adriangbot commented on PR #11524: URL: https://github.com/apache/arrow-rs/pull/11524#issuecomment-6473324732
🤖 Benchmark completed (GKE) | [trigger](https://github.com/apache/arrow-rs/pull/11524#issuecomment-6472264148) **Target:** arrow_writer Comparing improve-parquet-dictionary-computation (158861dc5dd13b8a9e260ad5bcdbf767603508e4) to 0706d31 (merge-base) [diff](https://github.com/apache/arrow-rs/compare/0706d317a94098cec4b631031efcdf16f51ed1f5..158861dc5dd13b8a9e260ad5bcdbf767603508e4) <details><summary>Run configuration</summary> ```yaml run benchmark arrow_writer env: BENCH_FILTER: dictionary shards: 1 ``` </details> <details><summary>Details</summary> ``` group base changed ----- ---- ------- bool_dictionary/bloom_filter 1.00 11.6±0.08ms 86.3 MElem/sec 1.00 11.6±0.06ms 85.9 MElem/sec bool_dictionary/cdc 1.01 12.2±0.16ms 81.9 MElem/sec 1.00 12.1±0.11ms 82.5 MElem/sec bool_dictionary/default 1.00 9.1±0.07ms 110.0 MElem/sec 1.02 9.2±0.06ms 108.3 MElem/sec bool_dictionary/number_distinct_values 1.08 24.9±4.01ms 40.2 MElem/sec 1.00 23.0±0.07ms 43.5 MElem/sec bool_dictionary/parquet_2 1.00 10.0±0.09ms 100.1 MElem/sec 1.00 10.0±0.06ms 99.7 MElem/sec bool_dictionary/zstd 1.00 9.3±0.09ms 107.7 MElem/sec 1.00 9.3±0.05ms 107.3 MElem/sec bool_dictionary/zstd_parquet_2 1.02 10.0±0.09ms 99.7 MElem/sec 1.00 9.9±0.10ms 101.3 MElem/sec decimal128_dictionary/bloom_filter 1.03 62.4±0.78ms 16.0 MElem/sec 1.00 60.6±0.68ms 16.5 MElem/sec decimal128_dictionary/cdc 1.00 38.4±0.39ms 26.0 MElem/sec 1.00 38.5±0.43ms 26.0 MElem/sec decimal128_dictionary/default 1.03 50.9±0.61ms 19.7 MElem/sec 1.00 49.5±0.54ms 20.2 MElem/sec decimal128_dictionary/number_distinct_values 1.08 91.3±2.88ms 10.9 MElem/sec 1.00 84.6±0.99ms 11.8 MElem/sec decimal128_dictionary/parquet_2 1.03 81.5±1.28ms 12.3 MElem/sec 1.00 79.2±1.01ms 12.6 MElem/sec decimal128_dictionary/zstd 1.04 56.3±2.06ms 17.8 MElem/sec 1.00 53.9±0.72ms 18.5 MElem/sec decimal128_dictionary/zstd_parquet_2 1.03 86.0±1.55ms 11.6 MElem/sec 1.00 83.6±1.10ms 12.0 MElem/sec decimal128_dictionary_1pct_cardinality/bloom_filter 1.00 50.7±0.67ms 19.7 MElem/sec 1.00 50.7±0.69ms 19.7 MElem/sec decimal128_dictionary_1pct_cardinality/cdc 1.00 37.8±0.37ms 26.4 MElem/sec 1.00 37.9±0.38ms 26.4 MElem/sec decimal128_dictionary_1pct_cardinality/default 1.00 49.9±0.59ms 20.0 MElem/sec 1.01 50.2±0.62ms 19.9 MElem/sec decimal128_dictionary_1pct_cardinality/number_distinct_values 1.01 67.2±2.80ms 14.9 MElem/sec 1.00 66.2±0.66ms 15.1 MElem/sec decimal128_dictionary_1pct_cardinality/parquet_2 1.00 50.2±0.69ms 19.9 MElem/sec 1.00 50.2±0.69ms 