adriangbot commented on PR #11524: URL: https://github.com/apache/arrow-rs/pull/11524#issuecomment-6125823028
🤖 Benchmark completed (GKE) | [trigger](https://github.com/apache/arrow-rs/pull/11524#issuecomment-6124982034) **Target:** arrow_writer Comparing improve-parquet-dictionary-computation (b1f10c7ae74037b17d2c72eec0f4137ea0f00332) to 0706d31 (merge-base) [diff](https://github.com/apache/arrow-rs/compare/0706d317a94098cec4b631031efcdf16f51ed1f5..b1f10c7ae74037b17d2c72eec0f4137ea0f00332) <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±0.05ms 86.5 MElem/sec 1.04 12.1±0.24ms 83.0 MElem/sec bool_dictionary/cdc 1.00 12.5±0.14ms 79.7 MElem/sec 1.02 12.8±0.14ms 78.2 MElem/sec bool_dictionary/default 1.00 9.4±0.11ms 105.9 MElem/sec 1.02 9.7±0.06ms 103.6 MElem/sec bool_dictionary/number_distinct_values 1.00 23.5±0.13ms 42.6 MElem/sec 1.00 23.6±0.11ms 42.4 MElem/sec bool_dictionary/parquet_2 1.00 10.3±0.14ms 97.6 MElem/sec 1.02 10.5±0.16ms 95.4 MElem/sec bool_dictionary/zstd 1.00 9.5±0.11ms 105.0 MElem/sec 1.03 9.8±0.15ms 102.3 MElem/sec bool_dictionary/zstd_parquet_2 1.00 10.3±0.12ms 97.4 MElem/sec 1.03 10.6±0.06ms 94.4 MElem/sec decimal128_dictionary/bloom_filter 1.04 45.9±0.43ms 21.8 MElem/sec 1.00 44.3±0.23ms 22.6 MElem/sec decimal128_dictionary/cdc 1.01 38.7±0.60ms 25.9 MElem/sec 1.00 38.2±0.29ms 26.2 MElem/sec decimal128_dictionary/default 1.02 34.4±0.24ms 29.1 MElem/sec 1.00 33.9±0.22ms 29.5 MElem/sec decimal128_dictionary/number_distinct_values 1.00 69.2±0.29ms 14.5 MElem/sec 1.00 69.0±0.39ms 14.5 MElem/sec decimal128_dictionary/parquet_2 1.02 64.1±1.24ms 15.6 MElem/sec 1.00 63.1±1.20ms 15.8 MElem/sec decimal128_dictionary/zstd 1.01 38.4±0.23ms 26.0 MElem/sec 1.00 37.9±0.22ms 26.4 MElem/sec decimal128_dictionary/zstd_parquet_2 1.01 68.4±1.35ms 14.6 MElem/sec 1.00 67.4±1.62ms 14.8 MElem/sec decimal128_dictionary_1pct_cardinality/bloom_filter 1.00 36.4±0.29ms 27.5 MElem/sec 1.01 36.6±0.31ms 27.3 MElem/sec decimal128_dictionary_1pct_cardinality/cdc 1.01 39.2±0.59ms 25.5 MElem/sec 1.00 39.0±0.27ms 25.6 MElem/sec decimal128_dictionary_1pct_cardinality/default 1.00 36.0±0.33ms 27.8 MElem/sec 1.01 36.2±0.46ms 27.6 MElem/sec decimal128_dictionary_1pct_cardinality/number_distinct_values 1.00 51.6±0.85ms 19.4 MElem/sec 1.01 52.3±0.37ms 19.1 MElem/sec decimal128_dictionary_1pct_cardinality/parquet_2 1.00 36.0±0.60ms 27.7 MElem/sec 1.00 36.2±0.31ms 27.7 MElem/sec decimal128_dictionary_1pct_cardinality/zstd 1.00 38.8±0.30ms 25.8 MElem/sec 1.00 39.0±0.29ms 25.6 MElem/sec decimal128_dictionary_1pct_cardinality/zstd_parquet_2 1.00 38.7±0.48ms 25.9 MElem/sec 1.01 39.0±0.30ms 25.7 MElem/sec float64_dictionary/bloom_filter 1.03 19.1±0.08ms 52.2 MElem/sec 1.00 18.7±0.07ms 53.6 MElem/sec float64_dictionary/cdc 1.01 19.1±0.11ms 52.3 MElem/sec 1.00 19.0±0.06ms 52.6 MElem/sec float64_dictionary/default 1.01 14.7±0.08ms 68.2 MElem/sec 1.00 14.6±0.09ms 68.6 MElem/sec float64_dictionary/number_distinct_values 1.00 54.6±0.40ms 18.3 MElem/sec 1.01 55.4±0.51ms 18.1 MElem/sec float64_dictionary/parquet_2 1.01 14.7±0.10ms 68.1 MElem/sec 1.00 14.6±0.07ms 68.7 MElem/sec float64_dictionary/zstd 1.00 21.6±0.09ms 46.3 MElem/sec 1.00 21.6±0.08ms 46.4 MElem/sec float64_dictionary/zstd_parquet_2 1.00 21.2±0.10ms 47.1 MElem/sec 1.00 21.2±0.10ms 47.2 MElem/sec float64_dictionary_1pct_cardinality/bloom_filter 1.00 13.8±0.08ms 72.3 MElem/sec 1.00 13.8±0.08ms 72.5 MElem/sec float64_dictionary_1pct_cardinality/cdc 1.02 16.9±0.05ms 59.1 MElem/sec 1.00 16.5±0.06ms 60.5 MElem/sec float64_dictionary_1pct_cardinality/default 1.00 13.6±0.06ms 73.4 MElem/sec 1.00 13.6±0.06ms 73.8 MElem/sec float64_dictionary_1pct_cardinality/number_distinct_values 1.00 28.4±0.12ms 35.2 MElem/sec 1.00 28.3±0.16ms 35.3 MElem/sec float64_dictionary_1pct_cardinality/parquet_2 1.00 13.6±0.05ms 73.5 MElem/sec 1.00 13.6±0.07ms 73.6 MElem/sec float64_dictionary_1pct_cardinality/zstd 1.00 16.3±0.07ms 61.5 MElem/sec 1.00 16.3±0.07ms 61.5 MElem/sec float64_dictionary_1pct_cardinality/zstd_parquet_2 1.00 16.2±0.07ms 61.9 MElem/sec 1.00 16.2±0.07ms 61.8 MElem/sec int64_dictionary/bloom_filter 1.01 18.5±0.09ms 54.0 MElem/sec 1.00 18.4±0.09ms 54.4 MElem/sec int64_dictionary/cdc 1.00 18.6±0.10ms 53.8 MElem/sec 1.00 18.6±0.07ms 53.7 MElem/sec int64_dictionary/default 1.00 14.2±0.10ms 70.5 MElem/sec 1.00 14.2±0.10ms 70.3 MElem/sec int64_dictionary/number_distinct_values 1.00 54.4±0.38ms 18.4 MElem/sec 1.01 54.9±0.52ms 18.2 MElem/sec int64_dictionary/parquet_2 1.00 16.4±0.07ms 61.0 MElem/sec 1.00 16.4±0.05ms 60.8 MElem/sec int64_dictionary/zstd 1.00 17.2±0.11ms 58.0 MElem/sec 1.01 17.4±0.08ms 57.5 MElem/sec int64_dictionary/zstd_parquet_2 1.00 21.6±0.07ms 46.3 MElem/sec 1.01 21.9±0.09ms 45.7 MElem/sec int64_dictionary_1pct_cardinality/bloom_filter 1.01 13.5±0.09ms 74.2 MElem/sec 1.00 13.4±0.07ms 74.6 MElem/sec int64_dictionary_1pct_cardinality/cdc 1.02 16.4±0.04ms 60.9 MElem/sec 1.00 16.2±0.05ms 61.9 MElem/sec int64_dictionary_1pct_cardinality/default 1.01 13.3±0.10ms 75.2 MElem/sec 1.00 13.2±0.06ms 75.6 MElem/sec int64_dictionary_1pct_cardinality/number_distinct_values 1.00 28.0±0.13ms 35.8 MElem/sec 1.00 28.0±0.11ms 35.7 MElem/sec int64_dictionary_1pct_cardinality/parquet_2 1.00 13.3±0.06ms 75.4 MElem/sec 1.00 13.2±0.06ms 75.7 MElem/sec int64_dictionary_1pct_cardinality/zstd 1.00 15.9±0.11ms 62.7 MElem/sec 1.00 15.9±0.06ms 63.0 MElem/sec int64_dictionary_1pct_cardinality/zstd_parquet_2 1.00 15.8±0.05ms 63.4 MElem/sec 1.00 15.8±0.07ms 63.4 MElem/sec primitive_dictionary/bloom_filter 1.00 21.2±0.08ms 47.3 MElem/sec 1.00 21.1±0.10ms 47.5 MElem/sec primitive_dictionary/cdc 1.01 22.5±0.07ms 44.3 MElem/sec 1.00 22.4±0.05ms 44.6 MElem/sec primitive_dictionary/default 1.01 17.9±0.09ms 56.0 MElem/sec 1.00 17.7±0.04ms 56.4 MElem/sec primitive_dictionary/number_distinct_values 1.00 60.1±0.54ms 16.6 MElem/sec 