Skip to content

Conversation

@alamb
Copy link
Contributor

@alamb alamb commented Jan 10, 2026

Which issue does this PR close?

Oustanding issues

Rationale for this change

Keep datafusion up to date (and test Arrow using DataFusion tests)

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

@github-actions github-actions bot added sqllogictest SQL Logic Tests (.slt) common Related to common crate proto Related to proto crate functions Changes to functions implementation datasource Changes to the datasource crate physical-plan Changes to the physical-plan crate labels Jan 10, 2026
| alltypes_plain.parquet | 1851 | 8882 | 2 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 269266 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1347 | 2 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 269074 | 2 | page_index=true |
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this reduction in metadata size is a direct consequence of @WaterWhisperer's PR to improve PageEncoding representation

@Dandandan
Copy link
Contributor

Run benchmarks

@alamb-ghbot
Copy link

🤖 ./gh_compare_branch.sh gh_compare_branch.sh Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing alamb/update_arrow_58 (35b97fa) to b9a3b9f diff using: tpch_mem clickbench_partitioned clickbench_extended
Results will be posted here when complete

@alamb-ghbot
Copy link

🤖: Benchmark completed

Details

Comparing HEAD and alamb_update_arrow_58
--------------------
Benchmark clickbench_extended.json
--------------------
┏━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query    ┃        HEAD ┃ alamb_update_arrow_58 ┃    Change ┃
┡━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 0 │  2354.54 ms │            2406.77 ms │ no change │
│ QQuery 1 │   939.82 ms │             929.76 ms │ no change │
│ QQuery 2 │  1882.93 ms │            1891.80 ms │ no change │
│ QQuery 3 │  1163.47 ms │            1165.13 ms │ no change │
│ QQuery 4 │  2306.07 ms │            2241.55 ms │ no change │
│ QQuery 5 │ 28452.06 ms │           28080.09 ms │ no change │
│ QQuery 6 │  4018.71 ms │            4055.12 ms │ no change │
│ QQuery 7 │  3790.29 ms │            3670.14 ms │ no change │
└──────────┴─────────────┴───────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 44907.89ms │
│ Total Time (alamb_update_arrow_58)   │ 44440.36ms │
│ Average Time (HEAD)                  │  5613.49ms │
│ Average Time (alamb_update_arrow_58) │  5555.05ms │
│ Queries Faster                       │          0 │
│ Queries Slower                       │          0 │
│ Queries with No Change               │          8 │
│ Queries with Failure                 │          0 │
└──────────────────────────────────────┴────────────┘
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃        HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │     1.86 ms │               1.94 ms │     no change │
│ QQuery 1  │    50.56 ms │              50.42 ms │     no change │
│ QQuery 2  │   134.60 ms │             134.00 ms │     no change │
│ QQuery 3  │   156.94 ms │             152.15 ms │     no change │
│ QQuery 4  │  1074.92 ms │            1227.05 ms │  1.14x slower │
│ QQuery 5  │  1349.11 ms │            1512.35 ms │  1.12x slower │
│ QQuery 6  │     1.82 ms │               1.86 ms │     no change │
│ QQuery 7  │    56.21 ms │              53.80 ms │     no change │
│ QQuery 8  │  1404.44 ms │            1546.63 ms │  1.10x slower │
│ QQuery 9  │  1744.32 ms │            1884.58 ms │  1.08x slower │
│ QQuery 10 │   344.43 ms │             351.00 ms │     no change │
│ QQuery 11 │   393.88 ms │             399.97 ms │     no change │
│ QQuery 12 │  1259.31 ms │            1442.13 ms │  1.15x slower │
│ QQuery 13 │  1916.02 ms │            2053.79 ms │  1.07x slower │
│ QQuery 14 │  1228.80 ms │            1371.03 ms │  1.12x slower │
│ QQuery 15 │  1223.04 ms │            1359.64 ms │  1.11x slower │
│ QQuery 16 │  2568.94 ms │            2675.51 ms │     no change │
│ QQuery 17 │  2521.47 ms │            2647.03 ms │     no change │
│ QQuery 18 │  6120.19 ms │            5000.68 ms │ +1.22x faster │
│ QQuery 19 │   120.13 ms │             119.44 ms │     no change │
│ QQuery 20 │  1948.33 ms │            1896.06 ms │     no change │
│ QQuery 21 │  2245.14 ms │            2178.01 ms │     no change │
│ QQuery 22 │  3847.87 ms │            3802.23 ms │     no change │
│ QQuery 23 │ 21572.08 ms │           12373.92 ms │ +1.74x faster │
│ QQuery 24 │   225.72 ms │             216.64 ms │     no change │
│ QQuery 25 │   471.41 ms │             478.99 ms │     no change │
│ QQuery 26 │   218.83 ms │             235.13 ms │  1.07x slower │
│ QQuery 27 │  2823.98 ms │            2691.15 ms │     no change │
│ QQuery 28 │ 23860.88 ms │           23263.75 ms │     no change │
│ QQuery 29 │   982.83 ms │             966.29 ms │     no change │
│ QQuery 30 │  1343.19 ms │            1378.01 ms │     no change │
│ QQuery 31 │  1521.78 ms │            1379.20 ms │ +1.10x faster │
│ QQuery 32 │  5104.40 ms │            4890.24 ms │     no change │
│ QQuery 33 │  5837.64 ms │            5506.92 ms │ +1.06x faster │
│ QQuery 34 │  5933.39 ms │            5605.95 ms │ +1.06x faster │
│ QQuery 35 │  1921.56 ms │            1960.63 ms │     no change │
│ QQuery 36 │    65.96 ms │              68.18 ms │     no change │
│ QQuery 37 │    45.85 ms │              45.16 ms │     no change │
│ QQuery 38 │    66.53 ms │              65.89 ms │     no change │
│ QQuery 39 │   102.71 ms │             106.18 ms │     no change │
│ QQuery 40 │    28.23 ms │              25.52 ms │ +1.11x faster │
│ QQuery 41 │    24.10 ms │              23.51 ms │     no change │
│ QQuery 42 │    19.09 ms │              18.80 ms │     no change │
└───────────┴─────────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃             ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 103882.45ms │
│ Total Time (alamb_update_arrow_58)   │  93161.37ms │
│ Average Time (HEAD)                  │   2415.87ms │
│ Average Time (alamb_update_arrow_58) │   2166.54ms │
│ Queries Faster                       │           6 │
│ Queries Slower                       │           9 │
│ Queries with No Change               │          28 │
│ Queries with Failure                 │           0 │
└──────────────────────────────────────┴─────────────┘
--------------------
Benchmark tpch_mem_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃      HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │ 119.70 ms │             118.08 ms │     no change │
│ QQuery 2  │  35.82 ms │              36.60 ms │     no change │
│ QQuery 3  │  40.70 ms │              36.99 ms │ +1.10x faster │
│ QQuery 4  │  30.37 ms │              30.72 ms │     no change │
│ QQuery 5  │  91.59 ms │              90.47 ms │     no change │
│ QQuery 6  │  21.09 ms │              20.76 ms │     no change │
│ QQuery 7  │ 222.34 ms │             225.43 ms │     no change │
│ QQuery 8  │  44.85 ms │              40.29 ms │ +1.11x faster │
│ QQuery 9  │ 122.80 ms │             104.76 ms │ +1.17x faster │
│ QQuery 10 │  81.06 ms │              66.33 ms │ +1.22x faster │
│ QQuery 11 │  23.80 ms │              24.89 ms │     no change │
│ QQuery 12 │  52.22 ms │              52.78 ms │     no change │
│ QQuery 13 │  48.94 ms │              49.75 ms │     no change │
│ QQuery 14 │  14.95 ms │              14.96 ms │     no change │
│ QQuery 15 │  30.50 ms │              30.48 ms │     no change │
│ QQuery 16 │  28.47 ms │              29.06 ms │     no change │
│ QQuery 17 │ 151.61 ms │             154.03 ms │     no change │
│ QQuery 18 │ 287.03 ms │             288.27 ms │     no change │
│ QQuery 19 │  39.57 ms │              39.77 ms │     no change │
│ QQuery 20 │  57.69 ms │              57.36 ms │     no change │
│ QQuery 21 │ 322.81 ms │             318.54 ms │     no change │
│ QQuery 22 │  21.98 ms │              21.61 ms │     no change │
└───────────┴───────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃           ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 1889.89ms │
│ Total Time (alamb_update_arrow_58)   │ 1851.95ms │
│ Average Time (HEAD)                  │   85.90ms │
│ Average Time (alamb_update_arrow_58) │   84.18ms │
│ Queries Faster                       │         4 │
│ Queries Slower                       │         0 │
│ Queries with No Change               │        18 │
│ Queries with Failure                 │         0 │
└──────────────────────────────────────┴───────────┘

