Deduplicate non-inline StringView values in GroupValuesColumn by Dandandan · Pull Request #21332 · apache/datafusion

Dandandan · 2026-04-03T07:53:12Z

Which issue does this PR close?

Closes #.

Rationale for this change

In multi-column GROUP BY, ByteViewGroupValueBuilder stores every non-inline string value (>12 bytes) by copying the full bytes into its buffer, even when the same value has already been stored. For columns with low cardinality (e.g., state, country), this leads to significant memory waste.

What changes are included in this PR?

Adds a per-builder hash-based dedup map (HashMap<u64, u128>) that maps value hashes to their views. In the vectorized append path (the hot path), before copying bytes for a non-inline value, we check if a value with the same hash was already appended. If so, we reuse the existing view — skipping the byte copy entirely.

Key details:

Only affects the vectorized append path (single-row append_val is unchanged)
Only deduplicates values > 12 bytes (inline values have no buffer cost)
The dedup map persists across batches for cross-batch dedup
Cleared on take_n since buffer indices shift
Extracted shared append_value_to_buffer() helper to avoid code duplication

Are these changes tested?

Yes — added test_byte_view_vectorized_append_dedup which verifies:

Duplicate long strings within a batch share buffer storage
Cross-batch dedup works (same string in batch 2 doesn't grow the buffer)
Output correctness is preserved

Are there any user-facing changes?

No — this is an internal optimization. Query results are unchanged.

🤖 Generated with Claude Code

For values > 12 bytes in the vectorized append path, use a hash-based dedup map to avoid storing duplicate string bytes in the buffer. This reduces memory usage when the same string values appear across multiple batches in GROUP BY columns. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Dandandan · 2026-04-03T07:54:31Z

run benchmarks

adriangbot · 2026-04-03T07:56:39Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4182395292-704-jmbxc 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 dedup-stringview-group-values (4413ff4) to 1e93a67 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-03T07:56:39Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4182395292-706-q2p4h 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 dedup-stringview-group-values (4413ff4) to 1e93a67 (merge-base) diff using: tpch
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-03T07:57:07Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4182395292-705-p62jd 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 dedup-stringview-group-values (4413ff4) to 1e93a67 (merge-base) diff using: tpcds
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-04-03T08:08:12Z