1.00 60.2±1.02ms 16.6 MElem/sec primitive_dictionary/parquet_2 1.00 19.8±0.05ms 50.5 MElem/sec 1.00 19.8±0.07ms 50.5 MElem/sec primitive_dictionary/zstd 1.00 19.9±0.06ms 50.1 MElem/sec 1.00 19.9±0.05ms 50.2 MElem/sec primitive_dictionary/zstd_parquet_2 1.00 23.3±0.06ms 42.9 MElem/sec 1.00 23.3±0.05ms 42.9 MElem/sec primitive_dictionary_1pct_cardinality/bloom_filter 1.02 13.6±0.20ms 73.5 MElem/sec 1.00 13.4±0.11ms 74.8 MElem/sec primitive_dictionary_1pct_cardinality/cdc 1.02 16.4±0.05ms 61.1 MElem/sec 1.00 16.1±0.04ms 62.0 MElem/sec primitive_dictionary_1pct_cardinality/default 1.00 13.2±0.22ms 75.5 MElem/sec 1.00 13.3±0.17ms 75.3 MElem/sec primitive_dictionary_1pct_cardinality/number_distinct_values 1.00 27.7±0.12ms 36.1 MElem/sec 1.02 28.1±0.27ms 35.5 MElem/sec primitive_dictionary_1pct_cardinality/parquet_2 1.01 13.3±0.14ms 75.3 MElem/sec 1.00 13.1±0.04ms 76.2 MElem/sec primitive_dictionary_1pct_cardinality/zstd 1.00 15.8±0.18ms 63.2 MElem/sec 1.01 16.0±0.29ms 62.6 MElem/sec primitive_dictionary_1pct_cardinality/zstd_parquet_2 1.01 15.8±0.28ms 63.4 MElem/sec 1.00 15.6±0.09ms 64.1 MElem/sec string_dictionary/bloom_filter 1.24 135.0±5.27ms 7.4 MElem/sec 1.00 108.8±3.23ms 9.2 MElem/sec string_dictionary/cdc 1.07 67.2±5.03ms 14.9 MElem/sec 1.00 62.6±3.39ms 16.0 MElem/sec string_dictionary/default 1.10 89.7±6.27ms 11.2 MElem/sec 1.00 81.4±14.31ms 12.3 MElem/sec string_dictionary/number_distinct_values 1.00 124.2±2.25ms 8.1 MElem/sec 1.01 124.9±6.32ms 8.0 MElem/sec string_dictionary/parquet_2 1.40 98.1±2.77ms 10.2 MElem/sec 1.00 70.1±1.71ms 14.3 MElem/sec string_dictionary/zstd 1.00 224.2±7.39ms 4.5 MElem/sec 1.00 225.0±8.00ms 4.4 MElem/sec string_dictionary/zstd_parquet_2 1.01 193.6±4.77ms 5.2 MElem/sec 1.00 191.1±3.65ms 5.2 MElem/sec string_dictionary_1pct_cardinality/bloom_filter 1.06 22.3±0.19ms 44.9 MElem/sec 1.00 21.1±0.10ms 47.5 MElem/sec string_dictionary_1pct_cardinality/cdc 1.05 25.1±0.08ms 39.8 MElem/sec 1.00 23.9±0.08ms 41.8 MElem/sec string_dictionary_1pct_cardinality/default 1.04 21.6±0.08ms 46.4 MElem/sec 1.00 20.7±0.08ms 48.3 MElem/sec string_dictionary_1pct_cardinality/number_distinct_values 1.03 40.2±0.07ms 24.9 MElem/sec 1.00 39.1±0.10ms 25.6 MElem/sec string_dictionary_1pct_cardinality/parquet_2 1.05 21.7±0.09ms 46.1 MElem/sec 1.00 20.7±0.09ms 48.2 MElem/sec string_dictionary_1pct_cardinality/zstd 1.04 24.4±0.09ms 40.9 MElem/sec 1.00 23.5±0.09ms 42.5 MElem/sec string_dictionary_1pct_cardinality/zstd_parquet_2 1.04 24.4±0.09ms 41.0 MElem/sec 1.00 23.4±0.09ms 42.8 MElem/sec string_dictionary_low_cardinality_100/bloom_filter 1.07 22.3±0.05ms 44.8 MElem/sec 1.00 20.9±0.07ms 47.8 MElem/sec string_dictionary_low_cardinality_100/cdc 1.06 24.4±0.05ms 40.9 MElem/sec 1.00 23.0±0.05ms 43.4 MElem/sec string_dictionary_low_cardinality_100/default 1.07 22.3±0.06ms 44.9 MElem/sec 1.00 20.8±0.05ms 48.1 MElem/sec string_dictionary_low_cardinality_100/number_distinct_values 1.04 45.2±0.11ms 22.1 MElem/sec 1.00 43.6±0.08ms 22.9 MElem/sec string_dictionary_low_cardinality_100/parquet_2 1.07 22.2±0.05ms 45.0 MElem/sec 1.00 20.8±0.04ms 48.1 MElem/sec string_dictionary_low_cardinality_100/zstd 1.07 22.6±0.05ms 44.3 MElem/sec 1.00 21.1±0.04ms 47.3 MElem/sec string_dictionary_low_cardinality_100/zstd_parquet_2 1.07 22.5±0.05ms 44.4 MElem/sec 1.00 21.1±0.05ms 47.4 MElem/sec string_dictionary_low_cardinality_20/bloom_filter 1.07 22.3±0.07ms 44.9 MElem/sec 1.00 20.8±0.06ms 48.1 MElem/sec string_dictionary_low_cardinality_20/cdc 1.07 24.5±0.07ms 40.9 MElem/sec 1.00 23.0±0.07ms 43.5 MElem/sec string_dictionary_low_cardinality_20/default 1.07 22.2±0.06ms 45.0 MElem/sec 1.00 20.8±0.06ms 48.1 MElem/sec string_dictionary_low_cardinality_20/number_distinct_values 1.03 45.2±0.08ms 22.1 MElem/sec 1.00 43.7±0.10ms 22.9 MElem/sec string_dictionary_low_cardinality_20/parquet_2 1.07 22.2±0.13ms 45.1 MElem/sec 1.00 20.8±0.07ms 48.2 MElem/sec string_dictionary_low_cardinality_20/zstd 1.07 22.4±0.08ms 44.7 MElem/sec 1.00 20.9±0.06ms 48.0 MElem/sec string_dictionary_low_cardinality_20/zstd_parquet_2 1.07 22.4±0.07ms 44.7 MElem/sec 1.00 20.8±0.06ms 48.0 MElem/sec string_dictionary_low_cardinality_400/bloom_filter 1.08 23.3±0.07ms 42.9 MElem/sec 1.00 21.6±0.09ms 46.3 MElem/sec string_dictionary_low_cardinality_400/cdc 1.07 25.3±0.09ms 39.5 MElem/sec 1.00 23.6±0.06ms 42.3 MElem/sec string_dictionary_low_cardinality_400/default 1.08 23.1±0.09ms 43.2 MElem/sec 1.00 21.4±0.07ms 46.8 MElem/sec string_dictionary_low_cardinality_400/number_distinct_values 1.05 46.8±0.11ms 21.4 MElem/sec 1.00 44.6±0.14ms 22.4 MElem/sec string_dictionary_low_cardinality_400/parquet_2 1.08 23.1±0.10ms 43.2 MElem/sec 1.00 21.4±0.07ms 46.8 MElem/sec string_dictionary_low_cardinality_400/zstd 1.09 23.8±0.08ms 42.0 MElem/sec 1.00 21.9±0.08ms 45.7 MElem/sec string_dictionary_low_cardinality_400/zstd_parquet_2 1.08 23.6±0.08ms 42.4 MElem/sec 1.00 21.8±0.07ms 45.8 MElem/sec ``` </details> <details><summary>Per-runner information</summary> <details><summary>arrow_writer — shard 1/1</summary> **Node:** gk3-benchmark-cluster-nap-1bmn2koy-714a42d6-jj4x **Instance:** c4a-highmem-16 (12 vCPU / 65 GiB) **uname:** ```text Linux bench-c6124982034-3338-qvrgw 6.12.94+ #1 SMP Fri Aug 21 08:00:16 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 | 1155.3s | | Peak memory | 1.4 GiB | | Avg memory | 105.4 MiB | | CPU user | 1115.4s | | CPU sys | 35.7s | | Peak spill | 0 B | **branch** | Metric | Value | |--------|-------| | Wall time | 1140.3s | | Peak memory | 348.1 MiB | | Avg memory | 107.4 MiB | | CPU user | 1107.7s | | CPU sys | 26.7s | | Peak spill | 0 B | </details> </details> </details> --- [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner <!-- benchmark-request:6124982034:finish:2d16a274f8e55e00900a90da5d3cca15 --> -- 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]
