Skip to content

chore(ordered-partial-aggregate): move OrderedPartialAggregateStream to generators for readability - #23951

Open
rluvaton wants to merge 3 commits into
apache:mainfrom
rluvaton:move-ordered-partial-stream-to-async
Open

chore(ordered-partial-aggregate): move OrderedPartialAggregateStream to generators for readability#23951
rluvaton wants to merge 3 commits into
apache:mainfrom
rluvaton:move-ordered-partial-stream-to-async

Conversation

@rluvaton

@rluvaton rluvaton commented Jul 28, 2026

Copy link
Copy Markdown
Member

Which issue does this PR close?

N/A

Rationale for this change

Simplify the code by making it linear and with less state to hold in mind

What changes are included in this PR?

change OrderedPartialAggregateStream into async generators

Are these changes tested?

existing tests

Are there any user-facing changes?

no

@github-actions github-actions Bot added the physical-plan Changes to the physical-plan crate label Jul 28, 2026
@rluvaton
rluvaton requested a review from 2010YOUY01 July 28, 2026 20:08
@rluvaton
rluvaton marked this pull request as ready for review July 28, 2026 20:10
@rluvaton

Copy link
Copy Markdown
Member Author

@2010YOUY01 can you please run the benchmark that you think are the most appropriate here and review

@codecov-commenter

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 88.40580% with 8 lines in your changes missing coverage. Please review.
✅ Project coverage is 80.69%. Comparing base (1c3232c) to head (5c3ef5c).
⚠️ Report is 16 commits behind head on main.

Files with missing lines Patch % Lines
...ical-plan/src/aggregates/ordered_partial_stream.rs 89.39% 0 Missing and 7 partials ⚠️
datafusion/physical-plan/src/aggregates/mod.rs 66.66% 0 Missing and 1 partial ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main   #23951      +/-   ##
==========================================
+ Coverage   80.67%   80.69%   +0.02%     
==========================================
  Files        1095     1095              
  Lines      372376   372447      +71     
  Branches   372376   372447      +71     
==========================================
+ Hits       300397   300563     +166     
+ Misses      54052    53913     -139     
- Partials    17927    17971      +44     

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@2010YOUY01

Copy link
Copy Markdown
Contributor

Thank you, this looks much better now. It should be good to go after verifying the benchmarks.

@2010YOUY01 can you please run the benchmark that you think are the most appropriate here and review

There is no benchmark suite targeting ordered aggregation now, but previously we have found regressions for ordered aggregation with tcpds, so I think we could run that.

Additionally, I tried a simple query, the performance number is good.

select v1, avg(v1+1)
from generate_series(1000000000) as t1(v1)
group by v1;

@2010YOUY01

Copy link
Copy Markdown
Contributor

@adriangb Could you grant me access to the benchmark bot? Thanks.

