Optimize TopK before computed projections by Dandandan · Pull Request #22606 · apache/datafusion

Dandandan · 2026-05-28T20:50:54Z

Which issue does this PR close?

Does not close an issue.

Rationale for this change

TopK can currently run after a ProjectionExec even when the sort key is just a projected input column. If the projection computes values not needed for ordering, such as SELECT 1 ... ORDER BY c LIMIT 10, those expressions are materialized for all input rows instead of only the rows retained by TopK.

What changes are included in this PR?

Adds a physical projection pushdown rewrite that moves TopK below computed projections when all sort keys map through the projection to plain input columns.

Are these changes tested?

Are there any user-facing changes?

No API changes. Physical plans for some TopK queries with computed projections can change; query results are unchanged.

Dandandan · 2026-05-28T21:00:19Z

run benchmarks

adriangbot · 2026-05-28T21:03:10Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4568213890-356-dvljt 6.12.68+ #1 SMP Wed Apr 1 02:23:28 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 codex/topk-before-projection (46573ef) to 0da8961 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-05-28T21:03:17Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4568213890-357-prl56 6.12.68+ #1 SMP Wed Apr 1 02:23:28 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 codex/topk-before-projection (46573ef) to 0da8961 (merge-base) diff using: tpcds
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-05-28T21:03:25Z

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4568213890-358-hvl95 6.12.68+ #1 SMP Wed Apr 1 02:23:28 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 codex/topk-before-projection (46573ef) to 0da8961 (merge-base) diff using: tpch
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-05-28T21:15:53Z

🤖 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 codex_topk-before-projection
--------------------
Benchmark tpch_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                           HEAD ┃   codex_topk-before-projection ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │ 38.47 / 39.90 ±1.03 / 41.37 ms │ 38.32 / 39.13 ±0.99 / 41.02 ms │     no change │
│ QQuery 2  │ 20.11 / 20.33 ±0.26 / 20.73 ms │ 19.93 / 20.32 ±0.27 / 20.69 ms │     no change │
│ QQuery 3  │ 34.42 / 36.56 ±2.05 / 40.29 ms │ 33.23 / 34.58 ±1.47 / 36.51 ms │ +1.06x faster │
│ QQuery 4  │ 17.47 / 18.11 ±0.70 / 19.38 ms │ 17.73 / 18.45 ±0.65 / 19.25 ms │     no change │
