Remove len field from buffer builder

[cetra3]

Which issue does this PR close?

• Split out of Buffer builder hot path opts #9393

Rationale for this change

The buffer builder doesn't need to keep its own len field, as it can be derived from the inner mutablebuffer

What changes are included in this PR?

Removes the len field from Bufferbuilder

Are these changes tested?

Yes, all tests green

Are there any user-facing changes?

Nope!

[alamb]

run benchmark builder json_reader take_kernels

[adriangbot]

🤖 Arrow criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4293483126-1735-6f8p7 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 remove_buffer_builder_len (61b9178) to 89b1497 (merge-base) diff
BENCH_NAME=take_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench take_kernels
BENCH_FILTER=
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Arrow criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4293483126-1733-79cmv 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 remove_buffer_builder_len (61b9178) to 89b1497 (merge-base) diff
BENCH_NAME=builder
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench builder
BENCH_FILTER=
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Arrow criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4293483126-1734-w78m5 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 remove_buffer_builder_len (61b9178) to 89b1497 (merge-base) diff
BENCH_NAME=json_reader
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench json_reader
BENCH_FILTER=
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Arrow 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                                    remove_buffer_builder_len
-----                                          ----                                    -------------------------
bench_bool/bench_bool                          1.00    295.4±0.20µs  1692.9 MB/sec     1.00    294.9±0.24µs  1695.3 MB/sec
bench_decimal128_builder                       1.00    199.7±7.00µs        ? ?/sec     1.01    201.9±7.23µs        ? ?/sec
bench_decimal256_builder                       1.00    201.2±7.55µs        ? ?/sec     1.00    202.2±7.43µs        ? ?/sec
bench_decimal32_builder                        1.00     81.4±2.38µs        ? ?/sec     1.00     81.5±2.14µs        ? ?/sec
bench_decimal64_builder                        1.00     99.5±4.35µs        ? ?/sec     1.00     99.5±3.99µs        ? ?/sec
bench_primitive/bench_primitive                1.00     48.9±0.30µs    79.9 GB/sec     1.01     49.3±0.24µs    79.3 GB/sec
bench_primitive/bench_string                   3.26      6.0±0.07ms  1079.9 MB/sec     1.00   1847.3±8.23µs     3.4 GB/sec
bench_primitive_nulls/bench_primitive_nulls    1.00  1206.7±140.46µs        ? ?/sec    1.14  1378.2±113.88µs        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	80.0s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	72.6s
CPU sys	6.4s
Peak spill	0 B

branch

Metric	Value
Wall time	85.0s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	82.9s
CPU sys	0.2s
Peak spill	0 B

---

File an issue against this benchmark runner

[adriangbot]

