You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@datafusion.apache.org by "comphead (via GitHub)" <gi...@apache.org> on 2026/06/25 20:10:54 UTC
[PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
comphead opened a new pull request, #23195:
URL: https://github.com/apache/datafusion/pull/23195
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and enhancements and this helps us generate change logs for our releases. You can link an issue to this PR using the GitHub syntax. For example `Closes #123` indicates that this PR will close issue #123.
-->
- Followup https://github.com/apache/datafusion/pull/23192#discussion_r3476455650
## Rationale for this change
`arrow::buffer::OffsetBufferBuilder` is a thin wrapper around `Vec<O>` plus a `last_offset: usize` running counter; every `push_length(n)` does a `checked_add` on `usize` and a `usize_as(O)` conversion. For
per-row loops with a known upfront row count, a direct `Vec<O>` that stores the running offset via `offsets[row] + O::usize_as(len)` can save measurable work in tight per-row loops — provided the offset push
is a meaningful fraction of per-row cost.
I swapped the pattern in all eight `OffsetBufferBuilder` call sites in the repo (`array_normalize`, `array_filter`, `remove`, `replace`, `array_add`, `utils::general_array_zip_with`, `array_scale`,
`encoding::delegated_decode`), benchmarked the three sites that have criterion benches, and found the win is **not** uniform.
## What changes are included in this PR?
Replace `OffsetBufferBuilder<O>` with `Vec<O>` (preinitialized with `O::zero()` and finalized with `OffsetBuffer::new(v.into())`) **only** in `datafusion/functions-nested/src/remove.rs`, where benches show
clean wins with no regressions.
The other seven sites are left on `OffsetBufferBuilder` — benches showed flat-to-regressing results, see below.
## Are these changes tested?
Existing unit tests, doctests, and sqllogictests (`array_remove*`) pass unchanged. No new tests — refactor is functionally equivalent.
## Are there any user-facing changes?
No.
## Benchmark results
The biggest win is `array_remove`
### `array_remove`
| Bench | size 10 | size 100 | size 500 |
|---|---:|---:|---:|
| `int64` | −0.2% | −1.0% | **−50.0%** |
| `n_int64` | −0.7% | +0.05% | **−23.1%** |
| `all_int64` | +0.2% | −1.8% | **−15.1%** |
| `strings` | +3.8% | +0.6% | **−4.6%** |
| `boolean` | −0.01% | +1.1% | +0.3% |
| `fixed_size_binary` | −0.06% | **−20.0%** | **−2.6%** |
| `int64_nested` | flat | flat | flat |
For others its more like noise
--
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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "comphead (via GitHub)" <gi...@apache.org>.
comphead merged PR #23195:
URL: https://github.com/apache/datafusion/pull/23195
--
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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "comphead (via GitHub)" <gi...@apache.org>.
comphead commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4804849009
the benchmark is confusing, the same metric from 2 different runs, reports
```
array_remove_n_int64/remove/list size: 500, num_rows: 10000 1.00 9.3±0.24ms ? ?/sec 1.83 17.0±0.26ms ? ?/sec
and then
array_remove_n_int64/remove/list size: 500, num_rows: 10000 1.85 16.6±0.15ms ? ?/sec 1.00 9.0±0.13ms ? ?/sec
```
I'll check again my local benchmarks, if its reported as faster I'll follow local recommendations, however even now the PR brings some purpose in terms of unification
--
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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "alamb (via GitHub)" <gi...@apache.org>.