│ QQuery 5  │ 40.61 / 42.19 ±0.90 / 43.07 ms │ 40.00 / 42.58 ±1.48 / 44.03 ms │     no change │
│ QQuery 6  │ 16.41 / 16.57 ±0.13 / 16.79 ms │ 16.38 / 16.54 ±0.10 / 16.68 ms │     no change │
│ QQuery 7  │ 47.60 / 47.92 ±0.32 / 48.49 ms │ 47.34 / 48.06 ±0.90 / 49.74 ms │     no change │
│ QQuery 8  │ 45.26 / 46.06 ±1.30 / 48.66 ms │ 44.83 / 45.54 ±0.72 / 46.89 ms │     no change │
│ QQuery 9  │ 50.12 / 50.65 ±0.39 / 51.10 ms │ 50.52 / 51.21 ±1.02 / 53.21 ms │     no change │
│ QQuery 10 │ 64.07 / 64.25 ±0.17 / 64.46 ms │ 64.00 / 64.31 ±0.32 / 64.74 ms │     no change │
│ QQuery 11 │ 13.81 / 14.06 ±0.14 / 14.19 ms │ 13.72 / 13.84 ±0.12 / 14.02 ms │     no change │
│ QQuery 12 │ 24.35 / 25.02 ±0.58 / 25.99 ms │ 24.68 / 25.48 ±0.81 / 26.93 ms │     no change │
│ QQuery 13 │ 34.41 / 36.21 ±2.27 / 40.62 ms │ 33.69 / 34.53 ±0.77 / 35.91 ms │     no change │
│ QQuery 14 │ 25.54 / 26.18 ±0.82 / 27.79 ms │ 25.56 / 25.80 ±0.20 / 26.04 ms │     no change │
│ QQuery 15 │ 32.01 / 32.82 ±0.66 / 33.62 ms │ 31.95 / 32.64 ±0.58 / 33.51 ms │     no change │
│ QQuery 16 │ 14.86 / 14.99 ±0.09 / 15.13 ms │ 14.90 / 15.04 ±0.13 / 15.26 ms │     no change │
│ QQuery 17 │ 75.81 / 77.53 ±1.60 / 80.50 ms │ 74.73 / 75.61 ±0.75 / 76.96 ms │     no change │
│ QQuery 18 │ 63.11 / 64.40 ±0.72 / 65.17 ms │ 61.71 / 62.58 ±0.49 / 63.07 ms │     no change │
│ QQuery 19 │ 34.67 / 35.91 ±1.51 / 37.78 ms │ 33.82 / 34.99 ±1.19 / 37.15 ms │     no change │
│ QQuery 20 │ 38.31 / 38.74 ±0.56 / 39.73 ms │ 37.63 / 37.80 ±0.11 / 37.89 ms │     no change │
│ QQuery 21 │ 58.70 / 60.25 ±1.33 / 62.46 ms │ 55.94 / 59.00 ±1.92 / 61.02 ms │     no change │
│ QQuery 22 │ 23.96 / 24.19 ±0.16 / 24.39 ms │ 23.60 / 25.45 ±2.18 / 29.71 ms │  1.05x slower │
└───────────┴────────────────────────────────┴────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Benchmark Summary                           ┃          ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Total Time (HEAD)                           │ 832.85ms │
│ Total Time (codex_topk-before-projection)   │ 823.47ms │
│ Average Time (HEAD)                         │  37.86ms │
│ Average Time (codex_topk-before-projection) │  37.43ms │
│ Queries Faster                              │        1 │
│ Queries Slower                              │        1 │
│ Queries with No Change                      │       20 │
│ Queries with Failure                        │        0 │
└─────────────────────────────────────────────┴──────────┘