🤖 Arrow 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                                   remove_buffer_builder_len
-----                                                                     ----                                   -------------------------
take bool 1024                                                            1.00   1034.0±0.58ns        ? ?/sec    1.00   1032.2±0.68ns        ? ?/sec
take bool 512                                                             1.01    573.6±0.79ns        ? ?/sec    1.00    569.8±0.56ns        ? ?/sec
take bool null indices 1024                                               1.00   854.8±31.32ns        ? ?/sec    1.08   922.4±28.23ns        ? ?/sec
take bool null values 1024                                                1.00      2.0±0.00µs        ? ?/sec    1.00      2.0±0.01µs        ? ?/sec
take bool null values null indices 1024                                   1.01   1644.7±0.93ns        ? ?/sec    1.00   1629.9±5.06ns        ? ?/sec
take check bounds i32 1024                                                1.14    663.3±1.71ns        ? ?/sec    1.00    582.7±0.86ns        ? ?/sec
take check bounds i32 512                                                 1.02    387.7±0.90ns        ? ?/sec    1.00    379.8±0.84ns        ? ?/sec
take fsb value len: 12, indices: 1024                                     1.04      2.6±0.16µs        ? ?/sec    1.00      2.5±0.00µs        ? ?/sec
take fsb value len: 12, null values, indices: 1024                        1.02      3.7±0.15µs        ? ?/sec    1.00      3.6±0.01µs        ? ?/sec
take fsb value optimized len: 16, indices: 1024                           1.00    695.1±2.57ns        ? ?/sec    1.10    767.1±1.24ns        ? ?/sec
take fsb value optimized len: 16, null values, indices: 1024              1.00   1735.5±1.58ns        ? ?/sec    1.00   1734.1±2.22ns        ? ?/sec
take i32 1024                                                             1.03    523.5±0.84ns        ? ?/sec    1.00    510.6±0.60ns        ? ?/sec
take i32 512                                                              1.01    354.9±2.87ns        ? ?/sec    1.00    351.2±0.96ns        ? ?/sec
take i32 null indices 1024                                                1.00    855.9±0.68ns        ? ?/sec    1.00    854.0±1.13ns        ? ?/sec
take i32 null values 1024                                                 1.00   1539.2±1.88ns        ? ?/sec    1.00   1534.3±1.08ns        ? ?/sec
take i32 null values null indices 1024                                    1.00   1729.0±2.42ns        ? ?/sec    1.00   1724.5±2.93ns        ? ?/sec
take list i32 1024                                                        1.00      7.8±0.04µs        ? ?/sec    1.00      7.8±0.01µs        ? ?/sec
take list i32 512                                                         1.00      4.3±0.01µs        ? ?/sec    1.00      4.3±0.02µs        ? ?/sec
take list i32 null indices 1024                                           1.00      9.5±0.06µs        ? ?/sec    1.01      9.7±0.06µs        ? ?/sec
take list i32 null values 1024                                            1.00      5.8±0.01µs        ? ?/sec    1.00      5.8±0.02µs        ? ?/sec
take list i32 null values null indices 1024                               1.00      6.8±0.05µs        ? ?/sec    1.01      6.9±0.09µs        ? ?/sec
take listview i32 1024                                                    1.00   1253.7±3.41ns        ? ?/sec    1.05   1320.2±5.31ns        ? ?/sec
take listview i32 512                                                     1.02    981.4±3.76ns        ? ?/sec    1.00    961.0±2.34ns        ? ?/sec
take listview i32 null indices 1024                                       1.04   1989.2±2.92ns        ? ?/sec    1.00   1921.7±6.91ns        ? ?/sec
take listview i32 null values 1024                                        1.00      2.3±0.00µs        ? ?/sec    1.01      2.4±0.01µs        ? ?/sec
take listview i32 null values null indices 1024                           1.03      2.9±0.01µs        ? ?/sec    1.00      2.8±0.00µs        ? ?/sec
take primitive run logical len: 1024, physical len: 512, indices: 1024    1.08     17.0±0.06µs        ? ?/sec    1.00     15.8±0.01µs        ? ?/sec
take str 1024                                                             1.00      8.9±0.04µs        ? ?/sec    1.00      8.9±0.05µs        ? ?/sec
take str 512                                                              1.01      4.0±0.02µs        ? ?/sec    1.00      4.0±0.02µs        ? ?/sec
take str null indices 1024                                                1.00      6.0±0.01µs        ? ?/sec    1.01      6.0±0.02µs        ? ?/sec
take str null indices 512                                                 1.00      2.8±0.01µs        ? ?/sec    1.01      2.8±0.01µs        ? ?/sec
take str null values 1024                                                 1.00      6.5±0.01µs        ? ?/sec    1.00      6.5±0.02µs        ? ?/sec
take str null values null indices 1024                                    1.00      5.3±0.01µs        ? ?/sec    1.00      5.3±0.01µs        ? ?/sec
take stringview 1024                                                      1.00    737.7±5.28ns        ? ?/sec    1.00    739.4±1.10ns        ? ?/sec
take stringview 512                                                       1.01    471.6±1.55ns        ? ?/sec    1.00    467.8±0.83ns        ? ?/sec
take stringview null indices 1024                                         1.06    983.7±2.10ns        ? ?/sec    1.00    931.7±6.02ns        ? ?/sec
take stringview null indices 512                                          1.00    564.1±1.88ns        ? ?/sec    1.01    568.4±6.35ns        ? ?/sec
take stringview null values 1024                                          1.01   1804.7±2.35ns        ? ?/sec    1.00   1785.9±1.21ns        ? ?/sec
take stringview null values null indices 1024                             1.00   1752.4±3.40ns        ? ?/sec    1.04   1814.4±2.34ns        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	370.1s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	367.1s
CPU sys	0.7s
Peak spill	0 B

branch

Metric	Value
Wall time	370.1s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	368.6s
CPU sys	0.1s
Peak spill	0 B

---

File an issue against this benchmark runner

[adriangbot]