@kumarUjjawal

Copy link
Copy Markdown
Contributor

run benchmark tpcds

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c5113724024-1284-gsx96 6.12.85+ #1 SMP Mon May 11 08:17:35 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 move-ordered-partial-stream-to-async (5c3ef5c) to 1c3232c (merge-base) diff using: tpcds
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 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 move-ordered-partial-stream-to-async
--------------------
Benchmark tpcds_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                   HEAD ┃   move-ordered-partial-stream-to-async ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │            5.40 / 6.06 ±0.89 / 7.70 ms │            5.48 / 6.03 ±0.91 / 7.84 ms │     no change │
│ QQuery 2  │         80.10 / 80.88 ±0.46 / 81.53 ms │         80.44 / 80.96 ±0.45 / 81.80 ms │     no change │
│ QQuery 3  │         29.42 / 29.62 ±0.21 / 29.96 ms │         29.62 / 29.87 ±0.25 / 30.21 ms │     no change │
│ QQuery 4  │      486.00 / 489.31 ±2.94 / 492.97 ms │      482.76 / 490.65 ±5.60 / 497.22 ms │     no change │
│ QQuery 5  │         51.94 / 52.65 ±0.46 / 53.28 ms │         52.03 / 52.30 ±0.25 / 52.77 ms │     no change │
│ QQuery 6  │         36.20 / 36.51 ±0.28 / 36.92 ms │         36.28 / 36.56 ±0.21 / 36.79 ms │     no change │
│ QQuery 7  │         95.07 / 95.36 ±0.22 / 95.57 ms │         95.29 / 95.90 ±0.64 / 97.03 ms │     no change │
│ QQuery 8  │         37.11 / 38.30 ±1.83 / 41.95 ms │         37.09 / 37.44 ±0.36 / 38.10 ms │     no change │
│ QQuery 9  │         54.69 / 56.77 ±2.77 / 62.19 ms │         52.38 / 53.72 ±1.87 / 57.42 ms │ +1.06x faster │
│ QQuery 10 │         63.54 / 63.91 ±0.26 / 64.21 ms │         63.27 / 63.71 ±0.31 / 64.16 ms │     no change │
│ QQuery 11 │     296.30 / 334.05 ±29.52 / 363.59 ms │      298.46 / 299.87 ±1.72 / 303.24 ms │ +1.11x faster │
│ QQuery 12 │         30.88 / 31.57 ±0.52 / 32.27 ms │         28.62 / 29.10 ±0.58 / 30.16 ms │ +1.08x faster │
│ QQuery 13 │      119.44 / 123.78 ±2.25 / 125.76 ms │      118.48 / 118.80 ±0.23 / 119.17 ms │     no change │
│ QQuery 14 │      415.58 / 420.22 ±4.05 / 426.03 ms │      416.96 / 420.42 ±2.48 / 422.98 ms │     no change │
│ QQuery 15 │         57.18 / 57.78 ±0.56 / 58.85 ms │         59.05 / 59.66 ±0.45 / 60.45 ms │     no change │
│ QQuery 16 │            6.56 / 6.79 ±0.18 / 7.08 ms │            6.58 / 6.68 ±0.13 / 6.95 ms │     no change │
│ QQuery 17 │         79.88 / 82.35 ±2.43 / 85.36 ms │         80.62 / 81.55 ±0.90 / 83.26 ms │     no change │
│ QQuery 18 │      123.79 / 125.46 ±1.59 / 127.93 ms │      124.54 / 126.19 ±1.50 / 128.55 ms │     no change │
│ QQuery 19 │         41.94 / 42.52 ±0.31 / 42.75 ms │         44.68 / 44.83 ±0.10 / 44.98 ms │  1.05x slower │
│ QQuery 20 │         35.84 / 36.46 ±0.50 / 37.26 ms │         38.50 / 39.86 ±1.19 / 41.98 ms │  1.09x slower │
│ QQuery 21 │         17.45 / 17.81 ±0.33 / 18.28 ms │         18.77 / 18.97 ±0.21 / 19.37 ms │  1.06x slower │
│ QQuery 22 │         63.69 / 64.03 ±0.30 / 64.41 ms │         71.76 / 72.62 ±0.73 / 73.66 ms │  1.13x slower │
│ QQuery 23 │      345.15 / 349.45 ±4.12 / 357.10 ms │     352.65 / 378.17 ±17.32 / 397.32 ms │  1.08x slower │
│ QQuery 24 │      224.43 / 227.99 ±3.91 / 235.17 ms │      225.73 / 227.09 ±1.69 / 230.23 ms │     no change │
