|
| 1 | +================================================================================================ |
| 2 | +Benchmark for performance of JSON parsing |
| 3 | +================================================================================================ |
| 4 | + |
| 5 | +Preparing data for benchmarking ... |
| 6 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 7 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 8 | +JSON schema inferring: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 9 | +------------------------------------------------------------------------------------------------------------------------ |
| 10 | +No encoding 70863 71147 417 1.4 708.6 1.0X |
| 11 | +UTF-8 is set 133520 133658 131 0.7 1335.2 0.5X |
| 12 | + |
| 13 | +Preparing data for benchmarking ... |
| 14 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 15 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 16 | +count a short column: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 17 | +------------------------------------------------------------------------------------------------------------------------ |
| 18 | +No encoding 44462 44655 313 2.2 444.6 1.0X |
| 19 | +UTF-8 is set 89342 89386 53 1.1 893.4 0.5X |
| 20 | + |
| 21 | +Preparing data for benchmarking ... |
| 22 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 23 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 24 | +count a wide column: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 25 | +------------------------------------------------------------------------------------------------------------------------ |
| 26 | +No encoding 58617 59071 541 0.2 5861.7 1.0X |
| 27 | +UTF-8 is set 102650 102948 493 0.1 10265.0 0.6X |
| 28 | + |
| 29 | +Preparing data for benchmarking ... |
| 30 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 31 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 32 | +select wide row: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 33 | +------------------------------------------------------------------------------------------------------------------------ |
| 34 | +No encoding 168197 168256 61 0.0 336393.0 1.0X |
| 35 | +UTF-8 is set 191539 191724 186 0.0 383078.2 0.9X |
| 36 | + |
| 37 | +Preparing data for benchmarking ... |
| 38 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 39 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 40 | +Select a subset of 10 columns: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 41 | +------------------------------------------------------------------------------------------------------------------------ |
| 42 | +Select 10 columns 18983 18998 22 0.5 1898.3 1.0X |
| 43 | +Select 1 column 23544 23575 32 0.4 2354.4 0.8X |
| 44 | + |
| 45 | +Preparing data for benchmarking ... |
| 46 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 47 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 48 | +creation of JSON parser per line: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 49 | +------------------------------------------------------------------------------------------------------------------------ |
| 50 | +Short column without encoding 9336 9402 66 1.1 933.6 1.0X |
| 51 | +Short column with UTF-8 13310 13870 489 0.8 1331.0 0.7X |
| 52 | +Wide column without encoding 112821 113012 202 0.1 11282.1 0.1X |
| 53 | +Wide column with UTF-8 156408 156910 776 0.1 15640.8 0.1X |
| 54 | + |
| 55 | +Preparing data for benchmarking ... |
| 56 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 57 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 58 | +JSON functions: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 59 | +------------------------------------------------------------------------------------------------------------------------ |
| 60 | +Text read 743 744 1 13.5 74.3 1.0X |
| 61 | +from_json 22379 22566 279 0.4 2237.9 0.0X |
| 62 | +json_tuple 32201 32271 89 0.3 3220.1 0.0X |
| 63 | +get_json_object 21973 22405 375 0.5 2197.3 0.0X |
| 64 | + |
| 65 | +Preparing data for benchmarking ... |
| 66 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 67 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 68 | +Dataset of json strings: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 69 | +------------------------------------------------------------------------------------------------------------------------ |
| 70 | +Text read 3771 3780 8 13.3 75.4 1.0X |
| 71 | +schema inferring 34808 35213 506 1.4 696.2 0.1X |
| 72 | +parsing 36917 38889 1757 1.4 738.3 0.1X |
| 73 | + |
| 74 | +Preparing data for benchmarking ... |
| 75 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 76 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 77 | +Json files in the per-line mode: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 78 | +------------------------------------------------------------------------------------------------------------------------ |
| 79 | +Text read 11928 11955 38 4.2 238.6 1.0X |
| 80 | +Schema inferring 44716 44921 220 1.1 894.3 0.3X |
| 81 | +Parsing without charset 35749 35838 77 1.4 715.0 0.3X |
| 82 | +Parsing with UTF-8 50521 50530 12 1.0 1010.4 0.2X |
| 83 | + |
| 84 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 85 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 86 | +Write dates and timestamps: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 87 | +------------------------------------------------------------------------------------------------------------------------ |
| 88 | +Create a dataset of timestamps 2473 2487 18 4.0 247.3 1.0X |
| 89 | +to_json(timestamp) 16100 16284 236 0.6 1610.0 0.2X |
| 90 | +write timestamps to files 13226 13852 676 0.8 1322.6 0.2X |
| 91 | +Create a dataset of dates 2661 2680 16 3.8 266.1 0.9X |
| 92 | +to_json(date) 10696 10730 55 0.9 1069.6 0.2X |
| 93 | +write dates to files 8543 8926 384 1.2 854.3 0.3X |
| 94 | + |
| 95 | +OpenJDK 64-Bit Server VM 11.0.4+11-LTS on Linux 3.10.0-862.3.2.el7.x86_64 |
| 96 | +Intel(R) Xeon(R) CPU E5-2670 v2 @ 2.50GHz |
| 97 | +Read dates and timestamps: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| 98 | +------------------------------------------------------------------------------------------------------------------------ |
| 99 | +read timestamp text from files 2822 2829 8 3.5 282.2 1.0X |
| 100 | +read timestamps from files 34884 34900 23 0.3 3488.4 0.1X |
| 101 | +infer timestamps from files 70310 71551 1079 0.1 7031.0 0.0X |
| 102 | +read date text from files 2649 2655 6 3.8 264.9 1.1X |
| 103 | +read date from files 22875 22904 33 0.4 2287.5 0.1X |
| 104 | +timestamp strings 4025 4059 31 2.5 402.5 0.7X |
| 105 | +parse timestamps from Dataset[String] 43040 43157 115 0.2 4304.0 0.1X |
| 106 | +infer timestamps from Dataset[String] 81762 81927 144 0.1 8176.2 0.0X |
| 107 | +date strings 4899 4913 21 2.0 489.9 0.6X |
| 108 | +parse dates from Dataset[String] 33530 33560 27 0.3 3353.0 0.1X |
| 109 | +from_json(timestamp) 60762 60877 142 0.2 6076.2 0.0X |
| 110 | +from_json(date) 52482 52620 150 0.2 5248.2 0.1X |
| 111 | + |
| 112 | + |
0 commit comments