🤖 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

Comparing HEAD and dedup-stringview-group-values
--------------------
Benchmark tpch_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query     ┃                           HEAD ┃  dedup-stringview-group-values ┃    Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 1  │ 45.22 / 45.73 ±0.74 / 47.17 ms │ 45.11 / 45.88 ±0.77 / 47.34 ms │ no change │
│ QQuery 2  │ 20.98 / 21.24 ±0.16 / 21.45 ms │ 21.42 / 21.96 ±0.47 / 22.82 ms │ no change │
│ QQuery 3  │ 31.54 / 31.76 ±0.28 / 32.31 ms │ 32.30 / 32.53 ±0.19 / 32.82 ms │ no change │
│ QQuery 4  │ 21.02 / 21.44 ±0.26 / 21.66 ms │ 20.12 / 21.50 ±1.34 / 23.44 ms │ no change │
│ QQuery 5  │ 48.73 / 51.15 ±3.27 / 57.34 ms │ 48.69 / 50.74 ±1.67 / 52.76 ms │ no change │
│ QQuery 6  │ 16.94 / 17.28 ±0.26 / 17.72 ms │ 17.38 / 17.54 ±0.18 / 17.88 ms │ no change │
│ QQuery 7  │ 54.69 / 56.53 ±1.20 / 58.08 ms │ 56.57 / 57.82 ±1.06 / 59.27 ms │ no change │
│ QQuery 8  │ 47.64 / 48.28 ±0.90 / 50.04 ms │ 48.22 / 48.76 ±0.35 / 49.27 ms │ no change │
│ QQuery 9  │ 53.73 / 54.60 ±0.45 / 54.96 ms │ 55.17 / 56.15 ±0.79 / 57.40 ms │ no change │
│ QQuery 10 │ 71.27 / 72.70 ±1.01 / 74.16 ms │ 72.45 / 74.82 ±1.60 / 76.56 ms │ no change │
│ QQuery 11 │ 14.03 / 14.34 ±0.26 / 14.80 ms │ 14.31 / 14.51 ±0.16 / 14.81 ms │ no change │
│ QQuery 12 │ 27.56 / 28.15 ±0.48 / 29.02 ms │ 27.82 / 28.21 ±0.43 / 29.01 ms │ no change │
│ QQuery 13 │ 38.93 / 41.42 ±2.08 / 44.66 ms │ 38.99 / 40.45 ±1.29 / 42.84 ms │ no change │
│ QQuery 14 │ 28.40 / 28.57 ±0.18 / 28.92 ms │ 28.48 / 29.15 ±0.83 / 30.79 ms │ no change │
│ QQuery 15 │ 33.20 / 33.59 ±0.29 / 33.92 ms │ 33.44 / 33.81 ±0.27 / 34.29 ms │ no change │
│ QQuery 16 │ 16.15 / 16.47 ±0.27 / 16.83 ms │ 15.84 / 16.55 ±0.46 / 17.17 ms │ no change │
│ QQuery 17 │ 73.50 / 75.10 ±1.53 / 77.56 ms │ 73.17 / 74.41 ±1.10 / 75.82 ms │ no change │
│ QQuery 18 │ 77.78 / 79.35 ±1.44 / 81.42 ms │ 76.92 / 78.95 ±1.32 / 80.38 ms │ no change │
│ QQuery 19 │ 37.31 / 37.73 ±0.27 / 38.11 ms │ 38.39 / 38.55 ±0.18 / 38.87 ms │ no change │
│ QQuery 20 │ 39.93 / 40.67 ±0.57 / 41.65 ms │ 40.05 / 41.23 ±0.92 / 42.40 ms │ no change │
│ QQuery 21 │ 65.10 / 65.61 ±0.41 / 66.29 ms │ 65.65 / 67.07 ±1.23 / 68.77 ms │ no change │
│ QQuery 22 │ 17.85 / 18.12 ±0.39 / 18.90 ms │ 17.81 / 18.36 ±0.34 / 18.84 ms │ no change │
└───────────┴────────────────────────────────┴────────────────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Benchmark Summary                            ┃          ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Total Time (HEAD)                            │ 899.83ms │
│ Total Time (dedup-stringview-group-values)   │ 908.95ms │
│ Average Time (HEAD)                          │  40.90ms │
│ Average Time (dedup-stringview-group-values) │  41.32ms │
│ Queries Faster                               │        0 │
│ Queries Slower                               │        0 │
│ Queries with No Change                       │       22 │
│ Queries with Failure                         │        0 │
└──────────────────────────────────────────────┴──────────┘

Resource Usage

tpch — base (merge-base)

Metric	Value
Wall time	4.8s
Peak memory	4.1 GiB
Avg memory	3.6 GiB
CPU user	33.6s
CPU sys	2.7s
Disk read	0 B
Disk write	136.0 KiB

tpch — branch

Metric	Value
Wall time	4.8s
Peak memory	4.1 GiB
Avg memory	3.6 GiB
CPU user	34.1s
CPU sys	2.7s
Disk read	0 B
Disk write	72.0 KiB