alamb commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4804368805
run benchmark array_remove
--
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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4804385994
🤖 Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/23195#issuecomment-4804368805)
**Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c4804368805-682-wj72w 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux`
<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>
Comparing arrays (4303be4b6333fc4cefd4125a74406aa3c62bbdb5) to a0e9887 (merge-base) [diff](https://github.com/apache/datafusion/compare/a0e9887550065324320c6fd52001aa23bae67485..4303be4b6333fc4cefd4125a74406aa3c62bbdb5) using: array_remove
Results will be posted here when complete
---
[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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4804497454
🤖 Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/23195#issuecomment-4804368805)
**Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
<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 arrays
----- ---- ------
array_remove_all_int64/remove/list size: 10, num_rows: 4000 1.00 243.0±1.36µs ? ?/sec 1.01 245.3±2.26µs ? ?/sec
array_remove_all_int64/remove/list size: 100, num_rows: 10000 1.00 2.6±0.03ms ? ?/sec 1.02 2.7±0.03ms ? ?/sec
array_remove_all_int64/remove/list size: 500, num_rows: 10000 1.00 12.4±0.19ms ? ?/sec 1.24 15.4±1.06ms ? ?/sec
array_remove_all_int64_nested/remove/list size: 10, num_rows: 4000 1.00 12.2±0.10ms ? ?/sec 1.00 12.3±0.10ms ? ?/sec
array_remove_all_int64_nested/remove/list size: 100, num_rows: 3000 1.00 68.5±0.87ms ? ?/sec 1.02 69.9±1.16ms ? ?/sec
array_remove_all_int64_nested/remove/list size: 300, num_rows: 1500 1.02 100.7±1.11ms ? ?/sec 1.00 98.5±1.59ms ? ?/sec
array_remove_boolean/remove/list size: 10, num_rows: 4000 1.00 313.5±1.31µs ? ?/sec 1.01 316.3±0.71µs ? ?/sec
array_remove_boolean/remove/list size: 100, num_rows: 10000 1.00 1668.1±3.93µs ? ?/sec 1.01 1683.3±9.46µs ? ?/sec
array_remove_boolean/remove/list size: 500, num_rows: 10000 1.00 5.4±0.01ms ? ?/sec 1.00 5.4±0.01ms ? ?/sec
array_remove_fixed_size_binary/remove/list size: 10, num_rows: 4000 1.00 306.9±1.50µs ? ?/sec 1.00 307.5±1.84µs ? ?/sec
array_remove_fixed_size_binary/remove/list size: 100, num_rows: 10000 1.00 3.5±0.08ms ? ?/sec 1.00 3.5±0.08ms ? ?/sec
array_remove_fixed_size_binary/remove/list size: 500, num_rows: 10000 1.00 32.4±0.15ms ? ?/sec 1.02 33.1±0.15ms ? ?/sec
array_remove_int64/remove/list size: 10, num_rows: 4000 1.00 232.5±1.43µs ? ?/sec 1.00 233.1±1.66µs ? ?/sec
array_remove_int64/remove/list size: 100, num_rows: 10000 1.00 1209.3±12.20µs ? ?/sec 1.00 1205.7±22.04µs ? ?/sec
array_remove_int64/remove/list size: 500, num_rows: 10000 1.00 12.5±0.19ms ? ?/sec 1.02 12.7±0.22ms ? ?/sec
array_remove_int64_nested/remove/list size: 10, num_rows: 4000 1.00 12.2±0.10ms ? ?/sec 1.00 12.2±0.09ms ? ?/sec
array_remove_int64_nested/remove/list size: 100, num_rows: 3000 1.00 67.9±0.72ms ? ?/sec 1.00 67.9±0.72ms ? ?/sec
array_remove_int64_nested/remove/list size: 300, num_rows: 1500 1.00 97.6±1.68ms ? ?/sec 1.00 97.4±1.55ms ? ?/sec
array_remove_n_int64/remove/list size: 10, num_rows: 4000 1.00 241.2±1.27µs ? ?/sec 1.01 244.4±2.29µs ? ?/sec
