dongjoon-hyun commented on code in PR #54313:
URL: https://github.com/apache/spark/pull/54313#discussion_r2805653931
##########
sql/core/benchmarks/DataSourceReadBenchmark-results.txt:
##########
@@ -2,437 +2,437 @@
SQL Single Numeric Column Scan
================================================================================================
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single BOOLEAN Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 13035 13115
113 1.2 828.7 1.0X
-SQL Json 8550 8638
125 1.8 543.6 1.5X
-SQL Json with UnsafeRow 9735 9768
46 1.6 618.9 1.3X
-SQL Parquet Vectorized: DataPageV1 99 114
8 158.1 6.3 131.0X
-SQL Parquet Vectorized: DataPageV2 116 122
5 135.0 7.4 111.9X
-SQL Parquet MR: DataPageV1 1875 1876
2 8.4 119.2 7.0X
-SQL Parquet MR: DataPageV2 1777 1781
5 8.9 113.0 7.3X
-SQL ORC Vectorized 140 146
5 112.6 8.9 93.3X
-SQL ORC MR 1645 1648
4 9.6 104.6 7.9X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 10368 10430
88 1.5 659.2 1.0X
+SQL Json 8514 8587
104 1.8 541.3 1.2X
+SQL Json with UnsafeRow 9480 9519
56 1.7 602.7 1.1X
+SQL Parquet Vectorized: DataPageV1 96 110
11 163.0 6.1 107.5X
+SQL Parquet Vectorized: DataPageV2 98 109
8 160.8 6.2 106.0X
+SQL Parquet MR: DataPageV1 1776 1793
23 8.9 112.9 5.8X
+SQL Parquet MR: DataPageV2 1702 1713
15 9.2 108.2 6.1X
+SQL ORC Vectorized 144 150
6 109.5 9.1 72.2X
+SQL ORC MR 1546 1548
3 10.2 98.3 6.7X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Parquet Reader Single BOOLEAN Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------
-ParquetReader Vectorized: DataPageV1 88 90
1 177.8 5.6 1.0X
-ParquetReader Vectorized: DataPageV2 110 113
3 142.7 7.0 0.8X
-ParquetReader Vectorized -> Row: DataPageV1 72 74
1 218.8 4.6 1.2X
-ParquetReader Vectorized -> Row: DataPageV2 95 97
1 164.8 6.1 0.9X
+ParquetReader Vectorized: DataPageV1 97 98
1 161.5 6.2 1.0X
+ParquetReader Vectorized: DataPageV2 105 107
2 149.6 6.7 0.9X
+ParquetReader Vectorized -> Row: DataPageV1 73 74
1 215.0 4.7 1.3X
+ParquetReader Vectorized -> Row: DataPageV2 82 83
1 191.1 5.2 1.2X
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single TINYINT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 12001 12087
122 1.3 763.0 1.0X
-SQL Json 10982 11044
88 1.4 698.2 1.1X
-SQL Json with UnsafeRow 11780 11837
81 1.3 748.9 1.0X
-SQL Parquet Vectorized: DataPageV1 98 105
6 161.2 6.2 123.0X
-SQL Parquet Vectorized: DataPageV2 95 103
8 165.7 6.0 126.4X
-SQL Parquet MR: DataPageV1 1916 1938
31 8.2 121.8 6.3X
-SQL Parquet MR: DataPageV2 1854 1855
1 8.5 117.9 6.5X
-SQL ORC Vectorized 99 103
4 159.1 6.3 121.4X
-SQL ORC MR 1528 1583
77 10.3 97.2 7.9X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 9830 9846
23 1.6 625.0 1.0X
+SQL Json 9519 9533
21 1.7 605.2 1.0X
+SQL Json with UnsafeRow 9926 9985
83 1.6 631.1 1.0X
+SQL Parquet Vectorized: DataPageV1 133 138
4 117.8 8.5 73.6X
+SQL Parquet Vectorized: DataPageV2 132 137
4 119.3 8.4 74.6X
+SQL Parquet MR: DataPageV1 1852 1871
26 8.5 117.8 5.3X
+SQL Parquet MR: DataPageV2 1840 1927
123 8.5 117.0 5.3X
+SQL ORC Vectorized 100 105
4 157.3 6.4 98.3X
+SQL ORC MR 1493 1500
11 10.5 94.9 6.6X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Parquet Reader Single TINYINT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------
-ParquetReader Vectorized: DataPageV1 73 75
2 215.9 4.6 1.0X
-ParquetReader Vectorized: DataPageV2 73 75
1 214.9 4.7 1.0X
-ParquetReader Vectorized -> Row: DataPageV1 50 52
2 313.2 3.2 1.5X
-ParquetReader Vectorized -> Row: DataPageV2 50 51
1 313.1 3.2 1.4X
+ParquetReader Vectorized: DataPageV1 145 146
1 108.6 9.2 1.0X
+ParquetReader Vectorized: DataPageV2 145 146
1 108.4 9.2 1.0X
+ParquetReader Vectorized -> Row: DataPageV1 50 52
2 317.1 3.2 2.9X
+ParquetReader Vectorized -> Row: DataPageV2 50 52
1 313.0 3.2 2.9X