File an issue against this benchmark runner

adriangbot · 2026-04-03T08:13:43Z

🤖 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

Comparing HEAD and dedup-stringview-group-values
--------------------
Benchmark tpcds_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                     HEAD ┃            dedup-stringview-group-values ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │           43.24 / 44.26 ±0.79 / 45.34 ms │           43.47 / 44.01 ±0.72 / 45.38 ms │     no change │
│ QQuery 2  │        146.75 / 148.71 ±1.25 / 150.31 ms │        150.12 / 151.43 ±1.02 / 152.71 ms │     no change │
│ QQuery 3  │        115.09 / 115.77 ±0.38 / 116.16 ms │        115.09 / 116.07 ±0.76 / 116.92 ms │     no change │
│ QQuery 4  │    1319.71 / 1350.54 ±19.16 / 1375.31 ms │    1322.19 / 1354.44 ±21.63 / 1375.10 ms │     no change │
│ QQuery 5  │        174.20 / 175.97 ±1.72 / 179.25 ms │        173.36 / 174.64 ±1.01 / 176.00 ms │     no change │
│ QQuery 6  │     992.62 / 1029.83 ±42.70 / 1101.78 ms │    1020.62 / 1040.61 ±14.54 / 1058.38 ms │     no change │
│ QQuery 7  │        351.55 / 354.92 ±2.69 / 358.41 ms │        353.22 / 354.13 ±0.66 / 354.93 ms │     no change │
│ QQuery 8  │        117.06 / 117.61 ±0.48 / 118.48 ms │        116.38 / 117.54 ±1.21 / 119.51 ms │     no change │
│ QQuery 9  │        101.24 / 102.78 ±2.15 / 107.04 ms │        101.45 / 105.79 ±2.28 / 107.98 ms │     no change │
│ QQuery 10 │        105.30 / 106.82 ±1.03 / 107.77 ms │        106.21 / 107.53 ±0.77 / 108.34 ms │     no change │
│ QQuery 11 │        925.88 / 938.05 ±7.94 / 946.30 ms │       915.12 / 937.71 ±14.51 / 958.51 ms │     no change │
│ QQuery 12 │           44.33 / 45.56 ±0.87 / 47.04 ms │           44.85 / 46.26 ±1.14 / 48.33 ms │     no change │
│ QQuery 13 │        397.57 / 402.36 ±3.29 / 406.40 ms │        398.13 / 400.34 ±1.75 / 402.46 ms │     no change │
│ QQuery 14 │     1021.06 / 1025.40 ±3.83 / 1031.86 ms │     1016.81 / 1024.76 ±8.67 / 1039.07 ms │     no change │
│ QQuery 15 │           15.62 / 16.78 ±1.52 / 19.61 ms │           15.08 / 15.87 ±0.75 / 16.88 ms │ +1.06x faster │
│ QQuery 16 │           41.81 / 42.48 ±0.51 / 43.31 ms │           40.92 / 41.92 ±0.79 / 43.00 ms │     no change │
│ QQuery 17 │        238.56 / 241.46 ±1.80 / 243.06 ms │        234.98 / 239.92 ±2.64 / 242.72 ms │     no change │
│ QQuery 18 │        128.36 / 130.81 ±1.72 / 133.43 ms │        127.56 / 128.59 ±0.65 / 129.50 ms │     no change │
│ QQuery 19 │        155.76 / 156.48 ±0.70 / 157.73 ms │        154.54 / 156.72 ±1.88 / 158.85 ms │     no change │
│ QQuery 20 │           14.10 / 14.42 ±0.30 / 14.79 ms │           13.98 / 14.27 ±0.24 / 14.62 ms │     no change │
│ QQuery 21 │           19.71 / 20.08 ±0.28 / 20.49 ms │           19.44 / 19.75 ±0.29 / 20.20 ms │     no change │
│ QQuery 22 │        494.40 / 499.93 ±4.84 / 508.99 ms │        489.42 / 492.06 ±3.05 / 497.93 ms │     no change │
│ QQuery 23 │        903.30 / 914.43 ±8.00 / 924.88 ms │        896.23 / 904.19 ±6.20 / 914.48 ms │     no change │
│ QQuery 24 │        418.29 / 422.99 ±5.72 / 433.45 ms │        414.54 / 416.80 ±2.74 / 422.07 ms │     no change │