@Dandandan
Copy link
Contributor

run benchmarks

@Dandandan
Copy link
Contributor

run benchmark tpch

@alamb-ghbot
Copy link

🤖 ./gh_compare_branch.sh gh_compare_branch.sh Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing alamb/update_arrow_58 (35b97fa) to b9a3b9f diff using: tpch_mem clickbench_partitioned clickbench_extended
Results will be posted here when complete

@alamb-ghbot
Copy link

🤖: Benchmark completed

Details

Comparing HEAD and alamb_update_arrow_58
--------------------
Benchmark clickbench_extended.json
--------------------
┏━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query    ┃        HEAD ┃ alamb_update_arrow_58 ┃    Change ┃
┡━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 0 │  2389.61 ms │            2355.66 ms │ no change │
│ QQuery 1 │   975.65 ms │             969.78 ms │ no change │
│ QQuery 2 │  1875.49 ms │            1871.78 ms │ no change │
│ QQuery 3 │  1174.32 ms │            1145.53 ms │ no change │
│ QQuery 4 │  2258.94 ms │            2223.01 ms │ no change │
│ QQuery 5 │ 27824.57 ms │           28406.72 ms │ no change │
│ QQuery 6 │  4031.59 ms │            4002.29 ms │ no change │
│ QQuery 7 │  3463.56 ms │            3533.17 ms │ no change │
└──────────┴─────────────┴───────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 43993.73ms │
│ Total Time (alamb_update_arrow_58)   │ 44507.93ms │
│ Average Time (HEAD)                  │  5499.22ms │
│ Average Time (alamb_update_arrow_58) │  5563.49ms │
│ Queries Faster                       │          0 │
│ Queries Slower                       │          0 │
│ Queries with No Change               │          8 │
│ Queries with Failure                 │          0 │
└──────────────────────────────────────┴────────────┘
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃        HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │     1.90 ms │               1.92 ms │     no change │
│ QQuery 1  │    52.12 ms │              50.35 ms │     no change │
│ QQuery 2  │   142.92 ms │             133.95 ms │ +1.07x faster │
│ QQuery 3  │   154.00 ms │             152.77 ms │     no change │
│ QQuery 4  │  1072.51 ms │            1063.15 ms │     no change │
│ QQuery 5  │  1369.60 ms │            1320.07 ms │     no change │
│ QQuery 6  │     1.82 ms │               1.86 ms │     no change │
│ QQuery 7  │    54.39 ms │              52.98 ms │     no change │
│ QQuery 8  │  1446.73 ms │            1417.75 ms │     no change │
│ QQuery 9  │  1835.01 ms │            1706.51 ms │ +1.08x faster │
│ QQuery 10 │   344.52 ms │             354.29 ms │     no change │
│ QQuery 11 │   392.19 ms │             397.62 ms │     no change │
│ QQuery 12 │  1286.14 ms │            1275.41 ms │     no change │
│ QQuery 13 │  1947.40 ms │            1962.96 ms │     no change │
│ QQuery 14 │  1259.13 ms │            1231.11 ms │     no change │
│ QQuery 15 │  1247.90 ms │            1222.46 ms │     no change │
│ QQuery 16 │  2534.25 ms │            2515.84 ms │     no change │
│ QQuery 17 │  2514.25 ms │            2527.22 ms │     no change │
│ QQuery 18 │  5440.35 ms │            4806.73 ms │ +1.13x faster │
│ QQuery 19 │   119.26 ms │             118.76 ms │     no change │
│ QQuery 20 │  1929.28 ms │            1872.84 ms │     no change │
│ QQuery 21 │  2213.86 ms │            2178.92 ms │     no change │
│ QQuery 22 │  4264.32 ms │            3784.45 ms │ +1.13x faster │
│ QQuery 23 │ 20258.80 ms │           12236.28 ms │ +1.66x faster │
│ QQuery 24 │   215.95 ms │             219.20 ms │     no change │
│ QQuery 25 │   488.91 ms │             481.13 ms │     no change │
│ QQuery 26 │   226.35 ms │             216.76 ms │     no change │
│ QQuery 27 │  2799.99 ms │            2713.67 ms │     no change │