array_remove_n_int64/remove/list size: 100, num_rows: 10000 1.00 1830.5±15.44µs ? ?/sec 1.00 1838.8±18.10µs ? ?/sec
array_remove_n_int64/remove/list size: 500, num_rows: 10000 1.00 9.3±0.24ms ? ?/sec 1.83 17.0±0.26ms ? ?/sec
array_remove_n_int64_nested/remove/list size: 10, num_rows: 4000 1.00 12.3±0.10ms ? ?/sec 1.00 12.4±0.12ms ? ?/sec
array_remove_n_int64_nested/remove/list size: 100, num_rows: 3000 1.01 70.9±2.12ms ? ?/sec 1.00 70.4±2.23ms ? ?/sec
array_remove_n_int64_nested/remove/list size: 300, num_rows: 1500 1.00 98.3±2.01ms ? ?/sec 1.03 101.2±2.05ms ? ?/sec
array_remove_strings/remove/list size: 10, num_rows: 4000 1.01 416.3±1.20µs ? ?/sec 1.00 412.5±1.39µs ? ?/sec
array_remove_strings/remove/list size: 100, num_rows: 10000 1.00 6.5±0.03ms ? ?/sec 1.00 6.5±0.03ms ? ?/sec
array_remove_strings/remove/list size: 500, num_rows: 10000 1.10 46.1±0.21ms ? ?/sec 1.00 41.8±0.90ms ? ?/sec
```
</p>
</details>
<details><summary>Resource Usage</summary>
**array_remove — base (merge-base)**
| Metric | Value |
|--------|-------|
| Wall time | 525.1s |
| Peak memory | 222.9 MiB |
| Avg memory | 37.2 MiB |
| CPU user | 341.4s |
| CPU sys | 17.8s |
| Peak spill | 0 B |
**array_remove — branch**
| Metric | Value |
|--------|-------|
| Wall time | 515.1s |
| Peak memory | 188.4 MiB |
| Avg memory | 37.7 MiB |
| CPU user | 333.6s |
| CPU sys | 22.6s |
| 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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "comphead (via GitHub)" <gi...@apache.org>.
comphead commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4803858338
@alamb FYI, for `array_remove` the win is obvious, however for others the perf is same.
--
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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4804739656
🤖 Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/23195#issuecomment-4804721008)
**Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c4804721008-683-b54h9 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux`
<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>
Comparing arrays (4303be4b6333fc4cefd4125a74406aa3c62bbdb5) to a0e9887 (merge-base) [diff](https://github.com/apache/datafusion/compare/a0e9887550065324320c6fd52001aa23bae67485..4303be4b6333fc4cefd4125a74406aa3c62bbdb5) using: array_remove
Results will be posted here when complete
---
[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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4804820119
🤖 Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/23195#issuecomment-4804721008)
**Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
<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 arrays
----- ---- ------
array_remove_all_int64/remove/list size: 10, num_rows: 4000 1.00 243.1±1.49µs ? ?/sec 1.01 245.3±2.06µs ? ?/sec
array_remove_all_int64/remove/list size: 100, num_rows: 10000 1.00 2.6±0.03ms ? ?/sec 1.03 2.6±0.03ms ? ?/sec
array_remove_all_int64/remove/list size: 500, num_rows: 10000 1.00 12.2±0.16ms ? ?/sec 1.01 12.3±0.16ms ? ?/sec
array_remove_all_int64_nested/remove/list size: 10, num_rows: 4000 1.00 12.3±0.10ms ? ?/sec 1.00 12.2±0.11ms ? ?/sec
array_remove_all_int64_nested/remove/list size: 100, num_rows: 3000 1.01 68.7±1.02ms ? ?/sec 1.00 68.3±0.71ms ? ?/sec
array_remove_all_int64_nested/remove/list size: 300, num_rows: 1500 1.00 98.6±1.35ms ? ?/sec 1.00 98.1±1.03ms ? ?/sec
array_remove_boolean/remove/list size: 10, num_rows: 4000 1.00 313.7±1.30µs ? ?/sec 1.01 316.3±0.78µs ? ?/sec
array_remove_boolean/remove/list size: 100, num_rows: 10000 1.00 1667.6±3.21µs ? ?/sec 1.01 1683.6±9.54µs ? ?/sec
array_remove_boolean/remove/list size: 500, num_rows: 10000 1.00 5.4±0.01ms ? ?/sec 1.00 5.4±0.01ms ? ?/sec
array_remove_fixed_size_binary/remove/list size: 10, num_rows: 4000 1.04 319.5±2.31µs ? ?/sec 1.00 306.5±1.85µs ? ?/sec
array_remove_fixed_size_binary/remove/list size: 100, num_rows: 10000 1.02 3.4±0.05ms ? ?/sec 1.00 3.4±0.04ms ? ?/sec
array_remove_fixed_size_binary/remove/list size: 500, num_rows: 10000 1.00 33.1±0.09ms ? ?/sec 1.03 34.0±0.10ms ? ?/sec
array_remove_int64/remove/list size: 10, num_rows: 4000 1.00 232.7±1.52µs ? ?/sec 1.01 234.8±1.71µs ? ?/sec
array_remove_int64/remove/list size: 100, num_rows: 10000 1.00 1184.6±9.16µs ? ?/sec 1.04 1234.0±23.88µs ? ?/sec
array_remove_int64/remove/list size: 500, num_rows: 10000 1.00 12.3±0.29ms ? ?/sec 1.08 13.3±0.10ms ? ?/sec
array_remove_int64_nested/remove/list size: 10, num_rows: 4000 1.00 12.2±0.11ms ? ?/sec 1.00 12.2±0.10ms ? ?/sec
array_remove_int64_nested/remove/list size: 100, num_rows: 3000 1.00 68.0±0.99ms ? ?/sec 1.00 67.7±0.88ms ? ?/sec
array_remove_int64_nested/remove/list size: 300, num_rows: 1500 1.00 97.5±1.52ms ? ?/sec 1.02 99.6±1.25ms ? ?/sec
array_remove_n_int64/remove/list size: 10, num_rows: 4000 1.00 241.3±1.34µs ? ?/sec 1.02 244.9±3.31µs ? ?/sec
array_remove_n_int64/remove/list size: 100, num_rows: 10000 1.00 1808.5±13.70µs ? ?/sec 1.01 1828.9±15.19µs ? ?/sec
array_remove_n_int64/remove/list size: 500, num_rows: 10000 1.85 16.6±0.15ms ? ?/sec 1.00 9.0±0.13ms ? ?/sec
array_remove_n_int64_nested/remove/list size: 10, num_rows: 4000 1.00 12.3±0.09ms ? ?/sec 1.00 12.3±0.10ms ? ?/sec
array_remove_n_int64_nested/remove/list size: 100, num_rows: 3000 1.01 68.3±1.06ms ? ?/sec 1.00 68.0±0.79ms ? ?/sec
array_remove_n_int64_nested/remove/list size: 300, num_rows: 1500 1.00 97.8±1.29ms ? ?/sec 1.00 97.7±1.07ms ? ?/sec
array_remove_strings/remove/list size: 10, num_rows: 4000 1.01 414.3±1.18µs ? ?/sec 1.00 412.2±1.45µs ? ?/sec
array_remove_strings/remove/list size: 100, num_rows: 10000 1.00 6.5±0.02ms ? ?/sec 1.00 6.5±0.02ms ? ?/sec
array_remove_strings/remove/list size: 500, num_rows: 10000 1.00 36.7±0.08ms ? ?/sec 1.28 46.9±0.10ms ? ?/sec
```
</p>
</details>
<details><summary>Resource Usage</summary>
**array_remove — base (merge-base)**
| Metric | Value |
|--------|-------|
| Wall time | 375.1s |
| Peak memory | 206.1 MiB |
| Avg memory | 53.9 MiB |
| CPU user | 336.7s |
| CPU sys | 20.7s |
| Peak spill | 0 B |
**array_remove — branch**
| Metric | Value |
|--------|-------|
| Wall time | 370.1s |
| Peak memory | 225.0 MiB |
| Avg memory | 51.2 MiB |
| CPU user | 338.6s |
| CPU sys | 18.8s |
| 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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org
Re: [PR] chore: use `Vec` instead of `OffsetBuilder` [datafusion]
Posted by "comphead (via GitHub)" <gi...@apache.org>.
comphead commented on PR #23195:
URL: https://github.com/apache/datafusion/pull/23195#issuecomment-4804721008
run benchmark array_remove
--
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: github-unsubscribe@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org