│ QQuery 25 │        358.77 / 359.54 ±1.26 / 362.05 ms │        354.21 / 356.64 ±1.40 / 358.21 ms │     no change │
│ QQuery 26 │           83.07 / 84.77 ±1.75 / 88.14 ms │           81.50 / 82.75 ±0.97 / 84.17 ms │     no change │
│ QQuery 27 │        347.46 / 351.90 ±4.71 / 359.22 ms │        347.62 / 350.82 ±3.12 / 356.34 ms │     no change │
│ QQuery 28 │        149.15 / 150.93 ±1.50 / 152.55 ms │        148.08 / 150.75 ±2.21 / 153.39 ms │     no change │
│ QQuery 29 │        297.40 / 302.45 ±3.69 / 308.24 ms │        293.12 / 299.25 ±3.38 / 303.29 ms │     no change │
│ QQuery 30 │           43.46 / 46.66 ±3.01 / 52.12 ms │           43.65 / 45.46 ±1.73 / 48.04 ms │     no change │
│ QQuery 31 │        171.49 / 174.29 ±1.66 / 176.39 ms │        169.74 / 173.87 ±2.80 / 177.57 ms │     no change │
│ QQuery 32 │         56.86 / 66.81 ±17.36 / 101.47 ms │          56.52 / 65.47 ±16.29 / 98.00 ms │     no change │
│ QQuery 33 │        140.71 / 142.13 ±1.21 / 143.42 ms │        140.21 / 142.01 ±1.01 / 143.02 ms │     no change │
│ QQuery 34 │        106.78 / 108.37 ±1.26 / 110.57 ms │        107.81 / 108.08 ±0.25 / 108.51 ms │     no change │
│ QQuery 35 │        106.35 / 108.99 ±1.58 / 110.87 ms │        106.27 / 107.18 ±0.66 / 108.29 ms │     no change │
│ QQuery 36 │        214.18 / 221.48 ±4.07 / 226.17 ms │        215.81 / 220.51 ±3.17 / 224.63 ms │     no change │
│ QQuery 37 │        176.81 / 179.49 ±3.13 / 184.25 ms │        173.53 / 177.13 ±2.51 / 179.65 ms │     no change │
│ QQuery 38 │           85.39 / 89.95 ±3.11 / 95.05 ms │           83.83 / 87.80 ±3.79 / 94.17 ms │     no change │
│ QQuery 39 │        126.69 / 129.14 ±2.31 / 133.32 ms │        126.11 / 129.21 ±2.66 / 132.40 ms │     no change │
│ QQuery 40 │        118.17 / 121.00 ±3.05 / 126.66 ms │        109.72 / 116.22 ±5.41 / 126.07 ms │     no change │
│ QQuery 41 │           14.48 / 15.51 ±1.05 / 17.46 ms │           14.25 / 16.96 ±1.69 / 19.40 ms │  1.09x slower │
│ QQuery 42 │        109.43 / 110.66 ±0.63 / 111.14 ms │        107.61 / 108.86 ±1.07 / 110.47 ms │     no change │
│ QQuery 43 │           83.33 / 84.45 ±0.74 / 85.49 ms │           84.20 / 85.25 ±0.85 / 86.70 ms │     no change │
│ QQuery 44 │           11.61 / 12.27 ±1.01 / 14.28 ms │           11.47 / 11.83 ±0.38 / 12.55 ms │     no change │
│ QQuery 45 │           52.39 / 53.43 ±1.46 / 56.31 ms │           51.65 / 53.01 ±0.93 / 53.85 ms │     no change │
│ QQuery 46 │        230.88 / 234.92 ±3.33 / 239.10 ms │        233.80 / 235.54 ±1.74 / 237.70 ms │     no change │
│ QQuery 47 │        711.49 / 717.97 ±5.29 / 727.31 ms │        693.14 / 699.52 ±4.33 / 706.53 ms │     no change │
│ QQuery 48 │        284.39 / 289.36 ±3.14 / 293.69 ms │        288.90 / 292.51 ±3.07 / 296.32 ms │     no change │
│ QQuery 49 │        257.18 / 258.07 ±0.86 / 259.26 ms │        256.04 / 258.43 ±2.12 / 261.22 ms │     no change │
│ QQuery 50 │        236.78 / 238.62 ±1.62 / 241.61 ms │        224.00 / 230.77 ±5.01 / 238.06 ms │     no change │
│ QQuery 51 │        183.70 / 185.52 ±1.70 / 188.57 ms │        183.11 / 185.43 ±2.14 / 188.91 ms │     no change │