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single SMALLINT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 12715 12744
42 1.2 808.4 1.0X
-SQL Json 11912 11914
2 1.3 757.4 1.1X
-SQL Json with UnsafeRow 12449 12465
23 1.3 791.5 1.0X
-SQL Parquet Vectorized: DataPageV1 128 133
4 122.9 8.1 99.3X
-SQL Parquet Vectorized: DataPageV2 148 152
4 106.1 9.4 85.8X
-SQL Parquet MR: DataPageV1 1969 1993
34 8.0 125.2 6.5X
-SQL Parquet MR: DataPageV2 1923 1929
8 8.2 122.3 6.6X
-SQL ORC Vectorized 143 147
3 110.1 9.1 89.0X
-SQL ORC MR 1969 1971
4 8.0 125.2 6.5X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 9978 9995
24 1.6 634.4 1.0X
+SQL Json 9841 9854
19 1.6 625.7 1.0X
+SQL Json with UnsafeRow 10645 10648
4 1.5 676.8 0.9X
+SQL Parquet Vectorized: DataPageV1 129 133
6 122.3 8.2 77.6X
+SQL Parquet Vectorized: DataPageV2 153 159
5 103.1 9.7 65.4X
+SQL Parquet MR: DataPageV1 2044 2044
1 7.7 129.9 4.9X
+SQL Parquet MR: DataPageV2 1934 1935
1 8.1 123.0 5.2X
+SQL ORC Vectorized 138 144
5 114.4 8.7 72.6X
+SQL ORC MR 1571 1578
9 10.0 99.9 6.3X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Parquet Reader Single SMALLINT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------
-ParquetReader Vectorized: DataPageV1 159 163
3 98.8 10.1 1.0X
-ParquetReader Vectorized: DataPageV2 179 180
1 88.0 11.4 0.9X
-ParquetReader Vectorized -> Row: DataPageV1 157 158
2 100.4 10.0 1.0X
-ParquetReader Vectorized -> Row: DataPageV2 180 181
3 87.6 11.4 0.9X
+ParquetReader Vectorized: DataPageV1 165 167
1 95.3 10.5 1.0X
+ParquetReader Vectorized: DataPageV2 189 191
1 83.3 12.0 0.9X
+ParquetReader Vectorized -> Row: DataPageV1 155 157
2 101.3 9.9 1.1X
+ParquetReader Vectorized -> Row: DataPageV2 184 185
1 85.6 11.7 0.9X
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single INT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 13989 14016
38 1.1 889.4 1.0X
-SQL Json 10049 10075
37 1.6 638.9 1.4X
-SQL Json with UnsafeRow 10684 10697
17 1.5 679.3 1.3X
-SQL Parquet Vectorized: DataPageV1 122 127
4 129.1 7.7 114.8X
-SQL Parquet Vectorized: DataPageV2 192 200
7 81.9 12.2 72.8X
-SQL Parquet MR: DataPageV1 2006 2017
17 7.8 127.5 7.0X
-SQL Parquet MR: DataPageV2 2039 2057
26 7.7 129.6 6.9X
-SQL ORC Vectorized 142 149
6 110.7 9.0 98.5X
-SQL ORC MR 1793 1829
51 8.8 114.0 7.8X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 11189 11195
9 1.4 711.4 1.0X
+SQL Json 10290 10304
21 1.5 654.2 1.1X
+SQL Json with UnsafeRow 11092 11100
11 1.4 705.2 1.0X
+SQL Parquet Vectorized: DataPageV1 130 135
4 121.2 8.3 86.2X
+SQL Parquet Vectorized: DataPageV2 203 208
3 77.4 12.9 55.1X
+SQL Parquet MR: DataPageV1 2112 2130
27 7.4 134.2 5.3X
+SQL Parquet MR: DataPageV2 2012 2026
20 7.8 127.9 5.6X
+SQL ORC Vectorized 139 144
2 113.1 8.8 80.5X
+SQL ORC MR 1589 1600
15 9.9 101.0 7.0X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Parquet Reader Single INT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------
-ParquetReader Vectorized: DataPageV1 157 159
2 100.1 10.0 1.0X
-ParquetReader Vectorized: DataPageV2 223 225
1 70.4 14.2 0.7X
-ParquetReader Vectorized -> Row: DataPageV1 152 155
3 103.2 9.7 1.0X
-ParquetReader Vectorized -> Row: DataPageV2 224 226
1 70.1 14.3 0.7X
+ParquetReader Vectorized: DataPageV1 168 169
1 93.7 10.7 1.0X
+ParquetReader Vectorized: DataPageV2 242 244
1 65.0 15.4 0.7X
+ParquetReader Vectorized -> Row: DataPageV1 160 163
4 98.4 10.2 1.0X
+ParquetReader Vectorized -> Row: DataPageV2 236 237
1 66.7 15.0 0.7X
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single BIGINT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 13373 13375
3 1.2 850.2 1.0X
-SQL Json 10163 10188
34 1.5 646.2 1.3X
-SQL Json with UnsafeRow 10853 10860
10 1.4 690.0 1.2X
-SQL Parquet Vectorized: DataPageV1 304 308
4 51.8 19.3 44.0X
-SQL Parquet Vectorized: DataPageV2 196 200
9 80.4 12.4 68.4X