│ QQuery 25 │      110.13 / 112.46 ±3.28 / 118.91 ms │      111.20 / 114.22 ±4.57 / 123.26 ms │     no change │
│ QQuery 26 │         58.15 / 58.54 ±0.65 / 59.83 ms │         57.93 / 58.99 ±0.58 / 59.68 ms │     no change │
│ QQuery 27 │            6.17 / 6.31 ±0.14 / 6.57 ms │            6.38 / 6.47 ±0.14 / 6.75 ms │     no change │
│ QQuery 28 │         57.04 / 60.95 ±2.01 / 62.56 ms │         57.46 / 61.08 ±1.85 / 62.52 ms │     no change │
│ QQuery 29 │       97.00 / 101.43 ±6.81 / 114.94 ms │       97.40 / 100.07 ±2.20 / 103.76 ms │     no change │
│ QQuery 30 │         32.34 / 33.04 ±0.62 / 33.98 ms │         32.47 / 32.92 ±0.25 / 33.16 ms │     no change │
│ QQuery 31 │      112.04 / 112.31 ±0.26 / 112.69 ms │      111.69 / 112.73 ±0.61 / 113.58 ms │     no change │
│ QQuery 32 │         20.67 / 22.39 ±2.74 / 27.82 ms │         20.50 / 22.01 ±2.61 / 27.21 ms │     no change │
│ QQuery 33 │         38.90 / 39.33 ±0.43 / 40.16 ms │         38.56 / 38.79 ±0.16 / 38.96 ms │     no change │
│ QQuery 34 │          9.92 / 10.30 ±0.29 / 10.71 ms │          9.93 / 10.41 ±0.35 / 10.86 ms │     no change │
│ QQuery 35 │         72.88 / 73.33 ±0.36 / 73.87 ms │         72.11 / 73.16 ±0.55 / 73.64 ms │     no change │
│ QQuery 36 │            5.83 / 5.98 ±0.21 / 6.39 ms │            5.73 / 5.92 ±0.15 / 6.19 ms │     no change │
│ QQuery 37 │            6.92 / 7.02 ±0.08 / 7.13 ms │            6.90 / 6.93 ±0.03 / 6.97 ms │     no change │
│ QQuery 38 │         62.04 / 62.17 ±0.14 / 62.43 ms │         61.93 / 63.23 ±1.92 / 67.05 ms │     no change │
│ QQuery 39 │         89.94 / 91.01 ±0.78 / 92.16 ms │         89.89 / 90.76 ±0.53 / 91.30 ms │     no change │
│ QQuery 40 │         23.00 / 23.48 ±0.35 / 24.06 ms │         23.39 / 23.66 ±0.15 / 23.83 ms │     no change │
│ QQuery 41 │         11.60 / 11.80 ±0.22 / 12.22 ms │         11.76 / 11.89 ±0.15 / 12.18 ms │     no change │
│ QQuery 42 │         23.87 / 24.48 ±0.43 / 25.16 ms │         23.93 / 24.29 ±0.40 / 25.04 ms │     no change │
│ QQuery 43 │            5.00 / 5.14 ±0.18 / 5.48 ms │            4.96 / 5.07 ±0.14 / 5.34 ms │     no change │
│ QQuery 44 │            9.29 / 9.46 ±0.18 / 9.82 ms │            9.05 / 9.26 ±0.17 / 9.56 ms │     no change │
│ QQuery 45 │         38.58 / 39.94 ±1.66 / 43.14 ms │         38.33 / 40.01 ±1.99 / 43.82 ms │     no change │
│ QQuery 46 │         12.02 / 12.70 ±0.44 / 13.19 ms │         11.88 / 12.30 ±0.40 / 12.88 ms │     no change │
│ QQuery 47 │      227.57 / 230.79 ±2.31 / 233.02 ms │      228.13 / 230.25 ±1.11 / 231.15 ms │     no change │
│ QQuery 48 │         95.80 / 96.19 ±0.39 / 96.81 ms │         96.07 / 96.54 ±0.40 / 97.21 ms │     no change │
│ QQuery 49 │         76.00 / 76.67 ±0.49 / 77.49 ms │         77.33 / 80.31 ±3.30 / 86.54 ms │     no change │
│ QQuery 50 │         59.27 / 60.41 ±1.16 / 61.94 ms │         59.77 / 60.54 ±0.93 / 62.29 ms │     no change │
│ QQuery 51 │         91.06 / 93.28 ±1.33 / 94.94 ms │         92.07 / 93.24 ±1.05 / 94.62 ms │     no change │
│ QQuery 52 │         24.34 / 26.08 ±2.96 / 31.98 ms │         24.67 / 26.81 ±3.52 / 33.79 ms │     no change │
│ QQuery 53 │         30.04 / 30.69 ±0.49 / 31.29 ms │         29.74 / 30.64 ±1.16 / 32.88 ms │     no change │