│ QQuery 52 │        108.10 / 109.53 ±1.02 / 111.17 ms │        107.06 / 109.01 ±0.99 / 109.67 ms │     no change │
│ QQuery 53 │        102.58 / 103.52 ±0.89 / 104.78 ms │        102.58 / 104.01 ±1.69 / 107.19 ms │     no change │
│ QQuery 54 │        148.28 / 149.60 ±1.01 / 151.32 ms │        147.53 / 147.89 ±0.30 / 148.41 ms │     no change │
│ QQuery 55 │        107.49 / 108.55 ±1.16 / 110.70 ms │        107.21 / 108.74 ±1.20 / 110.33 ms │     no change │
│ QQuery 56 │        140.74 / 142.59 ±1.49 / 145.05 ms │        140.42 / 141.38 ±0.67 / 142.48 ms │     no change │
│ QQuery 57 │        173.32 / 177.86 ±2.67 / 181.10 ms │        175.57 / 177.16 ±1.46 / 179.81 ms │     no change │
│ QQuery 58 │        291.53 / 298.46 ±4.46 / 305.00 ms │        291.74 / 297.73 ±3.60 / 303.05 ms │     no change │
│ QQuery 59 │        199.58 / 201.54 ±2.23 / 205.73 ms │        200.89 / 203.08 ±1.57 / 205.16 ms │     no change │
│ QQuery 60 │        144.82 / 146.46 ±1.54 / 148.87 ms │        142.79 / 144.36 ±1.54 / 147.03 ms │     no change │
│ QQuery 61 │        171.44 / 174.13 ±1.84 / 177.21 ms │        172.36 / 173.08 ±0.73 / 173.99 ms │     no change │
│ QQuery 62 │      890.23 / 954.50 ±52.35 / 1043.93 ms │       937.34 / 964.06 ±14.07 / 977.54 ms │     no change │
│ QQuery 63 │        102.46 / 105.05 ±2.69 / 109.03 ms │        104.71 / 106.31 ±1.52 / 108.96 ms │     no change │
│ QQuery 64 │        696.96 / 705.64 ±5.10 / 712.19 ms │        696.40 / 702.82 ±4.57 / 710.03 ms │     no change │
│ QQuery 65 │        249.97 / 256.65 ±4.24 / 263.06 ms │        251.18 / 255.63 ±2.49 / 258.17 ms │     no change │
│ QQuery 66 │       245.10 / 257.22 ±10.04 / 274.50 ms │       238.77 / 251.36 ±11.52 / 266.80 ms │     no change │
│ QQuery 67 │        311.25 / 317.44 ±6.82 / 327.28 ms │        311.65 / 319.93 ±7.37 / 333.63 ms │     no change │
│ QQuery 68 │        276.59 / 284.51 ±4.99 / 290.43 ms │        280.61 / 283.11 ±1.85 / 286.16 ms │     no change │
│ QQuery 69 │        102.34 / 103.43 ±0.80 / 104.48 ms │        102.18 / 105.05 ±4.09 / 112.81 ms │     no change │
│ QQuery 70 │        345.12 / 347.98 ±2.02 / 350.51 ms │       340.61 / 352.10 ±11.02 / 370.88 ms │     no change │
│ QQuery 71 │        135.56 / 137.62 ±1.18 / 139.14 ms │        135.05 / 137.06 ±1.31 / 138.85 ms │     no change │
│ QQuery 72 │        708.86 / 715.02 ±3.86 / 720.73 ms │       695.45 / 712.95 ±10.29 / 722.88 ms │     no change │
│ QQuery 73 │        101.73 / 105.48 ±2.61 / 108.87 ms │        102.58 / 103.99 ±0.86 / 104.80 ms │     no change │
│ QQuery 74 │        570.98 / 579.28 ±4.71 / 585.48 ms │        569.52 / 583.25 ±6.92 / 587.82 ms │     no change │
│ QQuery 75 │        277.16 / 283.33 ±3.10 / 285.40 ms │        278.76 / 279.78 ±0.86 / 281.35 ms │     no change │
│ QQuery 76 │        133.06 / 135.75 ±2.27 / 139.48 ms │        131.49 / 134.18 ±2.40 / 137.41 ms │     no change │
│ QQuery 77 │        190.62 / 191.70 ±1.02 / 193.15 ms │        188.43 / 190.45 ±1.04 / 191.39 ms │     no change │
│ QQuery 78 │        347.87 / 355.22 ±7.04 / 366.74 ms │        348.04 / 355.91 ±4.21 / 360.23 ms │     no change │