19.9 MElem/sec decimal128_dictionary_1pct_cardinality/zstd 1.00 52.8±0.77ms 19.0 MElem/sec 1.01 53.2±0.63ms 18.8 MElem/sec decimal128_dictionary_1pct_cardinality/zstd_parquet_2 1.01 53.3±1.01ms 18.8 MElem/sec 1.00 53.0±0.63ms 18.9 MElem/sec float64_dictionary/bloom_filter 1.00 18.9±0.20ms 52.8 MElem/sec 1.00 18.9±0.21ms 52.9 MElem/sec float64_dictionary/cdc 1.00 18.8±0.11ms 53.3 MElem/sec 1.00 18.7±0.11ms 53.5 MElem/sec float64_dictionary/default 1.01 14.7±0.15ms 68.1 MElem/sec 1.00 14.5±0.16ms 68.8 MElem/sec float64_dictionary/number_distinct_values 1.04 57.3±3.34ms 17.5 MElem/sec 1.00 55.1±0.73ms 18.2 MElem/sec float64_dictionary/parquet_2 1.01 14.7±0.12ms 67.9 MElem/sec 1.00 14.6±0.13ms 68.5 MElem/sec float64_dictionary/zstd 1.00 21.6±0.14ms 46.2 MElem/sec 1.00 21.6±0.17ms 46.3 MElem/sec float64_dictionary/zstd_parquet_2 1.00 21.1±0.11ms 47.4 MElem/sec 1.00 21.1±0.15ms 47.4 MElem/sec float64_dictionary_1pct_cardinality/bloom_filter 1.00 13.1±0.19ms 76.3 MElem/sec 1.00 13.1±0.16ms 76.5 MElem/sec float64_dictionary_1pct_cardinality/cdc 1.00 15.5±0.15ms 64.4 MElem/sec 1.01 15.7±0.12ms 63.7 MElem/sec float64_dictionary_1pct_cardinality/default 1.01 12.9±0.14ms 77.8 MElem/sec 1.00 12.8±0.17ms 78.4 MElem/sec float64_dictionary_1pct_cardinality/number_distinct_values 1.05 29.1±3.06ms 34.4 MElem/sec 1.00 27.8±0.16ms 36.0 MElem/sec float64_dictionary_1pct_cardinality/parquet_2 1.00 12.9±0.13ms 77.5 MElem/sec 1.00 12.9±0.13ms 77.7 MElem/sec float64_dictionary_1pct_cardinality/zstd 1.00 15.5±0.14ms 64.6 MElem/sec 1.00 15.5±0.15ms 64.7 MElem/sec float64_dictionary_1pct_cardinality/zstd_parquet_2 1.00 15.4±0.14ms 65.0 MElem/sec 1.00 15.4±0.17ms 65.0 MElem/sec int64_dictionary/bloom_filter 1.01 18.6±0.16ms 53.9 MElem/sec 1.00 18.5±0.17ms 54.2 MElem/sec int64_dictionary/cdc 1.00 18.3±0.14ms 54.8 MElem/sec 1.00 18.3±0.13ms 54.8 MElem/sec int64_dictionary/default 1.02 14.2±0.12ms 70.2 MElem/sec 1.00 14.0±0.14ms 71.4 MElem/sec int64_dictionary/number_distinct_values 1.04 57.2±3.43ms 17.5 MElem/sec 1.00 54.9±0.92ms 18.2 MElem/sec int64_dictionary/parquet_2 1.01 16.5±0.13ms 60.6 MElem/sec 1.00 16.3±0.13ms 61.5 MElem/sec int64_dictionary/zstd 1.01 17.3±0.13ms 57.8 MElem/sec 1.00 17.2±0.18ms 58.1 MElem/sec int64_dictionary/zstd_parquet_2 1.00 21.6±0.14ms 46.3 MElem/sec 1.00 21.5±0.13ms 46.4 MElem/sec int64_dictionary_1pct_cardinality/bloom_filter 1.00 12.6±0.20ms 79.4 MElem/sec 1.00 12.5±0.20ms 79.7 MElem/sec int64_dictionary_1pct_cardinality/cdc 1.00 15.0±0.12ms 66.4 MElem/sec 1.00 15.1±0.12ms 66.3 MElem/sec int64_dictionary_1pct_cardinality/default 