chore: use bench array helpers from Arrow bench_util by theirix · Pull Request #21544 · apache/datafusion

theirix · 2026-04-10T20:29:07Z

Which issue does this PR close?

Closes #.

Rationale for this change

While working on function benchmarks, I've noticed duplicated code, which can be replaced with arrow::util::bench_util helpers. I recall a discussion in apache/arrow-rs#7294 about bench_util / test_utils usage, and seems like it can be used to simplify clients code.

What changes are included in this PR?

Equivalent changes in benchmarks. More complicated and targeted helpers are left as is

Are these changes tested?

Run benchmarks to check errors or performance degradations

Are there any user-facing changes?

# Conflicts: # datafusion/functions-nested/benches/array_remove.rs

Jefffrey · 2026-04-16T10:54:20Z

run benchmarks array_agg array_min_max array_remove array_repeat array_to_string

adriangbot · 2026-04-16T10:56:24Z

🤖 Criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4259453514-1359-d4bxd 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

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

Comparing use-bench-utils (2112144) to 3911f0c (merge-base) diff
BENCH_NAME=array_to_string
BENCH_COMMAND=cargo bench --features=parquet --bench array_to_string
BENCH_FILTER=
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-16T10:56:28Z

🤖 Criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4259453514-1356-bxxkq 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

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

Comparing use-bench-utils (2112144) to 3911f0c (merge-base) diff
BENCH_NAME=array_min_max
BENCH_COMMAND=cargo bench --features=parquet --bench array_min_max
BENCH_FILTER=
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-16T10:56:35Z

🤖 Criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4259453514-1358-v4bsg 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

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

Comparing use-bench-utils (2112144) to 3911f0c (merge-base) diff
BENCH_NAME=array_repeat
BENCH_COMMAND=cargo bench --features=parquet --bench array_repeat
BENCH_FILTER=
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-16T10:56:49Z

🤖 Criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4259453514-1357-mzxvb 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

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

Comparing use-bench-utils (2112144) to 3911f0c (merge-base) diff
BENCH_NAME=array_remove
BENCH_COMMAND=cargo bench --features=parquet --bench array_remove
BENCH_FILTER=
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-16T10:56:50Z

🤖 Criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4259453514-1355-tzh8v 6.12.55+ #1 SMP Sun Feb 1 08:59:41 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

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

Comparing use-bench-utils (2112144) to 3911f0c (merge-base) diff
BENCH_NAME=array_agg
BENCH_COMMAND=cargo bench --features=parquet --bench array_agg
BENCH_FILTER=
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-16T10:59:32Z

Benchmark for this request failed.

Last 20 lines of output:

Click to expand

 * [new ref]         refs/pull/21544/head -> use-bench-utils
 * branch            main                 -> FETCH_HEAD
Switched to branch 'use-bench-utils'
3911f0cc089a347434cf07202b340b1475df88cc
Cloning into '/workspace/datafusion-base'...
HEAD is now at 3911f0c chore: Add array_slice tests for overlapping nulls across inputs (#21540)
rustc 1.94.1 (e408947bf 2026-03-25)
211214403dd8b172ebbeb80cd52078b7fd07fe36
3911f0cc089a347434cf07202b340b1475df88cc

    Finished `bench` profile [optimized] target(s) in 0.24s
     Running benches/array_repeat.rs (target/release/deps/array_repeat-720dc2b8b22510f7)
Gnuplot not found, using plotters backend
Benchmarking array_repeat_int64/repeat_5_count/100
Benchmarking array_repeat_int64/repeat_5_count/100: Warming up for 3.0000 s

thread 'main' (30730) panicked at datafusion/functions-nested/benches/array_repeat.rs:88:30:
called `Result::unwrap()` on an `Err` value: Internal("could not cast array of type UInt64 to arrow_array::array::primitive_array::PrimitiveArray<arrow_array::types::Int64Type>")
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
error: bench failed, to rerun pass `-p datafusion-functions-nested --bench array_repeat`