│ QQuery 28 │ 23840.67 ms │           23084.98 ms │     no change │
│ QQuery 29 │   974.43 ms │             971.18 ms │     no change │
│ QQuery 30 │  1351.52 ms │            1299.11 ms │     no change │
│ QQuery 31 │  1399.75 ms │            1421.76 ms │     no change │
│ QQuery 32 │  4761.26 ms │            4490.64 ms │ +1.06x faster │
│ QQuery 33 │  5521.96 ms │            5313.98 ms │     no change │
│ QQuery 34 │  5548.81 ms │            5584.56 ms │     no change │
│ QQuery 35 │  1979.74 ms │            1851.73 ms │ +1.07x faster │
│ QQuery 36 │    66.91 ms │              67.24 ms │     no change │
│ QQuery 37 │    46.16 ms │              47.24 ms │     no change │
│ QQuery 38 │    66.08 ms │              67.97 ms │     no change │
│ QQuery 39 │   102.12 ms │             100.78 ms │     no change │
│ QQuery 40 │    28.61 ms │              27.21 ms │     no change │
│ QQuery 41 │    23.45 ms │              22.02 ms │ +1.06x faster │
│ QQuery 42 │    19.24 ms │              19.38 ms │     no change │
└───────────┴─────────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃             ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 101344.52ms │
│ Total Time (alamb_update_arrow_58)   │  90386.74ms │
│ Average Time (HEAD)                  │   2356.85ms │
│ Average Time (alamb_update_arrow_58) │   2102.02ms │
│ Queries Faster                       │           8 │
│ Queries Slower                       │           0 │
│ Queries with No Change               │          35 │
│ Queries with Failure                 │           0 │
└──────────────────────────────────────┴─────────────┘
--------------------
Benchmark tpch_mem_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃      HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │ 118.62 ms │             117.02 ms │     no change │
│ QQuery 2  │  37.93 ms │              38.57 ms │     no change │
│ QQuery 3  │  41.97 ms │              37.52 ms │ +1.12x faster │
│ QQuery 4  │  31.39 ms │              30.22 ms │     no change │
│ QQuery 5  │  91.63 ms │              91.98 ms │     no change │
│ QQuery 6  │  21.13 ms │              20.89 ms │     no change │
│ QQuery 7  │ 229.95 ms │             228.06 ms │     no change │
│ QQuery 8  │  39.25 ms │              37.93 ms │     no change │
│ QQuery 9  │ 107.60 ms │             107.66 ms │     no change │
│ QQuery 10 │  69.45 ms │              69.75 ms │     no change │
│ QQuery 11 │  23.16 ms │              24.35 ms │  1.05x slower │
│ QQuery 12 │  53.07 ms │              52.75 ms │     no change │
│ QQuery 13 │  51.17 ms │              48.55 ms │ +1.05x faster │
│ QQuery 14 │  15.28 ms │              15.11 ms │     no change │
│ QQuery 15 │  30.14 ms │              30.73 ms │     no change │
│ QQuery 16 │  31.26 ms │              29.13 ms │ +1.07x faster │
│ QQuery 17 │ 159.46 ms │             154.29 ms │     no change │
│ QQuery 18 │ 287.59 ms │             284.81 ms │     no change │
│ QQuery 19 │  39.20 ms │              39.99 ms │     no change │
│ QQuery 20 │  56.56 ms │              57.03 ms │     no change │
│ QQuery 21 │ 300.14 ms │             325.49 ms │  1.08x slower │
│ QQuery 22 │  22.64 ms │              22.18 ms │     no change │
└───────────┴───────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃           ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 1858.59ms │
│ Total Time (alamb_update_arrow_58)   │ 1864.00ms │
│ Average Time (HEAD)                  │   84.48ms │
│ Average Time (alamb_update_arrow_58) │   84.73ms │
│ Queries Faster                       │         3 │
│ Queries Slower                       │         2 │
│ Queries with No Change               │        17 │
│ Queries with Failure                 │         0 │
└──────────────────────────────────────┴───────────┘