1.00 12.3±0.13ms 81.4 MElem/sec 1.00 12.2±0.14ms 81.6 MElem/sec int64_dictionary_1pct_cardinality/number_distinct_values 1.05 28.5±3.05ms 35.1 MElem/sec 1.00 27.3±0.14ms 36.7 MElem/sec int64_dictionary_1pct_cardinality/parquet_2 1.00 12.3±0.14ms 81.3 MElem/sec 1.00 12.3±0.14ms 81.5 MElem/sec int64_dictionary_1pct_cardinality/zstd 1.00 15.0±0.16ms 66.8 MElem/sec 1.00 15.0±0.14ms 66.7 MElem/sec int64_dictionary_1pct_cardinality/zstd_parquet_2 1.00 14.8±0.17ms 67.6 MElem/sec 1.00 14.8±0.16ms 67.5 MElem/sec primitive_dictionary/bloom_filter 1.01 21.3±0.22ms 47.0 MElem/sec 1.00 21.1±0.22ms 47.3 MElem/sec primitive_dictionary/cdc 1.00 22.3±0.24ms 44.8 MElem/sec 1.00 22.4±0.20ms 44.7 MElem/sec primitive_dictionary/default 1.01 17.9±0.20ms 56.0 MElem/sec 1.00 17.8±0.22ms 56.3 MElem/sec primitive_dictionary/number_distinct_values 1.03 61.9±3.39ms 16.2 MElem/sec 1.00 60.1±0.80ms 16.6 MElem/sec primitive_dictionary/parquet_2 1.01 19.9±0.21ms 50.3 MElem/sec 1.00 19.8±0.24ms 50.6 MElem/sec primitive_dictionary/zstd 1.00 20.1±0.21ms 49.9 MElem/sec 1.00 20.0±0.25ms 49.9 MElem/sec primitive_dictionary/zstd_parquet_2 1.00 23.5±0.21ms 42.6 MElem/sec 1.00 23.4±0.23ms 42.7 MElem/sec primitive_dictionary_1pct_cardinality/bloom_filter 1.02 13.0±0.14ms 77.1 MElem/sec 1.00 12.7±0.17ms 78.8 MElem/sec primitive_dictionary_1pct_cardinality/cdc 1.00 15.3±0.08ms 65.5 MElem/sec 1.00 15.3±0.10ms 65.6 MElem/sec primitive_dictionary_1pct_cardinality/default 1.03 12.7±0.12ms 78.7 MElem/sec 1.00 12.4±0.15ms 80.7 MElem/sec primitive_dictionary_1pct_cardinality/number_distinct_values 1.06 28.8±3.10ms 34.8 MElem/sec 1.00 27.0±0.11ms 37.0 MElem/sec primitive_dictionary_1pct_cardinality/parquet_2 1.02 12.6±0.14ms 79.2 MElem/sec 1.00 12.4±0.17ms 80.8 MElem/sec primitive_dictionary_1pct_cardinality/zstd 1.02 15.2±0.13ms 65.7 MElem/sec 1.00 14.9±0.15ms 67.2 MElem/sec primitive_dictionary_1pct_cardinality/zstd_parquet_2 1.02 15.1±0.14ms 66.4 MElem/sec 1.00 14.8±0.14ms 67.6 MElem/sec string_dictionary/bloom_filter 1.04 143.0±5.23ms 7.0 MElem/sec 1.00 137.6±5.71ms 7.3 MElem/sec string_dictionary/cdc 1.17 67.1±4.18ms 14.9 MElem/sec 1.00 57.5±2.47ms 17.4 MElem/sec string_dictionary/default 1.11 93.1±2.22ms 10.7 MElem/sec 1.00 83.7±11.82ms 12.0 MElem/sec string_dictionary/number_distinct_values 1.02 124.7±2.61ms 8.0 MElem/sec 1.00 121.8±2.29ms 8.2 MElem/sec string_dictionary/parquet_2 1.00 48.9±3.09ms 20.4 MElem/sec 1.09 53.3±10.74ms 18.8 MElem/sec string_dictionary/zstd 1.00 206.4±2.24ms 4.8 MElem/sec 1.00 206.5±1.76ms 4.8 MElem/sec string_dictionary/zstd_parquet_2 1.00 192.3±1.06ms 5.2 MElem/sec 1.04 200.9±8.49ms 5.0 MElem/sec string_dictionary_1pct_cardinality/bloom_filter 1.00 21.6±0.15ms 46.3 MElem/sec 1.03 22.3±0.17ms 44.9 MElem/sec string_dictionary_1pct_cardinality/cdc 1.00 24.1±0.12ms 41.5 MElem/sec 1.03 24.9±0.17ms 40.1 MElem/sec string_dictionary_1pct_cardinality/default 1.00 21.1±0.09ms 47.3 MElem/sec 1.02 21.6±0.14ms 46.2 MElem/sec string_dictionary_1pct_cardinality/number_distinct_values 1.00 40.5±2.03ms 24.7 MElem/sec 1.00 40.5±0.14ms 24.7 MElem/sec string_dictionary_1pct_cardinality/parquet_2 1.00 21.1±0.10ms 47.4 MElem/sec 1.03 21.7±0.14ms 46.2 MElem/sec string_dictionary_1pct_cardinality/zstd 1.00 23.9±0.09ms 41.9 MElem/sec 1.03 24.5±0.13ms 40.8 MElem/sec string_dictionary_1pct_cardinality/zstd_parquet_2 1.00 23.6±0.10ms 42.3 MElem/sec 1.03 24.4±0.13ms 41.0 MElem/sec string_dictionary_low_cardinality_100/bloom_filter 1.00 21.6±0.06ms 46.2 MElem/sec 1.00 21.6±0.06ms 46.4 MElem/sec string_dictionary_low_cardinality_100/cdc 1.01 23.9±0.07ms 41.9 MElem/sec 1.00 23.7±0.07ms 42.2 MElem/sec string_dictionary_low_cardinality_100/default 1.00 21.5±0.05ms 46.5 MElem/sec 1.00 21.4±0.06ms 46.7 MElem/sec string_dictionary_low_cardinality_100/number_distinct_values 1.03 45.8±2.52ms 21.8 MElem/sec 1.00 44.5±0.10ms 22.5 MElem/sec string_dictionary_low_cardinality_100/parquet_2 1.00 21.5±0.06ms 46.5 MElem/sec 1.00 21.4±0.06ms 46.7 MElem/sec string_dictionary_low_cardinality_100/zstd 1.00 21.9±0.05ms 45.7 MElem/sec 1.00 21.8±0.06ms 45.9 MElem/sec string_dictionary_low_cardinality_100/zstd_parquet_2 1.00 21.8±0.05ms 45.8 MElem/sec 1.00 21.8±0.06ms 46.0 MElem/sec string_dictionary_low_cardinality_20/bloom_filter 1.01 21.7±0.09ms 46.0 MElem/sec 1.00 21.4±0.09ms 46.6 MElem/sec string_dictionary_low_cardinality_20/cdc 1.01 23.9±0.07ms 41.9 MElem/sec 1.00 23.6±0.08ms 42.3 MElem/sec string_dictionary_low_cardinality_20/default 1.01 21.6±0.09ms 46.3 MElem/sec 1.00 21.4±0.09ms 46.8 MElem/sec string_dictionary_low_cardinality_20/number_distinct_values 1.03 45.8±2.56ms 21.8 MElem/sec 1.00 44.4±0.09ms 22.5 MElem/sec string_dictionary_low_cardinality_20/parquet_2 1.01 21.6±0.09ms 46.3 MElem/sec 1.00 21.4±0.10ms 46.8 MElem/sec string_dictionary_low_cardinality_20/zstd 1.01 21.7±0.10ms 46.1 MElem/sec 1.00 21.4±0.10ms 46.6 MElem/sec string_dictionary_low_cardinality_20/zstd_parquet_2 1.01 21.6±0.09ms 46.2 MElem/sec 1.00 21.5±0.09ms 46.5 MElem/sec string_dictionary_low_cardinality_400/bloom_filter 1.02 22.7±0.06ms 44.1 MElem/sec 1.00 22.3±0.11ms 44.8 MElem/sec string_dictionary_low_cardinality_400/cdc 1.02 24.9±0.16ms 40.2 MElem/sec 