-SQL Parquet MR: DataPageV1 2626 2645
26 6.0 167.0 5.1X
-SQL Parquet MR: DataPageV2 2124 2141
24 7.4 135.0 6.3X
-SQL ORC Vectorized 128 136
7 122.5 8.2 104.1X
-SQL ORC MR 1993 1994
0 7.9 126.7 6.7X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 11035 11038
4 1.4 701.6 1.0X
+SQL Json 10311 10313
4 1.5 655.5 1.1X
+SQL Json with UnsafeRow 11108 11113
8 1.4 706.2 1.0X
+SQL Parquet Vectorized: DataPageV1 311 320
6 50.6 19.8 35.5X
+SQL Parquet Vectorized: DataPageV2 247 251
4 63.8 15.7 44.8X
+SQL Parquet MR: DataPageV1 2478 2488
14 6.3 157.5 4.5X
+SQL Parquet MR: DataPageV2 2051 2067
23 7.7 130.4 5.4X
+SQL ORC Vectorized 133 138
6 118.0 8.5 82.8X
+SQL ORC MR 1686 1689
4 9.3 107.2 6.5X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Parquet Reader Single BIGINT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------
-ParquetReader Vectorized: DataPageV1 333 336
2 47.3 21.2 1.0X
-ParquetReader Vectorized: DataPageV2 224 226
2 70.1 14.3 1.5X
-ParquetReader Vectorized -> Row: DataPageV1 354 355
1 44.5 22.5 0.9X
-ParquetReader Vectorized -> Row: DataPageV2 243 245
2 64.7 15.5 1.4X
+ParquetReader Vectorized: DataPageV1 366 372
8 42.9 23.3 1.0X
+ParquetReader Vectorized: DataPageV2 300 304
3 52.5 19.0 1.2X
+ParquetReader Vectorized -> Row: DataPageV1 364 367
3 43.2 23.2 1.0X
+ParquetReader Vectorized -> Row: DataPageV2 297 301
5 52.9 18.9 1.2X
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single FLOAT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 14040 14073
47 1.1 892.6 1.0X
-SQL Json 11667 11710
61 1.3 741.8 1.2X
-SQL Json with UnsafeRow 12474 12504
43 1.3 793.1 1.1X
-SQL Parquet Vectorized: DataPageV1 95 100
4 164.9 6.1 147.2X
-SQL Parquet Vectorized: DataPageV2 96 99
4 164.4 6.1 146.8X
-SQL Parquet MR: DataPageV1 2008 2025
24 7.8 127.7 7.0X
-SQL Parquet MR: DataPageV2 1863 1883
28 8.4 118.5 7.5X
-SQL ORC Vectorized 230 235
5 68.3 14.6 60.9X
-SQL ORC MR 1659 1669
14 9.5 105.5 8.5X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 11608 11615
9 1.4 738.0 1.0X
+SQL Json 12062 12085
32 1.3 766.9 1.0X
+SQL Json with UnsafeRow 12850 12860
15 1.2 817.0 0.9X
+SQL Parquet Vectorized: DataPageV1 144 148
4 109.6 9.1 80.9X
+SQL Parquet Vectorized: DataPageV2 140 144
4 112.1 8.9 82.7X
+SQL Parquet MR: DataPageV1 2144 2147
4 7.3 136.3 5.4X
+SQL Parquet MR: DataPageV2 2068 2071
4 7.6 131.5 5.6X
+SQL ORC Vectorized 237 242
4 66.2 15.1 48.9X
+SQL ORC MR 1678 1693
22 9.4 106.7 6.9X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Parquet Reader Single FLOAT Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------
-ParquetReader Vectorized: DataPageV1 146 147
1 107.7 9.3 1.0X
-ParquetReader Vectorized: DataPageV2 144 146
1 108.9 9.2 1.0X
-ParquetReader Vectorized -> Row: DataPageV1 146 148
2 107.8 9.3 1.0X
-ParquetReader Vectorized -> Row: DataPageV2 144 147
4 109.0 9.2 1.0X
+ParquetReader Vectorized: DataPageV1 162 164
1 97.0 10.3 1.0X
+ParquetReader Vectorized: DataPageV2 162 163
2 97.3 10.3 1.0X
+ParquetReader Vectorized -> Row: DataPageV1 154 158
3 102.0 9.8 1.1X
+ParquetReader Vectorized -> Row: DataPageV2 157 159
3 100.3 10.0 1.0X
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single DOUBLE Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 14089 14117
39 1.1 895.8 1.0X
-SQL Json 11634 11669
49 1.4 739.7 1.2X
-SQL Json with UnsafeRow 12486 12496
14 1.3 793.9 1.1X
-SQL Parquet Vectorized: DataPageV1 282 287
5 55.7 17.9 49.9X
-SQL Parquet Vectorized: DataPageV2 280 287
6 56.2 17.8 50.3X
-SQL Parquet MR: DataPageV1 2396 2424
40 6.6 152.3 5.9X
-SQL Parquet MR: DataPageV2 2352 2376
34 6.7 149.5 6.0X
-SQL ORC Vectorized 598 604
5 26.3 38.0 23.6X
-SQL ORC MR 2048 2065
25 7.7 130.2 6.9X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 11816 11843
38 1.3 751.3 1.0X
+SQL Json 12149 12158
12 1.3 772.4 1.0X
+SQL Json with UnsafeRow 12973 12985
17 1.2 824.8 0.9X
+SQL Parquet Vectorized: DataPageV1 286 292
6 55.1 18.2 41.4X
+SQL Parquet Vectorized: DataPageV2 280 289
5 56.1 17.8 42.2X
+SQL Parquet MR: DataPageV1 2465 2472
10 6.4 156.7 4.8X
+SQL Parquet MR: DataPageV2 2401 2405
7 6.6 152.6 4.9X
+SQL ORC Vectorized 579 583
4 27.2 36.8 20.4X
+SQL ORC MR 2078 2078
1 7.6 132.1 5.7X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Parquet Reader Single DOUBLE Column Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------
-ParquetReader Vectorized: DataPageV1 336 337
1 46.8 21.4 1.0X
-ParquetReader Vectorized: DataPageV2 336 337
2 46.9 21.3 1.0X
-ParquetReader Vectorized -> Row: DataPageV1 354 368
30 44.4 22.5 0.9X
-ParquetReader Vectorized -> Row: DataPageV2 352 353
1 44.7 22.4 1.0X
+ParquetReader Vectorized: DataPageV1 367 374
8 42.8 23.4 1.0X
+ParquetReader Vectorized: DataPageV2 366 368
2 42.9 23.3 1.0X
+ParquetReader Vectorized -> Row: DataPageV1 345 355
9 45.6 21.9 1.1X
+ParquetReader Vectorized -> Row: DataPageV2 344 345
2 45.8 21.9 1.1X
================================================================================================
SQL Single Numeric Column Scan in Struct
================================================================================================
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single TINYINT Column Scan in Struct: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------------------------------------------------------
-SQL ORC MR 2265
2273 12 6.9 144.0 1.0X
-SQL ORC Vectorized (Nested Column Disabled) 2269
2270 1 6.9 144.2 1.0X
-SQL ORC Vectorized (Nested Column Enabled) 136
142 4 115.3 8.7 16.6X
-SQL Parquet MR: DataPageV1 2392
2396 7 6.6 152.0 0.9X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 3060
3060 1 5.1 194.5 0.7X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 105
110 4 150.2 6.7 21.6X
-SQL Parquet MR: DataPageV2 2336
2339 4 6.7 148.5 1.0X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2858
2869 16 5.5 181.7 0.8X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 103
108 4 152.0 6.6 21.9X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL ORC MR 2060
2063 4 7.6 131.0 1.0X
+SQL ORC Vectorized (Nested Column Disabled) 2050
2078 40 7.7 130.3 1.0X
+SQL ORC Vectorized (Nested Column Enabled) 138
142 3 113.7 8.8 14.9X
+SQL Parquet MR: DataPageV1 2165
2175 14 7.3 137.6 1.0X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 2637
2655 26 6.0 167.7 0.8X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 206
209 2 76.5 13.1 10.0X
+SQL Parquet MR: DataPageV2 2128
2130 4 7.4 135.3 1.0X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2725
2727 4 5.8 173.2 0.8X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 206
210 3 76.4 13.1 10.0X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single SMALLINT Column Scan in Struct: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------------------------------------------------------
-SQL ORC MR 2252
2257 7 7.0 143.2 1.0X
-SQL ORC Vectorized (Nested Column Disabled) 2245
2256 15 7.0 142.8 1.0X
-SQL ORC Vectorized (Nested Column Enabled) 279
288 19 56.5 17.7 8.1X
-SQL Parquet MR: DataPageV1 2400
2418 25 6.6 152.6 0.9X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 2844
2850 10 5.5 180.8 0.8X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 138
142 3 114.0 8.8 16.3X
-SQL Parquet MR: DataPageV2 2331
2345 19 6.7 148.2 1.0X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2680
2737 81 5.9 170.4 0.8X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 259
263 4 60.8 16.4 8.7X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL ORC MR 2039
2054 22 7.7 129.6 1.0X
+SQL ORC Vectorized (Nested Column Disabled) 2060
2066 8 7.6 131.0 1.0X
+SQL ORC Vectorized (Nested Column Enabled) 277
282 6 56.8 17.6 7.4X
+SQL Parquet MR: DataPageV1 2370