Resource Usage

tpch — base (merge-base)

Metric	Value
Wall time	5.0s
Peak memory	5.5 GiB
Avg memory	5.0 GiB
CPU user	30.1s
CPU sys	2.5s
Peak spill	0 B

tpch — branch

Metric	Value
Wall time	5.0s
Peak memory	5.5 GiB
Avg memory	5.0 GiB
CPU user	30.0s
CPU sys	2.3s
Peak spill	0 B

File an issue against this benchmark runner

adriangbot · 2026-05-28T21:17:07Z

🤖 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 codex_topk-before-projection
--------------------
Benchmark tpcds_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃          codex_topk-before-projection ┃       Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩
│ QQuery 1  │           5.63 / 6.14 ±0.81 / 7.75 ms │           5.70 / 6.17 ±0.88 / 7.93 ms │    no change │
│ QQuery 2  │        80.11 / 80.25 ±0.11 / 80.44 ms │        79.60 / 79.89 ±0.18 / 80.15 ms │    no change │
│ QQuery 3  │        29.04 / 29.37 ±0.20 / 29.64 ms │        28.46 / 28.98 ±0.40 / 29.68 ms │    no change │
│ QQuery 4  │     505.54 / 509.25 ±3.70 / 516.13 ms │     500.84 / 506.03 ±3.19 / 509.18 ms │    no change │
│ QQuery 5  │        50.35 / 51.00 ±0.41 / 51.43 ms │        50.06 / 50.63 ±0.48 / 51.44 ms │    no change │
│ QQuery 6  │        35.01 / 35.47 ±0.39 / 36.03 ms │        34.90 / 35.41 ±0.27 / 35.63 ms │    no change │
│ QQuery 7  │     107.17 / 107.99 ±1.47 / 110.92 ms │     107.21 / 108.84 ±1.90 / 112.55 ms │    no change │
│ QQuery 8  │        36.18 / 36.49 ±0.24 / 36.81 ms │        36.25 / 36.66 ±0.24 / 36.97 ms │    no change │
│ QQuery 9  │        52.17 / 54.14 ±1.38 / 56.10 ms │        52.95 / 55.23 ±1.17 / 56.17 ms │    no change │
│ QQuery 10 │        80.02 / 80.22 ±0.15 / 80.36 ms │        79.40 / 80.22 ±0.47 / 80.66 ms │    no change │
│ QQuery 11 │     307.91 / 311.85 ±2.35 / 314.30 ms │     313.41 / 315.34 ±1.39 / 317.31 ms │    no change │
│ QQuery 12 │        28.29 / 28.59 ±0.34 / 29.25 ms │        27.90 / 28.59 ±0.52 / 29.49 ms │    no change │
│ QQuery 13 │     125.57 / 126.48 ±0.82 / 127.54 ms │     125.62 / 125.94 ±0.31 / 126.44 ms │    no change │
│ QQuery 14 │     502.35 / 503.83 ±0.95 / 505.02 ms │     502.62 / 504.34 ±1.39 / 506.01 ms │    no change │
│ QQuery 15 │        60.41 / 61.41 ±0.53 / 61.92 ms │        60.15 / 60.58 ±0.38 / 61.13 ms │    no change │
│ QQuery 16 │           6.29 / 6.44 ±0.16 / 6.74 ms │           6.29 / 6.46 ±0.23 / 6.92 ms │    no change │
│ QQuery 17 │        81.01 / 81.12 ±0.11 / 81.28 ms │        80.39 / 80.72 ±0.27 / 81.11 ms │    no change │
│ QQuery 18 │     150.42 / 151.29 ±0.47 / 151.75 ms │     150.92 / 151.63 ±0.57 / 152.56 ms │    no change │
│ QQuery 19 │        40.87 / 41.09 ±0.13 / 41.28 ms │        40.72 / 41.00 ±0.20 / 41.27 ms │    no change │
│ QQuery 20 │        34.57 / 34.78 ±0.23 / 35.21 ms │        35.18 / 35.50 ±0.25 / 35.82 ms │    no change │
│ QQuery 21 │        16.36 / 16.80 ±0.26 / 17.13 ms │        16.80 / 17.03 ±0.18 / 17.32 ms │    no change │
│ QQuery 22 │        62.65 / 63.07 ±0.45 / 63.91 ms │        61.48 / 62.41 ±0.52 / 62.99 ms │    no change │