│ QQuery 79 │        233.78 / 237.39 ±2.92 / 242.67 ms │        235.32 / 236.47 ±0.71 / 237.46 ms │     no change │
│ QQuery 80 │        328.66 / 332.98 ±3.14 / 338.04 ms │        331.26 / 334.08 ±2.20 / 337.48 ms │     no change │
│ QQuery 81 │           26.81 / 28.75 ±1.34 / 30.72 ms │           26.91 / 27.65 ±0.82 / 29.24 ms │     no change │
│ QQuery 82 │        197.61 / 201.67 ±2.68 / 205.79 ms │        197.84 / 200.47 ±2.33 / 203.68 ms │     no change │
│ QQuery 83 │           40.56 / 41.54 ±0.61 / 42.44 ms │           40.18 / 41.36 ±0.87 / 42.29 ms │     no change │
│ QQuery 84 │           49.16 / 50.15 ±1.04 / 51.58 ms │           47.70 / 49.27 ±1.10 / 50.87 ms │     no change │
│ QQuery 85 │        147.64 / 150.49 ±2.01 / 153.81 ms │        146.64 / 148.52 ±1.76 / 151.36 ms │     no change │
│ QQuery 86 │           39.65 / 40.69 ±0.70 / 41.79 ms │           38.82 / 40.37 ±1.04 / 42.02 ms │     no change │
│ QQuery 87 │           87.05 / 89.99 ±3.06 / 95.40 ms │           86.08 / 90.66 ±4.44 / 99.12 ms │     no change │
│ QQuery 88 │        100.18 / 100.79 ±0.60 / 101.91 ms │        100.29 / 101.03 ±0.67 / 102.06 ms │     no change │
│ QQuery 89 │        117.80 / 119.67 ±1.10 / 120.81 ms │        118.60 / 119.83 ±0.66 / 120.38 ms │     no change │
│ QQuery 90 │           23.97 / 24.42 ±0.66 / 25.74 ms │           23.30 / 23.99 ±0.55 / 24.96 ms │     no change │
│ QQuery 91 │           62.53 / 64.41 ±1.23 / 65.97 ms │           63.06 / 65.07 ±1.41 / 66.94 ms │     no change │
│ QQuery 92 │           56.91 / 57.82 ±0.76 / 59.13 ms │           57.56 / 58.28 ±0.75 / 59.61 ms │     no change │
│ QQuery 93 │        192.18 / 195.13 ±1.75 / 196.94 ms │        193.22 / 195.40 ±1.57 / 197.99 ms │     no change │
│ QQuery 94 │           61.62 / 62.00 ±0.30 / 62.35 ms │           60.87 / 61.86 ±0.80 / 63.28 ms │     no change │
│ QQuery 95 │        134.41 / 136.32 ±1.51 / 138.35 ms │        136.01 / 137.51 ±0.96 / 139.01 ms │     no change │
│ QQuery 96 │           73.75 / 74.91 ±0.84 / 75.91 ms │           72.12 / 73.73 ±0.98 / 75.05 ms │     no change │
│ QQuery 97 │        129.47 / 131.24 ±0.99 / 132.13 ms │        129.00 / 131.56 ±1.67 / 134.01 ms │     no change │
│ QQuery 98 │        154.70 / 156.30 ±0.90 / 157.35 ms │        154.22 / 156.40 ±1.21 / 157.93 ms │     no change │
│ QQuery 99 │ 10682.61 / 10741.97 ±30.34 / 10768.25 ms │ 10738.22 / 10780.96 ±27.78 / 10823.77 ms │     no change │
└───────────┴──────────────────────────────────────────┴──────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                            ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                            │ 33743.80ms │
│ Total Time (dedup-stringview-group-values)   │ 33715.45ms │
│ Average Time (HEAD)                          │   340.85ms │
│ Average Time (dedup-stringview-group-values) │   340.56ms │
│ Queries Faster                               │          1 │
│ Queries Slower                               │          1 │
│ Queries with No Change                       │         97 │
│ Queries with Failure                         │          0 │
└──────────────────────────────────────────────┴────────────┘