2384 19 6.6 150.7 0.9X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 2868
2880 17 5.5 182.3 0.7X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 202
205 3 78.0 12.8 10.1X
+SQL Parquet MR: DataPageV2 2245
2263 26 7.0 142.7 0.9X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2741
2741 1 5.7 174.3 0.7X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 296
302 5 53.1 18.8 6.9X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single INT Column Scan in Struct: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------------------------------------------------------
-SQL ORC MR 2228
2250 31 7.1 141.6 1.0X
-SQL ORC Vectorized (Nested Column Disabled) 2272
2289 24 6.9 144.5 1.0X
-SQL ORC Vectorized (Nested Column Enabled) 277
283 5 56.7 17.6 8.0X
-SQL Parquet MR: DataPageV1 2393
2401 12 6.6 152.1 0.9X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 2849
2870 29 5.5 181.1 0.8X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 140
143 3 112.6 8.9 15.9X
-SQL Parquet MR: DataPageV2 2314
2346 45 6.8 147.1 1.0X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2731
2765 48 5.8 173.7 0.8X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 275
281 4 57.1 17.5 8.1X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL ORC MR 2196
2278 116 7.2 139.6 1.0X
+SQL ORC Vectorized (Nested Column Disabled) 2181
2193 18 7.2 138.6 1.0X
+SQL ORC Vectorized (Nested Column Enabled) 280
284 3 56.1 17.8 7.8X
+SQL Parquet MR: DataPageV1 2389
2398 13 6.6 151.9 0.9X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 2774
2800 37 5.7 176.4 0.8X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 209
212 4 75.3 13.3 10.5X
+SQL Parquet MR: DataPageV2 2331
2332 2 6.7 148.2 0.9X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2718
2741 33 5.8 172.8 0.8X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 332
334 2 47.4 21.1 6.6X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single BIGINT Column Scan in Struct: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------------------------------------------------------
-SQL ORC MR 2196
2227 43 7.2 139.6 1.0X
-SQL ORC Vectorized (Nested Column Disabled) 2201
2207 10 7.1 139.9 1.0X
-SQL ORC Vectorized (Nested Column Enabled) 278
293 29 56.7 17.7 7.9X
-SQL Parquet MR: DataPageV1 2817
2843 37 5.6 179.1 0.8X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 3278
3302 33 4.8 208.4 0.7X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 311
314 2 50.6 19.7 7.1X
-SQL Parquet MR: DataPageV2 2305
2321 22 6.8 146.6 1.0X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2672
2699 38 5.9 169.9 0.8X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 195
199 4 80.7 12.4 11.3X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL ORC MR 2091
2104 18 7.5 133.0 1.0X
+SQL ORC Vectorized (Nested Column Disabled) 2103
2118 22 7.5 133.7 1.0X
+SQL ORC Vectorized (Nested Column Enabled) 275
278 3 57.2 17.5 7.6X
+SQL Parquet MR: DataPageV1 2767
2780 18 5.7 175.9 0.8X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 3427
3433 9 4.6 217.9 0.6X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 389
428 22 40.4 24.7 5.4X
+SQL Parquet MR: DataPageV2 2352
2365 18 6.7 149.6 0.9X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2915
2928 18 5.4 185.3 0.7X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 334
337 3 47.1 21.2 6.3X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single FLOAT Column Scan in Struct: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------------------------------------------------------
-SQL ORC MR 2442
2470 40 6.4 155.2 1.0X
-SQL ORC Vectorized (Nested Column Disabled) 2486
2516 42 6.3 158.1 1.0X
-SQL ORC Vectorized (Nested Column Enabled) 355
358 4 44.3 22.6 6.9X
-SQL Parquet MR: DataPageV1 2419
2419 1 6.5 153.8 1.0X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 3011