│ QQuery 23 │     472.18 / 477.95 ±4.00 / 483.44 ms │     478.32 / 482.81 ±3.59 / 488.19 ms │    no change │
│ QQuery 24 │     233.33 / 235.59 ±2.65 / 240.49 ms │     232.22 / 235.23 ±4.68 / 244.46 ms │    no change │
│ QQuery 25 │     112.37 / 113.86 ±1.23 / 116.01 ms │     112.20 / 115.28 ±3.62 / 122.36 ms │    no change │
│ QQuery 26 │        70.32 / 70.54 ±0.23 / 70.95 ms │        69.41 / 70.38 ±0.59 / 71.18 ms │    no change │
│ QQuery 27 │           6.54 / 6.65 ±0.18 / 7.01 ms │           6.65 / 6.72 ±0.09 / 6.90 ms │    no change │
│ QQuery 28 │        57.35 / 61.00 ±1.87 / 62.63 ms │        56.92 / 60.00 ±2.17 / 62.15 ms │    no change │
│ QQuery 29 │      98.84 / 100.42 ±1.75 / 102.81 ms │      99.09 / 101.58 ±2.79 / 106.39 ms │    no change │
│ QQuery 30 │        29.66 / 30.06 ±0.33 / 30.50 ms │        29.97 / 30.26 ±0.32 / 30.84 ms │    no change │
│ QQuery 31 │     110.45 / 112.16 ±2.53 / 117.20 ms │     110.32 / 112.27 ±2.13 / 116.42 ms │    no change │
│ QQuery 32 │        19.86 / 20.20 ±0.42 / 20.98 ms │        19.71 / 20.14 ±0.34 / 20.76 ms │    no change │
│ QQuery 33 │        37.95 / 38.30 ±0.26 / 38.67 ms │        37.96 / 38.38 ±0.36 / 38.87 ms │    no change │
│ QQuery 34 │           9.08 / 9.27 ±0.16 / 9.52 ms │          9.28 / 9.58 ±0.25 / 10.02 ms │    no change │
│ QQuery 35 │        79.40 / 79.82 ±0.29 / 80.26 ms │        79.82 / 80.42 ±0.50 / 81.11 ms │    no change │
│ QQuery 36 │           5.75 / 5.87 ±0.16 / 6.18 ms │           5.95 / 6.08 ±0.16 / 6.39 ms │    no change │
│ QQuery 37 │           6.61 / 6.73 ±0.09 / 6.83 ms │           6.77 / 6.86 ±0.10 / 7.04 ms │    no change │
│ QQuery 38 │        67.66 / 68.65 ±0.65 / 69.43 ms │        68.98 / 69.51 ±0.41 / 70.23 ms │    no change │
│ QQuery 39 │       97.55 / 99.14 ±2.66 / 104.45 ms │       98.31 / 99.51 ±1.36 / 101.82 ms │    no change │
│ QQuery 40 │        22.44 / 22.89 ±0.30 / 23.24 ms │        22.54 / 22.94 ±0.24 / 23.25 ms │    no change │
│ QQuery 41 │        11.38 / 11.52 ±0.14 / 11.77 ms │        11.27 / 11.48 ±0.21 / 11.86 ms │    no change │
│ QQuery 42 │        23.37 / 23.73 ±0.19 / 23.90 ms │        23.55 / 24.15 ±0.90 / 25.95 ms │    no change │
│ QQuery 43 │           4.71 / 4.79 ±0.08 / 4.94 ms │           4.80 / 4.88 ±0.10 / 5.07 ms │    no change │
│ QQuery 44 │        10.53 / 10.92 ±0.37 / 11.60 ms │        10.52 / 10.60 ±0.09 / 10.77 ms │    no change │
│ QQuery 45 │        38.89 / 40.00 ±0.69 / 40.72 ms │        40.00 / 40.28 ±0.22 / 40.52 ms │    no change │
│ QQuery 46 │        12.53 / 12.67 ±0.14 / 12.92 ms │        12.69 / 13.14 ±0.29 / 13.55 ms │    no change │
│ QQuery 47 │     227.23 / 228.61 ±1.17 / 230.18 ms │     226.33 / 228.18 ±1.57 / 230.44 ms │    no change │
│ QQuery 48 │     102.19 / 102.69 ±0.37 / 103.21 ms │     102.46 / 103.18 ±0.74 / 104.59 ms │    no change │
│ QQuery 49 │        78.66 / 80.31 ±2.30 / 84.85 ms │        78.05 / 79.13 ±0.98 / 80.76 ms │    no change │
│ QQuery 50 │        59.45 / 59.89 ±0.38 / 60.60 ms │        59.29 / 59.52 ±0.17 / 59.71 ms │    no change │
│ QQuery 51 │        91.81 / 93.65 ±1.13 / 95.18 ms │        92.32 / 95.23 ±2.43 / 98.81 ms │    no change │
│ QQuery 52 │        23.76 / 24.03 ±0.26 / 24.44 ms │        23.66 / 24.19 ±0.39 / 24.58 ms │    no change │
│ QQuery 53 │        29.18 / 29.63 ±0.28 / 29.99 ms │        29.43 / 29.80 ±0.28 / 30.26 ms │    no change │
│ QQuery 54 │        54.22 / 54.58 ±0.24 / 54.85 ms │        54.07 / 54.40 ±0.38 / 55.09 ms │    no change │
│ QQuery 55 │        22.91 / 23.42 ±0.44 / 24.09 ms │        23.15 / 23.56 ±0.29 / 24.02 ms │    no change │
│ QQuery 56 │        38.38 / 38.74 ±0.26 / 38.97 ms │        38.05 / 38.73 ±0.42 / 39.37 ms │    no change │
│ QQuery 57 │     174.33 / 176.74 ±2.27 / 181.00 ms │     174.84 / 176.11 ±1.05 / 177.82 ms │    no change │
│ QQuery 58 │     115.76 / 117.01 ±0.89 / 117.90 ms │     117.51 / 118.98 ±1.68 / 122.24 ms │    no change │
│ QQuery 59 │     116.18 / 118.28 ±2.95 / 124.13 ms │     115.93 / 116.20 ±0.20 / 116.54 ms │    no change │
│ QQuery 60 │        39.44 / 39.86 ±0.31 / 40.30 ms │        38.81 / 39.57 ±0.45 / 40.18 ms │    no change │
│ QQuery 61 │        12.99 / 13.27 ±0.23 / 13.60 ms │        12.64 / 12.72 ±0.12 / 12.95 ms │    no change │
│ QQuery 62 │        46.02 / 46.79 ±0.80 / 47.88 ms │        45.95 / 46.22 ±0.16 / 46.45 ms │    no change │
│ QQuery 63 │        29.26 / 29.67 ±0.42 / 30.48 ms │        29.32 / 29.86 ±0.56 / 30.77 ms │    no change │
│ QQuery 64 │     455.30 / 460.24 ±3.52 / 464.50 ms │     455.73 / 460.87 ±5.07 / 469.43 ms │    no change │
│ QQuery 65 │     146.89 / 149.44 ±1.64 / 151.41 ms │     147.86 / 149.12 ±0.92 / 150.56 ms │    no change │
│ QQuery 66 │        77.78 / 78.60 ±0.74 / 79.55 ms │        77.87 / 80.15 ±2.90 / 85.79 ms │    no change │
│ QQuery 67 │     245.29 / 248.33 ±3.93 / 255.89 ms │     243.21 / 247.04 ±3.49 / 253.28 ms │    no change │
│ QQuery 68 │        12.71 / 12.96 ±0.23 / 13.37 ms │        12.92 / 13.03 ±0.17 / 13.36 ms │    no change │
│ QQuery 69 │        75.67 / 75.91 ±0.24 / 76.33 ms │        75.70 / 75.81 ±0.13 / 76.07 ms │    no change │
│ QQuery 70 │     104.97 / 109.60 ±4.69 / 118.47 ms │     105.57 / 110.63 ±5.79 / 117.84 ms │    no change │
│ QQuery 71 │        35.30 / 35.47 ±0.14 / 35.61 ms │        35.34 / 35.85 ±0.31 / 36.26 ms │    no change │
│ QQuery 72 │ 2111.66 / 2154.49 ±39.69 / 2214.28 ms │ 2079.72 / 2193.73 ±87.31 / 2316.17 ms │    no change │
│ QQuery 73 │           8.77 / 9.11 ±0.25 / 9.50 ms │           8.95 / 9.16 ±0.19 / 9.51 ms │    no change │
│ QQuery 74 │     175.34 / 179.05 ±3.79 / 185.90 ms │     179.32 / 181.34 ±1.79 / 184.45 ms │    no change │
│ QQuery 75 │     145.88 / 146.53 ±0.92 / 148.34 ms │     146.45 / 148.69 ±2.81 / 154.23 ms │    no change │
│ QQuery 76 │        35.46 / 36.62 ±1.34 / 39.11 ms │        35.32 / 35.97 ±0.48 / 36.56 ms │    no change │
│ QQuery 77 │        59.93 / 60.21 ±0.22 / 60.58 ms │        60.28 / 60.58 ±0.27 / 60.92 ms │    no change │
│ QQuery 78 │     187.00 / 190.24 ±3.41 / 195.82 ms │     187.08 / 188.89 ±0.97 / 189.85 ms │    no change │