Resource Usage

tpcds — base (merge-base)

Metric	Value
Wall time	169.1s
Peak memory	5.6 GiB
Avg memory	4.6 GiB
CPU user	272.3s
CPU sys	17.9s
Disk read	0 B
Disk write	638.1 MiB

tpcds — branch

Metric	Value
Wall time	168.9s
Peak memory	5.3 GiB
Avg memory	4.5 GiB
CPU user	271.1s
CPU sys	18.0s
Disk read	0 B
Disk write	148.0 KiB

File an issue against this benchmark runner

adriangbot · 2026-04-03T08:14:52Z

🤖 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

Comparing HEAD and dedup-stringview-group-values
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃         dedup-stringview-group-values ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.28 / 4.49 ±6.33 / 17.15 ms │          1.31 / 4.56 ±6.39 / 17.35 ms │     no change │
│ QQuery 1  │        14.37 / 14.59 ±0.16 / 14.77 ms │        14.25 / 14.61 ±0.21 / 14.85 ms │     no change │
│ QQuery 2  │        44.27 / 44.67 ±0.36 / 45.34 ms │        43.65 / 43.84 ±0.25 / 44.32 ms │     no change │
│ QQuery 3  │        43.21 / 46.17 ±1.71 / 48.23 ms │        45.13 / 47.97 ±1.71 / 50.23 ms │     no change │
│ QQuery 4  │    296.59 / 311.96 ±16.20 / 341.93 ms │    295.96 / 317.02 ±15.38 / 336.83 ms │     no change │
│ QQuery 5  │    348.40 / 361.71 ±10.76 / 378.55 ms │    352.20 / 372.51 ±14.47 / 396.70 ms │     no change │
│ QQuery 6  │           5.83 / 6.71 ±0.73 / 7.91 ms │           5.25 / 6.42 ±1.13 / 8.51 ms │     no change │
│ QQuery 7  │        16.72 / 17.06 ±0.28 / 17.55 ms │        16.87 / 18.33 ±1.37 / 20.20 ms │  1.07x slower │
│ QQuery 8  │    431.68 / 457.84 ±13.60 / 469.61 ms │    439.65 / 471.39 ±25.78 / 509.12 ms │     no change │
│ QQuery 9  │    645.58 / 670.23 ±23.92 / 701.75 ms │    639.90 / 671.31 ±22.25 / 694.20 ms │     no change │
│ QQuery 10 │        94.90 / 96.80 ±1.31 / 98.74 ms │        92.70 / 96.68 ±2.78 / 99.76 ms │     no change │
│ QQuery 11 │     109.52 / 110.31 ±0.63 / 111.36 ms │     102.98 / 107.26 ±2.58 / 109.53 ms │     no change │
│ QQuery 12 │    347.99 / 373.43 ±17.34 / 393.64 ms │    344.58 / 366.22 ±14.88 / 383.68 ms │     no change │
│ QQuery 13 │    512.07 / 521.57 ±10.26 / 538.70 ms │    576.02 / 603.47 ±21.52 / 625.19 ms │  1.16x slower │
│ QQuery 14 │     382.96 / 389.49 ±6.49 / 401.15 ms │    460.85 / 476.73 ±17.88 / 506.90 ms │  1.22x slower │
│ QQuery 15 │    393.12 / 408.91 ±18.49 / 443.93 ms │    369.22 / 404.73 ±30.67 / 460.16 ms │     no change │
│ QQuery 16 │    732.52 / 773.45 ±27.65 / 814.38 ms │    938.98 / 957.45 ±16.74 / 984.80 ms │  1.24x slower │
│ QQuery 17 │    758.78 / 805.38 ±59.59 / 919.63 ms │     935.36 / 946.28 ±7.46 / 957.31 ms │  1.17x slower │
│ QQuery 18 │ 1495.73 / 1542.28 ±34.27 / 1596.04 ms │ 1706.02 / 1788.28 ±59.90 / 1857.23 ms │  1.16x slower │
│ QQuery 19 │        34.87 / 36.47 ±1.66 / 39.11 ms │        34.73 / 38.39 ±4.88 / 47.23 ms │  1.05x slower │
│ QQuery 20 │    727.80 / 746.01 ±21.36 / 779.66 ms │    719.54 / 735.91 ±14.24 / 761.40 ms │     no change │
│ QQuery 21 │     766.10 / 770.03 ±4.16 / 776.45 ms │     763.11 / 774.55 ±6.45 / 780.73 ms │     no change │
│ QQuery 22 │  1148.26 / 1155.09 ±5.80 / 1163.55 ms │ 1135.57 / 1156.11 ±15.62 / 1177.08 ms │     no change │
│ QQuery 23 │ 3128.05 / 3171.86 ±27.91 / 3209.90 ms │ 3137.10 / 3183.02 ±36.16 / 3242.30 ms │     no change │
│ QQuery 24 │      98.21 / 104.19 ±4.59 / 109.96 ms │     103.34 / 106.34 ±3.09 / 112.24 ms │     no change │
│ QQuery 25 │     139.85 / 144.44 ±2.93 / 147.86 ms │     138.42 / 143.29 ±3.13 / 147.70 ms │     no change │
│ QQuery 26 │     102.98 / 105.71 ±2.43 / 108.93 ms │     100.52 / 103.58 ±2.45 / 107.28 ms │     no change │
│ QQuery 27 │    846.64 / 859.61 ±12.96 / 879.86 ms │     858.60 / 863.14 ±2.95 / 867.81 ms │     no change │