1.00 24.4±0.14ms 41.0 MElem/sec string_dictionary_low_cardinality_400/default 1.01 22.5±0.06ms 44.5 MElem/sec 1.00 22.2±0.11ms 45.0 MElem/sec string_dictionary_low_cardinality_400/number_distinct_values 1.04 47.2±2.53ms 21.2 MElem/sec 1.00 45.6±0.14ms 21.9 MElem/sec string_dictionary_low_cardinality_400/parquet_2 1.01 22.5±0.07ms 44.5 MElem/sec 1.00 22.2±0.09ms 45.0 MElem/sec string_dictionary_low_cardinality_400/zstd 1.01 23.0±0.11ms 43.5 MElem/sec 1.00 22.8±0.08ms 43.9 MElem/sec string_dictionary_low_cardinality_400/zstd_parquet_2 1.01 23.0±0.08ms 43.4 MElem/sec 1.00 22.7±0.08ms 44.1 MElem/sec ``` </details> <details><summary>Per-runner information</summary> <details><summary>arrow_writer — shard 1/1</summary> **Node:** gk3-benchmark-cluster-nap-1kxn11uo-aeaf8131-vtkr **Instance:** c4a-highmem-16 (12 vCPU / 65 GiB) **uname:** ```text Linux bench-c6472264148-4028-lkfc6 6.12.105+ #1 SMP Sat Sep 19 07:55:25 UTC 2026 aarch64 GNU/Linux ``` **BENCH_COMMAND:** ```sh cargo bench --features=arrow,async,test_common,experimental,object_store --bench arrow_writer ``` <details><summary>CPU Details (lscpu)</summary> ```text Architecture: aarch64 CPU op-mode(s): 64-bit Byte Order: Little Endian CPU(s): 16 On-line CPU(s) list: 0-15 Vendor ID: ARM Model name: Neoverse-V2 Model: 1 Thread(s) per core: 1 Core(s) per cluster: 16 Socket(s): - Cluster(s): 1 Stepping: r0p1 BogoMIPS: 2000.00 Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti L1d cache: 1 MiB (16 instances) L1i cache: 1 MiB (16 instances) L2 cache: 32 MiB (16 instances) L3 cache: 80 MiB (1 instance) NUMA node(s): 1 NUMA node0 CPU(s): 0-15 Vulnerability Gather data sampling: Not affected Vulnerability Indirect target selection: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; __user pointer sanitization Vulnerability Spectre v2: Mitigation; CSV2, BHB Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Not affected ``` </details> <details><summary>Resource Usage</summary> **base (merge-base)** | Metric | Value | |--------|-------| | Wall time | 1130.3s | | Peak memory | 997.4 MiB | | Avg memory | 81.7 MiB | | CPU user | 1069.0s | | CPU sys | 56.1s | | Peak spill | 0 B | **branch** | Metric | Value | |--------|-------| | Wall time | 1130.3s | | Peak memory | 458.2 MiB | | Avg memory | 80.1 MiB | | CPU user | 1066.7s | | CPU sys | 57.7s | | Peak spill | 0 B | </details> </details> </details> --- [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner <!-- benchmark-request:6472264148:finish:2048af2dc6fdda8422e3bd856f8062eb --> -- 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]