│ QQuery 79 │        67.59 / 67.88 ±0.22 / 68.16 ms │        66.98 / 67.47 ±0.30 / 67.83 ms │    no change │
│ QQuery 80 │      98.43 / 101.81 ±3.50 / 108.18 ms │     100.17 / 101.85 ±1.59 / 104.81 ms │    no change │
│ QQuery 81 │        23.99 / 24.16 ±0.12 / 24.31 ms │        23.96 / 24.33 ±0.31 / 24.83 ms │    no change │
│ QQuery 82 │        16.36 / 16.49 ±0.18 / 16.82 ms │        16.25 / 16.43 ±0.27 / 16.97 ms │    no change │
│ QQuery 83 │        36.07 / 36.61 ±0.31 / 36.96 ms │        36.42 / 36.74 ±0.26 / 37.20 ms │    no change │
│ QQuery 84 │        43.11 / 43.24 ±0.15 / 43.45 ms │        42.71 / 44.43 ±1.79 / 47.05 ms │    no change │
│ QQuery 85 │     135.11 / 136.69 ±1.61 / 139.80 ms │     134.45 / 135.82 ±0.85 / 137.09 ms │    no change │
│ QQuery 86 │        24.98 / 25.19 ±0.23 / 25.57 ms │        24.42 / 24.77 ±0.37 / 25.45 ms │    no change │
│ QQuery 87 │        68.10 / 68.45 ±0.30 / 68.88 ms │        68.99 / 70.88 ±2.21 / 74.89 ms │    no change │
│ QQuery 88 │        61.68 / 62.51 ±0.76 / 63.93 ms │        62.25 / 62.60 ±0.22 / 62.89 ms │    no change │
│ QQuery 89 │        35.65 / 36.08 ±0.38 / 36.63 ms │        35.52 / 36.10 ±0.34 / 36.50 ms │    no change │
│ QQuery 90 │        16.62 / 16.81 ±0.17 / 17.11 ms │        16.66 / 16.91 ±0.23 / 17.26 ms │    no change │
│ QQuery 91 │        51.22 / 51.76 ±0.29 / 52.02 ms │        51.22 / 51.43 ±0.17 / 51.66 ms │    no change │
│ QQuery 92 │        28.92 / 29.21 ±0.31 / 29.72 ms │        29.01 / 30.79 ±2.58 / 35.86 ms │ 1.05x slower │
│ QQuery 93 │        50.18 / 50.98 ±0.73 / 52.05 ms │        49.95 / 50.44 ±0.45 / 51.28 ms │    no change │
│ QQuery 94 │        37.39 / 37.87 ±0.32 / 38.32 ms │        37.60 / 37.86 ±0.21 / 38.07 ms │    no change │
│ QQuery 95 │        84.10 / 84.51 ±0.32 / 84.86 ms │        84.04 / 84.47 ±0.36 / 84.95 ms │    no change │
│ QQuery 96 │        23.84 / 24.11 ±0.24 / 24.55 ms │        23.84 / 24.26 ±0.33 / 24.75 ms │    no change │
│ QQuery 97 │        45.40 / 46.08 ±0.64 / 47.24 ms │        45.86 / 46.17 ±0.30 / 46.71 ms │    no change │
│ QQuery 98 │        41.96 / 42.38 ±0.50 / 43.14 ms │        42.27 / 42.64 ±0.34 / 43.26 ms │    no change │
│ QQuery 99 │        68.87 / 69.24 ±0.41 / 69.77 ms │        69.14 / 69.66 ±0.35 / 70.24 ms │    no change │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴──────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                           ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                           │ 10375.86ms │
│ Total Time (codex_topk-before-projection)   │ 10432.55ms │
│ Average Time (HEAD)                         │   104.81ms │
│ Average Time (codex_topk-before-projection) │   105.38ms │
│ Queries Faster                              │          0 │
│ Queries Slower                              │          1 │
│ Queries with No Change                      │         98 │
│ Queries with Failure                        │          0 │
└─────────────────────────────────────────────┴────────────┘