3015 5 5.2 191.4 0.8X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 105
113 7 149.2 6.7 23.2X
-SQL Parquet MR: DataPageV2 2287
2297 14 6.9 145.4 1.1X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2873
2883 15 5.5 182.6 0.8X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 105
112 7 149.4 6.7 23.2X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL ORC MR 2217
2242 35 7.1 140.9 1.0X
+SQL ORC Vectorized (Nested Column Disabled) 2188
2223 50 7.2 139.1 1.0X
+SQL ORC Vectorized (Nested Column Enabled) 354
359 5 44.5 22.5 6.3X
+SQL Parquet MR: DataPageV1 2323
2329 8 6.8 147.7 1.0X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 2719
2726 9 5.8 172.9 0.8X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 207
209 2 76.1 13.1 10.7X
+SQL Parquet MR: DataPageV2 2253
2257 5 7.0 143.2 1.0X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 2703
2794 128 5.8 171.9 0.8X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 205
207 2 76.6 13.0 10.8X
+
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Single DOUBLE Column Scan in Struct: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------------------------------------------------------
-SQL ORC MR 2696
2714 26 5.8 171.4 1.0X
-SQL ORC Vectorized (Nested Column Disabled) 2699
2714 21 5.8 171.6 1.0X
-SQL ORC Vectorized (Nested Column Enabled) 751
760 10 20.9 47.8 3.6X
-SQL Parquet MR: DataPageV1 2834
2865 44 5.6 180.2 1.0X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 3256
3264 11 4.8 207.0 0.8X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 295
300 6 53.3 18.8 9.1X
-SQL Parquet MR: DataPageV2 2853
2882 40 5.5 181.4 0.9X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 3223
3235 17 4.9 204.9 0.8X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 292
299 9 53.8 18.6 9.2X
+SQL ORC MR 2574
2584 15 6.1 163.6 1.0X
+SQL ORC Vectorized (Nested Column Disabled) 2573
2576 5 6.1 163.6 1.0X
+SQL ORC Vectorized (Nested Column Enabled) 731
735 3 21.5 46.5 3.5X
+SQL Parquet MR: DataPageV1 2735
2749 20 5.8 173.9 0.9X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 3149
3162 18 5.0 200.2 0.8X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 397
420 13 39.7 25.2 6.5X
+SQL Parquet MR: DataPageV2 2692
2706 20 5.8 171.1 1.0X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 3153
3154 1 5.0 200.5 0.8X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 390
395 6 40.3 24.8 6.6X
================================================================================================
SQL Nested Column Scan
================================================================================================
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
SQL Nested Column Scan: Best Time(ms)
Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------------------------------------------------------
-SQL ORC MR 13024
13164 105 0.1 12420.6 1.0X
-SQL ORC Vectorized (Nested Column Disabled) 13007
13159 112 0.1 12404.0 1.0X
-SQL ORC Vectorized (Nested Column Enabled) 7175
7249 46 0.1 6842.5 1.8X
-SQL Parquet MR: DataPageV1 8554
8604 45 0.1 8158.1 1.5X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 8959
9003 26 0.1 8544.0 1.5X
-SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 5782
5846 54 0.2 5514.5 2.3X
-SQL Parquet MR: DataPageV2 9459
9520 37 0.1 9020.9 1.4X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 9806
9882 58 0.1 9351.3 1.3X
-SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 5517
5612 75 0.2 5261.4 2.4X
+SQL ORC MR 13091
13246 138 0.1 12484.2 1.0X
+SQL ORC Vectorized (Nested Column Disabled) 13192
13303 104 0.1 12580.8 1.0X
+SQL ORC Vectorized (Nested Column Enabled) 7209
7243 19 0.1 6874.7 1.8X
+SQL Parquet MR: DataPageV1 8566
8618 30 0.1 8169.1 1.5X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Disabled) 8901
8940 30 0.1 8488.5 1.5X
+SQL Parquet Vectorized: DataPageV1 (Nested Column Enabled) 5744
5818 46 0.2 5478.2 2.3X
+SQL Parquet MR: DataPageV2 9499
9544 38 0.1 9059.2 1.4X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Disabled) 9787
9826 31 0.1 9333.6 1.3X
+SQL Parquet Vectorized: DataPageV2 (Nested Column Enabled) 5590
5670 54 0.2 5331.1 2.3X
================================================================================================
Int and String Scan
================================================================================================
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Int and String Scan: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 12945 13068
174 0.8 1234.5 1.0X
-SQL Json 10665 10697
45 1.0 1017.1 1.2X
-SQL Parquet Vectorized: DataPageV1 1804 1822
26 5.8 172.0 7.2X
-SQL Parquet Vectorized: DataPageV2 1932 1960
39 5.4 184.3 6.7X
-SQL Parquet MR: DataPageV1 3801 3834
47 2.8 362.5 3.4X
-SQL Parquet MR: DataPageV2 3858 3875
24 2.7 367.9 3.4X
-SQL ORC Vectorized 1877 1877
0 5.6 179.0 6.9X
-SQL ORC MR 3568 3574
9 2.9 340.2 3.6X
+SQL CSV 10322 10378
80 1.0 984.4 1.0X
+SQL Json 11113 11142
42 0.9 1059.8 0.9X
+SQL Parquet Vectorized: DataPageV1 1792 1796
6 5.9 170.9 5.8X
+SQL Parquet Vectorized: DataPageV2 2090 2104
20 5.0 199.3 4.9X
+SQL Parquet MR: DataPageV1 4071 4075
6 2.6 388.2 2.5X
+SQL Parquet MR: DataPageV2 3985 3986
2 2.6 380.1 2.6X
+SQL ORC Vectorized 1864 1872
11 5.6 177.8 5.5X
+SQL ORC MR 3579 3580
1 2.9 341.3 2.9X
================================================================================================
Repeated String Scan
================================================================================================
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Repeated String: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 7328 7341
19 1.4 698.8 1.0X
-SQL Json 6889 6894
7 1.5 657.0 1.1X
-SQL Parquet Vectorized: DataPageV1 482 487
3 21.7 46.0 15.2X
-SQL Parquet Vectorized: DataPageV2 485 509
33 21.6 46.3 15.1X
-SQL Parquet MR: DataPageV1 1578 1581
4 6.6 150.5 4.6X
-SQL Parquet MR: DataPageV2 1527 1531
6 6.9 145.6 4.8X
-SQL ORC Vectorized 373 379
4 28.1 35.6 19.6X
-SQL ORC MR 1634 1638
6 6.4 155.8 4.5X
+SQL CSV 5970 5999
41 1.8 569.3 1.0X
+SQL Json 6932 6960
40 1.5 661.1 0.9X
+SQL Parquet Vectorized: DataPageV1 470 476
5 22.3 44.8 12.7X
+SQL Parquet Vectorized: DataPageV2 485 487
3 21.6 46.2 12.3X
+SQL Parquet MR: DataPageV1 1620 1624
5 6.5 154.5 3.7X
+SQL Parquet MR: DataPageV2 1567 1573
8 6.7 149.5 3.8X
+SQL ORC Vectorized 373 380
9 28.1 35.6 16.0X
+SQL ORC MR 1662 1663
1 6.3 158.5 3.6X
================================================================================================
Partitioned Table Scan
================================================================================================
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
Partitioned Table: Best Time(ms) Avg
Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative
---------------------------------------------------------------------------------------------------------------------------------
-Data column - CSV 13765
13812 67 1.1 875.2 1.0X
-Data column - Json 9826
9858 45 1.6 624.7 1.4X
-Data column - Parquet Vectorized: DataPageV1 116
119 3 135.0 7.4 118.2X
-Data column - Parquet Vectorized: DataPageV2 259
265 7 60.8 16.4 53.2X
-Data column - Parquet MR: DataPageV1 2256
2258 3 7.0 143.4 6.1X
-Data column - Parquet MR: DataPageV2 2144
2150 8 7.3 136.3 6.4X
-Data column - ORC Vectorized 147
153 3 106.8 9.4 93.5X
-Data column - ORC MR 1864
1871 9 8.4 118.5 7.4X
-Partition column - CSV 3408
3414 9 4.6 216.7 4.0X
-Partition column - Json 8448
8462 20 1.9 537.1 1.6X
-Partition column - Parquet Vectorized: DataPageV1 32
34 3 497.7 2.0 435.5X
-Partition column - Parquet Vectorized: DataPageV2 31
34 4 502.1 2.0 439.4X
-Partition column - Parquet MR: DataPageV1 1162
1188 37 13.5 73.9 11.8X
-Partition column - Parquet MR: DataPageV2 1147
1155 11 13.7 72.9 12.0X
-Partition column - ORC Vectorized 34
36 3 466.5 2.1 408.3X
-Partition column - ORC MR 1185
1188 4 13.3 75.3 11.6X
-Both columns - CSV 13587
13612 35 1.2 863.8 1.0X
-Both columns - Json 10079
10151 102 1.6 640.8 1.4X
-Both columns - Parquet Vectorized: DataPageV1 120
141 24 131.0 7.6 114.6X
-Both columns - Parquet Vectorized: DataPageV2 264
278 18 59.5 16.8 52.1X
-Both columns - Parquet MR: DataPageV1 2472
2496 33 6.4 157.2 5.6X
-Both columns - Parquet MR: DataPageV2 2301
2301 0 6.8 146.3 6.0X
-Both columns - ORC Vectorized 176
203 26 89.3 11.2 78.2X
-Both columns - ORC MR 1930
1932 3 8.1 122.7 7.1X
+Data column - CSV 11374
11417 61 1.4 723.1 1.0X
+Data column - Json 10095
10123 40 1.6 641.8 1.1X
+Data column - Parquet Vectorized: DataPageV1 127
133 6 123.8 8.1 89.5X
+Data column - Parquet Vectorized: DataPageV2 249
255 6 63.1 15.9 45.6X
+Data column - Parquet MR: DataPageV1 2377
2394 25 6.6 151.1 4.8X
+Data column - Parquet MR: DataPageV2 2250
2271 30 7.0 143.0 5.1X
+Data column - ORC Vectorized 150
152 2 104.6 9.6 75.7X
+Data column - ORC MR 1872
1892 28 8.4 119.0 6.1X
+Partition column - CSV 3440
3468 39 4.6 218.7 3.3X
+Partition column - Json 8665
8680 21 1.8 550.9 1.3X
+Partition column - Parquet Vectorized: DataPageV1 30
35 5 531.6 1.9 384.4X
+Partition column - Parquet Vectorized: DataPageV2 29
31 3 548.3 1.8 396.5X
+Partition column - Parquet MR: DataPageV1 1250
1254 5 12.6 79.5 9.1X
+Partition column - Parquet MR: DataPageV2 1243
1243 1 12.7 79.0 9.2X
+Partition column - ORC Vectorized 30
33 4 528.3 1.9 382.0X
+Partition column - ORC MR 1263
1268 6 12.5 80.3 9.0X
+Both columns - CSV 11116
11119 5 1.4 706.7 1.0X
+Both columns - Json 10427
10452 36 1.5 662.9 1.1X
+Both columns - Parquet Vectorized: DataPageV1 124
153 18 127.2 7.9 92.0X
+Both columns - Parquet Vectorized: DataPageV2 244
267 22 64.4 15.5 46.6X
+Both columns - Parquet MR: DataPageV1 2540
2546 8 6.2 161.5 4.5X
+Both columns - Parquet MR: DataPageV2 2283
2287 5 6.9 145.2 5.0X
+Both columns - ORC Vectorized 175
187 11 89.6 11.2 64.8X
+Both columns - ORC MR 2001
2003 2 7.9 127.2 5.7X
================================================================================================
String with Nulls Scan
================================================================================================
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+OpenJDK 64-Bit Server VM 17.0.18+8-LTS on Linux 6.14.0-1017-azure
AMD EPYC 7763 64-Core Processor
String with Nulls Scan (0.0%): Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
-SQL CSV 8695 8745
70 1.2 829.2 1.0X
-SQL Json 9053 9061
10 1.2 863.4 1.0X
-SQL Parquet Vectorized: DataPageV1 1272 1282
14 8.2 121.3 6.8X
-SQL Parquet Vectorized: DataPageV2 1322 1324
2 7.9 126.1 6.6X
-SQL Parquet MR: DataPageV1 3310 3311
1 3.2 315.7 2.6X
-SQL Parquet MR: DataPageV2 3486 3492
8 3.0 332.4 2.5X
-ParquetReader Vectorized: DataPageV1 850 857
8 12.3 81.1 10.2X
-ParquetReader Vectorized: DataPageV2 919 920
2 11.4 87.7 9.5X
-SQL ORC Vectorized 928 940
11 11.3 88.5 9.4X
-SQL ORC MR 2887 2906
27 3.6 275.3 3.0X
-
-OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure
+SQL CSV 7255 7256
1 1.4 691.9 1.0X
+SQL Json 9443 9455
17 1.1 900.5 0.8X
+SQL Parquet Vectorized: DataPageV1 1285 1290
7 8.2 122.6 5.6X
+SQL Parquet Vectorized: DataPageV2 1476 1479
4 7.1 140.8 4.9X
+SQL Parquet MR: DataPageV1 3564 3582
26 2.9 339.9 2.0X
+SQL Parquet MR: DataPageV2 3578 3585
9 2.9 341.2 2.0X
+ParquetReader Vectorized: DataPageV1 879 886
7 11.9 83.8 8.3X
Review Comment:
Previously, this was the fastest but now becomes slower relatively than `SQL
ORC Vectorized` somehow.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]