│ QQuery 28 │ 7781.83 / 7824.20 ±30.06 / 7868.99 ms │ 7759.72 / 7845.06 ±49.07 / 7891.98 ms │     no change │
│ QQuery 29 │      50.64 / 75.28 ±33.57 / 141.00 ms │     83.76 / 100.10 ±18.78 / 129.24 ms │  1.33x slower │
│ QQuery 30 │     377.60 / 386.21 ±7.29 / 398.42 ms │    402.15 / 421.54 ±25.76 / 471.73 ms │  1.09x slower │
│ QQuery 31 │     401.44 / 410.23 ±6.50 / 420.77 ms │    389.00 / 427.40 ±27.95 / 459.21 ms │     no change │
│ QQuery 32 │ 1157.49 / 1279.83 ±74.84 / 1368.56 ms │ 1295.61 / 1325.24 ±21.24 / 1350.97 ms │     no change │
│ QQuery 33 │ 1516.03 / 1547.58 ±25.70 / 1587.62 ms │ 1593.27 / 1648.49 ±46.40 / 1729.53 ms │  1.07x slower │
│ QQuery 34 │ 1460.18 / 1576.98 ±80.25 / 1669.23 ms │ 1558.48 / 1607.82 ±33.97 / 1662.00 ms │     no change │
│ QQuery 35 │     454.08 / 457.34 ±2.30 / 460.42 ms │    384.63 / 413.70 ±27.07 / 457.79 ms │ +1.11x faster │
│ QQuery 36 │     128.79 / 130.79 ±1.49 / 132.48 ms │     121.09 / 125.71 ±2.74 / 129.34 ms │     no change │
│ QQuery 37 │        51.24 / 53.61 ±1.77 / 56.17 ms │        50.08 / 51.27 ±1.05 / 52.67 ms │     no change │
│ QQuery 38 │        77.36 / 79.04 ±0.98 / 79.99 ms │        74.18 / 75.46 ±1.36 / 77.84 ms │     no change │
│ QQuery 39 │    208.24 / 218.49 ±10.83 / 234.54 ms │    254.45 / 270.76 ±14.38 / 292.15 ms │  1.24x slower │
│ QQuery 40 │        27.75 / 29.87 ±1.92 / 33.43 ms │        23.67 / 25.90 ±1.36 / 27.58 ms │ +1.15x faster │
│ QQuery 41 │        23.21 / 23.68 ±0.35 / 24.23 ms │        20.46 / 21.86 ±1.30 / 24.16 ms │ +1.08x faster │
│ QQuery 42 │        21.60 / 21.72 ±0.09 / 21.86 ms │        18.89 / 19.73 ±0.54 / 20.42 ms │ +1.10x faster │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                            ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                            │ 28165.32ms │
│ Total Time (dedup-stringview-group-values)   │ 29199.44ms │
│ Average Time (HEAD)                          │   655.01ms │
│ Average Time (dedup-stringview-group-values) │   679.06ms │
│ Queries Faster                               │          4 │
│ Queries Slower                               │         11 │
│ Queries with No Change                       │         28 │
│ Queries with Failure                         │          0 │
└──────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric	Value
Wall time	142.1s
Peak memory	43.3 GiB
Avg memory	29.8 GiB
CPU user	1326.5s
CPU sys	102.7s
Disk read	0 B
Disk write	3.1 GiB

clickbench_partitioned — branch

Metric	Value
Wall time	147.2s
Peak memory	39.4 GiB
Avg memory	28.6 GiB
CPU user	1368.6s
CPU sys	117.5s
Disk read	0 B
Disk write	120.0 KiB

File an issue against this benchmark runner

Dandandan · 2026-04-03T08:21:14Z

quite a bit slower, but memory usage drops

github-actions Bot added the physical-plan Changes to the physical-plan crate label Apr 3, 2026

Dandandan closed this Apr 3, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Deduplicate non-inline StringView values in GroupValuesColumn#21332

Deduplicate non-inline StringView values in GroupValuesColumn#21332
Dandandan wants to merge 1 commit intoapache:mainfrom
Dandandan:dedup-stringview-group-values

Dandandan commented Apr 3, 2026

Uh oh!

Dandandan commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

Dandandan commented Apr 3, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

Dandandan commented Apr 3, 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!

Dandandan commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

adriangbot commented Apr 3, 2026

Uh oh!

Dandandan commented Apr 3, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants