You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by "cakeni (via GitHub)" <gi...@apache.org> on 2026/08/11 10:56:09 UTC
[PR] Replace BufferBuilder with Vec in MapArrayDecoder [arrow-rs]
cakeni opened a new pull request, #10629:
URL: https://github.com/apache/arrow-rs/pull/10629
# Which issue does this PR close?
- Part of #10245.
# Rationale for this change
Using `Vec` instead of `BufferBuilder` can improve performance by benefiting from Rust's optimized `Vec` implementation. This updates the remaining `BufferBuilder` usage in `arrow-json` and follows the existing `ListArrayDecoder` approach.
# What changes are included in this PR?
- Replace `MapArrayDecoder`'s offset `BufferBuilder<i32>` with a preallocated `Vec<i32>`.
- Construct the final `ScalarBuffer` directly from the vector.
- Remove the now-unused `BufferBuilder` import.
# Are these changes tested?
Yes. The following checks pass:
- `cargo +stable-x86_64-pc-windows-gnu fmt --all -- --check`
- `cargo +stable-x86_64-pc-windows-gnu clippy -p arrow-json --all-targets --all-features --no-deps -- -D warnings`
- `cargo +stable-x86_64-pc-windows-gnu test -p arrow-json --all-features` (134 unit tests and 17 doctests passed)
# Are there any user-facing changes?
No.
--
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@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Replace BufferBuilder with Vec in MapArrayDecoder [arrow-rs]
Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #10629:
URL: https://github.com/apache/arrow-rs/pull/10629#issuecomment-5264127424
🤖 Arrow criterion benchmark completed (GKE) | [trigger](https://github.com/apache/arrow-rs/pull/10629#issuecomment-5263922631)
**Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
Comparing perf/arrow-json-map-offsets-vec (4006e1462326d781c0a490218b32c74a5aae599c) to fc16607 (merge-base) [diff](https://github.com/apache/arrow-rs/compare/fc16607ccfdb298557ed6630742941761ac18ce3..4006e1462326d781c0a490218b32c74a5aae599c)
<details><summary>Run configuration</summary>
```yaml
run benchmark json_reader
```
</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 main perf_arrow-json-map-offsets-vec
----- ---- -------------------------------
decode_binary_hex_json 1.00 13.8±0.04ms ? ?/sec 1.00 13.7±0.05ms ? ?/sec
decode_binary_view_hex_json 1.00 14.2±0.06ms ? ?/sec 1.00 14.2±0.04ms ? ?/sec
decode_fixed_binary_hex_json 1.00 13.8±0.04ms ? ?/sec 1.02 14.1±0.10ms ? ?/sec
decode_list_long_json/131072 1.00 303.8±1.45ms 257.8 MB/sec 1.01 308.2±1.33ms 254.1 MB/sec
decode_list_long_serialize 1.00 206.2±1.09ms ? ?/sec 1.00 206.6±1.68ms ? ?/sec
decode_list_short_json/131072 1.00 19.7±0.09ms 264.6 MB/sec 1.01 20.0±0.07ms 261.2 MB/sec
decode_list_short_serialize 1.01 11.8±0.09ms ? ?/sec 1.00 11.6±0.12ms ? ?/sec
decode_list_view_long_json/131072 1.00 304.4±1.92ms 257.2 MB/sec 1.01 308.4±1.25ms 253.9 MB/sec
decode_list_view_long_serialize 1.00 207.2±1.07ms ? ?/sec 1.00 207.8±1.33ms ? ?/sec
decode_list_view_short_json/131072 1.00 20.7±0.06ms 252.5 MB/sec 1.00 20.6±0.06ms 253.4 MB/sec
decode_list_view_short_serialize 1.00 12.0±0.11ms ? ?/sec 1.00 12.0±0.12ms ? ?/sec
decode_map_large_json/131072 1.00 254.8±1.06ms 298.1 MB/sec 1.00 255.7±1.05ms 297.1 MB/sec
decode_map_large_serialize 1.00 288.4±2.08ms ? ?/sec 1.02 293.5±1.75ms ? ?/sec
decode_map_small_json/131072 1.00 29.5±0.13ms 278.6 MB/sec 1.01 29.8±0.12ms 276.2 MB/sec
decode_map_small_serialize 1.00 20.2±0.17ms ? ?/sec 1.01 20.4±0.16ms ? ?/sec
decode_ree_long_json/131072 1.00 5.9±0.01ms 258.9 MB/sec 1.01 5.9±0.01ms 256.6 MB/sec
decode_ree_long_serialize 1.01 4.4±0.05ms ? ?/sec 1.00 4.4±0.07ms ? ?/sec
decode_ree_short_json/131072 1.05 6.8±0.02ms 254.7 MB/sec 1.00 6.5±0.01ms 266.8 MB/sec
decode_ree_short_serialize 1.03 4.8±0.08ms ? ?/sec 1.00 4.7±0.05ms ? ?/sec
decode_wide_object_json/131072 1.00 459.6±6.89ms 209.4 MB/sec 1.00 457.6±2.80ms 210.3 MB/sec
decode_wide_object_serialize 1.01 440.7±6.38ms ? ?/sec 1.00 436.0±3.41ms ? ?/sec
decode_wide_projection_full_json/131072 1.00 765.1±9.52ms 227.4 MB/sec 1.01 774.3±6.01ms 224.7 MB/sec
decode_wide_projection_narrow_json/131072 1.00 434.9±1.59ms 400.1 MB/sec 1.00 433.5±1.44ms 401.4 MB/sec
infer_json_schema/1000 1.00 1521.2±20.56µs 83.0 MB/sec 1.00 1525.3±17.81µs 82.8 MB/sec
large_bench_primitive 1.00 1496.7±2.01µs ? ?/sec 1.01 1507.7±3.57µs ? ?/sec
small_bench_list 1.00 6.8±0.02µs ? ?/sec 1.00 6.8±0.03µs ? ?/sec
small_bench_primitive 1.00 3.9±0.02µs ? ?/sec 1.01 4.0±0.07µs ? ?/sec
small_bench_primitive_with_utf8view 1.00 4.0±0.01µs ? ?/sec 1.00 3.9±0.02µs ? ?/sec
```
</p>
</details>
<details><summary>Resource Usage</summary>
**base (merge-base)**
| Metric | Value |
|--------|-------|
| Wall time | 450.1s |
| Peak memory | 1.4 GiB |
| Avg memory | 923.4 MiB |
| CPU user | 406.7s |
| CPU sys | 37.6s |
| Peak spill | 0 B |
**branch**
| Metric | Value |
|--------|-------|
| Wall time | 450.1s |
| Peak memory | 1.4 GiB |
| Avg memory | 927.3 MiB |
| CPU user | 407.6s |
| CPU sys | 37.8s |
| 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@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Replace BufferBuilder with Vec in MapArrayDecoder [arrow-rs]
Posted by "Jefffrey (via GitHub)" <gi...@apache.org>.
Jefffrey merged PR #10629:
URL: https://github.com/apache/arrow-rs/pull/10629
--
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@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Replace BufferBuilder with Vec in MapArrayDecoder [arrow-rs]
Posted by "Jefffrey (via GitHub)" <gi...@apache.org>.
Jefffrey commented on PR #10629:
URL: https://github.com/apache/arrow-rs/pull/10629#issuecomment-5263922631
run benchmark json_reader
--
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@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] Replace BufferBuilder with Vec in MapArrayDecoder [arrow-rs]
Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #10629:
URL: https://github.com/apache/arrow-rs/pull/10629#issuecomment-5263952276
🤖 Arrow criterion benchmark running (GKE) | [trigger](https://github.com/apache/arrow-rs/pull/10629#issuecomment-5263922631)
**Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c5263922631-1556-tmcff 6.12.85+ #1 SMP Wed Jun 17 20:31:55 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 perf/arrow-json-map-offsets-vec (4006e1462326d781c0a490218b32c74a5aae599c) to fc16607 (merge-base) [diff](https://github.com/apache/arrow-rs/compare/fc16607ccfdb298557ed6630742941761ac18ce3..4006e1462326d781c0a490218b32c74a5aae599c)
<details><summary>Run configuration</summary>
```yaml
run benchmark json_reader
```
</details>
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench json_reader
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@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org