File an issue against this benchmark runner

adriangbot · 2026-04-16T11:01:48Z

🤖 Criterion benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

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

group                                main                                   use-bench-utils
-----                                ----                                   ---------------
array_max/no_nulls/list_size=10      1.00     43.6±0.23µs        ? ?/sec    1.50     65.6±0.72µs        ? ?/sec
array_max/no_nulls/list_size=100     1.69   412.3±12.11µs        ? ?/sec    1.00    244.6±0.92µs        ? ?/sec
array_max/no_nulls/list_size=1000    2.29      3.3±0.27ms        ? ?/sec    1.00  1438.3±33.34µs        ? ?/sec
array_max/nulls/list_size=10         1.47    135.9±0.55µs        ? ?/sec    1.00     92.4±0.70µs        ? ?/sec
array_max/nulls/list_size=100        1.68   1256.6±5.67µs        ? ?/sec    1.00    749.9±1.59µs        ? ?/sec
array_max/nulls/list_size=1000       1.94      8.4±0.18ms        ? ?/sec    1.00      4.4±0.10ms        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	63.7s
Peak memory	3.7 GiB
Avg memory	3.6 GiB
CPU user	77.2s
CPU sys	0.9s
Peak spill	0 B

branch

Metric	Value
Wall time	63.7s
Peak memory	3.6 GiB
Avg memory	3.6 GiB
CPU user	78.6s
CPU sys	0.2s
Peak spill	0 B

File an issue against this benchmark runner

adriangbot · 2026-04-16T11:03:20Z

🤖 Criterion benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

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

group                                                                              main                                   use-bench-utils
-----                                                                              ----                                   ---------------
array_agg i64 merge_batch 30% nulls, 0% of nulls point to a zero length array      1.00    499.0±5.38µs        ? ?/sec    1.01    503.7±5.81µs        ? ?/sec
array_agg i64 merge_batch 30% nulls, 100% of nulls point to a zero length array    1.00      4.6±0.00µs        ? ?/sec    1.00      4.6±0.00µs        ? ?/sec
array_agg i64 merge_batch 30% nulls, 50% of nulls point to a zero length array     1.00    499.3±5.57µs        ? ?/sec    1.01    504.3±5.71µs        ? ?/sec
array_agg i64 merge_batch 30% nulls, 90% of nulls point to a zero length array     1.00    504.6±5.95µs        ? ?/sec    1.00    504.2±6.07µs        ? ?/sec
array_agg i64 merge_batch 30% nulls, 99% of nulls point to a zero length array     1.02    508.6±5.89µs        ? ?/sec    1.00    500.0±5.76µs        ? ?/sec
array_agg i64 merge_batch 70% nulls, 0% of nulls point to a zero length array      1.00    213.6±2.41µs        ? ?/sec    1.01    216.6±2.62µs        ? ?/sec
array_agg i64 merge_batch 70% nulls, 100% of nulls point to a zero length array    1.00      4.4±0.00µs        ? ?/sec    1.00      4.4±0.00µs        ? ?/sec
array_agg i64 merge_batch 70% nulls, 50% of nulls point to a zero length array     1.00    217.0±2.48µs        ? ?/sec    1.00    218.1±2.48µs        ? ?/sec
array_agg i64 merge_batch 70% nulls, 90% of nulls point to a zero length array     1.12    242.7±2.15µs        ? ?/sec    1.00    217.4±2.47µs        ? ?/sec
array_agg i64 merge_batch 70% nulls, 99% of nulls point to a zero length array     1.00    217.3±2.47µs        ? ?/sec    1.00    217.2±2.47µs        ? ?/sec
array_agg i64 merge_batch all nulls, 100% of nulls point to a zero length array    1.00     70.8±1.60ns        ? ?/sec    1.11     78.7±4.62ns        ? ?/sec
array_agg i64 merge_batch all nulls, 90% of nulls point to a zero length array     1.00     70.8±1.54ns        ? ?/sec    1.00     70.9±1.47ns        ? ?/sec
array_agg i64 merge_batch no nulls                                                 1.04     82.0±5.47ns        ? ?/sec    1.00     78.8±0.56ns        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	133.0s
Peak memory	3.5 GiB
Avg memory	3.5 GiB
CPU user	164.1s
CPU sys	1.2s
Peak spill	0 B