│ QQuery 54 │         56.93 / 57.68 ±1.32 / 60.32 ms │         55.98 / 56.24 ±0.29 / 56.73 ms │     no change │
│ QQuery 55 │         23.96 / 24.55 ±0.40 / 25.09 ms │         23.77 / 24.18 ±0.29 / 24.61 ms │     no change │
│ QQuery 56 │         40.10 / 40.48 ±0.28 / 40.86 ms │         39.52 / 39.71 ±0.22 / 40.08 ms │     no change │
│ QQuery 57 │      178.89 / 181.19 ±3.32 / 187.73 ms │      178.04 / 179.38 ±1.19 / 181.55 ms │     no change │
│ QQuery 58 │      115.89 / 117.32 ±1.41 / 119.74 ms │      116.16 / 118.20 ±1.47 / 120.33 ms │     no change │
│ QQuery 59 │      117.95 / 118.71 ±0.57 / 119.58 ms │      117.67 / 118.66 ±0.71 / 119.76 ms │     no change │
│ QQuery 60 │         40.50 / 42.01 ±1.71 / 45.03 ms │         40.02 / 41.31 ±1.75 / 44.75 ms │     no change │
│ QQuery 61 │         13.43 / 13.63 ±0.12 / 13.77 ms │         12.19 / 12.37 ±0.22 / 12.79 ms │ +1.10x faster │
│ QQuery 62 │         49.93 / 50.44 ±0.37 / 50.82 ms │         46.92 / 47.71 ±0.90 / 49.44 ms │ +1.06x faster │
│ QQuery 63 │         31.95 / 32.16 ±0.23 / 32.60 ms │         29.56 / 29.84 ±0.29 / 30.20 ms │ +1.08x faster │
│ QQuery 64 │      440.51 / 446.62 ±7.31 / 460.45 ms │      408.79 / 415.85 ±5.04 / 423.21 ms │ +1.07x faster │
│ QQuery 65 │      135.87 / 140.94 ±5.72 / 151.83 ms │      126.09 / 130.27 ±3.22 / 135.43 ms │ +1.08x faster │
│ QQuery 66 │         87.82 / 88.84 ±0.67 / 89.79 ms │         81.31 / 81.82 ±0.40 / 82.50 ms │ +1.09x faster │
│ QQuery 67 │     282.50 / 290.14 ±10.30 / 309.89 ms │      240.62 / 244.66 ±4.03 / 250.02 ms │ +1.19x faster │
│ QQuery 68 │         13.33 / 13.47 ±0.12 / 13.65 ms │         11.94 / 12.30 ±0.19 / 12.50 ms │ +1.10x faster │
│ QQuery 69 │         60.54 / 62.00 ±1.67 / 65.23 ms │         58.90 / 64.61 ±7.27 / 78.97 ms │     no change │
│ QQuery 70 │      114.66 / 119.96 ±5.59 / 129.39 ms │      113.31 / 117.39 ±3.91 / 124.75 ms │     no change │
│ QQuery 71 │         37.71 / 38.12 ±0.43 / 38.94 ms │         37.76 / 39.46 ±2.57 / 44.55 ms │     no change │
│ QQuery 72 │ 1992.09 / 2200.27 ±148.62 / 2387.97 ms │ 2226.18 / 2427.52 ±132.85 / 2543.13 ms │  1.10x slower │
│ QQuery 73 │           9.69 / 9.92 ±0.21 / 10.25 ms │          9.84 / 10.17 ±0.31 / 10.59 ms │     no change │
│ QQuery 74 │      174.68 / 179.96 ±4.18 / 185.85 ms │     171.07 / 180.14 ±10.39 / 199.48 ms │     no change │
│ QQuery 75 │      152.84 / 156.97 ±4.98 / 165.34 ms │      149.53 / 153.13 ±2.59 / 157.10 ms │     no change │
│ QQuery 76 │         36.78 / 37.18 ±0.46 / 37.90 ms │         35.48 / 36.96 ±1.56 / 39.59 ms │     no change │
│ QQuery 77 │         62.89 / 63.42 ±0.47 / 64.11 ms │         62.52 / 63.54 ±1.67 / 66.87 ms │     no change │
│ QQuery 78 │      201.82 / 205.00 ±2.66 / 208.14 ms │      199.19 / 202.79 ±2.67 / 206.87 ms │     no change │
│ QQuery 79 │         68.97 / 70.84 ±2.21 / 74.86 ms │         67.50 / 68.55 ±0.97 / 70.38 ms │     no change │
│ QQuery 80 │      100.87 / 102.11 ±1.03 / 103.80 ms │      100.49 / 102.41 ±2.50 / 107.07 ms │     no change │
│ QQuery 81 │         26.39 / 26.73 ±0.23 / 27.08 ms │         25.76 / 26.07 ±0.24 / 26.30 ms │     no change │
│ QQuery 82 │         16.64 / 16.89 ±0.13 / 16.99 ms │         16.43 / 16.78 ±0.18 / 16.99 ms │     no change │
│ QQuery 83 │         40.41 / 41.66 ±1.75 / 45.11 ms │         39.94 / 40.36 ±0.54 / 41.38 ms │     no change │
│ QQuery 84 │         31.87 / 33.61 ±1.96 / 36.29 ms │         30.13 / 30.54 ±0.22 / 30.77 ms │ +1.10x faster │
│ QQuery 85 │      111.84 / 112.17 ±0.28 / 112.58 ms │      108.05 / 111.40 ±2.47 / 115.32 ms │     no change │
│ QQuery 86 │         27.43 / 27.69 ±0.35 / 28.37 ms │         25.92 / 26.54 ±0.42 / 27.16 ms │     no change │
│ QQuery 87 │         63.76 / 68.13 ±2.39 / 70.88 ms │         63.93 / 64.32 ±0.48 / 65.22 ms │ +1.06x faster │
│ QQuery 88 │         63.22 / 64.19 ±0.65 / 65.23 ms │         64.22 / 66.85 ±4.40 / 75.62 ms │     no change │
│ QQuery 89 │         36.27 / 36.61 ±0.29 / 37.10 ms │         36.73 / 37.94 ±1.06 / 39.89 ms │     no change │
│ QQuery 90 │         17.38 / 17.52 ±0.10 / 17.64 ms │         17.59 / 17.68 ±0.07 / 17.80 ms │     no change │
│ QQuery 91 │         45.67 / 46.10 ±0.23 / 46.30 ms │         45.55 / 46.74 ±0.86 / 47.72 ms │     no change │
│ QQuery 92 │         30.49 / 31.12 ±0.41 / 31.70 ms │         30.36 / 30.90 ±0.49 / 31.82 ms │     no change │
│ QQuery 93 │         50.89 / 51.37 ±0.49 / 52.09 ms │         50.02 / 51.23 ±0.80 / 52.18 ms │     no change │
│ QQuery 94 │         38.92 / 39.14 ±0.14 / 39.30 ms │         38.93 / 39.97 ±1.05 / 41.81 ms │     no change │
│ QQuery 95 │         81.00 / 82.43 ±2.23 / 86.84 ms │         81.49 / 82.28 ±0.73 / 83.47 ms │     no change │
│ QQuery 96 │         24.63 / 25.61 ±1.45 / 28.49 ms │         24.34 / 24.61 ±0.21 / 24.97 ms │     no change │
│ QQuery 97 │         47.41 / 48.04 ±0.51 / 48.97 ms │         47.03 / 48.46 ±2.08 / 52.60 ms │     no change │
│ QQuery 98 │         43.49 / 44.02 ±0.55 / 44.99 ms │         43.30 / 44.48 ±1.11 / 46.37 ms │     no change │
│ QQuery 99 │         70.98 / 71.72 ±0.55 / 72.37 ms │         71.03 / 71.67 ±0.41 / 72.32 ms │     no change │
└───────────┴────────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                   ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                   │ 10196.02ms │
│ Total Time (move-ordered-partial-stream-to-async)   │ 10311.44ms │
│ Average Time (HEAD)                                 │   102.99ms │
│ Average Time (move-ordered-partial-stream-to-async) │   104.16ms │
│ Queries Faster                                      │         13 │
│ Queries Slower                                      │          6 │
│ Queries with No Change                              │         80 │
│ Queries with Failure                                │          0 │
└─────────────────────────────────────────────────────┴────────────┘

Resource Usage

tpcds — base (merge-base)

Metric Value
Wall time 55.0s
Peak memory 2.1 GiB
Avg memory 1.5 GiB
CPU user 228.1s
CPU sys 6.4s
Peak spill 0 B

tpcds — branch

Metric Value
Wall time 55.0s
Peak memory 2.2 GiB
Avg memory 1.5 GiB
CPU user 241.5s
CPU sys 6.2s
Peak spill 0 B

File an issue against this benchmark runner

@rluvaton

rluvaton commented Jul 29, 2026

Copy link
Copy Markdown
Member Author

@adriangb Could you grant me access to the benchmark bot? Thanks.

@2010YOUY01 you should make a pr like adriangb/datafusion-benchmarking#16

@rluvaton

Copy link
Copy Markdown
Member Author

@2010YOUY01 can you please review?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

physical-plan Changes to the physical-plan crate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants