ORC MR 1557 1570 19 10.1 99.0 28.1X
0166 Both columns - CSV 48341 48524 259 0.3 3073.4 0.9X
0167 Both columns - Json 13636 13652 23 1.2 866.9 3.2X
0168 Both columns - Parquet Vectorized 341 354 16 46.1 21.7 128.2X
0169 Both columns - Parquet MR 2806 2825 26 5.6 178.4 15.6X
0170 Both columns - ORC Vectorized 548 554 8 28.7 34.8 79.8X
0171 Both columns - ORC MR 2602 2632 43 6.0 165.4 16.8X
0172
0173
0174 ================================================================================================
0175 String with Nulls Scan
0176 ================================================================================================
0177
0178 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0179 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0180 String with Nulls Scan (0.0%): Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0181 ------------------------------------------------------------------------------------------------------------------------
0182 SQL CSV 22570 22687 166 0.5 2152.4 1.0X
0183 SQL Json 11103 11129 38 0.9 1058.8 2.0X
0184 SQL Parquet Vectorized 1508 1516 12 7.0 143.8 15.0X
0185 SQL Parquet MR 3686 3692 9 2.8 351.5 6.1X
0186 ParquetReader Vectorized 1117 1133 22 9.4 106.6 20.2X
0187 SQL ORC Vectorized 1195 1212 24 8.8 114.0 18.9X
0188 SQL ORC MR 3617 3618 3 2.9 344.9 6.2X
0189
0190 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0191 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0192 String with Nulls Scan (50.0%): Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0193 ------------------------------------------------------------------------------------------------------------------------
0194 SQL CSV 19569 19819 354 0.5 1866.2 1.0X
0195 SQL Json 8292 8308 22 1.3 790.8 2.4X
0196 SQL Parquet Vectorized 1107 1136 41 9.5 105.6 17.7X
0197 SQL Parquet MR 2784 2812 39 3.8 265.5 7.0X
0198 ParquetReader Vectorized 990 994 5 10.6 94.4 19.8X
0199 SQL ORC Vectorized 1198 1199 2 8.8 114.2 16.3X
0200 SQL ORC MR 3164 3195 44 3.3 301.7 6.2X
0201
0202 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0203 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0204 String with Nulls Scan (95.0%): Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0205 ------------------------------------------------------------------------------------------------------------------------
0206 SQL CSV 15940 15969 41 0.7 1520.1 1.0X
0207 SQL Json 4845 4845 0 2.2 462.0 3.3X
0208 SQL Parquet Vectorized 243 249 6 43.1 23.2 65.5X
0209 SQL Parquet MR 1732 1751 26 6.1 165.2 9.2X
0210 ParquetReader Vectorized 241 243 3 43.4 23.0 66.0X
0211 SQL ORC Vectorized 425 431 7 24.7 40.5 37.5X
0212 SQL ORC MR 1713 1728 20 6.1 163.4 9.3X
0213
0214
0215 ================================================================================================
0216 Single Column Scan From Wide Columns
0217 ================================================================================================
0218
0219 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0220 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0221 Single Column Scan from 10 columns: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0222 ------------------------------------------------------------------------------------------------------------------------
0223 SQL CSV 3838 3885 66 0.3 3660.4 1.0X
0224 SQL Json 3615 3615 0 0.3 3447.8 1.1X
0225 SQL Parquet Vectorized 66 74 8 15.8 63.2 57.9X
0226 SQL Parquet MR 230 237 6 4.6 219.3 16.7X
0227 SQL ORC Vectorized 72 77 9 14.5 68.9 53.1X
0228 SQL ORC MR 194 201 5 5.4 185.3 19.7X
0229
0230 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0231 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0232 Single Column Scan from 50 columns: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0233 ------------------------------------------------------------------------------------------------------------------------
0234 SQL CSV 8711 8754 60 0.1 8307.9 1.0X
0235 SQL Json 14414 14423 12 0.1 13746.5 0.6X
0236 SQL Parquet Vectorized 97 106 12 10.8 92.7 89.6X
0237 SQL Parquet MR 267 274 7 3.9 254.2 32.7X
0238 SQL ORC Vectorized 100 104 7 10.5 95.1 87.4X
0239 SQL ORC MR 226 230 6 4.6 215.2 38.6X
0240
0241 OpenJDK 64-Bit Server VM 1.8.0_232-8u232-b09-0ubuntu1~18.04.1-b09 on Linux 4.15.0-1044-aws
0242 Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz
0243 Single Column Scan from 100 columns: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
0244 ------------------------------------------------------------------------------------------------------------------------
0245 SQL CSV 14509 14596 123 0.1 13836.8 1.0X
0246 SQL Json 27545 27909 515 0.0 26269.1 0.5X
0247 SQL Parquet Vectorized 141 151 13 7.4 134.8 102.7X
0248 SQL Parquet MR 313 341 23 3.4 298.4 46.4X
0249 SQL ORC Vectorized 121 129 15 8.7 115.4 119.9X
0250 SQL ORC MR 252 269 33 4.2 240.3 57.6X
0251
0252