Resource Usage

tpcds — base (merge-base)

Metric	Value
Wall time	55.0s
Peak memory	7.1 GiB
Avg memory	6.4 GiB
CPU user	231.6s
CPU sys	5.2s
Peak spill	0 B

tpcds — branch

Metric	Value
Wall time	55.0s
Peak memory	7.0 GiB
Avg memory	6.2 GiB
CPU user	232.5s
CPU sys	5.2s
Peak spill	0 B

File an issue against this benchmark runner

adriangbot · 2026-05-28T21:20:31Z

🤖 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 codex_topk-before-projection
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃          codex_topk-before-projection ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.17 / 4.61 ±6.79 / 18.20 ms │          1.14 / 4.59 ±6.84 / 18.28 ms │     no change │
│ QQuery 1  │        12.69 / 12.93 ±0.19 / 13.24 ms │        13.04 / 13.25 ±0.18 / 13.51 ms │     no change │
│ QQuery 2  │        35.85 / 36.03 ±0.16 / 36.26 ms │        36.24 / 36.49 ±0.21 / 36.84 ms │     no change │
│ QQuery 3  │        31.03 / 31.70 ±0.53 / 32.46 ms │        30.82 / 31.40 ±0.64 / 32.60 ms │     no change │
│ QQuery 4  │     217.70 / 224.89 ±4.90 / 230.39 ms │     218.91 / 224.78 ±4.32 / 231.71 ms │     no change │
│ QQuery 5  │     268.22 / 271.51 ±2.44 / 274.85 ms │     268.18 / 271.67 ±1.82 / 273.48 ms │     no change │
│ QQuery 6  │           1.17 / 1.32 ±0.22 / 1.76 ms │           1.20 / 1.34 ±0.20 / 1.74 ms │     no change │
│ QQuery 7  │        13.62 / 13.73 ±0.10 / 13.92 ms │        14.12 / 14.35 ±0.17 / 14.50 ms │     no change │
│ QQuery 8  │     316.74 / 321.86 ±3.10 / 325.59 ms │     314.22 / 318.73 ±3.28 / 323.37 ms │     no change │
│ QQuery 9  │     447.28 / 449.86 ±2.35 / 453.23 ms │     450.47 / 457.28 ±5.32 / 463.36 ms │     no change │
│ QQuery 10 │        69.24 / 69.72 ±0.44 / 70.51 ms │        69.23 / 70.36 ±0.86 / 71.76 ms │     no change │
│ QQuery 11 │        80.47 / 81.44 ±0.78 / 82.47 ms │        81.02 / 83.86 ±4.57 / 92.96 ms │     no change │
│ QQuery 12 │     263.15 / 267.63 ±4.64 / 276.53 ms │     264.82 / 268.92 ±5.25 / 278.46 ms │     no change │
│ QQuery 13 │     366.14 / 372.28 ±6.63 / 384.31 ms │    360.42 / 382.55 ±15.29 / 398.01 ms │     no change │
│ QQuery 14 │     274.71 / 282.24 ±6.69 / 291.95 ms │     276.20 / 279.18 ±3.67 / 286.39 ms │     no change │
│ QQuery 15 │     263.17 / 269.51 ±7.94 / 282.89 ms │     260.27 / 271.15 ±8.21 / 284.29 ms │     no change │
│ QQuery 16 │     601.91 / 608.38 ±6.28 / 617.19 ms │     602.25 / 608.51 ±5.60 / 617.37 ms │     no change │
│ QQuery 17 │     600.25 / 613.39 ±7.23 / 621.33 ms │    606.62 / 621.25 ±15.73 / 651.84 ms │     no change │
│ QQuery 18 │ 1240.97 / 1258.68 ±19.48 / 1288.16 ms │  1258.42 / 1266.38 ±9.27 / 1282.58 ms │     no change │
│ QQuery 19 │        27.75 / 30.15 ±3.47 / 36.97 ms │        28.19 / 32.46 ±7.40 / 47.21 ms │  1.08x slower │
│ QQuery 20 │    512.61 / 530.32 ±11.18 / 540.59 ms │     513.12 / 514.95 ±1.67 / 517.26 ms │     no change │
│ QQuery 21 │     587.35 / 593.87 ±4.52 / 600.74 ms │     590.00 / 592.64 ±2.77 / 597.27 ms │     no change │
│ QQuery 22 │  1053.77 / 1063.64 ±7.84 / 1077.82 ms │  1047.77 / 1054.98 ±7.39 / 1067.78 ms │     no change │
│ QQuery 23 │ 3130.95 / 3151.15 ±17.76 / 3181.30 ms │ 3142.38 / 3173.73 ±21.88 / 3211.05 ms │     no change │
│ QQuery 24 │        41.56 / 42.33 ±1.01 / 44.19 ms │        41.80 / 42.65 ±0.84 / 44.24 ms │     no change │
│ QQuery 25 │     110.33 / 113.62 ±3.82 / 120.23 ms │     110.72 / 112.08 ±1.13 / 113.57 ms │     no change │
│ QQuery 26 │        42.09 / 43.39 ±1.32 / 45.36 ms │        42.48 / 43.15 ±0.46 / 43.69 ms │     no change │
│ QQuery 27 │     668.30 / 673.95 ±4.61 / 679.99 ms │     673.02 / 679.38 ±6.04 / 686.67 ms │     no change │
│ QQuery 28 │ 3015.16 / 3057.02 ±36.95 / 3116.08 ms │  3012.95 / 3020.12 ±7.81 / 3033.87 ms │     no change │
│ QQuery 29 │        39.69 / 39.90 ±0.20 / 40.26 ms │        39.53 / 42.54 ±5.10 / 52.69 ms │  1.07x slower │
│ QQuery 30 │    294.49 / 304.10 ±10.18 / 323.41 ms │     296.86 / 300.86 ±5.74 / 312.22 ms │     no change │
│ QQuery 31 │    275.51 / 289.04 ±11.82 / 308.99 ms │     282.78 / 289.28 ±5.36 / 298.41 ms │     no change │
│ QQuery 32 │    901.13 / 923.22 ±19.80 / 955.83 ms │    918.28 / 939.53 ±14.00 / 958.53 ms │     no change │
│ QQuery 33 │ 1414.87 / 1428.32 ±19.99 / 1467.26 ms │ 1404.35 / 1427.34 ±19.36 / 1461.80 ms │     no change │
│ QQuery 34 │ 1395.64 / 1426.80 ±21.76 / 1451.20 ms │ 1405.77 / 1425.38 ±20.98 / 1465.82 ms │     no change │
│ QQuery 35 │    268.41 / 289.68 ±29.56 / 348.32 ms │    275.68 / 287.15 ±12.53 / 308.34 ms │     no change │
│ QQuery 36 │        64.93 / 69.20 ±4.71 / 77.59 ms │        64.47 / 66.79 ±2.09 / 69.68 ms │     no change │
│ QQuery 37 │        36.46 / 39.50 ±3.18 / 45.12 ms │        36.41 / 39.18 ±3.91 / 46.59 ms │     no change │
│ QQuery 38 │        42.07 / 43.01 ±0.99 / 44.63 ms │        40.28 / 44.73 ±3.93 / 51.76 ms │     no change │
│ QQuery 39 │     135.16 / 145.32 ±9.69 / 161.11 ms │     136.59 / 147.82 ±6.69 / 157.48 ms │     no change │
│ QQuery 40 │        14.06 / 16.91 ±3.86 / 24.49 ms │        13.59 / 14.18 ±0.54 / 15.05 ms │ +1.19x faster │
│ QQuery 41 │        13.40 / 13.53 ±0.10 / 13.72 ms │        13.38 / 15.16 ±2.23 / 19.29 ms │  1.12x slower │
│ QQuery 42 │        12.87 / 13.13 ±0.22 / 13.51 ms │        13.05 / 13.15 ±0.10 / 13.34 ms │     no change │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                           ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                           │ 19532.82ms │
│ Total Time (codex_topk-before-projection)   │ 19545.27ms │
│ Average Time (HEAD)                         │   454.25ms │
│ Average Time (codex_topk-before-projection) │   454.54ms │
│ Queries Faster                              │          1 │
│ Queries Slower                              │          3 │
│ Queries with No Change                      │         39 │
│ Queries with Failure                        │          0 │
└─────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric	Value
Wall time	100.0s
Peak memory	30.6 GiB
Avg memory	23.4 GiB
CPU user	1019.5s
CPU sys	60.2s
Peak spill	0 B

clickbench_partitioned — branch

Metric	Value
Wall time	100.0s
Peak memory	30.5 GiB
Avg memory	23.2 GiB
CPU user	1017.9s
CPU sys	61.4s
Peak spill	0 B

File an issue against this benchmark runner

Optimize TopK before computed projections

46573ef

github-actions Bot added optimizer Optimizer rules sqllogictest SQL Logic Tests (.slt) labels May 28, 2026

Push sorts below computed projections

238126b

github-actions Bot added the physical-plan Changes to the physical-plan crate label May 29, 2026

Dandandan closed this May 29, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Optimize TopK before computed projections#22606

Optimize TopK before computed projections#22606
Dandandan wants to merge 2 commits into
apache:mainfrom
Dandandan:codex/topk-before-projection

Dandandan commented May 28, 2026 •

edited

Loading

Uh oh!

Dandandan commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

Dandandan commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

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 May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

adriangbot commented May 28, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Dandandan commented May 28, 2026 •

edited

Loading