🤖 Arrow 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                                   remove_buffer_builder_len
-----                                        ----                                   -------------------------
decode_binary_hex_json                       1.00     13.7±0.12ms        ? ?/sec    1.01     13.9±0.10ms        ? ?/sec
decode_binary_view_hex_json                  1.01     14.4±0.12ms        ? ?/sec    1.00     14.3±0.15ms        ? ?/sec
decode_fixed_binary_hex_json                 1.00     13.9±0.12ms        ? ?/sec    1.00     13.9±0.06ms        ? ?/sec
decode_list_long_json/131072                 1.00    304.1±3.04ms   257.4 MB/sec    1.01    306.8±3.17ms   255.2 MB/sec
decode_list_long_serialize                   1.15    206.8±4.80ms        ? ?/sec    1.00    179.6±5.76ms        ? ?/sec
decode_list_short_json/131072                1.00     19.8±0.05ms   263.4 MB/sec    1.01     20.0±0.32ms   260.9 MB/sec
decode_list_short_serialize                  1.04     12.0±0.57ms        ? ?/sec    1.00     11.6±0.46ms        ? ?/sec
decode_list_view_long_json/131072            1.00    303.7±2.62ms   257.8 MB/sec    1.00    304.3±2.52ms   257.3 MB/sec
decode_list_view_long_serialize              1.19    207.4±5.51ms        ? ?/sec    1.00    174.8±5.56ms        ? ?/sec
decode_list_view_short_json/131072           1.00     19.8±0.10ms   263.4 MB/sec    1.01     20.1±0.34ms   259.9 MB/sec
decode_list_view_short_serialize             1.04     12.5±0.56ms        ? ?/sec    1.00     12.0±0.41ms        ? ?/sec
decode_map_large_json/131072                 1.00    259.8±2.81ms   292.4 MB/sec    1.01    262.6±2.60ms   289.2 MB/sec
decode_map_large_serialize                   1.00    286.8±7.86ms        ? ?/sec    1.03    295.4±7.17ms        ? ?/sec
decode_map_small_json/131072                 1.00     30.2±0.17ms   272.0 MB/sec    1.02     30.7±0.10ms   267.9 MB/sec
decode_map_small_serialize                   1.00     20.8±1.09ms        ? ?/sec    1.07     22.2±0.86ms        ? ?/sec
decode_ree_long_json/131072                  1.01     18.1±0.13ms    84.0 MB/sec    1.00     17.9±0.28ms    84.7 MB/sec
decode_ree_long_serialize                    1.00     16.6±0.36ms        ? ?/sec    1.08     17.9±0.87ms        ? ?/sec
decode_ree_short_json/131072                 1.00     18.5±0.20ms    93.2 MB/sec    1.01     18.7±0.28ms    92.4 MB/sec
decode_ree_short_serialize                   1.00     17.1±0.29ms        ? ?/sec    1.09     18.6±0.86ms        ? ?/sec
decode_wide_object_json/131072               1.00    475.1±7.94ms   202.5 MB/sec    1.00    473.2±6.48ms   203.3 MB/sec
decode_wide_object_serialize                 1.02    431.7±6.39ms        ? ?/sec    1.00    422.2±7.72ms        ? ?/sec
decode_wide_projection_full_json/131072      1.01   775.5±11.59ms   224.4 MB/sec    1.00   770.4±12.54ms   225.9 MB/sec
decode_wide_projection_narrow_json/131072    1.00    443.7±2.88ms   392.2 MB/sec    1.00    444.6±2.88ms   391.4 MB/sec
infer_json_schema/1000                       1.00   1560.6±9.13µs    80.9 MB/sec    1.01  1578.3±15.24µs    80.0 MB/sec
large_bench_primitive                        1.00   1485.8±2.93µs        ? ?/sec    1.00   1490.1±2.65µs        ? ?/sec
small_bench_list                             1.00      6.9±0.02µs        ? ?/sec    1.02      7.0±0.01µs        ? ?/sec
small_bench_primitive                        1.00      4.0±0.02µs        ? ?/sec    1.01      4.1±0.02µs        ? ?/sec
small_bench_primitive_with_utf8view          1.00      4.0±0.02µs        ? ?/sec    1.03      4.1±0.02µs        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	455.1s
Peak memory	4.7 GiB
Avg memory	4.2 GiB
CPU user	415.5s
CPU sys	36.3s
Peak spill	0 B

branch

Metric	Value
Wall time	455.1s
Peak memory	4.7 GiB
Avg memory	4.2 GiB
CPU user	421.1s
CPU sys	30.3s
Peak spill	0 B

---

File an issue against this benchmark runner

[alamb]

My analysis of the benchmark results is that this change has no appreciable change in performance on those runs. Since it cleans things up, let's merge it in!

[alamb]

Thank you @cetra3