@alamb-ghbot
Copy link

🤖: Benchmark completed

Details

Comparing HEAD and alamb_update_arrow_58
--------------------
Benchmark tpch_mem_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃      HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │ 103.86 ms │             102.37 ms │     no change │
│ QQuery 2  │  34.24 ms │              31.66 ms │ +1.08x faster │
│ QQuery 3  │  41.84 ms │              37.83 ms │ +1.11x faster │
│ QQuery 4  │  31.74 ms │              30.69 ms │     no change │
│ QQuery 5  │  93.78 ms │              81.15 ms │ +1.16x faster │
│ QQuery 6  │  20.98 ms │              20.41 ms │     no change │
│ QQuery 7  │ 164.38 ms │             151.24 ms │ +1.09x faster │
│ QQuery 8  │  41.61 ms │              40.04 ms │     no change │
│ QQuery 9  │ 110.11 ms │             105.14 ms │     no change │
│ QQuery 10 │  68.03 ms │              64.96 ms │     no change │
│ QQuery 11 │  18.85 ms │              19.20 ms │     no change │
│ QQuery 12 │  52.25 ms │              56.12 ms │  1.07x slower │
│ QQuery 13 │  51.50 ms │              52.96 ms │     no change │
│ QQuery 14 │  15.48 ms │              15.11 ms │     no change │
│ QQuery 15 │  31.13 ms │              30.64 ms │     no change │
│ QQuery 16 │  29.45 ms │              27.64 ms │ +1.07x faster │
│ QQuery 17 │ 146.17 ms │             149.32 ms │     no change │
│ QQuery 18 │ 293.06 ms │             277.06 ms │ +1.06x faster │
│ QQuery 19 │  41.97 ms │              43.65 ms │     no change │
│ QQuery 20 │  56.57 ms │              56.52 ms │     no change │
│ QQuery 21 │ 191.41 ms │             194.18 ms │     no change │
│ QQuery 22 │  22.69 ms │              22.41 ms │     no change │
└───────────┴───────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃           ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 1661.10ms │
│ Total Time (alamb_update_arrow_58)   │ 1610.31ms │
│ Average Time (HEAD)                  │   75.50ms │
│ Average Time (alamb_update_arrow_58) │   73.20ms │
│ Queries Faster                       │         6 │
│ Queries Slower                       │         1 │
│ Queries with No Change               │        15 │
│ Queries with Failure                 │         0 │
└──────────────────────────────────────┴───────────┘

@alamb alamb changed the title WIP: Upgrade DataFusion to arrow-rs/parquet 58.0.0 WIP: Upgrade DataFusion to arrow-rs/parquet 58.0.0 / object_store 13.0.0 Jan 30, 2026
@github-actions github-actions bot added core Core DataFusion crate datasource Changes to the datasource crate spark labels Jan 30, 2026
let timestamp = Utc::now();
let range = options.range.clone();

let head = options.head;
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A substantial amount of the changes in tis PR are due to the upgrade to object_store 0.13 where several of the trait methods are consolidated (e.g. get, get_opts, head, etc) have been consolidated.

You can see the upgrade guide here

https://github.com/apache/arrow-rs-object-store/blob/8ef1aaa9cad5699971de1173d16637d01795da6e/src/lib.rs#L698-L736

Sadly, the docs.rs page is broken, and I have filed a ticket for that:

self.inner.list_with_delimiter(prefix).await
}

async fn copy(&self, from: &Path, to: &Path) -> Result<()> {
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

copy and copy_if_not_exists were consolidated

// Testing case1:
// Inserting query schema mismatch: Expected table field 'a' with type Float16, but got 'a' with type Utf8.
// And the cast is not supported from Utf8 to Float16.
// And the cast is not supported from Binary to Float16.
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@Jefffrey added support for Utf8->Float casting in apache/arrow-rs#9262 so this test started failing it expected this not to work 😆

@alamb
Copy link
Contributor Author

alamb commented Jan 30, 2026

run benchmarks

@alamb-ghbot
Copy link

🤖 ./gh_compare_branch.sh gh_compare_branch.sh Running
Linux aal-dev 6.14.0-1018-gcp #19~24.04.1-Ubuntu SMP Wed Sep 24 23:23:09 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing alamb/update_arrow_58 (9276a8a) to b50e1f7 diff using: tpch_mem clickbench_partitioned clickbench_extended
Results will be posted here when complete

@alamb-ghbot
Copy link

🤖: Benchmark completed

Details

Comparing HEAD and alamb_update_arrow_58
--------------------
Benchmark clickbench_extended.json
--------------------
┏━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query    ┃        HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0 │  2300.55 ms │            2285.79 ms │     no change │
│ QQuery 1 │   888.82 ms │             848.38 ms │     no change │
│ QQuery 2 │  1838.33 ms │            1668.46 ms │ +1.10x faster │
│ QQuery 3 │  1062.70 ms │            1016.53 ms │     no change │
│ QQuery 4 │  2207.01 ms │            2149.28 ms │     no change │
│ QQuery 5 │ 28391.81 ms │           26709.42 ms │ +1.06x faster │
│ QQuery 6 │  4015.66 ms │            3798.09 ms │ +1.06x faster │
│ QQuery 7 │  2764.10 ms │            3129.12 ms │  1.13x slower │
└──────────┴─────────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 43468.98ms │
│ Total Time (alamb_update_arrow_58)   │ 41605.09ms │
│ Average Time (HEAD)                  │  5433.62ms │
│ Average Time (alamb_update_arrow_58) │  5200.64ms │
│ Queries Faster                       │          3 │
│ Queries Slower                       │          1 │
│ Queries with No Change               │          4 │
│ Queries with Failure                 │          0 │
└──────────────────────────────────────┴────────────┘
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃        HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │     2.57 ms │               2.62 ms │     no change │
│ QQuery 1  │    52.29 ms │              51.35 ms │     no change │
│ QQuery 2  │   131.21 ms │             157.22 ms │  1.20x slower │
│ QQuery 3  │   158.00 ms │             160.65 ms │     no change │
│ QQuery 4  │  1003.75 ms │            1100.67 ms │  1.10x slower │
│ QQuery 5  │  1274.89 ms │            1292.35 ms │     no change │
│ QQuery 6  │     8.90 ms │               8.68 ms │     no change │
│ QQuery 7  │    57.40 ms │              54.76 ms │     no change │
│ QQuery 8  │  1404.34 ms │            1450.20 ms │     no change │
│ QQuery 9  │  1779.84 ms │            1810.15 ms │     no change │
│ QQuery 10 │   348.93 ms │             343.77 ms │     no change │
│ QQuery 11 │   402.87 ms │             389.47 ms │     no change │
│ QQuery 12 │  1217.33 ms │            1236.32 ms │     no change │
│ QQuery 13 │  1884.21 ms │            1897.57 ms │     no change │
│ QQuery 14 │  1227.78 ms │            1186.45 ms │     no change │
│ QQuery 15 │  1194.65 ms │            1209.51 ms │     no change │
│ QQuery 16 │  2474.11 ms │            2475.47 ms │     no change │
│ QQuery 17 │  2495.10 ms │            2460.91 ms │     no change │
│ QQuery 18 │  5788.51 ms │            4774.53 ms │ +1.21x faster │
│ QQuery 19 │   122.74 ms │             119.04 ms │     no change │
│ QQuery 20 │  1951.17 ms │            1869.84 ms │     no change │
│ QQuery 21 │  2180.84 ms │            2164.30 ms │     no change │
│ QQuery 22 │  3769.84 ms │            3670.68 ms │     no change │
│ QQuery 23 │ 21956.02 ms │           11740.22 ms │ +1.87x faster │
│ QQuery 24 │   225.99 ms │             205.29 ms │ +1.10x faster │
│ QQuery 25 │   492.66 ms │             440.34 ms │ +1.12x faster │
│ QQuery 26 │   242.76 ms │             214.04 ms │ +1.13x faster │
│ QQuery 27 │  2648.17 ms │            2645.02 ms │     no change │
│ QQuery 28 │ 24806.18 ms │           23211.80 ms │ +1.07x faster │
│ QQuery 29 │   975.12 ms │             996.28 ms │     no change │
│ QQuery 30 │  1285.64 ms │            1226.34 ms │     no change │
│ QQuery 31 │  1353.60 ms │            1302.63 ms │     no change │
│ QQuery 32 │  4604.07 ms │            4118.16 ms │ +1.12x faster │
│ QQuery 33 │  5724.34 ms │            5290.62 ms │ +1.08x faster │
│ QQuery 34 │  6090.23 ms │            5758.74 ms │ +1.06x faster │
│ QQuery 35 │  1916.42 ms │            1903.83 ms │     no change │
│ QQuery 36 │   195.79 ms │             200.93 ms │     no change │
│ QQuery 37 │    80.83 ms │              76.20 ms │ +1.06x faster │
│ QQuery 38 │   121.70 ms │             120.20 ms │     no change │
│ QQuery 39 │   363.07 ms │             346.26 ms │     no change │
│ QQuery 40 │    47.72 ms │              45.95 ms │     no change │
│ QQuery 41 │    41.43 ms │              39.62 ms │     no change │
│ QQuery 42 │    35.37 ms │              35.41 ms │     no change │
└───────────┴─────────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃             ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 104138.38ms │
│ Total Time (alamb_update_arrow_58)   │  89804.36ms │
│ Average Time (HEAD)                  │   2421.82ms │
│ Average Time (alamb_update_arrow_58) │   2088.47ms │
│ Queries Faster                       │          10 │
│ Queries Slower                       │           2 │
│ Queries with No Change               │          31 │
│ Queries with Failure                 │           0 │
└──────────────────────────────────────┴─────────────┘
--------------------
Benchmark tpch_mem_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃      HEAD ┃ alamb_update_arrow_58 ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │ 127.36 ms │             101.81 ms │ +1.25x faster │
│ QQuery 2  │  34.57 ms │              30.76 ms │ +1.12x faster │
│ QQuery 3  │  43.88 ms │              34.21 ms │ +1.28x faster │
│ QQuery 4  │  30.62 ms │              30.60 ms │     no change │
│ QQuery 5  │  89.42 ms │              82.88 ms │ +1.08x faster │
│ QQuery 6  │  20.55 ms │              20.22 ms │     no change │
│ QQuery 7  │ 162.38 ms │             143.91 ms │ +1.13x faster │
│ QQuery 8  │  38.16 ms │              37.29 ms │     no change │
│ QQuery 9  │ 101.72 ms │             100.50 ms │     no change │
│ QQuery 10 │  67.45 ms │              62.15 ms │ +1.09x faster │
│ QQuery 11 │  19.52 ms │              17.23 ms │ +1.13x faster │
│ QQuery 12 │  51.35 ms │              54.04 ms │  1.05x slower │
│ QQuery 13 │  48.96 ms │              46.76 ms │     no change │
│ QQuery 14 │  15.54 ms │              14.75 ms │ +1.05x faster │
│ QQuery 15 │  30.39 ms │              29.28 ms │     no change │
│ QQuery 16 │  27.91 ms │              27.69 ms │     no change │
│ QQuery 17 │ 143.51 ms │             145.64 ms │     no change │
│ QQuery 18 │ 288.04 ms │             267.65 ms │ +1.08x faster │
│ QQuery 19 │  39.53 ms │              40.14 ms │     no change │
│ QQuery 20 │  56.22 ms │              55.93 ms │     no change │
│ QQuery 21 │ 184.76 ms │             193.64 ms │     no change │
│ QQuery 22 │  22.88 ms │              21.85 ms │     no change │
└───────────┴───────────┴───────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Benchmark Summary                    ┃           ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ Total Time (HEAD)                    │ 1644.73ms │
│ Total Time (alamb_update_arrow_58)   │ 1558.92ms │
│ Average Time (HEAD)                  │   74.76ms │
│ Average Time (alamb_update_arrow_58) │   70.86ms │
│ Queries Faster                       │         9 │
│ Queries Slower                       │         1 │
│ Queries with No Change               │        12 │
│ Queries with Failure                 │         0 │
└──────────────────────────────────────┴───────────┘

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

core Core DataFusion crate datasource Changes to the datasource crate spark sqllogictest SQL Logic Tests (.slt)

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[datafusion-spark] [SQL] [TEST] IntervalMonthDayNano(0,0,0) give line blank

5 participants