branch

Metric	Value
Wall time	124.3s
Peak memory	3.5 GiB
Avg memory	3.5 GiB
CPU user	156.6s
CPU sys	0.3s
Peak spill	0 B

File an issue against this benchmark runner

adriangbot · 2026-04-16T11:04:08Z

🤖 Criterion benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

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

group                               main                                   use-bench-utils
-----                               ----                                   ---------------
array_to_string_float64/100         2.34      6.8±0.01ms        ? ?/sec    1.00      2.9±0.00ms        ? ?/sec
array_to_string_float64/20          2.07   1464.1±5.67µs        ? ?/sec    1.00    706.3±1.21µs        ? ?/sec
array_to_string_float64/5           1.69    443.7±0.73µs        ? ?/sec    1.00    263.3±0.50µs        ? ?/sec
array_to_string_int64/100           1.13    819.1±3.75µs        ? ?/sec    1.00    727.2±1.44µs        ? ?/sec
array_to_string_int64/20            1.11    258.9±0.76µs        ? ?/sec    1.00    234.2±0.83µs        ? ?/sec
array_to_string_int64/5             1.02    147.1±0.56µs        ? ?/sec    1.00    143.6±3.15µs        ? ?/sec
array_to_string_nested_int64/100    1.13    851.4±4.27µs        ? ?/sec    1.00    755.0±2.57µs        ? ?/sec
array_to_string_nested_int64/20     1.07    287.0±0.72µs        ? ?/sec    1.00    267.4±0.71µs        ? ?/sec
array_to_string_nested_int64/5      1.01    177.4±1.22µs        ? ?/sec    1.00    174.9±0.52µs        ? ?/sec
array_to_string_string/100          1.00    622.2±1.15µs        ? ?/sec    1.00    624.9±0.79µs        ? ?/sec
array_to_string_string/20           1.00    225.4±0.80µs        ? ?/sec    1.01    228.4±0.66µs        ? ?/sec
array_to_string_string/5            1.00    144.2±0.56µs        ? ?/sec    1.00    144.0±0.49µs        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	127.6s
Peak memory	3.6 GiB
Avg memory	3.6 GiB
CPU user	156.8s
CPU sys	0.8s
Peak spill	0 B

branch

Metric	Value
Wall time	133.3s
Peak memory	3.6 GiB
Avg memory	3.6 GiB
CPU user	163.0s
CPU sys	0.3s
Peak spill	0 B

File an issue against this benchmark runner

Jefffrey · 2026-04-16T11:05:52Z

Benchmark for this request failed.

Last 20 lines of output:
Click to expand

File an issue against this benchmark runner

@theirix could you look into this, if this failure is related?

adriangbot · 2026-04-16T11:07:06Z

🤖 Criterion benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

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

group                                        main                                   use-bench-utils
-----                                        ----                                   ---------------
array_remove_binary/remove/10                1.00      4.8±0.03ms        ? ?/sec    1.00      4.8±0.02ms        ? ?/sec
array_remove_binary/remove/100               1.00     10.3±0.08ms        ? ?/sec    1.01     10.4±0.08ms        ? ?/sec
array_remove_binary/remove/500               1.01     40.0±0.52ms        ? ?/sec    1.00     39.7±0.81ms        ? ?/sec
array_remove_boolean/remove/10               1.00      3.5±0.02ms        ? ?/sec    1.00      3.5±0.08ms        ? ?/sec
array_remove_boolean/remove/100              1.00      5.7±0.03ms        ? ?/sec    1.00      5.7±0.06ms        ? ?/sec
array_remove_boolean/remove/500              1.00     14.0±0.03ms        ? ?/sec    1.00     14.0±0.05ms        ? ?/sec
array_remove_decimal64/remove/10             1.14      4.2±0.03ms        ? ?/sec    1.00      3.7±0.02ms        ? ?/sec
array_remove_decimal64/remove/100            1.38      8.8±0.11ms        ? ?/sec    1.00      6.3±0.06ms        ? ?/sec
array_remove_decimal64/remove/500            1.82     39.4±1.17ms        ? ?/sec    1.00     21.6±0.16ms        ? ?/sec
array_remove_f64/remove/10                   1.12      4.0±0.02ms        ? ?/sec    1.00      3.6±0.02ms        ? ?/sec
array_remove_f64/remove/100                  1.35      6.6±0.07ms        ? ?/sec    1.00      4.9±0.05ms        ? ?/sec
array_remove_f64/remove/500                  2.88     24.4±0.18ms        ? ?/sec    1.00      8.5±0.09ms        ? ?/sec
array_remove_fixed_size_binary/remove/10     1.00      3.9±0.05ms        ? ?/sec    1.03      4.1±0.12ms        ? ?/sec
array_remove_fixed_size_binary/remove/100    1.00      8.8±0.12ms        ? ?/sec    1.03      9.1±0.14ms        ? ?/sec
array_remove_fixed_size_binary/remove/500    1.00     42.9±0.28ms        ? ?/sec    1.06     45.4±0.27ms        ? ?/sec
array_remove_int64/remove/10                 1.13      4.1±0.02ms        ? ?/sec    1.00      3.6±0.02ms        ? ?/sec
array_remove_int64/remove/100                1.37      6.7±0.05ms        ? ?/sec    1.00      4.9±0.04ms        ? ?/sec
array_remove_int64/remove/500                2.83     24.4±0.18ms        ? ?/sec    1.00      8.6±0.11ms        ? ?/sec
array_remove_strings/remove/10               1.00      4.8±0.02ms        ? ?/sec    1.00      4.8±0.02ms        ? ?/sec
array_remove_strings/remove/100              1.01     10.5±0.07ms        ? ?/sec    1.00     10.4±0.07ms        ? ?/sec
array_remove_strings/remove/500              1.02     44.1±1.97ms        ? ?/sec    1.00     43.1±3.13ms        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	228.0s
Peak memory	3.8 GiB
Avg memory	3.7 GiB
CPU user	236.7s
CPU sys	37.7s
Peak spill	0 B

branch

Metric	Value
Wall time	224.5s
Peak memory	3.8 GiB
Avg memory	3.7 GiB
CPU user	245.5s
CPU sys	25.5s
Peak spill	0 B

File an issue against this benchmark runner

theirix · 2026-04-16T18:13:23Z

Benchmark for this request failed.
Last 20 lines of output:
Click to expand
File an issue against this benchmark runner

@theirix could you look into this, if this failure is related?

that's strange, because running cargo bench --bench array_repeat on this branch use-bench-utils (2112144) works well on my computer.

Use bench array helpers from arrow bench_util

19ce24b

# Conflicts: # datafusion/functions-nested/benches/array_remove.rs

github-actions bot added the functions Changes to functions implementation label Apr 10, 2026

theirix added 2 commits April 10, 2026 21:31

Format

2156b81

Clippy

2112144

theirix marked this pull request as ready for review April 10, 2026 20:57

theirix changed the title ~~Use bench array helpers from arrow bench_util~~ chore: use bench array helpers from Arrow bench_util Apr 10, 2026

Conversation

theirix commented Apr 10, 2026

Which issue does this PR close?

Rationale for this change

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

Uh oh!

Jefffrey commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

Jefffrey commented Apr 16, 2026

Uh oh!

adriangbot commented Apr 16, 2026

Uh oh!

theirix commented Apr 16, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants