adriangbot commented on PR #23648: URL: https://github.com/apache/datafusion/pull/23648#issuecomment-5558661513
🤖 Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/23648#issuecomment-5558396112) **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) Comparing nested-group-column-for-lists (6f73226c277e9b36b070c77da99678eed904a5f6) to 3a4c310 (merge-base) [diff](https://github.com/apache/datafusion/compare/3a4c310da72ea419e777bf56bbedaf1fb83e087e..6f73226c277e9b36b070c77da99678eed904a5f6) <details><summary>Run configuration</summary> ```yaml run benchmark multi_group_by ``` </details> <details><summary>CPU Details (lscpu)</summary> ``` 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>Details</summary> <p> ``` group HEAD nested-group-column-for-lists ----- ---- ----------------------------- batch_size_sensitivity/row_based/batch_1024 1.00 10.7±0.01ms ? ?/sec 1.00 10.7±0.03ms ? ?/sec batch_size_sensitivity/row_based/batch_16384 1.01 10.6±0.00ms ? ?/sec 1.00 10.5±0.01ms ? ?/sec batch_size_sensitivity/row_based/batch_32768 1.00 10.8±0.00ms ? ?/sec 1.00 10.8±0.02ms ? ?/sec batch_size_sensitivity/row_based/batch_4096 1.00 10.6±0.00ms ? ?/sec 1.00 10.6±0.00ms ? ?/sec batch_size_sensitivity/row_based/batch_8192 1.01 10.7±0.01ms ? ?/sec 1.00 10.5±0.01ms ? ?/sec batch_size_sensitivity/vectorized/batch_1024 1.00 9.6±0.01ms ? ?/sec 1.00 9.6±0.01ms ? ?/sec batch_size_sensitivity/vectorized/batch_16384 1.00 9.5±0.01ms ? ?/sec 1.02 9.7±0.01ms ? ?/sec batch_size_sensitivity/vectorized/batch_32768 1.06 10.1±0.10ms ? ?/sec 1.00 9.6±0.00ms ? ?/sec batch_size_sensitivity/vectorized/batch_4096 1.03 9.8±0.32ms ? ?/sec 1.00 9.6±0.00ms ? ?/sec batch_size_sensitivity/vectorized/batch_8192 1.01 9.7±0.01ms ? ?/sec 1.00 9.6±0.01ms ? ?/sec column_scaling/row_based/cols_10_grp_1024 1.00 25.1±0.06ms ? ?/sec 1.00 25.1±0.10ms ? ?/sec column_scaling/row_based/cols_2_grp_100 1.03 9.4±0.06ms ? ?/sec 1.00 9.1±0.01ms ? ?/sec column_scaling/row_based/cols_3_grp_125 1.01 11.0±0.03ms ? ?/sec 1.00 10.9±0.22ms ? ?/sec column_scaling/row_based/cols_4_grp_81 1.02 13.6±0.15ms ? ?/sec 1.00 13.3±0.01ms ? ?/sec column_scaling/row_based/cols_6_grp_729 1.00 17.6±0.01ms ? ?/sec 1.01 17.7±0.01ms ? ?/sec column_scaling/row_based/cols_8_grp_256 1.00 22.0±0.03ms ? ?/sec 1.02 22.3±0.02ms ? ?/sec column_scaling/vectorized/cols_10_grp_1024 1.16 26.7±0.13ms ? ?/sec 1.00 23.1±0.10ms ? ?/sec column_scaling/vectorized/cols_2_grp_100 1.01 7.8±0.01ms ? ?/sec 1.00 7.7±0.01ms ? ?/sec column_scaling/vectorized/cols_3_grp_125 1.01 9.7±0.01ms ? ?/sec 1.00 9.7±0.01ms ? ?/sec column_scaling/vectorized/cols_4_grp_81 1.02 11.8±0.15ms ? ?/sec 1.00 11.6±0.01ms ? ?/sec column_scaling/vectorized/cols_6_grp_729 1.11 17.1±0.39ms ? ?/sec 1.00 15.3±0.04ms ? ?/sec column_scaling/vectorized/cols_8_grp_256 1.17 22.9±0.69ms ? ?/sec 1.00 19.5±0.03ms ? ?/sec decimal256/row_based/grp_1000 1.01 14.0±0.03ms ? ?/sec 1.00 13.9±0.04ms ? ?/sec decimal256/row_based/grp_1000000 1.01 43.5±0.07ms ? ?/sec 1.00 42.8±0.05ms ? ?/sec decimal256/vectorized/grp_1000 1.00 9.6±0.02ms ? ?/sec 1.02 9.8±0.18ms ? ?/sec decimal256/vectorized/grp_1000000 1.00 38.2±0.05ms ? ?/sec 1.00 38.1±0.04ms ? ?/sec duration/row_based/grp_1000 1.03 9.8±0.01ms ? ?/sec 1.00 9.5±0.03ms ? ?/sec duration/row_based/grp_1000000 1.00 37.9±0.17ms ? ?/sec 1.00 37.8±0.10ms ? ?/sec duration/vectorized/grp_1000 1.01 7.9±0.01ms ? ?/sec 1.00 7.9±0.01ms ? ?/sec duration/vectorized/grp_1000000 1.00 34.3±0.07ms ? ?/sec 1.02 35.0±0.03ms ? ?/sec fixed_size_binary/row_based/grp_1000 1.00 12.7±0.05ms ? ?/sec 1.00 12.8±0.01ms ? ?/sec fixed_size_binary/row_based/grp_1000000 1.02 41.3±0.19ms ? ?/sec 1.00 40.6±0.10ms ? ?/sec fixed_size_binary/vectorized/grp_1000 1.03 11.5±0.36ms ? ?/sec 1.00 11.2±0.37ms ? ?/sec fixed_size_binary/vectorized/grp_1000000 1.01 37.3±0.07ms ? ?/sec 1.00 36.8±0.02ms ? ?/sec float16/row_based/grp_1000 1.02 10.2±0.09ms ? ?/sec 1.00 10.0±0.12ms ? ?/sec float16/row_based/grp_60000 1.00 17.3±0.03ms ? ?/sec 1.03 17.9±0.05ms ? ?/sec float16/vectorized/grp_1000 1.00 8.1±0.00ms ? ?/sec 1.02 8.3±0.19ms ? ?/sec float16/vectorized/grp_60000 1.00 13.0±0.03ms ? ?/sec 1.00 13.0±0.06ms ? ?/sec group_count_sweep/row_based/grp_1000 1.02 13.7±0.05ms ? ?/sec 1.00 13.5±0.01ms ? ?/sec group_count_sweep/row_based/grp_10000 1.00 14.6±0.02ms ? ?/sec 1.00 14.6±0.14ms ? ?/sec group_count_sweep/row_based/grp_100000 1.00 23.3±0.03ms ? ?/sec 1.01 23.7±0.06ms ? ?/sec group_count_sweep/row_based/grp_1000000 1.00 41.1±0.05ms ? ?/sec 1.02 41.8±0.06ms ? ?/sec group_count_sweep/row_based/grp_16 1.00 13.1±0.01ms ? ?/sec 1.01 13.2±0.01ms ? ?/sec group_count_sweep/row_based/grp_256 1.03 13.6±0.04ms ? ?/sec 1.00 13.2±0.01ms ? ?/sec group_count_sweep/row_based/grp_5000 1.00 14.1±0.07ms ? ?/sec 1.00 14.1±0.13ms ? ?/sec group_count_sweep/row_based/grp_50000 1.00 19.9±0.02ms ? ?/sec 1.00 19.8±0.02ms ? ?/sec group_count_sweep/row_based/grp_500000 1.00 35.9±0.25ms ? ?/sec 1.01 36.4±0.22ms ? ?/sec group_count_sweep/row_based/grp_64 1.01 13.8±0.05ms ? ?/sec 1.00 13.8±0.01ms ? ?/sec group_count_sweep/vectorized/grp_1000 1.01 11.6±0.01ms ? ?/sec 1.00 11.5±0.01ms ? ?/sec group_count_sweep/vectorized/grp_10000 1.02 12.4±0.18ms ? ?/sec 1.00 12.1±0.05ms ? ?/sec group_count_sweep/vectorized/grp_100000 1.00 17.9±0.15ms ? ?/sec 1.01 18.1±0.11ms ? ?/sec group_count_sweep/vectorized/grp_1000000 1.00 40.2±0.03ms ? ?/sec 1.01 40.4±0.05ms ? ?/sec group_count_sweep/vectorized/grp_16 1.00 11.4±0.01ms ? ?/sec 1.00 11.4±0.01ms ? ?/sec group_count_sweep/vectorized/grp_256 1.00 11.5±0.01ms ? ?/sec 1.19 13.6±0.38ms ? ?/sec group_count_sweep/vectorized/grp_5000 1.00 12.1±0.39ms ? ?/sec 1.01 12.2±0.04ms ? ?/sec group_count_sweep/vectorized/grp_50000 1.00 15.2±0.13ms ? ?/sec 1.02 15.5±0.07ms ? ?/sec group_count_sweep/vectorized/grp_500000 1.00 30.1±0.14ms ? ?/sec 1.01 30.2±0.20ms ? ?/sec group_count_sweep/vectorized/grp_64 1.00 11.5±0.01ms ? ?/sec 1.03 11.8±0.00ms ? ?/sec high_cardinality_scaling/row_based/cols_10_grp_1M 1.00 55.8±0.12ms ? ?/sec 1.03 57.4±0.14ms ? ?/sec high_cardinality_scaling/row_based/cols_2_grp_1M 1.01 38.5±0.04ms ? ?/sec 1.00 38.0±0.07ms ? ?/sec high_cardinality_scaling/row_based/cols_3_grp_1M 1.00 38.7±0.05ms ? ?/sec 1.01 39.2±0.02ms ? ?/sec high_cardinality_scaling/row_based/cols_4_grp_1M 1.02 41.8±0.08ms ? ?/sec 1.00 41.2±0.10ms ? ?/sec high_cardinality_scaling/row_based/cols_6_grp_1M 1.00 46.4±0.04ms ? ?/sec 1.03 48.0±0.10ms ? ?/sec high_cardinality_scaling/row_based/cols_8_grp_1M 1.00 50.9±0.05ms ? ?/sec 1.02 52.0±0.06ms ? ?/sec high_cardinality_scaling/vectorized/cols_10_grp_1M 1.01 59.4±0.29ms ? ?/sec 1.00 59.0±0.09ms ? ?/sec high_cardinality_scaling/vectorized/cols_2_grp_1M 1.00 34.1±0.02ms ? ?/sec 1.00 33.9±0.03ms ? ?/sec high_cardinality_scaling/vectorized/cols_3_grp_1M 1.00 37.0±0.03ms ? ?/sec 1.01 37.3±0.15ms ? ?/sec high_cardinality_scaling/vectorized/cols_4_grp_1M 1.00 40.2±0.05ms ? ?/sec 1.00 40.4±0.04ms ? ?/sec high_cardinality_scaling/vectorized/cols_6_grp_1M 1.00 46.3±0.09ms ? ?/sec 1.03 47.8±0.06ms ? ?/sec high_cardinality_scaling/vectorized/cols_8_grp_1M 1.00 52.6±0.15ms ? ?/sec 1.02 53.7±0.09ms ? ?/sec interval/row_based/grp_1000 1.00 11.5±0.01ms ? ?/sec 1.00 11.5±0.01ms ? ?/sec interval/row_based/grp_1000000 1.00 40.0±0.07ms ? ?/sec 1.01 40.2±0.03ms ? ?/sec interval/vectorized/grp_1000 1.00 8.7±0.02ms ? ?/sec 1.00 8.7±0.03ms ? ?/sec interval/vectorized/grp_1000000 1.00 35.7±0.09ms ? ?/sec 1.03 36.6±0.06ms ? ?/sec issue_17850_regression/row_based/10000000_rows 1.00 108.2±0.09ms ? ?/sec 1.00 107.7±0.08ms ? ?/sec issue_17850_regression/row_based/1000000_rows 1.00 10.5±0.01ms ? ?/sec 1.00 10.5±0.00ms ? ?/sec issue_17850_regression/row_based/20000000_rows 1.01 216.9±0.16ms ? ?/sec 1.00 215.8±0.80ms ? ?/sec issue_17850_regression/row_based/50000000_rows 1.00 544.1±3.64ms ? ?/sec 1.03 561.1±5.56ms ? ?/sec issue_17850_regression/row_based/5000000_rows 1.01 53.9±0.17ms ? ?/sec 1.00 53.2±0.04ms ? ?/sec issue_17850_regression/vectorized/10000000_rows 1.00 98.8±0.08ms ? ?/sec 1.04 102.3±0.48ms ? ?/sec issue_17850_regression/vectorized/1000000_rows 1.01 9.6±0.01ms ? ?/sec 1.00 9.5±0.01ms ? ?/sec issue_17850_regression/vectorized/20000000_rows 1.00 198.4±0.13ms ? ?/sec 1.00 198.2±0.10ms ? ?/sec issue_17850_regression/vectorized/50000000_rows 1.00 489.6±0.51ms ? ?/sec 1.09 531.8±24.98ms ? ?/sec issue_17850_regression/vectorized/5000000_rows 1.00 48.5±0.05ms ? ?/sec 1.00 48.7±0.09ms ? ?/sec list_int/row_based/grp_1000 1.02 32.3±0.50ms ? ?/sec 1.00 31.7±0.02ms ? ?/sec list_int/row_based/grp_1000000 1.00 61.0±0.09ms ? ?/sec 1.01 61.7±0.10ms ? ?/sec list_int/vectorized/grp_1000 1.56 34.2±0.11ms ? ?/sec 1.00 21.9±0.62ms ? ?/sec list_int/vectorized/grp_1000000 1.24 61.6±0.07ms ? ?/sec 1.00 49.6±0.07ms ? ?/sec list_utf8/row_based/grp_1000 1.00 46.1±0.13ms ? ?/sec 1.01 46.5±0.19ms ? ?/sec list_utf8/row_based/grp_1000000 1.00 78.5±0.23ms ? ?/sec 1.00 78.4±0.38ms ? ?/sec list_utf8/vectorized/grp_1000 1.71 48.9±0.76ms ? ?/sec 1.00 28.7±0.42ms ? ?/sec list_utf8/vectorized/grp_1000000 1.32 81.7±0.30ms ? ?/sec 1.00 61.8±0.13ms ? ?/sec low_cardinality/row_based/cols_3_card_2_grp_8 1.05 11.0±0.02ms ? ?/sec 1.00 10.5±0.01ms ? ?/sec low_cardinality/row_based/cols_3_card_4_grp_64 1.01 10.6±0.01ms ? ?/sec 1.00 10.5±0.01ms ? ?/sec low_cardinality/row_based/cols_3_card_8_grp_512 1.00 10.6±0.01ms ? ?/sec 1.03 10.9±0.11ms ? ?/sec low_cardinality/row_based/cols_4_card_2_grp_16 1.00 13.2±0.00ms ? ?/sec 1.00 13.2±0.01ms ? ?/sec low_cardinality/row_based/cols_4_card_4_grp_256 1.00 13.5±0.06ms ? ?/sec 1.00 13.5±0.12ms ? ?/sec low_cardinality/row_based/cols_4_card_8_grp_4096 1.00 14.1±0.01ms ? ?/sec 1.00 14.1±0.04ms ? ?/sec low_cardinality/vectorized/cols_3_card_2_grp_8 1.16 11.1±0.23ms ? ?/sec 1.00 9.5±0.01ms ? ?/sec low_cardinality/vectorized/cols_3_card_4_grp_64 1.00 9.6±0.01ms ? ?/sec 1.00 9.6±0.00ms ? ?/sec low_cardinality/vectorized/cols_3_card_8_grp_512 1.00 9.6±0.01ms ? ?/sec 1.00 9.7±0.01ms ? ?/sec low_cardinality/vectorized/cols_4_card_2_grp_16 1.13 12.9±1.24ms ? ?/sec 1.00 11.4±0.01ms ? ?/sec low_cardinality/vectorized/cols_4_card_4_grp_256 1.00 11.6±0.01ms ? ?/sec 1.00 11.5±0.01ms ? ?/sec low_cardinality/vectorized/cols_4_card_8_grp_4096 1.04 12.5±0.38ms ? ?/sec 1.00 11.9±0.17ms ? ?/sec ``` </p> </details> <details><summary>Resource Usage</summary> **multi_group_by — base (merge-base)** | Metric | Value | |--------|-------| | Wall time | 1570.3s | | Peak memory | 610.6 MiB | | Avg memory | 441.3 MiB | | CPU user | 1434.8s | | CPU sys | 1.4s | | Peak spill | 0 B | **multi_group_by — branch** | Metric | Value | |--------|-------| | Wall time | 1545.3s | | Peak memory | 610.4 MiB | | Avg memory | 440.8 MiB | | CPU user | 1414.0s | | CPU sys | 1.4s | | Peak spill | 0 B | </details> --- [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner -- 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]
